Abstract:
The present study aims to model systematic risk using financial and accounting
variables. Accordingly, the data for 174 companies in Tehran Stock Exchange are
extracted for the period of 2006 to 2016. First, the systematic risk index is estimated
using the ARFIMA-FIGARCH model. Then, based on the research background,
35 affective financial and accounting variables are simultaneously used
with the help of the backward elimination and forward selection method for modeling.
After analyzing and evaluating the variables in Eviews software, the four
variables of debt ratio (CL. E), size (SIZE), net profit to sales ratio (NETP. S), and
interest rate coverage ratio (ICR) are selected in the backward elimination method.
In the forward selection method, in addition to the above variables, operating
profit margin (OPM) is also chosen. The estimated model of these variables in
both methods shows a low ratio of R2 coefficient that is approximately 7%. In the
test case, the model of forward selection method has less error in all four criteria
of root mean squared error (RMSE), mean absolute error (MAE), mean absolute
percentage error (MAPE) and Tile coefficient (TIC) compared to the backward
elimination method.
Machine summary:
One of the criteria for the systematic risk estimation is market beta variable in the capital asset pricing model (CAPM) presented by William Sharp in 1964.
3 Research Background Ibrahim and Haron [26] examined the impact of corporate leverage and corporate finance policies on the systematic risk of non-financial companies listed in the Malaysian stock exchange and analysed financial data for 824 companies for the years 2000 to 2013 using panel data and fixed-effects models.
The results obtained from the multivariate regression model indicat- ed that the beta values have a direct relationship with the financial and operational leverage, the fluc- tuations in the return, and size of the company and a reverse relationship with the ratio of book value to market value and return on assets.
In this study, the relationship between the 8 financial ratios with the systematic risk system was tested by simple and multivariate regression for the data extracted for 226 companies during the years 2006-2009.
Namazi and Khajavi [9] used the simple regression method and the method of sequential selection of variables called "backward elimination" to examine the usefulness of accounting variables in predict- ing the systematic risk of companies accepted in Tehran Stock Exchange.
Table 9: Results of estimating research model using forward selection (View the image of this page) However, the relationship between the selected variables of the earnings per share ratio (DPS / EPS) and the net profit margin (NPM) was not approved due to insignificance at the error level of .