Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8, 113-137 2025 Publisher: Learning Gate DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate © 2025 by the authors; licensee Learning Gate History: Received: 5 June 2025; Revised: 1 July 2025; Accepted: 4 July 2025; Published: 2 August 2025 * Correspondence: petrit.hasanaj@ushaf.net The dynamics of macroeconomic indicators and stock market returns: An econometric perspective on advanced economies Leonora Haliti Rudhani1, Petrit Hasanaj2*, Taulant Rudhani3 1,2University of Applied Sciences, Ferizaj, Kosovo; petrit.hasanaj@ushaf.net (P.H.). 3University of Basel, Switzerland; The University of Sheffield, United Kingdom. Abstract: This study aims to analyze and examine the short-term and long-term relationships between macroeconomic indicators and stock market returns in Switzerland, Sweden, and Denmark. The research is based on secondary data covering the period from 1927 to 2021. Using empirical analyses such as VAR, Granger causality, and VECM, the study confirms both short-term and long-term relationships between macroeconomic indicators and stock market returns. The results of the analyses indicate that economic growth has a significant positive relationship with stock market returns, while a long-term negative effect of this indicator was confirmed in Switzerland. The short-term interest rate had a negative relationship with stock market returns in the short term only in Denmark, but similar results were not confirmed for Sweden and Switzerland. Population growth showed a positive effect on stock market returns in Sweden and Denmark in the short term but not in Switzerland. Inflation was not found to be a significant indicator for stock market returns in any of the three countries. Keywords: GDP per capita, Inflation rate, Short-term interest rate, Stock market returns. 1. Introduction The banking and financial markets are fundamental accelerators and key players in the economy. Many scholars argue that the stock market serves as a primary indicator of a country's economic growth. Consequently, in today's financial landscape, stock market performance is widely regarded as a measure of economic growth stability. Given the stock market’s high sensitivity to overall market conditions, numerous researchers have focused their studies on the impact of various macroeconomic indicators on stock market performance. Furthermore, analyzing the interactions between macroeconomic indicators including economic growth, inflation, interest rates, and population growth—on stock market returns is crucial for policymakers and investors. The extent to which macroeconomic indicators drive stock market returns remains an ongoing subject of debate. According to Khan, et al. [1] macroeconomic indicators such as interest rates, inflation, and GDP growth serve as critical barometers of economic health, significantly influencing market movements. Additionally, population growth is another factor that can affect fluctuations in financial markets, as individuals have varying financial needs at different stages of life borrowing when young, investing for retirement in middle age, and divesting upon retirement Geanakoplos, et al. [2]. Poterba [3] further asserts that if individuals were rational in their financial decisions, they would anticipate any stock price increases driven by demographic changes. Similarly, this study focuses on the aforementioned indicators, as Switzerland, Sweden, and Denmark have high GDP levels. According to a report published by Global Finance in 2023, these three countries rank among the nations with the highest GDP in the world. They are also classified as highly developed economies by scholars such as Lee and Choi [4] who further describe their financial markets as advanced. The findings of this research confirm that advanced financial markets are more efficient compared to those in developing economies. Empirical evidence suggests that highly developed https://orcid.org/0000-0002-9304-8817 https://orcid.org/0000-0003-1535-5835 114 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate economies are more resilient than lower-income countries, making their financial markets more predictable. However, Lee and Choi [4] emphasize that open economies, such as Switzerland, Denmark, and Sweden, are more vulnerable to global financial crises compared to more closed economies, such as Japan and other Asian nations. Based on the above considerations, this study aims to provide measurable results on the impact of macroeconomic indicators—including GDP per capita, short-term interest rates, inflation rates, and population growth—on stock market returns using advanced econometric analyses such as Vector Autoregression (VAR) and the Vector Error Correction Model (VECM). The findings of this research intend to serve as a valuable database for policymakers and investors in their decision-making processes. Through these analyses, the study aims to determine whether macroeconomic indicators in Switzerland, Sweden, and Denmark have any short-term or long-term relationship with stock market returns. The study also incorporates the Granger causality test to examine the direction of causality between macroeconomic variables and stock market returns. The research findings will contribute to the existing literature by providing empirical evidence on how macroeconomic indicators influence stock market performance across different economic environments. Additionally, the findings of this study will assist policymakers in formulating concrete macroeconomic policies that promote stable financial markets. At the same time, the results will support investors in making informed investment decisions, particularly regarding risk management and responsiveness to changes in financial market conditions. 2. Literature Review In the general literature, it is well established that macroeconomic indicators are decisive factors in the stability of capital markets. Therefore, analyzing these indicators is crucial for predicting stock market performance. Chen, et al. [5] emphasize that stock prices respond to external factors, particularly market conditions. Furthermore, relying on capital market theory, the authors argue that overall economic conditions can influence stock market prices. Based on their findings, it can be inferred that any variable affecting economic price mechanisms may impact stock market returns. From general knowledge and literature review, economic growth is recognized as a highly significant macroeconomic factor influencing stock market performance, as well as business profitability, investor confidence, and overall societal well-being. The research findings of Pan and Mishra [6] confirmed that, in the short term, no significant relationship exists between economic growth and the stock market. However, in the long run, their results demonstrated that economic growth fosters stock market development. Similarly, Mehrara, et al. [7] found a positive relationship between economic growth and stock market performance. On the other hand, Dabwor, et al. [8] who analyzed stock market returns and economic growth, identified a positive but statistically insignificant relationship. Many scholars consider the inflation rate a key determinant of financial market fluctuations. Countries with advanced financial systems, such as Switzerland, Denmark, and Sweden, implement various monetary policy instruments aimed at price stability. However, given that these three countries have open and internationally integrated economies, they are not immune to global financial crises. From general economic knowledge, it is understood that an increase in inflation leads to currency depreciation. Bahloul, et al. [9] highlight that the underlying cause of inflation is crucial—if inflation is driven by a monetary shock, it could result in lower interest rates, prompting investors to shift their assets from cash to stocks and bonds to maximize returns. Meanwhile, Fama and Gibbons [10] through the Mundell-Tobin model, confirm that high interest rates and expected inflation rates encourage asset reallocation from cash to bonds, ultimately reducing expected real stock market returns. Numerous authors have investigated the relationship between inflation and stock market returns. Humpe and Macmillan [11] established a negative long-term correlation between inflation and stock market prices, aligning with the findings of other scholars. Their results indicate that high inflation rates lead to market instability and create uncertainty among investors regarding long-term 115 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate investments. However, according to economic theory, a moderate inflation rate can stimulate economic growth and potentially lead to higher returns in stock markets. On the other hand, Bernanke and Kuttner [12] demonstrate that a tight monetary policy through high interest rates lowers stock prices, as it reduces investors' willingness to take on risk. Consistent with the findings of the aforementioned study, Jabeen, et al. [13] also confirmed a significant negative relationship between interest rates and stock market returns. Similarly, Bahloul, et al. [9] in their study on Islamic countries, found that short-term interest rates negatively affect stock market returns. According to their research, high interest rates decrease the present value of cash flows due to discounting, which in turn reduces investment incentives and negatively impacts stock market returns. Although there is limited research on the effect of population growth on stock market returns, the inclusion of this variable in the model is motivated by the fact that Switzerland, Denmark, and Sweden are highly developed economies that have experienced increasing migration inflows. Population growth indirectly influences financial market performance, as an increase in population can lead to higher consumer demand and an expanded labor force. This, in turn, can impact pension funds and contribute to corporate performance, as corporations may reinvest their profits into financial markets. Poterba [3] highlights that demographic demand driven by savings influences stock price appreciation. On the other hand, DellaVigna and Pollet [14] analyzed the impact of demographic changes across industries, arguing that such shifts affect profits and returns across various sectors. Their findings demonstrated that forecasted demographic demand five to ten years into the future can predict annual stock returns within specific industries. 