Estimation of Limited-Dependent Variable Models with Dummy Endogenous Regressors: Simple Strategies for Empirical Practice

Angrist, Joshua D.

doi:10.3386/t0248

Cited by 323 publications

(259 citation statements)

References 68 publications

Supporting

Mentioning

253

Contrasting

Unclassified

Order By: Relevance

“…In order to take this into account, we also conducted separate analyses for the counties where the university hospitals are located (Troms, Sør-Trøndelag and Hordaland). The results, which are presented in columns (3) and (4), show that the point estimates increase slightly relative to column (2), indicating an average individual-level treatment e ect of about ten percentage points for the compliant subpopulation.…”

mentioning

confidence: 93%

See 1 more Smart Citation

Access to treatment and educational inequalities in cancer survival

Fiva

Hægeland

Rønning

et al. 2014

Journal of Health Economics

View full text Add to dashboard Cite

The public health care systems in the Nordic countries provide high quality care almost free of charge to all citizens. However, social inequalities in health persist. Previous research has, for example, documented substantial educational inequalities in cancer survival. We investigate to what extent this may be driven by di erential access to and utilization of high quality treatment options. Quasi-experimental evidence based on the establishment of regional cancer wards indicates that i) highly educated individuals utilized centralized specialized treatment to a greater extent than less educated patients and ii) the use of such treatment improved these patients' survival.

show abstract

mentioning

confidence: 93%

“…2 Later research has shown that this result is sensitive to the inclusion of state speci c trends (Mazumder 2008). 3 Cutler and Lleras-Muney (2012) and Mazumder (2012) review this literature.…”

mentioning

confidence: 99%

Access to treatment and educational inequalities in cancer survival

Fiva

Hægeland

Rønning

et al. 2014

Journal of Health Economics

View full text Add to dashboard Cite

show abstract

“…To increase efficiency of the estimator, our instrumental variables (IV) approach takes account of the binary nature of the endogenous variables by estimating a Probit model in the first stage and by adopting GMM estimation in the second stage (Angrist, 2001;Wooldridge, 2010, chapter 21). Specifically, we adapt Wooldridge's Procedure 21.1 as follows:…”

Section: Estimationmentioning

confidence: 99%

Mobility across firms and occupations among graduates from apprenticeship

2015

View full text Add to dashboard Cite

Die Dis cus si on Pape rs die nen einer mög lichst schnel len Ver brei tung von neue ren For schungs arbei ten des ZEW. Die Bei trä ge lie gen in allei ni ger Ver ant wor tung der Auto ren und stel len nicht not wen di ger wei se die Mei nung des ZEW dar.Dis cus si on Papers are inten ded to make results of ZEW research prompt ly avai la ble to other eco no mists in order to encou ra ge dis cus si on and sug gesti ons for revi si ons. The aut hors are sole ly respon si ble for the con tents which do not neces sa ri ly repre sent the opi ni on of the ZEW. March 2015Abstract: Distinguishing carefully between mobility across firms and across occupations, this study provides causal estimates of the wage effects of mobility among graduates from apprenticeship in Germany. Our instrumental variables approach exploits variation in regional labor market characteristics. Pure firm changes and occupation-and-job changes after graduation from apprenticeship result in average wage losses, whereas an occupation change within the training firm results in persistent wage gains. For the majority of cases a change of occupation involves a career progression. In contrast, for job switches the wage loss dominates.

show abstract

“…The other option of demeaning all of the variables, to allow us to ignore the fixed effects terms, would bias the standard error estimates. Using the linear probability model in the first stage avoids these problems and allows us to estimate the causal effect of the treatment consistently and efficiently (Angrist 2000). For an earlier application of the linear probability model for endogenous regressors, see Heckman and MaCurdy (1985).…”

Section: Resultsmentioning

confidence: 99%

Subsidizing Addiction: Do State Health Insurance Mandates Increase Alcohol Consumption

Klick

Stratmann

2003

SSRN Journal

View full text Add to dashboard Cite

A model of addiction in which individuals are forward looking implies that as the availability of addiction treatment options grows, individuals will consume more of an addictive good.We test this implication using cross-state variation in the adoption of mental health parity mandates that include substance abuse treatments. We examine the effects of these mandates on the consumption of alcohol and find that parity legislation leads to an increase in alcohol consumption. To account for the possible endogeneity of the adoption of mental health parity mandates, we perform an instrumental variables analysis and find that the ordinary least squares estimation significantly underestimates the insurance effect on alcohol consumption.

show abstract

Estimation of Limited-Dependent Variable Models with Dummy Endogenous Regressors: Simple Strategies for Empirical Practice

Abstract: (1980), Bronars and Grogger (1994), Gangadharan and Rosenbloom (1996), andAngrist and Evans (1998

Cited by 323 publications

References 68 publications

Access to treatment and educational inequalities in cancer survival

Access to treatment and educational inequalities in cancer survival

Mobility across firms and occupations among graduates from apprenticeship

Subsidizing Addiction: Do State Health Insurance Mandates Increase Alcohol Consumption

Contact Info

Product

Resources

About