When to use parametric tests if the data is not normally distributed?Hello
.If I am investigating a dependent variable that is not normally distributed (Shapiro Wilk p <0.05)
Can I still use parametric tests like linear regression and t-tests knowing that the calculated sample size is 380 and the collected data 1400 (large sample size)
Basic Data Analysis and ModelingRe: When to use parametric tests if the data is not normally distributed?There is no assumption by these procedures that the response is normally distributed. The distribution of the residuals is assumed to be normal with a constant mean and variance. The conditional equation applies to the mean, variance, or both.
