Based on the calculation above, it is known that the EPS and ROA equally positive effect on the stock
price with a coefficient of 7.8579 and ROA EPS amounted to 705.6699. R-Squared value on the Random Effects
model is much smaller than the calculation of the fixed effect that is common effectdan 0.6233. That is, the
independent variable (EPS and ROA) is able to describe the dependent variable (stock price) of 62.33%. The
above results also demonstrate the value of the t-statistic EPS variables smaller than the value of the t-statistic on
the model common effect but still quite large compared to the value of the t-table, namely 10,228. Neither the
value of the variable ROA, which is equal to 0.159.
5.2.4.Selection of Panel Data Models
5.2.4.1. Chow-Test
To choose regression models which one is better between Model Ordinary Least Square (common effect) and the
Fixed Effects Model (Fixed Effect Model), the Chow test is done with the following hypothesis :
H0 : Ordinary Least Square
H1 : Fixed Effect Model