A Practitioner’s Guide to Cluster-Robust Inference

Cameron, A. Colin; Miller, Douglas L.

doi:10.3368/jhr.50.2.317

Cited by 3,545 publications

(2,332 citation statements)

References 85 publications

Supporting

Mentioning

2,296

Contrasting

Unclassified

Order By: Relevance

“…If there are a small number of clusters, Cameron et al (2008) and Cameron and Miller (2015) propose using the wild bootstrap to obtain correctly sized tests and confidence intervals. The method is, however, not so trivial to implement and, as acknowledged by the authors, computationally intensive for forming confidence intervals.…”

Section: Inference With a Small Number Of Clustersmentioning

confidence: 99%

Scars of recessions in a rigid labor market

Cockx

Ghirelli

2016

Labour Economics

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in EconStor may Scars of Recessions in a Rigid Labor Market AbstractWe study the impact of graduating in a recession in Flanders (Belgium), i.e. in a rigid labor market. In the presence of a high minimum wage, a typical recession hardly influences the hourly wage of low educated men, but reduces working time and earnings by about 4.5% up to twelve years after graduation. For the high educated, the working time is not persistently affected, but the penalty on the hourly wage (and earnings) increases with experience, and attains roughly -6% ten years after labor market entry. We also contribute to the literature on inference with few clusters.

show abstract

Section: Inference With a Small Number Of Clustersmentioning

confidence: 99%

Scars of recessions in a rigid labor market

Cockx

Ghirelli

2016

Labour Economics

View full text Add to dashboard Cite

show abstract

“…Previous research has shown that these preferences are determined to a large extent by mothers' level of education and their immigrant background [22,28,29]. Equation (1) was specified as a linear probability model, where the standard errors were clustered on hospital [30]. Support for defensive medicine would imply that > 0.…”

Section: Main Analysis -Empirical Specificationmentioning

confidence: 99%

“…We expect this coefficient to be positive. The standard errors were clustered at the hospital level [30]. We also present results without hospital fixed effects included in Model (3).…”

Section: A Longer Time Seriesmentioning

confidence: 99%

The impact of the mass media on obstetricians’ behavior in Norway

2017

View full text Add to dashboard Cite

Little is known about how physicians and hospitals respond to the risk of being negatively exposed in the mass media. We assume that newspapers will cover events more closely in the areas where they have most of their circulation. Within such areas the likelihood of negative publicity increases. The research question is whether obstetricians respond to negative newspaper coverage by choosing the least risky method of delivery, i.e. Caesarean section. This was tested on a large set of data from the Medical Birth Registry of Norway for the period 2000-2011. The Registry contains detailed medical information about all deliveries, for both the mother and the infant. This set of data was merged with a set of data that contained information about newspaper coverage for the municipalities in which all hospitals were located. Altogether, more than 620 000 deliveries in 46 municipalities were included in the study. The data were analyzed using a hospital 3 fixed effects regression. The main result was that newspaper coverage had a significant positive effect on the probability of having a Caesarean section. Several supplementary analyses supported the main finding. Altogether, our results indicate that obstetricians are sensitive to the risk of being exposed in the mass media. This is likely to be because obstetricians care about their reputation.

show abstract

“…To adjust for potential bias in hypothesis tests due to the small number of clusters, I use the t-distribution with degrees of freedom equal to the number of clusters minus the number of regressors rather than using the standard normal reference distribution (Donald and Lang, 2007;Cameron and Miller, forthcoming). An alternative approach to session-level clustering also suggested by Fréchette (2012) is controlling for feedback effects but assuming independence between subjects conditional on this feedback.…”

Section: Contribution Ratesmentioning

confidence: 99%

Cursed beliefs with common-value public goods

Cox

2015

Journal of Public Economics

View full text Add to dashboard Cite

The full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-pro t purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. AbstractI show how improper conditioning of beliefs can reduce contribution in public goods environments with interdependent values. I consider a simple model of a binary, excludable public good. In equilibrium, provision of the public good is good news about its value. Naïve players who condition expectations only on their private information contribute too little, despite the absence of free-riding incentives. In a laboratory experiment, contributions indeed fall short of the equilibrium prediction. Using modified games with different belief-conditioning effects, I verify that subjects fail to condition beliefs properly. However, improper belief conditioning cannot fully explain the results.

show abstract

A Practitioner’s Guide to Cluster-Robust Inference

Cited by 3,545 publications

References 85 publications

Scars of recessions in a rigid labor market

Scars of recessions in a rigid labor market

The impact of the mass media on obstetricians’ behavior in Norway

Cursed beliefs with common-value public goods

Contact Info

Product

Resources

About