Financial Economics
Saman Hatamerad; Bahram Adrangi; Hossein Asgharpur; Jafar Haghighat
Abstract
The present research aimed to investigate the relationship between Iran’s stock price index and nine macroeconomic variables during 1996–2019. Three methods were employed to reduce uncertainty, namely three Bayesian averaging methods (BMA, BMS, BAS), weighted average least squares (WALS), ...
Read More
The present research aimed to investigate the relationship between Iran’s stock price index and nine macroeconomic variables during 1996–2019. Three methods were employed to reduce uncertainty, namely three Bayesian averaging methods (BMA, BMS, BAS), weighted average least squares (WALS), and Vselect. The experimental results of the Bayesian methods and WALS showed that the exchange rate and the consumer price index are the most important variables among the nine macroeconomic variables considered in the model. Moreover, the results revealed that the exchange rate has a minor impact on the stock price index, while the stock price index exerts a substantial effect on the exchange rate. The findings of Vselect validated the conclusion that these two variables are the primary drivers of stock price estimation and are present in nearly all predictive modelsIntroductionThe harmonization of financial markets with the macroeconomic sector is crucial for stabilizing the economy and achieving the adopted policies. In recent years, several significant studies have been conducted on financial markets, particularly the stock market, highlighting their pivotal role in allocating capital resources efficiently in advanced economies. Empirical evidence supports the view that financial markets have evolved in tandem with all sectors of the economy. Therefore, it can be argued that financial markets constitute one of the most vital components of any country’s economy. Throughout history, major economic crises have resulted from the collapse of financial markets, which underscores their critical significance. The financial market comprises several components, with the stock market being a crucial part. Economists view it as a barometer of a country’s economic health due to its ability to reflect macroeconomic asset prices more accurately than other markets. The uncertainty surrounding stock prices in stock markets is a significant aspect of the entire economy, capable of generating and disrupting unsustainable growth. For investors, the risk of participating in an investment is a crucial consideration. To comprehend total risk, it is beneficial to examine two aspects: systematic and non-systematic risk.The present study aimed to examine the impact of economic factors on stock market prices in Iran with the high degree of risk involved. There is a consensus among economists that asset prices are responsive to economic news, and that stock prices and economic factors are strongly interconnected. Thus, this research investigated the potential impact of macroeconomic factors on the Iranian stock price index from 1996 to 2019 using Bayesian averaging methods, followed by an analysis of the effect size of each variable through the weighted average least square method (WALS).Materials and MethodsResearchers often draw conclusions based on the assumptions of their selected model, assuming that it can accurately predict real-world situations. However, this approach may overlook true uncertainty, leading to non-conservative conclusions. Statistical models comprise two parts: variables and assumptions, and the model selected based on these assumptions to estimate the variables. Uncertainty exists at both levels. For instance, a researcher estimating the impact of influential factors on an independent variable may choose a model based on their assumptions and report their estimates. But is this the best answer? Another researcher with different assumptions may opt for a different model with lower variance and error. In other words, numerous models may fit the sample data equally well but with different coefficient estimates and standard errors. Bayesian model averaging (BMA) is a robust method that aims to remove uncertainty. It assesses the robustness of results to alternative specifications by computing posterior distributions for coefficients and models. This study employed three models of BMA, BMS, and BAS, using various averaging methods to verify the reliability of the results. Moreover, two non-Bayesian methods, namely WALS and Vselect, were used to select the best variables for predicting the optimal models.ConclusionThis study tried to investigate the relationship between Iran’s stock market index and nine macroeconomic variables during 1996–2019 by using the models that identify and limit uncertainty. The models selected include three Bayesian averaging models as well as WALS and Vselect which were used to verify the results obtained. The results indicated that only two variables, the exchange rate and consumer price index, are statistically significant when assuming a uniform distribution of the prior distribution function, which is the assumption of the BMS method. The remaining variables are not statistically significant. Furthermore, the estimates derived from the BMA and BAS models were quite similar, with the exception of less important variables. However, the similarity decreased in the BAS method. Moreover, WALS and Vselect confirmed the results obtained from all the three methods.
Karim Eslamloueyan; Hashem Zare
Volume 8, Issue 29 , February 2007, , Pages 17-46
Abstract
This paper uses a quarterly data to study the effect of the main economic variables on the stock price index in Iran over the period 1993:3–2003:2. An autoregressive distributed lag (ARDL) approach to cointegration analysis is used to study both short- and long-run movements of stock prices in ...
Read More
This paper uses a quarterly data to study the effect of the main economic variables on the stock price index in Iran over the period 1993:3–2003:2. An autoregressive distributed lag (ARDL) approach to cointegration analysis is used to study both short- and long-run movements of stock prices in Tehran stock market. The explanatory variables include money supply, production level of large manufacturing companies, and the ratio of domestic to foreign price level, exchange rate, oil price, gold coin price, and housing price index.
The results show that there is a long-run equilibrium relationship between the variables. According to our finding, the ratio of domestic to foreign price levels, the price of housing and the gold coin price index have positive impacts on the stock prices. Exchange rate and money supply have significant negative effects on the stock price index in Iran. However, we found that the production level of large manufacturing companies has not affected the stock price index. The result of our error correction model indicated that 54 percent of deviation of the stock price from its equilibrium path is corrected each period.
Saeed Moshiri; Habib Morovat
Volume 7, Issue 25 , February 2006, , Pages 47-64
Abstract
The very complex movements in the stock prices are usually taken as random or stochastic, but they may be produced by a deterministic data generating process. Chaos refers to the nonlinear dynamic deterministic process that generates a series, which appears like random, but has a long memory. In the ...
Read More
The very complex movements in the stock prices are usually taken as random or stochastic, but they may be produced by a deterministic data generating process. Chaos refers to the nonlinear dynamic deterministic process that generates a series, which appears like random, but has a long memory. In the Economics and Finance literature, stock prices are known to be random due to their complexities, and therefore being unpredictable. In this paper, we test for chaos in the stock prices using the data from the daily and weekly stock prices listed in the Tehran Exchange Market (TEPIX) in 1377-1382 (1998-2003). We apply three tests for chaos, namely; BDS, Lyaponov Exponent, and Neural Networks; to the residuals of linear (ARIMA) and nonlinear (GARCH) models. The BDS and the Neural Networks tests results show that there exists nonlinearity in the ARIMA residuals, but not in the GARCH residuals. However, the Lyaponove exponent test result is positive for all different dimensions indicating that the TEPIX is chaotic.
