Heterogeneity in dynamic discrete choice models

Browning, Martin; Carro, Jesús M.

doi:10.1111/j.1368-423x.2009.00301.x

Cited by 33 publications

(26 citation statements)

References 21 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accordingly, much effort has been devoted to determining the unknown panel structure without resorting to the use of external factors. One approach is to use finite mixture models; see Sun (2005), Kasahara and Shimotsu (2009), and Browning and Carro (2010). Another approach adapts the K-means algorithm to panel data models; see Lin and Ng (2012), Sarafidis and Weber (2015), Bonhomme and Manresa (2015), and Ando and Bai (2016).…”

Section: Introductionmentioning

confidence: 99%

Homogeneity pursuit in panel data models: Theory and application

Wang

Phillips

2018

J of Applied Econometrics

View full text Add to dashboard Cite

Summary This paper studies the estimation of a panel data model with latent structures where individuals can be classified into different groups with the slope parameters being homogeneous within the same group but heterogeneous across groups. To identify the unknown group structure of vector parameters, we design an algorithm called Panel‐CARDS. We show that it can identify the true group structure asymptotically and estimate the model parameters consistently at the same time. Simulations evaluate the performance and corroborate the asymptotic theory in several practical design settings. The empirical application reveals the heterogeneous grouping effect of income on democracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Homogeneity pursuit in panel data models: Theory and application

Wang

Phillips

2018

J of Applied Econometrics

View full text Add to dashboard Cite

show abstract

“…The second problem with the conventional approach is that whenever we have long enough panels to estimate the model for each unit individually with minimal bias, we do …nd substantial heterogeneity in the both the 'intercept' and 'slope' parameters in (1.1). A situation where this is the case can be found in Browning and Carro (2010). Additional evidence will be provided in the empirical illustration in this paper.…”

Section: Introductionmentioning

confidence: 84%

“…Table (3.1) presents that minimum number of periods, min T + 1, for some cases. 8 As can be seen from Table (3.1), to identify a relatively rich distribution with 14 di¤erent points of support we only need a relatively short panel (T = 7). Even a short panel (T = 4, for example) is more than we need to identify a distribution with more than the two points commonly used in applied work.…”

Section: Identi…cation For the ‡Exible Discrete Schemementioning

confidence: 99%

See 1 more Smart Citation

Dynamic binary outcome models with maximal heterogeneity

Browning

Carro

2014

Journal of Econometrics

Self Cite

View full text Add to dashboard Cite

Most econometric schemes to allow for heterogeneity in micro behaviour have two drawbacks: they do not …t the data and they rule out interesting economic models. In this paper we consider the time homogeneous …rst order For comments and useful suggestions, we thank three referees, Enrique Sentana, Whitney Newey, Ivan Fernandez-Val, Sara Ayo, and participants at seminars at Boston University; MIT/Harvard; Yale University; Nu¢eld (Oxford); IFS (London); CEMFI; Manchester; Columbia, CAM (Copenhagen) and a conference at the Tinbergen Institute. The second author gratefully acknowledges that this research was supported by a Marie Curie International Outgoing Fellowship within the 7th European Community Framework Programme, by grants ECO2012-31358, ECO2009-11165 and SEJ2006-05710 from the Spanish Minister of Education, MCINN (Consolider-Ingenio2010), Consejería de Educación de la Comunidad de Madrid (Excelecon project); he also thanks the Department of Economics at the MIT at which he conducted part of this research as visiting scholar.y The …rst draft was titled "Identi…cation of the dynamic discrete choice model" and was presented at the CAM Summer Workshop (University of Copenhagen) in July 2007.Markov (HFOM) model that allows for maximal heterogeneity. That is, the modelling of the heterogeneity does not impose anything on the data (except the HFOM assumption for each agent) and it allows for any theory model (that gives a HFOM process for an individual observable variable). 'Maximal' means that the joint distribution of initial values and the transition probabilities is unrestricted.We establish necessary and su¢cient conditions for generic local point identi…cation of our heterogeneity structure that are very easy to check, and we show how it depends on the length of the panel.We apply our techniques to a long panel of Danish workers who are very homogeneous in terms of observables. We show that individual unemployment dynamics are very heterogeneous, even for such a homogeneous group. We also show that the impact of cyclical variables on individual unemployment probabilities di¤ers widely across workers. Some workers have unemployment dynamics that are independent of the cycle whereas others are highly sensitive to macro shocks.

show abstract

“…Guvenen (), Browning et al. () and Browning and Carro (, ), for example, provide extensive discussions and empirical evidence on this. An alternative extension of the Robinson framework that stays true to the fixed‐effect tradition would be

y_{i j} = x_{i j}^{'} α_{0} + θ_{i} (v_{i j}) + ɛ_{i j},

where, now,

θ_{i}

are unit‐specific non‐parametric functions, and the usual location parameter

λ_{i}

has been absorbed into it.…”

Section: Local First‐differencingmentioning

confidence: 99%

First-differencing in panel data models with incidental functions

Jochmans

2014

The Econometrics Journal

View full text Add to dashboard Cite

I discuss the fixed-effect estimation of panel data models with time-varying excess heterogeneity across cross-sectional units. These latent components are not given a parametric form. A modification to traditional first-differencing is motivated which, asymptotically, removes the permanent unobserved heterogeneity from the differenced model. Conventional estimation techniques can then be readily applied. Distribution theory for a kernel-weighted GMM estimator under large-n and fixed-T asymptotics is developed. The estimator is put to work in a series of numerical experiments to static and dynamic models.jel classification: C13, C14, C33 keywords: dynamic panel data, GMM, incidental functions, local firstdifferencing, time-varying fixed effects, nonparametric heterogeneity.

show abstract

Heterogeneity in dynamic discrete choice models

Cited by 33 publications

References 21 publications

Homogeneity pursuit in panel data models: Theory and application

Homogeneity pursuit in panel data models: Theory and application

Dynamic binary outcome models with maximal heterogeneity

First-differencing in panel data models with incidental functions

Contact Info

Product

Resources

About