# Thread: Logistic regression analysis and quantitative discrete variables

1. ## Logistic regression analysis and quantitative discrete variables

Maybe I should start this post explaining that I am a physician working in the public health system in Brazil with little knowledge about the subject underlying my question. I usually follow the tutorials Epi-Info 07 (www.cdc.gov/epiinfo) as help to solve problems of logistic regression. These tutorials work very well when dealing with a binary outcome and other dependent variables that are also binary. However, the task I am trying to solve now involves logistic regression that must include a binary outcome variable and a mix of other qualitative and quantitative discrete dependent variables. Thus, I wonder if exists some kind of logistic regression analysis technique that uses a binary outcome variable while handling both types of dependent variables, quantitative discrete as well as categorical or binary? Thanks for your attention.

2. ## Re: Logistic regression analysis and quantitative discrete variables

I think terminology might be messed up here. "Dependent variable" is usually used to refer to the 'outcome' or the value we're trying to predict. We use "independent variable" to refer to the variables that will be used to model the outcome. Were you using "dependent" to refer to "independent"?

3. ## Re: Logistic regression analysis and quantitative discrete variables

I assume you meant independent and not dependent variables. A generalized linear model can handle a mix of independent variable types (categorical, continuous, binary, etc).

4. ## Re: Logistic regression analysis and quantitative discrete variables

in general this can absolutely be done.
Seems EpiInfo is capable: https://wwwn.cdc.gov/epiinfo/user-gu...C-Command.html
R is free; g00gle for "r logistic regression" returned several nice examples of all sorts of logistic regression in R

5. ## Re: Logistic regression analysis and quantitative discrete variables

I am not sure I understand the question. Logistic regression can handle nominal (what I think you mean by qualitative) dependent variables with more than two levels. This is multinominal logistic regression. It can also handle ordinal dependent variables (these might also be interval I assume although I have not seen that addressed). If your variable is interval and has enough levels (different possible values) you would commonly use linear regression although how many unique levels of the DV you need to use linear regression appears to be something statisticians are unsure of or disagree on. Beyond a certain number of levels of the DV analysis of logistic regression becomes cumbersome.

Also ordinal logistic regression assumes that it does not matter how you would dichotomize the DV - there is a test for this assumption. If it is not met you should use multinominal logistic regression even if your data is ordered.

 Tweet

#### Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts