Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: nlogit defiant dissimilarity parameters
From
"Filippo Maria D'Arcangelo" <[email protected]>
To
[email protected]
Subject
st: nlogit defiant dissimilarity parameters
Date
Thu, 20 Jun 2013 15:17:22 +0200 (CEST)
Dear STATA users,
I'm quite new to the nested logit model and I'm not sure to have it completely clear in its every aspects.
In particular, I tried up the example in the nlogit help (you can find the commands hereafter):
. webuse restaurant
. nlogitgen type = restaurant(fast: Freebirds | MamasPizza, family: CafeEccell | LosNortenos | WingsNmore, fancy: Christophers | MadCows)
. nlogit chosen cost distance rating || type: income kids, base(family) || restaurant:, noconst case(family_id)
The output shows, among others, these results for IV or "dissimilarity parameters":
> ------------------------------------------------------------------------------
> dissimilarity parameters
> ------------------------------------------------------------------------------
> type |
> /fast_tau | 1.712878 1.48685 -1.201295 4.627051
> /family_tau | 2.505113 .9646351 .614463 4.395763
> /fancy_tau | 4.099844 2.810123 -1.407896 9.607583
> ------------------------------------------------------------------------------
> LR test for IIA (tau = 1): chi2(3) = 6.87 Prob > chi2 = 0.0762
> ------------------------------------------------------------------------------
As far as i know they should be comprised between 0 and 1 for the model to be coherent with RUM. Am I right here or am I mistakenly interpreting them?
It seems like the model is not normalized (i have read that this was the case of nlogit before STATA 10).
I even tried to launch the nlogitrum command. The results differ, without a clear explanation to me, while the IVs keep on being still bigger than 1.
What do I miss to understand here?
Thank you in advance for your kind reply.
f.
---
Se credi nei giovani di talento, investi sul loro futuro.
Dai il tuo 5x1000 alla Bocconi cf: 80024610158.
E' importante. E' per loro.
www.unibocconi.it/5x1000
Please note that the above message is addressed only to individuals filing Italian income tax returns.
---
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/