|
![](http://www.statmodel.com/discussion/icons/csc/1px.gif) |
Logistic regression with categorical ... |
![Previous](http://www.statmodel.com/discussion/icons/csc/navgen_arrow_left.gif) ![](http://www.statmodel.com/discussion/icons/csc/1px.gif)
|
Message/Author |
|
Julia posted on Monday, September 19, 2016 - 3:17 am
|
|
|
I have a question about defining the right model/variables. I want a logistic regression (dependent variable is binary) with 4 independent (categorical) variables. I read that I have to defnie these as dummy variables, e.g. age with 1/2/3: Define: age1 = age == 1; age 2 = age == 2; Than Mplus uses age = 3 as the reference category, right? And what is with variables with 2 categories (e.g. sex = 1, 2). Do I have to define it as sex1 = sex ==1) and take sex1 in my model to have sex = 2 as the reference category? Thank you |
|
|
Q1. right. Q2. Just define a variable Female which is 1 for females and 0 for Males. |
|
Julia posted on Tuesday, September 20, 2016 - 2:08 am
|
|
|
Ad Q2: Does Mplus uses "0" or "1" as the reference category? |
|
|
You decide. Mplus only assign scores for categorical DVs, not IVs. |
|
Back to top |
|
|