An Illustration of a Pitfall in Estimating the Effects of Aggregate Variables on Micro Units

Moulton, Brent R.

doi:10.2307/2109724

Cited by 2,224 publications

(1,453 citation statements)

References 20 publications

Supporting

Mentioning

1,421

Contrasting

Unclassified

Order By: Relevance

“…Our estimations show however that clustering does not change the estimated standard errors much. This result is consistent with Moulton's contention that the problem does not arise in a fixed effects model (see Moulton (1986)). 22 The advantage of the least square method (compared to Logit or Probit) is in that no distribution assumption is imposed on the error term.…”

Section: Patient Selectionsupporting

confidence: 91%

Changes in Hospital Quality after Conversion in Ownership Status

Farsi¹

2004

International Journal of Health Care Finance and Economics

View full text Add to dashboard Cite

This paper examines the effects of hospital conversions between For-Profit and Not-For-Profit forms on quality of medical care. The sample includes Medicare patients treated in California's private hospitals from 1990 to 1998 for Acute Myocardial Infarction and Congestive Heart Failure. The results suggest that converted hospitals have experienced quality changes before conversion, which may bias the estimated effects. Both conversions are found to have some adverse consequences regarding quality. Hospitals that converted to FP form show an increase in AMI mortality rates, while those converted to NFP status indicate an increase in CHF mortality and re-admission rates of AMI patients.JEL classification: L31; I18; I11

show abstract

Section: Patient Selectionsupporting

confidence: 91%

Changes in Hospital Quality after Conversion in Ownership Status

Farsi¹

2004

International Journal of Health Care Finance and Economics

View full text Add to dashboard Cite

show abstract

“…Moulton, 1990). It is easy to show that two group/two time period differences in difference is not consistent without assuming (2).…”

Section: Basic Model and Problemmentioning

confidence: 98%

“…1 It is complementary to typical approaches focusing on situations where the number of treatment and control groups, N 0 and N 1 , are both large (e.g. Moulton, 1990) or both small (e.g. Donald and Lang, 2002).…”

Section: Introductionmentioning

confidence: 99%

Inference with "Difference in Differences" with a Small Number of Policy Changes

2005

View full text Add to dashboard Cite

Difference in differences methods have become very popular in applied work. This paper provides a new method for inference in these models when there are a small number of policy changes. This situation occurs in many implementations of these estimators. Identification of the key parameter typically arises when a group "changes" some particular policy. The asymptotic approximations that are typically employed assume that the number of cross sectional groups, N, times the number of time periods, T, is large. However, even when N or T is large, the number of actual policy changes observed in the data is often very small. In this case, we argue that point estimators of treatment effects should not be thought of as being consistent and that the standard methods that researchers use to perform inference in these models are not appropriate. We develop an alternative approach to inference under the assumption that there are a finite number of policy changes in the data, using asymptotic approximations as the number of non-changing groups gets large. In this situation we cannot obtain a consistent point estimator for the key treatment effect parameter. However, we can consistently estimate the finite-sample distribution of the treatment effect estimator, up to the unknown parameter itself. This allows us to perform hypothesis tests and construct confidence intervals. For expositional and motivational purposes, we focus on the difference in differences case, but our approach should be appropriate more generally in treatment effect models which employ a large number of controls, but a small number of treatments. We demonstrate the use of the approach by analyzing the effect of college merit aide programs on college attendance. We show that in some cases the standard approach can give misleading results.

show abstract

“…We contrast these estimates with 2SLS (two stages least squares) estimates, which we obtain by instrumenting years of schooling with years of compulsory education and their interaction with the dummy RURAL. In all specifications we cluster standard errors by country and cohort, the dimensions of relevant variation for years of compulsory education (see Moulton, 1990). Table 8 presents our results: independently of the selected dependent variable, the F-test statistic for the inclusion of additional instruments in the first stage regressions is always above the rule of thumb value of 10, which allows us to reject the hypothesis that our instruments are weak.…”

Section: The Causal Effect Of Education On Lifetime Earningsmentioning

confidence: 86%

Books are Forever: Early Life Conditions, Education and Lifetime Earnings in Europe

2012

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. We estimate the effect of education on lifetime income in Europe, by distinguishing between individuals who lived in rural or urban areas during childhood and between individuals who had access to many or few books at age ten. We instrument years of education using reforms of compulsory education in nine different countries, and find that individuals in rural areas were most affected by the reforms. Among those affected, individuals with many books at home at age ten enjoyed substantially higher returns to their additional education. We argue that the long -lasting beneficial effects of having books at home are due to the cultural environment in the household and the development of cognitive skills rather than to the presence of short -term liquidity constraints. Terms of use: Documents in EconStor mayJEL Code: J24

show abstract

An Illustration of a Pitfall in Estimating the Effects of Aggregate Variables on Micro Units

Cited by 2,224 publications

References 20 publications

Changes in Hospital Quality after Conversion in Ownership Status

Changes in Hospital Quality after Conversion in Ownership Status

Inference with "Difference in Differences" with a Small Number of Policy Changes

Books are Forever: Early Life Conditions, Education and Lifetime Earnings in Europe

Contact Info

Product

Resources

About