|
Message/Author |
|
Al Rull posted on Thursday, November 04, 2010 - 10:48 am
|
|
|
Hello, I would like to estimate simultaneously with a path analysis the influence of six success drivers (x1-x6) as independent variables (all are metric scaled) on four dependent variables (2 of them are metric scaled: y1 y2 and two binary scaled: u1 u2). Besides, I would also like to estimate within the model the influence of the dependent variables y1 --> y2; y2 --> u1 and u1 --> u2. My question is now, how it is possible to estimate the influence of one binary coded variable (i.e., u1 (trial purchase no = 0; yes = 1) on the other binary variable u2 (repeat purchase with no = 0; yes = 1) within this model? u2 ON u1; is not working when these variables are coded as NOMINAL. -Output- *** ERROR in MODEL command A nominal variable may not appear on the right-hand side of an ON statement: U1 Does there exist any alternative which may work? Thank you very much in advance. Al |
|
|
Because u1 and u2 have only two categories, you should put them on the CATEGORICAL list not the NOMINAL list. |
|
Al Rull posted on Wednesday, November 10, 2010 - 8:26 am
|
|
|
Thank you for your answer! I coded u1 and u2 as CATEGORICAL, run the path analysis model and receive the following error message: THE STANDARD ERRORS OF THE MODEL PARAMETER ESTIMATES COULD NOT BE COMPUTED. THE MODEL MAY NOT BE IDENTIFIED. CHECK YOUR MODEL. PROBLEM INVOLVING PARAMETER 2. When I leave out "u1 ON u2;" the problem does not occur and I receive the normal output of data processing. Al |
|
|
If you want an answer to this question, please send the full outputs and your license number to support@statmodel.com. |
|
Back to top |
|
|