Dear STATA users,
I am very new to stata, so maybe this is a dumb question. I am trying to create a discrete choice model with cmmixlogit based on 444 routes who each have four alternatives. Any time i try to estimate more than four spatial variables in one model, i get the error that the input values are not feasible. It is even worse for interaction effects, sometimes i can't even estimate the interaction effect of one age variable on spatial variable on route choice. How do i solve this problem?
The code snippet that does work is cmmixlogit choice green_len aesthetic bridge_len waterperc light length, noconstant nolog or
However this does not: cmmixlogit choice aesthetic c.aesthetic#i.gender, noconstant nolog or
Related Posts with Question about numerical overflow
LSDV3 model: dummy variable omitted because of collinearityI am studying the notes titled "Practical Guides To Panel Data Modeling: A Step by Step Analysis Usi…
Nested locals in some commandsI constructed two locals, for instance, department and major , to show one's information: Code: loc…
Binary DV unbalanced panel data; replacing first year to missingI have unbalanced panel data of 600000 plus observations. I have created my Dependent Variable as bi…
Drawing simple path diagramDear all, I have an apparent simple question. I would like to graphically visualize my analytical st…
Can we create inverse-distance spatial weighting matrices for point data?Hello, Can we create inverse-distance spatial weighting matrices for point data? I can create inve…
Subscribe to:
Post Comments (Atom)
0 Response to Question about numerical overflow
Post a Comment