Abstract
In this paper, we show that the sequential logit (SL) model, in which a choice process is characterized as a sequence of independent multinomial logit models, is a limiting case of the nested logit (NL) model. For testing the SL model against the NL model, we propose Wald, likelihood ratio and Lagrange multiplier tests after suitably reparameterizing the NL model. It is found that when the NL model parameters are "weakly identified", the Wald test severely underrejects the true model, whereas the sizes of the LR and LM tests are not significantly affected.
| Original language | English |
|---|---|
| Pages (from-to) | 345-361 |
| Number of pages | 17 |
| Journal | Japanese Economic Review |
| Volume | 60 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - 2009 |
| Externally published | Yes |
Fingerprint
ASJC Scopus subject areas
- Economics and Econometrics
Cite this
Testing the sequential logit model against the nested logit model. / Nagakura, Daisuke; Kobayashi, Masahito.
In: Japanese Economic Review, Vol. 60, No. 3, 2009, p. 345-361.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Testing the sequential logit model against the nested logit model
AU - Nagakura, Daisuke
AU - Kobayashi, Masahito
PY - 2009
Y1 - 2009
N2 - In this paper, we show that the sequential logit (SL) model, in which a choice process is characterized as a sequence of independent multinomial logit models, is a limiting case of the nested logit (NL) model. For testing the SL model against the NL model, we propose Wald, likelihood ratio and Lagrange multiplier tests after suitably reparameterizing the NL model. It is found that when the NL model parameters are "weakly identified", the Wald test severely underrejects the true model, whereas the sizes of the LR and LM tests are not significantly affected.
AB - In this paper, we show that the sequential logit (SL) model, in which a choice process is characterized as a sequence of independent multinomial logit models, is a limiting case of the nested logit (NL) model. For testing the SL model against the NL model, we propose Wald, likelihood ratio and Lagrange multiplier tests after suitably reparameterizing the NL model. It is found that when the NL model parameters are "weakly identified", the Wald test severely underrejects the true model, whereas the sizes of the LR and LM tests are not significantly affected.
UR - http://www.scopus.com/inward/record.url?scp=69149094235&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=69149094235&partnerID=8YFLogxK
U2 - 10.1111/j.1468-5876.2008.00458.x
DO - 10.1111/j.1468-5876.2008.00458.x
M3 - Article
AN - SCOPUS:69149094235
VL - 60
SP - 345
EP - 361
JO - Japanese Economic Review
JF - Japanese Economic Review
SN - 1352-4739
IS - 3
ER -