The aim of my study is to investigate the impact of Integrated Reporting disclosure practices on operational performance (ROA) and firm value (Tobin's). I have applied panel data model for my analysis. Under descriptive statistics the Std. deviation of tobin's q is high i.e. 4.964. One of the reviewer commented that high std deviation of tobin's q means that variable is not normal, which may affect results. However, I have studied that normality is not required in panel data models? What justification should I give to satisfy reviewer? Please also mention some references.
If you do any of the models that employ regression and particularly cointegration then the dynamic stability of your variables are more important than anything else ,this will be true for time series data. If you employ cross section data there are several econometric tests that can be performed to assure soundness of the mode and standard deviation is only one criterion that may be covered by the the various tests.
As you say, you do not need to assume normality with a decent sample size. Actually, to have a large variation is a good thing, particularly, if you use fixed effects and you have large within-group variation.
José-Ignacio Antón Thankyou for your answer. Can you please suggest me some references or books for justification?
The issue of sample size and normality can be found in any introductory standard text, like wooldridge's introductory econometrics. It is just the result of the central limit theorem.
Maybe you should better first check the outliers and if the problem still exists about the variation you may consider normalization. On the other hand I don’t think the variation is a major problem here since data represents the population adequately. It’s important here how much of this variation can be modeled assuming your model is correct (Linear or nonlinear, parabolic or something else). If you think that the variation is much more than the expected for each of the values of independent variable values this may sign that correlation is not enough to consider a regression model.
Your model is suffering from outliers that's why the f value of Tobin's Q is quite higher. To remove the outliers from your data, you need to adopt a 3-sigma approach by removing extreme values in your data.
Sitara Karim Thankyou for your answer. Is there any other way to remove outliers by using e-views.
Dear Parthvi Rastogi you can google and find some related links. The video can also help you given in the link:
https://www.youtube.com/watch?v=aQiZ7uH7JUM
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Graphs