Panel Data Stock Return's Volatility Modeling (Case study of Tehran Stock Exchange)

Because of its extensive applications in financial analysis, stock market volatility modeling is a significantly important issue for stock market practitioners and academicians. Using GARCH models to formulate the conditional variance heteroskedasticity and the taking advantages of panel data technique such as higher degrees of freedom, more flexibility in the control of the omitted or unobserved variables effects, lead to a significant increase in the accuracy of estimations. In this paper, in order to examine the similarities and differences between the conditional variance structures of stocks in inter and intra industries sectors, we use a general to specific methodology of nested tests pioneered by Hendry. Our dataset consist of panel samples of sectors’ daily share prices and stocks returns of specific firms in each industry, in the Tehran Stock Exchange over (21 June 2006) and (22 July 2006). Any similarities are not observed in neither inter nor intra volatility structures of stocks and returns of industries.