Advanced Econometrics Takeshi Amemiya

Two-Step Estimator of Heckman

Heckman (1976a) proposed the two-step estimator of the reduced-form pa­rameters (which we discussed in Section 10.8.1); but he also reestimated the labor supply model of Heckman (1974) using the structural equations version. Because (10.8.6) is a reduced-form as well as a structural equation, the estima­tion of fi2 is done in the same way as discussed in Section 10.8.1, namely, by applying least squares to the regression equation for E( W,Hf> 0) after esti­mating the argument of X (the hazard rate) by probit MLE. So we shall discuss only the estimation of (10.8.7), which we can rewrite as

Hi = y~lWt - г',ау~1 ~ rlvt - (Ю.8.9)

By subtracting E(v,Hf > 0) from vt and adding the same, we can rewrite (10.8.9) further as

щ = ri Wi - Z'ay~‘ - olvo^rlK*uPJox)- Г'е„ (10.8.10)

where aXv = Cov (uu, vt), a = Vuu, and €t = vt — E(vtH* > 0). Then the consistent estimates of jr1, ay-1, and аХваї 1У~1 are obtained by the least squares regression applied to (10.8.10) after replacing fix /сг, by its probit MLE and Wf by Wt, the least squares predictor of Wt obtained by applying Heck­man’s two-step estimator to (10.8.6). The asymptotic variance-covariaiice matrix of this estimator can be deduced from the results in the article by Heckman (1978), who considered the estimation of a more general model (which we shall discuss in the section on Type 5 Tobit models).

Actually, there is no apparent reason why we must first solve (10.8.7) for H, and proceed as indicated earlier. Heckman could justas easily have subtracted and added E(vtHf > 0) to (10.8.7) itself and proceeded similarly. This method would yield alternative consistent estimates. Inferring from the well - known fact that the two-stage least squares estimates of the standard simulta­neous equations model yield asymptotically equivalent estimates regardless of which normalization is chosen, the Heckman two-step method applied to

(10.8.7) and (10.8.9) should also yield asymptotically equivalent estimates of у and a.

Lee, Maddala, and Trost (1980) extended Heckman’s simultaneous equa­tions two-step estimator and its WLS version (taking account of the hetero - scedasticity) to more general simultaneous equations Tobit models and ob­tained their asymptotic variance-covariance matrices.

Добавить комментарий

Advanced Econometrics Takeshi Amemiya

Nonlinear Limited Information Maximum Likelihood Estimator

In the preceding section we assumed the model (8.1.1) without specifying the model for Y( or assuming the normality of u, and derived the asymptotic distribution of the class of …

Results of Cosslett: Part II

Cosslett (1981b) summarized results obtained elsewhere, especially from his earlier papers (Cosslett, 1978, 1981a). He also included a numerical evalua­tion of the asymptotic bias and variance of various estimators. We …

Other Examples of Type 3 Tobit Models

Roberts, Maddala, and Enholm (1978) estimated two types of simultaneous equations Tobit models to explain how utility rates are determined. One of their models has a reduced form that is …

Как с нами связаться:

Украина:
г.Александрия
тел./факс +38 05235  77193 Бухгалтерия

+38 050 457 13 30 — Рашид - продажи новинок
e-mail: msd@msd.com.ua
Схема проезда к производственному офису:
Схема проезда к МСД

Партнеры МСД

Контакты для заказов оборудования:

Внимание! На этом сайте большинство материалов - техническая литература в помощь предпринимателю. Так же большинство производственного оборудования сегодня не актуально. Уточнить можно по почте: Эл. почта: msd@msd.com.ua

+38 050 512 1194 Александр
- телефон для консультаций и заказов спец.оборудования, дробилок, уловителей, дражираторов, гереторных насосов и инженерных решений.