Panel Probit Models with Time‐Varying Individual Effects: Reestimating the Effects of Fertility on Female Labour Participation*
| Published date | 01 August 2022 |
| Author | Jie Wei,Yonghui Zhang |
| Date | 01 August 2022 |
| DOI | http://doi.org/10.1111/obes.12478 |
Panel Probit Models with Time-Varying Individual
Effects: Reestimating the Effects of Fertility on
Female Labour Participation*
JIE WEI†and YONGHUI ZHANG‡
†School of Economics, Huazhong University of Science and Technology, Wuhan, Hubei
430074, China (e-mail: weijie@hust.edu.cn)
‡School of Economics, Renmin University of China, Beijing 100872, China (e-mail:
yonghui.zhang@ruc.edu.cn)
Abstract
This paper considers a probit model for panel data in which the individual effects vary
over time by interacting with unobserved factors. In estimation we adopt a correlated
random effects approach for individual effects to get around the incidental parameter
problem. This allows us to construct (asymptotically) unbiased estimators for average
marginal effects (AMEs), which are often the ultimate quantities of interest in many
empirical studies. We derive the asymptotic distributions for the AME estimators as
well as provide the consistent estimators for their asymptotic variances. Next, we
design a specification test for detecting whether individual effects are time-varying or
not, and establish the asymptotic distribution for the proposed test statistic under the
null hypothesis of no time variation of individual effects. Monte Carlo simulations
demonstrate satisfactory finite sample performance of our proposed method. An
empirical application to study the effect of fertility on labour force participation (LFP)
is provided. We find that fertility has a larger impact on female LFP in Germany than
in the US during the 1980s. We also provide some new empirical evidence of a even
stronger effect of fertility on LFP during the 2010s in Germany, which might call for a
reconsideration of relevant policies recently enacted such as the subsidized child care
programme.
JEL Classification numbers: C23, C25.
*The authors thank Iv´
an Fern´
andez-Val for providing his data and Matlab codes and helpful discussions, and
to DIW Berlin for providing the German SOEP data. The authors also thank the editor and two anonymous
referees for constructive comments on an earlier version of the paper, and appreciate suggestions from Xi Chen,
Ruoyao Shi and Aman Ullah. Wei thanks the Ministry of Education of Humanities and Social Sciences Project
of China (No.17YJC790159), the National Natural Science Foundation of China (No.71803054) and Program
for HUST Academic Frontier Youth Team for the financial support. Zhang thanks the National Natural Science
Foundation of China (Projects No.71973141 and No.71873033), Digital Economy Platform, Major Innovation &
Planning Interdisciplinary Platform for the ‘Double-First Class’Initiative of Renmin University of China, and
fund for building world-class universities (disciplines) of Renmin University of China for the financial support.
All errors are the authors’sole responsibilities.
799
©2021 Oxford University and John Wiley & Sons Ltd.
OXFORD BULLETIN OF ECONOMICS AND STATISTICS, 84, 4 (2022) 0305-9049
doi: 10.1111/obes.12478
I. Introduction
Panel data models are widely used in empirical economics because they are capable of
capturing the common feature among individuals, while allowing the possibility of
controlling for unobserved individual heterogeneity, such as a firm’s technology,
consumer preference and an employee’s latent ability. The individual heterogeneity is
very likely to be correlated with regressors, and the failure to control for it would
deliver inconsistent estimation and cause misleading statistical inference.
While there are some well-established methods (e.g. within group or first difference
transformation) to remove the unobserved individual heterogeneity in linear panel
models, they usually fail in general for nonlinear panels due to the nonlinear nature.
Only for a few particular nonlinear models in which sufficient statistics exist, can
people obtain consistent estimation and valid inference results free from individual
heterogeneity, such as Logit (see, e.g. Hsiao, 2014) and count data models (see, e.g.
Hausman, Hall and Griliches, 1984). To control for such heterogeneity in general, one
usually has to treat individual effects as nuisance parameters to be estimated
(Fern´
andez-Val, 2009). Unfortunately, this approach may still produce inconsistent
estimators for parameters of interest if the number of time periods Tis fixed. Even
when Tgoes to infinity at the same rate as N, such estimators are still subject to
asymptotic bias. So additional bias reduction technique such as analytical or Jackknife
correction method is needed for carrying out valid statistical inference; see Hahn and
Newey (2004); Fern´
andez-Val (2009). However, these bias reduction approaches
typically involve intricate calculations or heavy computation for estimating or
removing the bias terms.
Furthermore, in the literature of nonlinear panel data models, the unobserved
individual heterogeneity is usually treated as time-invariant. Obviously, such an
assumption can be quite restrictive. As Bonhomme and Manresa (2015), this paper
instead considers the time-varying individual effects (TVIE) in panel probit models,
where the unobserved time-invariant individual effects are interactive with the
unobserved time effects as in Bai (2009). In practice, it is also more sensible to allow
for the change of individual effects across different time periods, for instance, when all
individuals in economics are subject to period-specific common shocks. Our approach,
compared with the usual one-way or two-way additive fixed effects, permits the
heterogeneous impacts of common shocks, and can include the usual fixed effects
specifications as special cases. In the literature of linear panel data models when Tis
small, TVIE has been investigated by Holtz-Eakin, Newey and Rosen (1988) and Ahn,
Lee and Schmidt (2001), among many others. Pesaran (2006); Bai (2009); Moon and
Weidner (2015) study TVIE in linear panel models when both Nand Tare large.
In the nonlinear panel data models with interactive fixed effects, Chen, Fern´
andez-
Val and Weidner (2021) derive the fixed effects estimators that are biased due to the
same incidental parameter problem as in the additive models, so analytical or split-
sample corrections are needed for model parameters as well as average partial effects.
The approach is general but challenging in theory as the log-likelihood is non-concave
in factor and loading parameters of high dimensions, and it is quite involved to prove
convergence of the iterative algorithm (Chen, 2016). Moreover, it is still unclear how
©2021 Oxford University and John Wiley & Sons Ltd.
800 Bulletin
Get this document and AI-powered insights with a free trial of vLex and Vincent AI
Get Started for FreeStart Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting