9 votes

Is logistic regression suitable for high frequency values?

Ordinal regression might be a good choice here. Chapter 13 of Frank Harrell's Regression Modeling Strategies explains this approach. It makes no assumptions about the distribution of outcomes, working ...
EdM's user avatar
  • 86.7k
8 votes
Accepted

Is logistic regression suitable for high frequency values?

Logistic regression is for categorical outcomes; the "usual" form of logistic reg. is for dichotomous outcomes. So, you could divide your outcome into 3.9199 and everything else and then do ...
Peter Flom's user avatar
  • 110k
6 votes
Accepted

Variable selection in logistic regression

The problem with your proposed approach is that every predictor in itself may not correlate with the outcome, but interactions between them might. Or you might have a curvilinear relationship between ...
Stephan Kolassa's user avatar
5 votes
Accepted

How to estimate this specific logistic regression model which is not linear in its parameters?

Using a local optimizer is not sufficient for global optimization. Naïvely using a local optimizer (such as Levenberg–Marquardt) to find the parameters of a non-identified model is not a good idea ...
Sycorax's user avatar
  • 89.1k
4 votes

Can I perform logistic regression or any other type of regression on this dataset?

You are right that without data on those who didn't crash, you can't sensibly predict how likely a crash is. For example, maybe your data show there were twice as many crashes among young male drivers ...
civilstat's user avatar
  • 3,442
3 votes

Can I perform logistic regression or any other type of regression on this dataset?

The answer is pretty simple here. If your outcome variable has both outcomes (the event happens or doesn't happen), then you can easily fit this data to a logistic regression with the event as a ...
Shawn Hemelstrand's user avatar
3 votes

Variable selection in logistic regression

Adding to Stephen's excellent answer, there are lots of reasons not to do automatic variable selection. He covers some of them. But there are others: A variable could be a mediator without being ...
Peter Flom's user avatar
  • 110k
2 votes

SPSS and PSPP yield very different logistic reggression results with same dataset

You have specified different variables in the two models. Diff_CC_quadro_normalizadois in the PSPP model but not the SPSS model and ...
Thomas Lumley's user avatar
1 vote

Doing a logistic regression on a $2 \times 2$ table, why does R yield a different odds ratio than by hand-calculation?

The glm in R is an iterative procedure that uses Newton-Raphson to converge on the estimate and produce covariance estimates. These estimates are divergent, meaning ...
AdamO's user avatar
  • 60.6k
1 vote

Doing a logistic regression on a $2 \times 2$ table, why does R yield a different odds ratio than by hand-calculation?

Count data for discrete independent variables and a discrete dependent variable, this seems like a good application of Fisher's exact test: ...
Dave2e's user avatar
  • 1,633

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