Tagged Questions

0
votes
0answers
22 views

Modelling a skewed, 10-point Satisfaction variable

I am trying to replicate and hopefully improve on an analysis done in a study to find determinants of patient satisfaction after shoulder surgery. Satisfaction is heavily skewed (with over 60% of ...
0
votes
0answers
87 views

Question about the validation step for a multinomial logit model

I've been skimming through a couple of books (all german ones, hence I do not cite them here) at what residual plots one should look at if the usual model assumptions in the context of a multinomial ...
1
vote
1answer
74 views

residualize binary outcome variable

Does it make sense and what is the correct approach to residualize a binary variable? For a continuous variable y, I simply run a regression that predicts ...
8
votes
2answers
547 views

Logistic regression residual analysis

This question is sort of general and long-winded, but please bear with me. In my application, I have many datasets, each consisting of ~20,000 datapoints with ~50 features and a single dependent ...
2
votes
2answers
544 views

Residuals for Logistic Regression and Cooks Distance

1) Are there any particular assumptions regarding the errors for logistic regression such as the constant variance of the error terms and the normality of the residuals? 2) Also typically when you ...
3
votes
2answers
985 views

Logistic Regression - Getting Pearson Standardized Residuals in R vs Stata

I am working on an assignment involving a logistic regression model, where I need to plot the pearson standardized residuals against one of the predictors. Here's the basic setup: ...
6
votes
2answers
786 views

Assessing logistic regression models

This question arises from my actual confusion about how to decide if a logistic model is good enough. I have models that use the state of pairs individual-project two years after they are formed as a ...