|
|
Dichotomous and ordinal predictors |
|
Message/Author |
|
|
Dear Mr. and Mrs. Muthén I am running a multilevel model, more precisely an intercept-and-slope-as-outcome-model (TYPE = TWOLEVEL RANDOM). The predictors on level two are treated as manifest variables. Some of the predictors are continuous, some are ordinal, some are dichotomous. For the ordinal and dichotomous predictors, I am not sure, if I specifiy the model correctly. Ordinal predictors: Can I integrate these predictors just normally OR do I have to specify the ordinal scale somehow OR do I have to create dummy variables? Dichotomous predictors: Can I integrate these predictors just normally OR do I have to specify the dichotomous scale somehow? Thank you in advance! |
|
|
In regression, predictors can be binary or ordinal. In both cases, they are treated as continuous. You don't need to do anything about their scales. |
|
|
Dear Mr. and Mrs. Muthén: I have a similar question. I am running a mediation model with an ordinal predictor, two continuous mediators and one binary outcome. In this case, is the ordinal predictor also treated as continuous or do I have to create dummy variables? |
|
|
You should create dummies. |
|
Back to top |
|
|