|
|
Zero cells in path analysis |
|
Message/Author |
|
Sonia posted on Wednesday, April 29, 2015 - 12:16 pm
|
|
|
Both my outcome variable Y and the covariate X are dichotomous. There is one cell in the 2X2 table that is equal to zero. The chi-square is significant. But when I run the path model that includes Y on X (and some other variables), X is not significant and I think this is because of the zero cell. Is that correct. Conceptually, I need this variable in the model. What can I do? |
|
|
I don't think you want a zero cell for 2 such important variables in your model. I can only think of gathering a larger sample, or say that questions regarding the X impact cannot be answered in this sample. |
|
Back to top |
|
|