3. Methodology The objective of this research is to examine the short-term and long-term relationship between macroeconomic indicators and stock market returns, focusing on Switzerland, Sweden, and Denmark. The study is based on secondary data covering the period from 1927 to 2021. Through empirical models, we aim to explore the interconnection between nominal stock market returns (N_RETURNS), GDP per capita (GDPCAP), inflation (CPI), short-term interest rates (IR_SH), and population growth (POPGR). Furthermore, part of the data was sourced from the database used in the working paper published by the Swiss National Bank (SNB) by Fuhrer and Herger [15]. This paper compiled data on population growth (POPGR), GDP per capita, the Consumer Price Index (CPI), and short-term interest rates for the period 1927-1970 for Switzerland, Sweden, and Denmark. Additionally, the same macroeconomic variables for the years 1970-2021 were retrieved from World Bank and OECD statistics. The frequency of the data for empirical analysis over the period 1927-2021 is annual. Data processing was applied only to GDP per capita, which was converted from USD to the logarithmic form of the variable. Based on the collected data, we seek to identify the impact of macroeconomic indicators on stock market returns. To test the variables, we will employ the Vector Autoregression (VAR) model, which identifies short-term relationships between past and present values for each variable. Additionally, we apply the Granger causality test to examine the causal relationships between the variables. Finally, if cointegration is present and the variables exhibit co-movement, we will adopt the Vector Error Correction Model (VECM), utilizing a restricted VAR framework. The empirical analysis will be conducted using EViews 12 statistical software. Considering the aforementioned steps, we aim to provide a more in-depth explanation before proceeding with our data analysis. In light of a step-by-step explanation of the methodology, we seek to address the following research questions: Q1: Is there a relationship between economic growth and stock market returns? Q2: Are inflation (CPI) and short-term interest rates (IR_SH) key determinants of stock market fluctuations? 116 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate Q3: Is there a relationship between population growth and stock market returns, and how does this relationship differ among Switzerland, Sweden, and Denmark? 4. Empirical Analysis Results 4.1. Unit Root Test Before proceeding with the VAR estimation, the variables must be integrated at the same level. Due to the importance of stationarity in individual variables, we test each variable separately. According to the literature, if any of the variables appear to be non-stationary, they must be integrated at order I(1). This process involves differencing the current value with its previous value (e.g., Xt – Xt-1), resulting in the loss of one observation. Hence, if a variable is non-stationary, it must be integrated at order I(1). The Augmented Dickey-Fuller (ADF) test and the Phillips-Perron (PP) test help us examine unit roots and compare the results based on probability rules. By applying the ADF and PP tests, there is an option to include only a constant within the regression, both a constant and a trend as coefficients, or none of them. Based on the literature, we can illustrate the regression model as follows: • d(Xt) = C1Xt-1 + C2 + et – Normal linear regression with constant (C2) • d(Xt) = C1Xt-1 + C2 + C3@Trend + et – Trend (@Trend) and constant (C2) within regression • d(Xt) = C1Xt-1 + et – Removing Trend and constant To conduct the unit root test, we use two approaches. First, we compare the t-statistics with the critical t-values; in this case, if the t-statistics are higher than the critical t-values at a 1% or 5% significance level, the variable is considered stationary. Second, we base our findings on the probability rule, as the analysis will be carried out in this section. When the p-value is less than 1% or 5%, it indicates that the variable is stationary (see Appendix A-1). Since some variables were found to be non-stationary in the unit root test (see Appendix A-1, Table 1), we integrated them at the first-order I(1). According to Brockwell and Davis (2016), the first difference unit root is simply the difference between the current and previous values of a given variable. In our case, the first-differenced variables appear as follows: DN_RETURNS = N_RETURNS – N_RETURNS (-1) DLGDPCAP = LGDPCAP – LGDPCAP (-1) DIR_SH = IR_SH – IR_SH (-1) DCPI = CPI – CPI (-1) DPOPGR = POPGR – POPGR (-1) Following this outlined structure, we test each variable individually, and the results are presented in Table 1. 117 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate Table 1. Unit root test results at level. Variables T-statistics (ADF) T- Critical Values 1% level of significance T- Critical Values 5% level of significance Probability (Prob.) Switzerland DN_RETURNS -8.018189 -3.506484 -2.894716 0.0000* DLGDPCAP -8.126713 -3.501445 -2.892536 0.0000* DIR_SH -8.943069 -3.502238 -2.892879 0.0000* DCPI -8.933392 -3.502238 -2.892879 0.0000* DPOPGR -8.323602 -3.501445 -2.892536 0.0000* Sweden DN_RETURNS -8.585508 -3.504727 -2.893956 0.0000* DLGDPCAP -7.626860 -3.501445 -2.892536 0.0000* DIR_SH -10.50919 -3.501445 -2.892536 0.0000* DCPI -8.681854 -3.503049 -2.893230 0.0000* `DPOPGR -7.260216 -3.502238 -2.892879 0.0000* Denmark DN_RETURNS -7.758891 -3.506484 -2.894716 0.0000* DLGDPCAP -8,955,249 -3.501445 -2.892536 0.0000* DIR_SH -11.05273 -3.501445 -2.892536 0.0000* DCPI -10.63478 -3.502238 -2.892879 0.0000* DPOPGR -7.483284 -3.501445 -2.892536 0.0000* Note: *- indicates that variables are stationary at level – 1% and 5% level of significance. According to Table 1, we have confirmation to proceed with the VAR model and the Granger Causality test, as all variables appear to be stationary at the first difference. 4.2. Results of Vector Auto Regression (VAR) Vector Auto Regression (VAR) models represent a methodology designed to address the research questions by analyzing the relationship between the selected variables. The literature defines VAR as a multi-equation model that includes more than one endogenous variable. In this way, we analyze the interrelationship between the selected variables while accounting for their past values and the influence of other variables within the regression framework. An illustration of the VAR methodology with a combination of two variables can be represented as follows: 𝑦1𝑡 = 𝛼12 + 𝛼13𝑦1𝑡−1 + ⋯ + 𝛼1𝑘𝑦1𝑡−𝑘 + 𝛽13𝑦2𝑡−1 + ⋯ + 𝛽1𝑘𝑦2𝑡−𝑘 + 𝑢1𝑡 𝑦2𝑡 = 𝛼21 + 𝛼22𝑦2𝑡−1 + ⋯ + 𝛼2𝑘𝑦2𝑡−𝑘 + 𝛽22𝑦1𝑡−1 + ⋯ + 𝛽1𝑘𝑦1𝑡−𝑘 + 𝑢2𝑡 This equation contains likewise the error term 𝑢𝑖𝑡 which is supposed to be in the line with the assumption E(𝑢𝑖𝑡)= 0, in the our case the expectation includes two regressions and two disturbance terms E(𝑢1𝑡, 𝑢2𝑡)= 0. This study examines three VAR models for three different countries. Furthermore, we use similar variables for the three VAR models (for Switzerland, Sweden, and Denmark) because, beyond identifying the relationships between the variables, we will also obtain comparable results across the three datasets, which may be significant for future research. We will analyze Switzerland, Sweden, and Denmark in separate VAR models to examine the short- term relationship between the following variables: (DN_RETURNS), (DLGDPCAP), (DCPI), (DIR_SH), and (DPOPGR). In the generated VAR results, we exclude the constant due to its insignificance. In this context, Brooks [16] argues that all results are statistically tested by comparing the t-statistics with the critical t-value, which is determined by the significance level (tα), the number of observations (T), and the number of variables used in the model. The critical t-value accounts for all variables in the model, and an illustration of the determination of critical t-values follows. 