Different results for residual normal distribution between Jarque-Bera test and Q-Q Plot
I am trying to test for normality of residuals using 2 different ways.
- Using Jarque-Bera test
- Q-Q Plot
I can see different results, for the JB test the probability value is 19.9553 with a probability of 0.00005. Thus, we can't reject the null hypotheses, and this concludes that there is a non-normal distribution of results.
on the other hand, when I plotted the same dataset using Q-Q graph, I could see a partially linear relation, which might point to a normal distribution. Given the size of observations is 62 and the regression model that was used is the OLS model.
Do you think I did something wrong in my assumption?
The QQ graph does not show that the data are normally distributed. If you would calculate a single indicator from a QQ plot, then you would measure the (positive vertical ) distances of the points to the red reference line and sum them up. In your case, almost all points deviate from the reference line, voting for a non-normal distribution.
A typical QQ plot of normally distributed data has got a large majority of points on the red reference line and some points at the ends (left and right) may deviate.