[Limdep Nlogit List] NLOGIT command or data construction(No.2)

[H. KAMEYAMA]

Dear Prof. Greene,

thank you so much for your reply as usual.
Now in this case "CSET " is filled out all "4", which means each 
question, choice set, are consisted of four unlabelled choice option.
Then respondents are required to reply by choosing one of the option in 
each choise set.

As you mention, "my counter, CSET, is incorrect", does it mean due to 
unlabelled case?
On page 112 in "Applied Choice Analysis" I can see the example, but I 
have no idea how to construct dataset.

The example in the text the first optionis always for "Car", the 2nd for 
"Bas", the 3rd for "Train", the 4th for "Plane",
whereas in my case the format is different.

Maybe "place" can be the label , but how can I proceed?

Hiroshi KAMEYAMA


Prof. Greene wrote,
> The message means exactly what it says.  For observation 
> (group), 278 the LHS variable does not consist of (0,0,...,1,0,0...).  This
> usually occurs when your counter, in this case, CSET, is incorrect, so
> the data set is not correctly blocked for the estimator.
> /B. Greene
>
>   
>   


-- 
************************************************
KAMEYAMA, Hiroshi (亀山　宏)
Associate Professor
Farm Management,  Faculty of Agriculture 
Kagawa University, Japan 761-0795
2393 Ikenobe Miki-cho, Kita-gun, Kagawa 
〒761-0795 香川県木田郡三木町池戸2393
香川大学農学部　応用生物科学科生物資源生産学大講座
Phone: +81-(0)87-891-3054 (FAX: -3021. admin.,庶務)
URL:http://www.ag.kagawa-u.ac.jp/kameyama/index.html
Email: kameyama at ag.kagawa-u.ac.jp
************************************************