118 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate 𝑡𝑐 = ( 𝑡𝛼 2 ) ; 𝑇 − 𝑚 (1) According to this formula, we find the critical t-value, which is valid for all three VAR regressions used in this section, as we apply the same number of observations, variables, and significance level. 𝑡𝑐 = ( 0.05 2 ) ; 93 − 5 = 0.025 ; 88 = 1.9867 According to Brooks [16] whenever the t-statistics in absolute value are greater than the critical t- value, we can conclude that the relationship between the dependent and independent variables is statistically significant. From the results presented in Appendix A2 (Table 2.1) for Switzerland, we observe a positive and significant relationship between economic growth (DLGDPCAP) and stock market returns (DN_RETURNS). Additionally, there is a positive but insignificant relationship between population growth (DPOPGR), short-term interest rates (DIR_SH), and stock market returns. On the other hand, in the regression model for Switzerland, we find a negative and significant relationship between inflation (DCPI) and economic growth (DLGDPCAP), while there is also a positive and significant relationship between DLGDPCAP and DCPI. In the results presented in Appendix A2 (Table 2.2) for Sweden, we similarly observe a positive and significant relationship between economic growth (DLGDPCAP) and stock market returns (DN_RETURNS). Moreover, there is a positive and significant relationship between population growth (DPOPGR) and stock market returns (DN_RETURNS). However, inflation (DCPI) and short-term interest rates (DIR_SH) did not show any significant relationship with stock market returns (DN_RETURNS). Similarly, in the regression model results for Denmark, presented in Appendix A2 (Table 2.3), we find no significant short-term relationship between economic growth (DLGDPCAP) and stock market returns (DN_RETURNS). However, a significant reverse relationship is observed. Additionally, we find a positive and significant relationship between population growth (DPOPGR) and stock market returns. On the other hand, at the second level of analysis, we observe a negative relationship between short- term interest rates (DIR_SH) and stock market returns (DN_RETURNS). 4.3. Granger Causality Results Granger Causality is always a follow-up test after executing the VAR model. By performing the Granger Causality test, we can gain deeper insights into the relationship between the analyzed variables, determining whether one variable "Granger-causes" another, leading to either a unidirectional or bidirectional relationship between them. We execute the Pairwise Granger Causality test in EViews, which allows us to test the hypothesis derived from this approach. Based on the results of the Pairwise Granger Causality test, we verify whether a variable Granger- causes another by referring to the probability value (Prob). If the probability value is less than 0.01 or 0.05, we confirm the existence of Granger Causality between the variables. From the results presented in Appendix A2 (Table 2.4) for Switzerland, we observe that economic growth (DLGDPCAP) Granger-causes stock market returns (DN_RETURNS) in both directions. Additionally, we find Granger Causality between inflation (DCPI) and economic growth (DLGDPCAP) in both directions. However, this relationship is not observed between other variables. In the results presented in Appendix A2 (Table 2.5) for Sweden, we also observe that economic growth (DLGDPCAP) Granger-causes stock market returns (DN_RETURNS) in both directions. However, this is not the case for the relationship between economic growth (DLGDPCAP) and inflation (DCPI), as Granger Causality is found only in one direction. Additionally, population growth (DPOPGR) has a limited effect on stock market returns. Similar results are observed for Denmark, as presented in Appendix A2 (Table 2.6), where economic growth (DLGDPCAP) Granger-causes stock market returns (DN_RETURNS), but not vice versa. 119 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate Unlike the other two countries, in Denmark, stock market returns (DN_RETURNS) Granger-cause short-term interest rates (DIR_SH), but only in one direction. Furthermore, the results indicate that inflation (DCPI) Granger-causes economic growth (DLGDPCAP), but not in both directions, as the probability value is 0.07 > 0.05. The results confirm that there is no Granger Causality between the other variables. 4.4. Cointegration Test Results To apply the Johansen test, all variables must be integrated at the same order I(d), as supported by Brooks [16] who argues that "if a set of variables Xi,tX_(i,t) with different integration orders are combined, the combination will have an integration order equal to the highest among them" (p. 457). Considering this, we integrate all variables at order I(1), including those that are stationary. However, during the execution of the VECM model, the error correction term integrates the variables to be stationary at level. To adhere to the recommended literature, we apply the Johansen cointegration test using EViews. In this context, we ensure that sufficient evidence is available to answer the research questions regarding the long-term relationship between the variables. Furthermore, following the methodology outlined above, we use all variables integrated at order I(1). Before analyzing the results, it is essential to review the formulas for the Max-Eigen test and the Trace test. Formula for Trace Test: LRtr(r/n) = -T* Σ n (1 − λ^) (2) Formula for Max-Eigen Test: LRmax(r/ n +1) = −T * log (1 − λ^) (3) Table 2. Cointegration trace test results. Switzerland Variables: DN_RETURNS, DLGDPCAP, DIR_SH, DCPI, DPOPGR Hypothesized No. of CE(s) Eigen value Trace Statistic Critical Value at 5% Prob.** None * 0.59680 235.409 69.8188 0.0000* At most 1 * 0.47072 151.844 47.8561 0.0000* At most 2 * 0.40655 93.3089 29.787 0.0000* At most 3 * 0.26549 45.3017 15.4947 0.0000* At most 4 * 0.16794 16.9147 3.84146 0.0000* Sweden None * 0.57450 223.133 69.8188 0.0000* At most 1 * 0.47109 144.519 47.8561 0.0000* At most 2 * 0.32660 85.9205 29.7970 0.0000* At most 3 * 0.23722 49.5414 15.4947 0.0000* At most 4 * 0.23485 24.6279 3.84146 0.0000* Denmark None * 0.53254 201.820 69.8188 0.0000* At most 1 * 0.4279 131.859 47.8561 0.0000* At most 2 * 0.30195 80.4815 29.7970 0.0000* At most 3 * 0.25884 47.4098 15.4947 0.0000* At most 4 * 0.19408 19.8513 3.84146 0.0000* Note: * – Indicates significant result on testing the co-integration at 1% and 5% level of significance. Referring to Table 2, we conclude that there is a long-term relationship among the five variables in the three countries at a 1% significance level, confirming the existence of cointegration between stock market returns, GDP per capita, short-term interest rates, inflation rate, population growth, and stock market returns. The results presented in Table 2 (additional test results in Appendix A3) indicate that 120 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate VECM should be used to analyze the long-term interaction or relationship between the variables due to the presence of cointegration. 4.5. VECM Results The final step of the analysis is to examine the long-term relationship between the selected variables and attempt to answer the research questions. Since the findings suggested the existence of cointegration among the variables, it is essential to proceed with VECM to distinguish between short- term and long-term effects [17]. We follow this final step by running VECM on the long-term relationship between the variables, as previously done, by comparing the t-statistics with the critical t- values. These findings provide further support for the discussion and recommendations addressed in the following sections. From the VECM model results presented in Appendix A4 (Table 4.1) for Switzerland, we observe a negative and significant relationship between economic growth (LGDPCAP) and stock market returns (DN_RETURNS). A negative and significant relationship is also confirmed between inflation (DCPI) and economic growth (LGDPCAP). However, short-term interest rates, inflation, and population growth do not show a significant relationship with stock market returns, confirming that these indicators are not key determinants of long-term stock market returns. Similarly, the VECM analysis results for Sweden, presented in Appendix A4 (Table 4.2), show findings similar to those for Switzerland. A significant relationship is observed between stock market returns (DN_RETURNS) and economic growth (LGDPCAP), but not in the reverse direction. The results indicate that stock market returns positively impact GDP growth, but economic growth does not have a significant impact on stock market returns. Additionally, in Sweden, the findings confirm that in the long term, other macroeconomic factors are not key determinants of stock market returns. The VECM model results for Denmark, presented in Appendix A4 (Table 4.3), show nearly identical findings. The results confirm a positive relationship between stock market returns (DN_RETURNS) and economic growth (LGDPCAP), but again, no significant relationship is observed in the reverse direction. A positive but insignificant relationship is also identified between short-term interest rates and stock market returns. On the other hand, a negative but insignificant relationship is confirmed between inflation and stock market returns. 