Skip to main content
7 votes

Questions about how to proceed when residuals of linear regression are not exactly normally distributed

Regarding 1., no. You checked your assumptions. They were wrong. Regarding 2., there are a number of things that could cause non-normal residuals. There could be outliers or influential points; the ...
Peter Flom's user avatar
  • 120k
2 votes

Questions about how to proceed when residuals of linear regression are not exactly normally distributed

Your model is $Y_i=\boldsymbol{x}_i'\boldsymbol\beta + \epsilon_i$, for $i=1,\ldots,n$. The minimal set of assumptions we make about the errors is that they have zero mean, constant variance (i.e. the ...
Doctor Milt's user avatar
  • 3,231
1 vote

Are residuals important in logistic regression when all variables are factors?

The short answer is yes, residuals are important with logistic regression using categorical features. In fact, there are entire classes of models that are fitted to this information -- widely known as ...
user78229's user avatar
  • 10.6k
1 vote

Are residuals important in logistic regression when all variables are factors?

If a binary logistic regression model is saturated, then the residuals are completely uninteresting. That's a step beyond just having factor predictors; it's basically having factor predictors will ...
Thomas Lumley's user avatar
1 vote
Accepted

Bimodal residuals in logistic regression — what causes it, is it bad news, and what can be done?

As answers to each of your questions: Am I right in the interpretation that my residuals are bimodally distributed because there remains a lot of unexplained variation in my response variable? No. ...
Shawn Hemelstrand's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible