Does dependent variable need to be normally distributed for linear regression?

Does dependent variable need to be normally distributed for linear regression?

The basic answer is no. If you think/know the outcome is not normally distributed, then it’s not okay to use OLS (without correcting for that). It is a common misbelief that the outcome variable in linear regression needs to be normally distributed. Only residuals need to be normally distributed.

Should dependent variables be normally distributed?

So is the normality assumption necessary to be held for independent and dependent variables? The answer is no! The variable that is supposed to be normally distributed is just the prediction error. Prediction error should follow a normal distribution with a mean of 0.

Do you need normal distribution of independent variables?

My independent variables are, however, not normally distributed (moderately positively skewed). A square root transformation was successful in normalising the distribution of the IVs. However, after running the logistic regression on the normalised data, I get some very strange results – huge Odds Ratios and Confidence Intervals.

Do you have to normalize dependent variables in linear regression?

One of the most common questions asked by a researcher who wants to analyse their data through a linear regression model is: must variables, both dependent and predictors, be distributed normally to have a correct model? So if they are not, should I normalize them through a transformation, for example the logarithmic one?

Is the marginal distribution of dependent variables normal?

1) If the distribution of the residuals within each group is normal, and the groups have different means (i.e. in a linear regression there is a slope different from 0) then the marginal distribution of the dependent variable may very well be NOT normal at all.

When does a dependent variable have to be normal?

The dependent variable, Y, doesn’t have to be normal for the residuals to be normal (since Y is affected by the X’s). But Y does have to be continuous, unbounded, and measured on an interval or ratio scale.