5. Discussion of Results The objective of this study was to examine the short-term and long-term relationships between macroeconomic indicators and stock market returns. We applied VAR models, Granger Causality, and VECM to address the research questions. The unit root test results indicated that the variables were non-stationary, requiring first order differencing to proceed with the VAR model. Cointegration and VECM were used to distinguish between short-term and long-term relationships among the variables and to support the study’s research objectives. The findings reveal mixed relationships across the three countries Switzerland, Sweden, and Denmark between macroeconomic indicators and stock market returns. The results confirm that economic growth has a significant positive short-term relationship with stock market returns, except in Denmark, where the relationship was insignificant. The Granger Causality test further supports that economic growth influences stock market returns in all three countries, as the probability coefficient (Prob.) < 0.05. Additionally, the results confirm a significant relationship between economic growth and stock market returns in Sweden, but not in Denmark, where the relationship was insignificant. On the other hand, in Switzerland, the findings indicate that long-term economic growth negatively impacts stock market returns. Based on the results, we can conclude that in Switzerland and Sweden, an increase in GDP contributes to higher stock market returns. According to the literature and the findings of this study, economic growth fluctuations can serve as a basis for forecasting stock market returns in these two 121 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate countries. However, this is not the case for Denmark, as economic growth has not been identified as a key determinant of stock market returns in either the short-term or long-term. The findings of this study align with those of Oskooe [18] who confirms a positive relationship between economic growth and stock market returns, emphasizing that GDP growth increases the expected future cash flow, which contributes to enhancing corporations' economic opportunities and profitability, ultimately leading to higher stock prices. Similarly, the results of Paramati and Gupta [19] confirm that economic growth plays a crucial role in determining stock price movements, supporting the argument that economic growth is likely to stimulate and foster stock market development through the proper reallocation of resources. On the other hand, Nordmark [20] who studied the relationship between economic growth and stock market returns in Sweden, found no significant relationship or Granger Causality between these indicators, confirming that economic growth in Sweden from 1993 to 2008 had no connection with stock market performance. Other researchers have suggested that economic growth does not necessarily reflect the expansion of existing firms, as it may also result from the entry of new businesses into the market, which might not directly impact stock market returns. The literature also suggests that global economic conditions and domestic monetary policies can contribute to the insignificant long-term relationship between economic growth and stock market returns [21]. The negative relationship between economic growth and stock market returns found in Pan and Mishra [6] in their study on China supports the argument that the Chinese stock market serves as a tool for government policy objectives rather than a true reflection of economic growth. They also point to the possible existence of irrational exuberance in China's stock markets, which can lead to financial bubbles. From a broader economic perspective, the negative effect of economic growth on stock market returns in Switzerland can be explained by the fact that Switzerland, as a highly developed and stable economy, is often used by investors as a safe haven to preserve their capital. However, when the global economy experiences rapid growth, investors might shift their capital to higher risk, higher return markets as part of their portfolio diversification strategy. This capital outflow can, in turn, have a negative long-term impact on stock market returns in Switzerland. The results of this study reveal varied relationships between inflation and stock market returns. Based on the VAR analysis, Granger Causality, and VECM models, we observe that inflation has a negative long-term relationship with stock market returns in Switzerland. On the other hand, the results for Sweden and Denmark indicate a positive relationship between inflation and stock market returns. The Granger Causality test results for these two countries, based on their coefficients (Prob. = 0.0035 for Sweden, Prob. = 0.0284 for Denmark), suggest that inflation movements may serve as a limited predictor of stock market returns. However, the relationship between inflation and stock market returns was not found to be statistically significant in any of the three countries. According to the research by Fama and Gibbons [10] moderate inflation can stimulate economic growth, which in turn contributes to higher stock market returns. However, the authors also emphasize that an increase in inflation rates due to monetary effects raises uncertainty among investors and reduces purchasing power, leading individuals to shift their holdings from cash to debt instruments. In line with these findings, Sathyanarayana and Gargesa [22] support the negative relationship between inflation and stock market returns, arguing that high inflation can affect the economy in multiple ways. It erodes the purchasing power of money, discourages investments, and reduces the value of savings, impacting all segments of the economy. The findings of this study confirm that in Sweden and Denmark, there is a negative relationship between short-term interest rates and stock market returns, although this relationship does not appear to be significant for Sweden. The Granger Causality test results also confirm that only in Denmark does the inflation rate impact stock market returns. 122 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate Analyzing this result, we can assume that as short-term interest rates increase, companies face higher costs, which in turn may lead to a rise in liabilities and, consequently, a decline in stock market returns. However, these effects were not observed in the long term, as no significant relationships were confirmed in any of the three countries. Previous research has presented varied findings on the relationship between these indicators. Campbell and Ammer [23] argue that nominal short-term interest rates may have a limited impact on stock returns, as fluctuations in the asset market are likely influenced by multiple factors. On the other hand, population growth showed a significant positive short-term relationship with stock market returns in Sweden and Denmark, but no significant relationship was found for Switzerland. The Granger Causality test also did not confirm a causal relationship between these two indicators. Poterba [3] examined the relationship between demographic changes and asset returns in the United States. The results of this study suggested a weak relationship between demographic changes and stock market returns. However, we can argue that population growth, based on age structure, may provide meaningful insights into identifying which demographic categories have a direct impact on financial markets, particularly young individuals and retirees. 6. Conclusion The objective of this study was to identify the relationships between macroeconomic indicators and stock market returns. To analyze these relationships in detail, we selected the same variables and frequency to determine whether Switzerland, Sweden, and Denmark yield similar results, allowing us to compare the findings. Through empirical analyses using VAR and VECM, we tested short-term and long-term relationships between macroeconomic indicators and stock market returns. Based on the results, we can confirm that economic growth was the most significant factor influencing stock market returns, although in the long term, this effect was not observed in Denmark and was found to be negative in Switzerland. Short-term interest rates had a negative short-term effect only in Denmark, but no significant relationship was observed between interest rates and stock market returns in the other two countries. The findings also revealed a complex relationship between population growth and stock market returns in Sweden and Denmark, but no significant relationship was found for Switzerland. The results further indicated that inflation was not a significant determinant of stock market returns in any of the countries studied. Given the negative effect of economic growth on stock market returns in Switzerland, we suggest that investors should be aware that economic growth may signal a decline in stock market returns in the long term. Therefore, the results recommend that investors adopt a portfolio diversification strategy to manage the negative impact on stock market returns. Conversely, investors in Sweden and Denmark benefit from economic growth, as it positively affects their stock market returns. Additionally, the results suggest that investors in Denmark should be cautious about short-term interest rates, especially during periods of tight monetary policy. On the other hand, the findings recommend that policymakers in Switzerland should manage the negative impact of economic growth on stock market returns by implementing policies that diversify the financial market. Further research is needed to deepen the analysis of the negative effects of economic growth on stock market returns, including sectoral analyses and long-term effects of integrating new populations into stock market sectors. Transparency: The authors confirm that the manuscript is an honest, accurate, and transparent account of the study; that no vital features of the study have been omitted; and that any discrepancies from the study as planned have been explained. This study followed all ethical practices during writing. 