Normality in the residual

1. Normality assumption
Professor Sudarshan Bhattacharjee​ commented about diagnostic checking as such >> If
the data series is sufficiently large... about more than 30 0bservations then you can ignore
the violation of normality assumption coz by central limit theorem a long series will
converge to normality.... for auto-correlation and heteroskedasticity we can try first some
transformation in the variables.... however, if that does not work then use Newey-West
test for HC and HAC... This is readily available in R and Stata... Not sure about Eviews....
hope this helps..


2. Normality in the residual
Professor Sayed Hossain posted the following figure.























Moritz J. Sch commented> shouldn't we rather state: "we fail to reject the null" instead of
"accept the null"?

Sayed Hossain commented> Fail to reject null sounds good

Moritz J. Sch commented>  This has somehow become the standard phrase in empirical
work. My professor never got tired of mentioning, that "accepting" is a horrible
misconception, because the null must not necessarily be true, especially with a p-Value of

Muhammad Anees commented> In research and as per the Williams, Elements of Style,
double negatives sounds good :)

George Savva commented> You should not use any statistical test for normality of
residuals. Whether they are 'significantly' non-normal is not important for the validity of the
regression.
Normality in the residuals
Hossain Academy Note
POPOLAR BLOGS
Dave
Meo School of Research
Shishir Shakya
Noman Arshed
Univariate Models
Multivariate Models