Standard errors in the multinomial logit model |
| |
Authors: | Thomas B Fomby James E Pearce |
| |
Institution: | 1. Department of Economics , Southern Methodist University , Dallas, TX, 75275;2. Research Department , Federal Reserve Bank of Dallas , Dallas, TX, 75222 |
| |
Abstract: | Asymptotic stmdard errors in the multinomial log it model are derived for efficient estimates of (A) the probability of choosing an alternative , (B) the change in the probability of choosing an alternative given a change in an explanatory variable , (C) the expected response, and (D) the change in the expected response given a change in an explanatory variable. An empirical example illustrates the usefulness of the concepts developed here. |
| |
Keywords: | multinomial logit model δ-method information matrix |
|
|