123 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate Copyright: © 2025 by the authors. This open-access article is distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). References [1] A. M. Khan, H. Ali, H. Shabbir, F. Noor, and D. M. Majid, "Impact of macroeconomic indicators on stock market predictions: A cross-country analysis," Journal of Computing & Biomedical Informatics, vol. 8, no. 1, pp. 1–13, 2024. [2] J. Geanakoplos, M. Magill, and M. Quinzii, "Demography and the long-run predictability of the stock market," Brookings Papers on Economic Activity, vol. 1, pp. 241–325, 2004. https://dx.doi.org/10.1353/eca.2004.0010 [3] J. M. Poterba, "Demographic structure and asset returns," The Review of Economics and Statistics, vol. 83, no. 4, pp. 565-584, 2001. https://doi.org/10.1162/003465301753237650 [4] M.-J. Lee and S.-Y. Choi, "Comparing market efficiency in developed, emerging, and frontier equity markets: A multifractal detrended fluctuation analysis," Fractal and Fractional, vol. 7, no. 6, p. 478doi: https://doi.org/10.3390/fractalfract7060478. [5] N. F. Chen, R. Roll, and S. A. Ross, "Economic forces and the stock market," Journal of Business, vol. 59, no. 3, pp. 383–403, 1986. https://doi.org/10.1086/296344 [6] L. Pan and V. Mishra, "Stock market development and economic growth: Empirical evidence from China," Economic Modelling, vol. 68, pp. 661-673, 2018. https://doi.org/10.1016/j.econmod.2017.07.005 [7] M. Mehrara, G. Y. Farahani, F. Faninam, and R. A. Karsalari, "The effect of macroeconomic variables on the stock market index of the Tehran stock exchange," International Letters of Social and Humanistic Sciences, vol. 71, pp. 17–24, 2016. [8] T. D. Dabwor, T. P. Iorember, and Y. S. Danjuma, "Stock market returns, globalization and economic growth in Nigeria: Evidence from volatility and cointegrating analyses," Journal of Public Affairs, vol. 22, no. 2, p. e2393, 2022. https://doi.org/10.1002/pa.2393 [9] S. Bahloul, M. Mroua, and N. Naifar, "The impact of macroeconomic and conventional stock market variables on Islamic index returns under regime switching," Borsa Istanbul Review, vol. 17, no. 1, pp. 62-74, 2017. https://doi.org/10.1016/j.bir.2016.09.003 [10] E. F. Fama and M. R. Gibbons, "Inflation, real returns and capital investment," Journal of Monetary Economics, vol. 9, no. 3, pp. 297-323, 1982. https://doi.org/10.1016/0304-3932(82)90021-6 [11] A. Humpe and P. Macmillan, "Can macroeconomic variables explain long-term stock market movements? A comparison of the US and Japan," CDMA Working Paper No. 07/20. Centre for Dynamic Macroeconomic Analysis, University of St Andrews, 2007. https://doi.org/10.2139/ssrn.1026219 [12] B. S. Bernanke and K. N. Kuttner, "What explains the stock market’s reaction to federal reserve policy?," Journal of Finance, vol. 60, no. 3, pp. 1221–1257, 2005. https://doi.org/10.1111/j.1540-6261.2005.00760.x [13] A. Jabeen, M. Yasir, Y. Ansari, S. Yasmin, J. Moon, and S. Rho, "An empirical study of macroeconomic factors and stock returns in the context of economic uncertainty news sentiment using machine learning," Complexity, p. 4646733, 2022. https://doi.org/10.1155/2022/4646733 [14] S. DellaVigna and M. J. Pollet, "Demographics and industry returns," American Economic Review, vol. 97, no. 5, pp. 1667–1702, 2007. https://doi.org/10.1257/aer.97.5.1667 [15] L. Fuhrer and N. Herger, "Real interest rates and demographic developments across generations: A panel-data analysis over two centuries," SNB Working Papers, 2021. https://www.snb.ch/n/mmr/reference/working_paper_2021_07/source/working_paper_2021_07 [16] C. Brooks, Introductory econometrics for finance, 4th ed. Cambridge, UK: Cambridge University Press, 2019. [17] H. A. Studenmund, Using econometrics: A practical guide, 6th ed. Harlow, England: Pearson Education, 2014. [18] P. A. S. Oskooe, "Emerging stock market performance and economic growth," American Journal of Applied Sciences, vol. 7, no. 2, pp. 265–269, 2010. https://doi.org/10.3844/ajassp.2010.265.269 [19] S. R. Paramati and R. Gupta, "An empirical analysis of stock market performance and economic growth: Evidence from India," International Research Journal of Finance and Economics, vol. 73, pp. 133–149, 2011. https://doi.org/10.2139/ssrn.2335996 [20] J. Nordmark, "Stock returns and production growth in Sweden: Is there a relationship?," Bachelor Thesis, The School of Management and Economics DiVA Portal, 2009. [21] MSCI Barra Research, "Is there a link between GDP growth and equity returns?," MSCI Barra, 2010. https://www.msci.com/documents/10199/a134c5d5-dca0-420d-875d-06adb948f578 [22] S. Sathyanarayana and S. Gargesa, "An analytical study of the effect of inflation on stock market returns," IRA- International Journal of Management & Social Sciences, vol. 13, no. 2, pp. 48–64, 2018. https://doi.org/10.21013/jmss.v13.n2.p3 [23] Y. J. Campbell and J. Ammer, "What moves the stock and bond markets? A variance decomposition for long-term asset returns," The Journal of Finance, vol. 48, no. 1, pp. 3–37, 1993. https://doi.org/10.1111/j.1540- 6261.1993.tb04700.x https://creativecommons.org/licenses/by/4.0/ https://dx.doi.org/10.1353/eca.2004.0010 https://doi.org/10.1162/003465301753237650 https://doi.org/10.3390/fractalfract7060478 https://doi.org/10.1086/296344 https://doi.org/10.1016/j.econmod.2017.07.005 https://doi.org/10.1002/pa.2393 https://doi.org/10.1016/j.bir.2016.09.003 https://doi.org/10.1016/0304-3932(82)90021-6 https://doi.org/10.2139/ssrn.1026219 https://doi.org/10.1111/j.1540-6261.2005.00760.x https://doi.org/10.1155/2022/4646733 https://doi.org/10.1257/aer.97.5.1667 https://www.snb.ch/n/mmr/reference/working_paper_2021_07/source/working_paper_2021_07 https://doi.org/10.3844/ajassp.2010.265.269 https://doi.org/10.2139/ssrn.2335996 https://www.msci.com/documents/10199/a134c5d5-dca0-420d-875d-06adb948f578 https://doi.org/10.21013/jmss.v13.n2.p3 https://doi.org/10.1111/j.1540-6261.1993.tb04700.x https://doi.org/10.1111/j.1540-6261.1993.tb04700.x 124 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate Appendix A1. Table 1. Unit Root Test. Variables T-statistics (ADF) Adj. T- statistics (PP) T- Critical Values 1% level of significance T- Critical Values 5% level of significance Probability (Prob.) Switzerland N_RETURNS -9.357663 -9.78198 -3.500669 -2.8922 0.0000* LGDPCAP -0.154261 2.11166 -3.500669 -2.8922 0.9394 IR_SH -3.136996 -3.10064 -3.500669 -2.8922 0.0272* CPI -4.680057 -3.60768 -3.501445 -2.892536 0.0002* POPGR -3.613771 -3.16316 -3.501445 -2.892536 0.0072* Sweden N_RETURNS -7.903702 -9.38974 -3.501445 -2.892536 0.0000* LGDPCAP -1.186342 -1.18634 -3.500669 -2.892200 0.6778 IR_SH -1.227858 -1.05492 -3.500669 -2.892200 0.6598 CPI -3.947785 -3.91026 -3.500669 -2.892200 0.0025* POPGR -3.032522 -1.96344 -3.501445 -2.892536 0.0355* Denmark N_RETURNS -9.034881 -9.08846 -3.500669 -2.8922 0.0000* LGDPCAP -0.707323 -0.70859 -3.500669 -2.8922 0.8391 IR_SH -1.286927 -1.25157 -3.500669 -2.8922 0.6331 CPI -5.525335 -5.52727 -3.500669 -2.8922 0.0000* POPGR -2.005475 -1.59761 -3.501445 -2.892536 0.2841 Note: *- indicates that variables are stationary at level – 1% and 5% level of significance. Table 1.1. ADF – Unit Root test for Switzerland. Null Hypothesis: N_RETURNS has a unit root Exogenous: Constant Lag Length: 0 (Automatic - based on SIC, maxlag=11) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -9.35766 0 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Null Hypothesis: IR_SH has a unit root Exogenous: Constant Lag Length: 0 (Automatic - based on SIC, maxlag=11) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -3.137 0.0272 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Null Hypothesis: CPI has a unit root Exogenous: Constant Lag Length: 1 (Automatic - based on SIC, maxlag=11) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -3.61377 0.0072 Test critical values: 1% level -3.50145 5% level -2.89254 125 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate 10% level -2.58337 Table 1.2. PP – Unit Root Test for Switzerland. Null Hypothesis: N_RETURNS has a unit root Exogenous: Constant Bandwidth: 11 (Newey-West automatic) using Bartlett kernel Adj. t-Stat Prob.* Phillips-Perron test statistic -9.78199 0.000 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Null Hypothesis: IR_SH has a unit root Exogenous: Constant Bandwidth: 2 (Newey-West automatic) using Bartlett kernel Adj. t-Stat Prob.