How to make loop for one-at-a time logistic regression in R

Question

The question concerns the practical difference between the == and %in% operators in R.

I have run into an instance at work where filtering with either operator gives different results (e.g. one results on 800 rows, and the other 1200). I have a problem in the past and am able to validate that ensures I get the results I desire. However, I am still stumped regarding how they are different.

Answer 1

You're probably looking for something similar to this:

glm(as.formula(paste0('casecontrol ', 'rs', I data = mydata, family = binomial)) lapply(1:30, function(i) glm(as.formula(paste0('casecontrol ', 'rs', I data = mydata, family = binomial))

This command will run 30 logistic regressions with the chosen predictor.

Rather of hard-coding the total number of predictors, use sum(grepl('rs', names(mydata)), which returns 30.

To get the summary in a tidy format, use the tidy function from the broom package.

data.frame(model = I tidy(glm(as.formula(paste0('casecontrol ', 'rs', I data = mydata, family = binomial))) purrr::map dfr(1:30, function(i) data.frame(model = I tidy(glm(as.formula(paste0('casecontrol ', 'rs', I