Contents
Are linear regression techniques appropriate for analysis when the dependent outcome variable is not normally distributed?
In short, when a dependent variable is not distributed normally, linear regression remains a statistically sound technique in studies of large sample sizes. Figure 2 provides appropriate sample sizes (i.e., >3000) where linear regression techniques still can be used even if normality assumption is violated.
What are the drawbacks of the linear model?
Since linear regression assumes a linear relationship between the input and output varaibles, it fails to fit complex datasets properly. In most real life scenarios the relationship between the variables of the dataset isn’t linear and hence a straight line doesn’t fit the data properly.
Why would a model not converge in logistic regression?
Model 1 includes var 1 and var 2 (<-this is the model that does not converge, due to var 1) and model 2 includes var 1 and var 3. Thanks for any help here.
When to worry about cross validation in logistic regression?
If you’re getting better cross-validation scores, then you should probably be “close enough” to that optimum to not worry about it. Increase max_iter for the refit, if you’d like. * (In logistic regression the loss is convex, so there’s just one global optimum, barring collinear features or perfect separation.)
What does it mean when solver does not converge?
I wouldn’t advise making that constraint. Failure of the solver to converge just means it hasn’t reached the global optimum* to within the specified tolerance. If you’re getting better cross-validation scores, then you should probably be “close enough” to that optimum to not worry about it.
How to interpret output from linear mixed effects model?
I have used “glmer” function, family binomial (package lme4 from R), but I am quite confused because the intercept is negative and not all of the levels of the variables on the model statement appear. I then do not know if they are important or not, or if they have an effect on the dependent variable.