* Phillips-Perron test statistic -3.10065 0.0298 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Null Hypothesis: POPGR has a unit root Exogenous: Constant Bandwidth: 3 (Newey-West automatic) using Bartlett kernel Adj. t-Stat Prob.* Phillips-Perron test statistic -3.16317 0.0254 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Null Hypothesis: LGDPCAP has a unit root Exogenous: Constant Bandwidth: 3 (Newey-West automatic) using Bartlett kernel Adj. t-Stat Prob.* Phillips-Perron test statistic -2.20738 0.9328 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Null Hypothesis: CPI has a unit root Exogenous: Constant Bandwidth: 6 (Newey-West automatic) using Bartlett kernel Adj. t-Stat Prob.* Phillips-Perron test statistic -3.60768 0.0073 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Table 1.2.1. ADF – Unit Root test for Sweden. Null Hypothesis: N_RETURNS has a unit root Exogenous: Constant Lag Length: 1 (Automatic - based on SIC, maxlag=11) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -7.9037 0 Test critical values: 1% level -3.50145 5% level -2.89254 10% level -2.58337 Null Hypothesis: IR_SH has a unit root Exogenous: Constant 126 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate Lag Length: 0 (Automatic - based on SIC, maxlag=11) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -1.22786 0.6598 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Null Hypothesis: POPGR has a unit root Exogenous: Constant Lag Length: 1 (Automatic - based on SIC, maxlag=11) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -3.03252 0.0355 Test critical values: 1% level -3.50145 5% level -2.89254 10% level -2.58337 Null Hypothesis: LGDPCAP has a unit root Exogenous: Constant Lag Length: 0 (Automatic - based on SIC, maxlag=11) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -1.18634 0.6778 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Null Hypothesis: CPI has a unit root Exogenous: Constant Lag Length: 0 (Automatic - based on SIC, maxlag=11) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -3.94779 0.0025 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Table 1.2.2. PP – Unit Root Test for Sweden. Null Hypothesis: N_RETURNS has a unit root Exogenous: Constant Bandwidth: 9 (Newey-West automatic) using Bartlett kernel Adj. t-Stat Prob.* Phillips-Perron test statistic -9.38975 0 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Null Hypothesis: IR_SH has a unit root Exogenous: Constant Bandwidth: 2 (Newey-West automatic) using Bartlett kernel Adj. t-Stat Prob.* Phillips-Perron test statistic -1.05492 0.7307 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Null Hypothesis: POPGR has a unit root Exogenous: Constant Bandwidth: 0 (Newey-West automatic) using Bartlett kernel Adj. t-Stat Prob.* Phillips-Perron test statistic -1.96344 0.3024 Test critical values: 1% level -3.50067 5% level -2.8922 127 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate 10% level -2.58319 Null Hypothesis: LGDPCAP has a unit root Exogenous: Constant Bandwidth: 0 (Newey-West automatic) using Bartlett kernel Adj. t-Stat Prob.* Phillips-Perron test statistic -1.18634 0.6778 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Null Hypothesis: CPI has a unit root Exogenous: Constant Bandwidth: 7 (Newey-West automatic) using Bartlett kernel Adj. t-Stat Prob.* Phillips-Perron test statistic -3.91027 0.0029 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Table 1.3. ADF – Unit Root test Denmark. Null Hypothesis: N_RETURNS has a unit root Exogenous: Constant Lag Length: 0 (Automatic - based on SIC, maxlag=11) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -9.03488 0 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Null Hypothesis: IR_SH has a unit root Exogenous: Constant Lag Length: 0 (Automatic - based on SIC, maxlag=11) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -1.28693 0.6331 Test critical values: 1% level -3.50067 5% level -2.8922 10% level -2.58319 Null Hypothesis: POPGR has a unit root Exogenous: Constant Lag Length: 1 (Automatic - based on SIC, maxlag=11) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -2.00548 0.2841 Test critical values: 1% level -3.50145 5% level -2.89254 10% level -2.58337 Null Hypothesis: LGDPCAP has a unit root Exogenous: Constant Lag Length: 0 (Automatic - based on SIC, maxlag=11) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -0.707323 0.8391 Test critical values: 1% level -3.500669 5% level -2.8922 10% level -2.583192 Null Hypothesis: CPI has a unit root Exogenous: Constant Lag Length: 0 (Automatic - based on SIC, maxlag=11) t-Statistic Prob.* 128 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate Augmented Dickey-Fuller test statistic -5.525335 0 Test critical values: 1% level -3.500669 5% level -2.8922 10% level -2.583192 Table 1.3.1. PP – Unit Root Test Denmark. Null Hypothesis: N_RETURNS has a unit root Exogenous: Constant Bandwidth: 5 (Newey-West automatic) using Bartlett kernel Adj. t-Stat Prob.* Phillips-Perron test statistic -9.088461 0 Test critical values: 1% level -3.500669 5% level -2.8922 10% level -2.583192 Null Hypothesis: IR_SH has a unit root Exogenous: Constant Bandwidth: 3 (Newey-West automatic) using Bartlett kernel Adj. t-Stat Prob.* Phillips-Perron test statistic -1.251577 0.6492 Test critical values: 1% level -3.500669 5% level -2.8922 10% level -2.583192 Null Hypothesis: POPGR has a unit root Exogenous: Constant Bandwidth: 0 (Newey-West automatic) using Bartlett kernel Adj. t-Stat Prob.* Phillips-Perron test statistic -1.597619 0.4799 Test critical values: 1% level -3.500669 5% level -2.8922 10% level -2.583192 Null Hypothesis: LGDPCAP has a unit root Exogenous: Constant Bandwidth: 4 (Newey-West automatic) using Bartlett kernel Adj. t-Stat Prob.* Phillips-Perron test statistic -0.708593 0.8388 Test critical values: 1% level -3.500669 5% level -2.8922 10% level -2.583192 Null Hypothesis: CPI has a unit root Exogenous: Constant Bandwidth: 4 (Newey-West automatic) using Bartlett kernel Adj. t-Stat Prob.* Phillips-Perron test statistic -5.527276 0 Test critical values: 1% level -3.500669 5% level -2.8922 10% level -2.583192 Apendix A 2. VAR Model Results for Switzerland, Sweden and Denmark 129 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate Table 2.1. VAR Model Results for Switzerland. Included observations: 93 after adjustments Standard errors in () & t-statistics in [] DN RETU… DLGDPPCAP DIR_SH DCPI DPOPGPR DN RETURNS(-1) -0.57024 0.025551 -0.592269 -0.75608 0.239407 -0.10453 -0.00606 -0.66333 -0.98834 -0.15758 [-5.45550] [4.21401] [-0.89287] [-0.76655] [1.51925] DN RETURNS(-2) -0.47849 0.012515 0.444013 -0.18367 0.298322 -0.11092 -0.00643 -0.70388 -1.05883 -0.16722 [-4.31398] [1.94523] [0.63081] [-0.17548] [1.78405] DLGDPPCAP(-1) -0.79092 0.231122 8.80685 -0.00283 1.815947 -1.68265 -0.09761 -10.6783 -0.00065 -2.53876 [-0.47006] [2.36792] [0.82463] [-4.32754] [0.71585] DLGDPPCAP(-2) -3.14766 0.482542 -0.699353 -28.0936 0.028742 -1.09568 -0.09836 -10.761 -16.001 -2.55641 [-1.85615] [4.70248] [-0.08499] [-1.75574] [0.01124] DIR_SH(-1) -0.00046 0.001004 -0.08054 0.238075 -0.01244 -0.01808 -0.00105 -0.11475 -0.17062 -0.02726 [-0.25586] [0.95724] [-0.70109] [1.39534] [-0.45851] DIR_SH(-2) 0.000598 4.75E-05 -0.301232 -0.15339 -0.00075 -0.01823 -0.00106 -0.11571 0.17205) -0.02749 [0.03277] [0.04493] [-2.60341] [-0.89156] [-0.02737] DCPI(-1) 0.011466 40.98592 0.087227 0.18002 0.000156 (0.01128) -15.878 -0.07159 -0.10644 -0.01701 [1.01649] [2.58130] [1.21849] [1.69122] [0.00917] DCPI(-2) -0.00156 0.046608 (0.07200) [0.64731] -0.24713 -0.01533 -0.01135 -0.00066 -0.10706 -0.01711 [-0.30189] [-2.36525] [-2.30821] [0.89623] DPOPGPR(-1) 0.016612 0.000153 0.095551 -0.10961 0.189581 -0.07209 -0.00418 -0.45746 -0.68022 -0.10868 [1.23045] [0.03670] [0.20887] [-0.15967] [1.74428] DPOPGPR(-2) -0.13714 0.001022 0.32592 0.717994 -0.128367 -0.07178 -0.00416 -0.45551 -0.67732 -0.10821 [-1.83542] [0.24547] [0.71551] [1.06006] [-1.19626] R squared 0.352529 0.293265 0.120368 0.240042 0.135106 Adj. R squared 0.282322 0.216631 0.024987 0.157637 0.041322 Suma sq.resids 3.977944 0.013385 160.2044 354.2117 9.041206 S.E. equation 0.218922 0.012699 1.389307 2.06582 0.330047 F statistic 5.021239 3.826829 1.261963 2.912952 1.440614 Log likelihood 14.59901 279.3876 -157.25 -194.1455 -23.5792 Akaike AIC -0.0989 -5.79328 3.596782 4.390226 0.722133 Schwarz SC -0.17342 -5.52096 3.869105 4.662549 0.994455 Mean dependent 0.000163 0.008627 -0.04581 -0.004497 -0.00027 S.D. dependent 0.25842 0.014348 1.406996 2.25063 0.337065 130 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate Table 2.2. VAR Model Results for Sweden. Included observations: 93 after adjustments Standard errors in ( ) & t-statistics in [ ] DN RETU… DLGDPPCAP DIR_SH DCPI DPOPGPR DN RETURNS(-1) -0.576126 0.020519 -0.532162 -1.260066 0.044361 -0.1113 -0.00588 -0.52078 -1.23144 -0.05422 [-5.17850] [3.61105] [-1.02190] [-102325] [0.81822] DN RETURNS(-2) -0.472602 0.000739 0.775627 2.086518 0.098338 -0.12353 -0.00631 -0.578 -1.36679 -0.06018 [-3.82583] [0.11714] [1.34192] [1.52658] [1.63418] DLGDPPCAP(-1) -1.083599 0.471417 3.864048 23.35645 -2.035205 -2.13323 -0.10892 -9.98145 -23.6031 -1.03918 [-0.50796] [4.32829] [0.38712] [0.98955] [-1.95848] DLGDPPCAP(-2) -3.197765 0.206069 1.805527 15.68147 1.689876 -2.20182 -0.11242 -10.3024 -24.362 -1.07259 [-1.45233] [1.83307] [0.17525] [0.64369] [1.57551] DIR_SH(-1) 0.015884 -0.001541 -0.092326 0.285092 -0.004143 -0.02491 -0.00127 -0.11655 -0.27561 -0.01213 [0.63687] [-1.21150] [-0.79215] [1.03441] [-0.34141] DIR_SH(-2) -0.039783 -0.000753 -0.129628 -0.081006 0.003829 -0.02516 -0.00128 -0.11775 -0.27843 -0.01226 [-1.58090] [-0.58611] [-1.10092] [-0.29093] [0.31235] DCPI(-1) -0.009082 -0.000406 0.060071 -0.126572 -0.003191 (0..00953) -0.00049 -0.04461 -0.10549 -0.00464 [-0.95260] [-0.83458] [1.34655] [-1.19983] [-0.68699] DCPI(-2) 0.003492 0.000246 0.043625 -0.234265 -0.00078 -0.00925 -0.00047 -0.04326 -0.10231 -0.0045 [0.37769] [0.52054] [1.00835] [-2.28986] [-0.17321] DPOPGPR(-1) -0.410401 0.023836 1.118205 4.50164 0.470046 -0.223 -0.01139 -1.04344 -2.48741 -0.10863 [-1.84034] [2.09346] [1.07166] [1.82444] [4.32692] DPOPGPR(-2) 0.084039 -0.021232 -0.853256 -3.818029 -0.252957 -0.22522 -0.0115 -1.05383 -2.49199 -0.10972 [0.37313] [-1.84640] [-0.80967] [-1.53212] [-2.30558] R squared 0.355886 0.15941 0.098959 0.218354 0.222915 Adj. R squared 0.286042 0.068262 0.001255 0.133598 0.138653 Suma sq.resids 5.076655 0.013234 111.1445 621.3992 1.2047 S.E. equation 0.247315 0.012627 1.157191 2.73641 0.120476 F statistic 5.09546 1.748906 1.261963 2.576246 2.645496 Log likelihood 3.258246 279.9168 -140.2491 -220.2897 70.14487 Akaike AIC 0.141984 -5.804663 3.231162 4.952466 -1.293438 Schwarz SC 0.417306 -5.53234 3.503485 5.224788 -1.021115 Mean dependent 0.001866 0.009775 -0.05957 0.02326 0.004315 S.D. dependent 0.292694 0.013081 1.157918 2.939824 0.129811 131 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate Table 2.3. VAR Model Results for Denmark. Included observations: 93 after adjustments Standard errors in ( ) & t-statistics in [ ] DN RETU… DLGDPPCAP DIR_SH DCPI DPOPGPR DN RETURNS(-1) -0.534584 (0.10902) [-4.90356] 0.005879 (0.00881) [0.66753] -2.016642 (0.60903) [-3.31122] -2.951458 (1.46046) [-2.02091] 0.023507 (0,04568) [0.51456] DN RETURNS(-2) -0.488268 (0.11321) [-4.31284] 0.003188 (0.00915) [0.34859] 0.742652 (0.63246) [1.17423] 0.578448 (1.51663) [0.38140] 0.061808 (0.04744) [1.30284] DLGDPPCAP(-1) -1.451574 (1.36409) [-1.06414] 0.148861 (0.11021) [1.35075] 3741481 (7.62042) [0.49098] 22.75496 (18.2737) [1.24523] 1.354397 (0.57161) [2.36943] DLGDPPCAP(-2) -2.347758 (1.38205) [-1.69876] 0.263779 (0.11166) [2.36240] 5.516321 (7.72076) [0.71448] 21.39323 (18.5143) [1.15549] 0.937153 (0.57914) [1.61819] DIR_SH(-1) 0.027959 (0.02113) [1.32303] -0.000569 (0.00171) [-0.33348] -0.009786 (0.11806) [-0.08289] 0.095374 (0.28310) [0.33689] -0.004551 (0.00886) [-0.51389] DIR_SH(-2) -0.042622 (0.02035) [-2.09409] -0.000867 (0.00164) [-0.52751] 0.075248 (0.11370) [0.66180] 0.024242 (0.27266) [0.08891] -0.004588 (0.00853) [-0.53796] DCPI(-1) 0.004711 (0.00830) [0.56775] -0.002402 (0.00067) [-3.58236] -0.018264 (0.04636) [-0.39399] - 0.005572 (0.11116) [-0.05013] -0.009743 (0.00348) [-2.80212] DCPI(-2) -0.002403 (0.00765) [-0.31398] 0.001163 (0.00062) [1.88203] -0.030859 (0.04275) [-0.72188] -0.307560 (0.10251) [-3.00034] 0.001425 (0.00321) [0.44451] DPOPGPR(-1) 0.598059 (0.26255) [2.27785] 0.004862 (0.02121) [0.22919] -0.893434 (1.46675) [-0.60913] 1.028779 (3.51726) [0.29249] 0.280112 (0.11002) [2.54597] DPOPGPR(-2) 0.221692 (0.25743) [0.86117] -0.014488 (0.02080) [-0.69662] -1.555816 (1.43814) [-1.08182] -0.702143 (3.44866) [-0.20360] -0.100700 (0.10788) [-0.93348] R squared 0.384563 0.071063 0.200518 0.229046 0.198097 Adj. R squared Suma sq.resids 0.317829 4.110314 -0.029665 0.026829 0.113827 128.2773 0.145448 737.6439 0.111144 0.721762 S.E. equation 0.222535 0.017979 1.243185 2.981153 0.093252 F statistic 5.762622 0.705490 2.313021 2.739867 2.278203 Log likelihood 13.07687 247.0546 -146.9154 -228.2564 93.96637 Akaike AIC -0.066169 -5.097948 3.374526 5.123793 -1.805728 Schwarz SC 0.206153 -4.825625 3.646848 5.396115 -1.533406 Mean dependent 0.001382 0.008820 -0.055170 -0.009107 -0.002622 S.D. dependent 0.269434 0.017718 1.320616 3.224892 0.098910 132 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate Granger Causality Results Table 2.4. Pairwise Granger Causality test for Switzerland. Sample: 1927 2021 Lags: 2 Null Hypothesis: Obs. F-Statistic Prob. DLGDPCAP does not Granger Cause DN_RETURNS 93 4.85645 0.0100 DN_RETURNS does not Granger Cause DLGDPCAP 5.61359 0.0051 DIR_SH does not Granger Cause DN_RETURNS 93 0.04921 0.9520 DN_RETURNS does not Granger Cause DIR_SH 0.47971 0.6206 DCPI does not Granger Cause DN_RETURNS 93 0.21171 0.8096 DN_RETURNS does not Granger Cause DCPI 0.23737 0.7892 DPOPGR does not Granger Cause DN_RETURNS 93 2.14126 0.1236 DN_RETURNS does not Granger Cause DPOPGR 2.81151 0.0655 DIR_SH does not Granger Cause DLGDPCAP 93 1.11190 0.3335 DLGDPCAP does not Granger Cause DIR_SH 1.23164 0.2968 DCPI does not Granger Cause DLGDPCAP 93 10.6561 7.E-05 DLGDPCAP does not Granger Cause DCPI 4.02258 0.0213 DPOPGR does not Granger Cause DLGDPCAP 93 0.20431 0.8156 DLGDPCAP does not Granger Cause DPOPGR 1.13117 0.3273 DCPI does not Granger Cause DIR_SH 93 1.31903 0.2726 DIR_SH does not Granger Cause DCPI 1.44029 0.2424 DPOPGR does not Granger Cause DIR_SH 93 0.36364 0.6962 DIR_SH does not Granger Cause DPOPGR 0.71528 0.4919 DPOPGR does not Granger Cause DCPI 93 0.39514 0.6748 DCPI does not Granger Cause DPOPGR 0.75070 0.4750 Table 2.5. Pairwise Granger Causality test for Sweden. Sample: 1927 2021 Lags: 2 Null Hypothesis: Obs. F-Statistic Prob. DLGDPCAP does not Granger Cause DN_RETURNS 93 6.02731 0.0035 DN_RETURNS does not Granger Cause DLGDPCAP 7.51555 0.0010 DIR_SH does not Granger Cause DN_RETURNS 93 1.06761 0.3482 DN_RETURNS does not Granger Cause DIR_SH 1.05179 0.3537 DCPI does not Granger Cause DN_RETURNS 93 0.89914 0.4106 DN_RETURNS does not Granger Cause DCPI 1.99228 0.1425 DPOPGR does not Granger Cause DN_RETURNS 93 1.16692 0.3161 DN_RETURNS does not Granger Cause DPOPGR 0.57747 0.5634 DIR_SH does not Granger Cause DLGDPCAP 93 2.56074 0.0830 DLGDPCAP does not Granger Cause DIR_SH 1.21191 0.3025 DCPI does not Granger Cause DLGDPCAP 93 0.78810 0.4579 DLGDPCAP does not Granger Cause DCPI 3.82426 0.0256 DPOPGR does not Granger Cause DLGDPCAP 93 2.06736 0.1326 DLGDPCAP does not Granger Cause DPOPGR 1.67692 0.1929 DCPI does not Granger Cause DIR_SH 93 0.85636 0.4282 DIR_SH does not Granger Cause DCPI 1.33676 0.2680 DPOPGR does not Granger Cause DIR_SH 93 0.36412 0.6958 DIR_SH does not Granger Cause DPOPGR 0.33691 0.7149 133 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate DPOPGR does not Granger Cause DCPI 93 2.26620 0.1097 DCPI does not Granger Cause DPOPGR 0.16260 0.8502 Table 2.6. Pairwise Granger Causality test for Denmark. Sample: 1927 2021 Lags: 2 Null Hypothesis: Obs. F-Statistic Prob. DLGDPCAP does not Granger Cause DN_RETURNS 93 3.71115 0.0284 DN_RETURNS does not Granger Cause DLGDPCAP 0.50304 0.6064 DIR_SH does not Granger Cause DN_RETURNS 93 2.58758 0.0809 DN_RETURNS does not Granger Cause DIR_SH 7.38530 0.0011 DCPI does not Granger Cause DN_RETURNS 93 0.64040 0.5295 DN_RETURNS does not Granger Cause DCPI 1.89163 0.1569 DPOPGR does not Granger Cause DN_RETURNS 93 2.36128 0.1002 DN_RETURNS does not Granger Cause DPOPGR 0.44617 0.6415 DIR_SH does not Granger Cause DLGDPCAP 93 0.30428 0.7384 DLGDPCAP does not Granger Cause DIR_SH 1.15168 0.3208 DCPI does not Granger Cause DLGDPCAP 93 9.25918 0.0002 DLGDPCAP does not Granger Cause DCPI 2.60884 0.0793 DPOPGR does not Granger Cause DLGDPCAP 93 0.42177 0.6572 DLGDPCAP does not Granger Cause DPOPGR 1.07097 0.3471 DCPI does not Granger Cause DIR_SH 93 0.29401 0.7460 DIR_SH does not Granger Cause DCPI 0.12803 0.8800 DPOPGR does not Granger Cause DIR_SH 93 2.33328 0.1029 DIR_SH does not Granger Cause DPOPGR 0.67144 0.5136 DPOPGR does not Granger Cause DCPI 93 0.17399 0.8406 DCPI does not Granger Cause DPOPGR 2.21896 0.1148 Appendix A 3. Cointegration test. Table 3.1. Testing residuals for unit root in three data sets. Switzerland Variable Probability t-statistics (ADF) Critical Values 1% level of significance Critical Values 5% level of significance Probability Resid-Swiss -11.11596 -3.502238 -2.892879 0.0001* Sweden Variable Probability t-statistics (ADF) Critical Values 1% level of significance Critical Values 5% level of significance Probability Resid-Sweden -11.13024 -3.502238 -2.892879 0.0001* Denmark Variable Probability t-statistics (ADF) Critical Values 1% level of significance Critical Values 5% level of significance Probability Resid-Denmark -9.863267 -3.502238 -2.892879 0.0000* 134 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate Appendix A 4. VECM Model Results for Switzerland, Sweden and Denmark. Table 4.1. VECM Model Results for Switzerland. Vector Error Correction Estimates Date: 06/28/22 Time: 00:26 Sample (adjusted): 1930 2021 Included observations: 92 after adjustments Standard errors in () & t-statistics in [] Error Correction: D(DN RET… D(DIR_SH) D(DPOPGR) D(DLGDPC… D(DCPI) CointEq1 -2.447873 (0.28741) [-8.51698] 2.542345 (1.86498) [1.36321] 1.245264 (0.44244) [2.81455] 0.068704 (0.01763) [3.89612] -1.870674 (2.92597) [-0.63933] CointEq2 0.018418 (0.03640) [0.50598] -1.512229 (0.23620) [-6.40229] 0.019879 (0.05604) [0.35477] 0.000710 (0.00223) [0.31777] -0.031045 (0.37058) [-0.08378] CointEq3 -0.126891 (0.11508) [-1.10261] 1.694242 (0.74676) [2.26880] -1.027351 (0.17716) [-5.79910] 0.005928 (0.00706) [0.83962] 0.704706 (1.17159) [0.60149] CointEq4 -1.282128 (0.30675) [-4.17968] 3.934164 (1.99048) [1.97649] 0.293354 (0.47221) [0.62123] -0.040894 (0.01882) [-2.17282] -15.70708 (3.12288) [-5.02968] D(DN_RETURNS(-1)) 0.807894 (0.21627) [3.73552] 1.459928 (1.40337) [1.04030] 0.911026 (0.33293) [1.36321] 0.034719 (0.01327) [2.61649] 1.901137 (2.20176) [0.86346] D(DN_RETURNS(-2)) 0.235331 (0.12218) [1.92614] -0.693959 (0.79279) [-0.87533] 0.400652 (0.18808) [2.13023] -0.013165 (0.00750) [-1.75631] 1.119391 (1.24382) [0.89996] D(DIR_SH(-1)) -0.016900 (0.02698) [-0.62629] 0.407679 (0.17510) [2.32828] -0.026493 (0.04154) [-0.63778] 0.000267 (0.00166) [0.16104] 0.246976 (0.27471) [0.89903] D(DIR_SH(-2)) -0.014066 (0.01832) [-0.76782] 0.099095 (0.11887) [0.83363] -0.017560 (0.02820) [-0.62268] 0.000505 (0.00112) [0.44939] 0.080394 (0.18650) [0.43107] D(DPOPGR(-1)) 0.172082 (0.09085) [1.89404] -1.374402 (0.58954) [-2.33130] 0.146800 (0.13986) [1.04962] -0.005098 (0.00557) [-0.91451] -0.701057 (0.92494) [-0.75795] D(DPOPGR(-2)) 0.017923 (0.07198) [0.24902] -1.278511 (0.46704) [-2.73746] 0.059353 (0.11080) [0.53568] -0.005926 (0.00442) [-1.34199] 0.012488 (0.73275) [0.01704] D(DLGDPCAP(-1)) -0.137366 (1.70396) [-0.08062] 0.545984 (11.0568) [0.04938] 1.046548 (2.62306) [0.39898] 0.755436 (0.10455) [7.22590] -44.18992 (17.3471) [-2.54740] D(DLGDPCAP(-2)) -2.956976 (1.80437) [-1.63879] -2.617489 (11.7083) [-0.22356] 0.343428 (2.77763) [0.12364] 0.267242 (0.11071) [2.41398] 3.770119 (18.3693) [0.20524] D(DCPI(-1)) 0.026823 (0.01755) [1.52879] -0.043267 (0.11385) [-0.38004] 0.034226 (0.02701) [1.26722] 0.002210 (0.00108) [2.05279] 0.299184 (0.17862) [1.67500] D(DCPI(-2)) 0.014989 (0.01177) [1.27371] 0.004171 (0.07636) [0.05462] 0.020523 (0.01812) [1.13289] -8.14E-O5 (0.00072) [-0.11274] 0.080931 (0.11981) [0.67552] R squared 0.795459 0.614930 0.544445 0.589372 0.549935 Adj. R squared Suma sq.resids 0.761369 3.450989 0.550751 145.3058 0.468519 8.177878 0.520934 0.012991 0.474924 357.6651 S.E. equation 0.210341 1.364879 0.323797 0.012905 2.141366 F statistic 23.33402 9.581568 7.170743 8.611762 7.331406 Log likelihood 20.48153 -151.5667 -19.20597 277.2616 -193.0015 135 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate Akaike AIC -0.140903 3.599277 0.721869 -5.723079 4.500033 Schwarz SC 0.242848 3.983027 1.105619 -5.339329 4.883784 Mean dependent 0.004271 -0.000552 0.000639 -0.000231 0.025084 S.D. dependent 0.430587 2.036342 0.444149 0.018645 2.955153 Table 4.2. VECM Model Results for Sweden. Vector Error Correction Estimates Date: 06/28/22 Time: 01:14 Sample (adjusted): 1930 2021 Included observations: 92 after adjustments Standard errors in () & t-statistics in [] Error Correction: D(DN RET… D(DLGDPC… D(DIR_SH) D(DCPI) D(DPOPGR) CointEq1 -2.367886 (0.30930) [-7.65551] 0.057109 (0.01557) [3.66698] 1.955852 (1.49949) [1.30434] 1.025630 (3.36377) [0.30490] 0.154310 (0.15578) [0.99055] CointEq2 0.028938 (0.35860) [0.08070] -0.011268 (0.01806) [-0.62408] -6.525278 (1.73849) [-3.75342] 15.41750 (3.89990) [3.95331] -0.126544 (0.18061) [-0.70064] CointEq3 -0.028589 (0.04907) [-0.58265] -0.002324 (0.00247) [-0.94072] -0.925048 (0.23787) [-3.88886] 0.918612 (0.53361) [1.72150] -0.012239 (0.02471) [-0.49525] CointEq4 0.003859 (0.02048) [0.18839] -0.001618 (0.00103) [-1.56872] 0.044259 (0.09931) [0.44569] -1.742847 (0.22277) [-7.82351] -0.004260 (0.01032) [-0.41289] D(DN_RETURNS(-1)) 0.764430 (0.23740) [3.21998] 0.029833 (0.01195) [2.49576] 1.264672 (1.15091) [1.09884] 0.205140 (2.58181) [0.07946] 0.111849 (0.11957) [0.93544] D(DN_RETURNS(-2)) 0.201096 (0.13487) [1.49104] 0.018105 (0.00679) [2.66608] 0.475810 (0.65384) [0.72771] 1.089865 (1.46675) [0.74305] 0.001024 (0.06793) [0.01507] D(DLGDPCAP(-1)) 0.368808 (2.13036) [0.17312] 0.470820 (0.10727) [4.38923] 7.554244 (10.3279) [0.73144] 10.21505 (23.1683) [0.44091] 1.962013 (1.07296) [1.82860] D(DLGDPCAP(-2)) 2.954560 (2.13344) [1.38488] 0.396176 (0.10742) [3.68804] 3.857769 (10.3428) [0.37299] 20.70657 (23.2017) [0.89246] 0.086066 (1.07451) [0.08010] D(DIR_SH(-1)) 0.047094 (0.03733) [1.26159] 0.000803 (0.00188) [0.42739] -0.104807 (0.18097) [-0.57915] -0.405496 (0.40596) [-0.99886] 0.004887 (0.01880) [0.25993] D(DIR_SH(-2)) 0.005292 (0.02583) [0.20486] 0.000389 (0.00130) [0.29879] 0.196541 (0.12523) [1.56939] 0.385151 (0.28093) [1.37096] 0.008209 (0.01301) [0.63098] D(DCPI(-1)) 0.006847 (0.01506) [0.45456] 0.000813 (0.00076) [1.07156] 0.011826 (0.07302) [0.16196] 0.598885 (0.16380) [3.65612] 0.000537 (0.00759) [0.07076] D(DCPI(-2)) 0.007061 (0.00959) [0.73662] 0.000579 (0.00048) [1.20062] 0.045760 (0.04647) [0.98467] 0.298068 (0.10425) [2.85918] 0.000205 (0.00483) [0.04244] D(DPOPGR(-1)) 0.115979 (0.26594) [0.43612] 0.000288 (0.01339) [0.02153] 0.727968 (1.28924) [0.56465] 3.959512 (2.89212) [1.36907] 0.310290 (0.13394) [2.31665] D(DPOPGR(-2)) 0.105970 (0.24059) [0.44046] 0.014909 (0.01211) [1.23070] 0.182813 (1.16638) [0.15674] 2.312958 (2.61650) [0.88399] 0.109043 (0.12117) [0.89988] R squared 0.786444 0.514344 0.590631 0.688171 0.431978 Adj. R squared Suma sq.resids 0.750852 4.665833 0.433402 0.011829 0.522403 109.6591 0.636199 551.8335 0.337308 1.183557 S.E. equation 0.244578 0.012315 1.185701 2.659847 0.123182 136 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate F statistic 22.09572 6.354432 8.656701 13.24129 4.562969 Log likelihood 6.607673 281.5706 -138.6194 -212.9494 69.70781 Akaike AIC 0.160703 -5.816751 3.317813 4.933683 -1.211039 Schwarz SC 0.544453 -5.433001 3.701564 5.317433 -0.827289 Mean dependent -0.000180 -0.000358 0.001033 0.028976 0.000855 S.D. dependent 0.489991 0.016360 1.715711 4.409860 0.151318 Determinant resid covariance (dof adj.) 9.57E-07 Determinant resid covariance 4.19E-07 Log likelihood 22.79220 Akaike information criterion 1.461039 Schwarz criterion 3.928006 Number of coefficients 90 Table 4.3. VECM Model Results for Denmark. Vector Error Correction Estimates Date: 06/28/22 Time: 01:27 Sample (adjusted): 1930 2021 Included observations: 92 after adjustments Standard errors in () & t-statistics in [] Error Correction: D(DN RET… D(DLGDPC… D(DIR_SH) D(DCPI) D(DPOPGR) CointEq1 -2.013033 (0.29629) [-6.79409] 0.057863 (0.02448) [2.36385] 0.437346 (1.63640) [0.26726] 1.237852 (3.93017) [0.31496] 0.071720 (0.12277) [0.58416] CointEq2 -0.343819 (0.57169) [-0.60141] -0.036778 (0.04723) [-0.77869] -2.913196 (3.15738) [-0.92266] -2.253482 (7.58314) [-0.29717] -1.126239 (0.23689) [-4.75427] CointEq3 0.001832 (0.03633) [0.05044] -0.001285 (0.00300) [-0.42820] -0.926723 (0.20063) [-4.61902] 0.286026 (0.48186) [0.59359] -0.006504 (0.01505) [-0.43209] CointEq4 0.004157 (0.01796) [0.23144] -0.001918 (0.00148) [-1.29278] -0.009055 (0.09919) [-0.09128] -1.549097 (0.23824) [-6.50235] -0.003146 (0.00744) [-0.42265] D(DN_RETURNS(-1)) 0.512813 (0.21935) [2.33790] 0.039995 (0.01812) [2.20705] 1.106599 (1.21144) [0.91346] 0.758447 (2.90953) [0.26068] 0.046910 (0.09089) [0.51612] D(DN_RETURNS(-2)) 0.025723 (0.12953) [0.19858] 0.021356 (0.01070) [1.99560] 1.135224 (0.71541) [1.58682] 0.782509 (1.71822) [0.45542] 0.005656 (0.05368) [0.10537] D(DLGDPCAP(-1)) 0.677342 (1.44845) [0.46763] 0.795923 (0.11966) [6.64960] 6.612406 (7.99967) [0.82659] 14.44573 (19.2130) [0.75187] 0.215385 (0.60019) [0.35886] D(DLGDPCAP(-2)) 1.983041 (1.42142) [1.39512] 0.421048 (0.11743) [3.58548] 11.77779 (7.85036) [1.50029] 16.34799 (18.8544) [0.86707] 0.860696 (0.58899) [1.46130] D(DIR_SH(-1)) 0.023477 (0.02949) [0.79603] 0.000772 (0.00244) [0.31667] -0.087213 (0.16289) [-0.53543] -0.147974 (0.39121) [-0.37825] 0.002437 (0.01222) [0.19942] D(DIR_SH(-2)) 0.020953 (0.02153) [0.97340] -0.000733 (0.00178) [-0.41227] 0.024416 (0.11889) [0.20538] 0.023318 (0.28553) [0.08166] 0.003329 (0.00892) [0.37319] D(DCPI(-1)) -0.000749 (0.01264) [-0.05925] -0.001076 (0.00104) [-1.03051] 0.010586 (0.06983) [0.15160] 0.509500 (0.16772) [3.03786] 0.004729 (0.00524) [0.90269] D(DCPI(-2)) -0.003967 (0.00830) [-0.47801] -0.000835 (0.00069) [-1.21774] 0.004592 (0.04583) [0.10020] 0.136887 (0.11007) [1.24360] 0.001850 (0.00344) [0.53808] D(DPOPGR(-1)) 0.021012 (0.35150) 0.000689 (0.02904) 2.507277 (1.94133) 3.031602 (4.66254) 0.126947 (0.14565) 137 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 8: 113-137, 2025 DOI: 10.55214/2576-8484.v9i8.9225 © 2025 by the authors; licensee Learning Gate [0.05978] [0.02372] [1.29152] [0.65020] [0.87157] D(DPOPGR(-2)) 0.301651 (0.26919) [1.12057] 0.003255 (0.02224) [0.14636] 0.490181 (1.48674) [0.32970] 6.389871 (3.57073) [1.78952] 0.035528 (0.11155) [0.31850] R squared 0.781444 0.480924 0.660203 0.638012 0.487125 Adj. R squared Suma sq.resids 0.745018 4.075944 0.394412 0.027820 0.603571 124.3269 0.577681 717.1502 0.401646 0.699852 S.E. equation 0.228595 0.018886 1.262511 3.032199 0.094723 F statistic 21.45294 5.559007 11.65762 10.57514 5.698758 Log likelihood 12.82522 242.2323 -144.3941 -225.0032 93.87673 Akaike AIC 0.025539 -4.961571 3.443351 5.195722 -1.736451 Schwarz SC 0.409289 -4.577820 3.827102 5.579472 -1.352700 Mean dependent 0.001185 -0.000191 -0.003143 0.026438 0.000702 S.D. dependent 0.452702 0.024268 2.005176 4.665920 0.122455 Determinant resid covariance (dof adj.) 1.45E-06 Determinant resid covariance 6.35E-07 Log likelihood 3.713997 Akaike information criterion 1.875783 Schwarz criterion 4.342750 Number of coefficients 90