Sensitivity of Propensity Score Methods to the Specifications

نویسندگان

  • Zhong Zhao
  • IZA Bonn
چکیده

Sensitivity of Propensity Score Methods to the Specifications Propensity score matching estimators have two advantages. One is that they overcome the curse of dimensionality of covariate matching, and the other is that they are nonparametric. However, the propensity score is usually unknown and needs to be estimated. If we estimate it nonparametrically, we are incurring the curse-of-dimensionality problem we are trying to avoid. If we estimate it parametrically, how sensitive the estimated treatment effects are to the specifications of the propensity score becomes an important question. In this paper, we study this issue. First, we use a Monte Carlo experimental method to investigate the sensitivity issue under the unconfoundedness assumption. We find that the estimates are not sensitive to the specifications. Next, we provide some theoretical justifications, using the insight from Rosenbaum and Rubin (1983) that any score finer than the propensity score is a balancing score. Then, we reconcile our finding with the finding in Smith and Todd (2005) that, if the unconfoundedness assumption fails, the matching results can be sensitive. However, failure of the unconfoundedness assumption will not necessarily result in sensitive estimates. Matching estimators can be speciously robust in the sense that the treatment effects are consistently overestimated or underestimated. Sensitivity checks applied in empirical studies are helpful in eliminating sensitive cases, but in general, it cannot help to solve the fundamental problem that the matching assumptions are inherently untestable. Last, our results suggest that including irrelevant variables in the propensity score will not bias the results, but overspecifying it (e.g., adding unnecessary nonlinear terms) probably will. JEL Classification: C21, C14, C15, C16, C52

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

استفاده از Propensity Score برای همسان سازی نمونه ها در یک مطالعه مورد شاهدی

Background and Aim: Case-Control studies provide evidence in the area of health. Validity and accuracy of such studies depend to a large extent on the similarity (similar distributions) of the case and control groups according to confounding variables. Matching is a method for controlling or eliminating the effects of important confounders. Matching using propensity score has recently been intr...

متن کامل

An Application of Non-response Bias Reduction Using Propensity Score Methods

‎In many statistical studies some units do not respond to a number or all of the questions‎. ‎This situation causes a problem called non-response‎. ‎Bias and variance inflation are two important consequences of non-response in surveys‎. ‎Although increasing the sample size can prevented variance inflation‎, ‎but cannot necessary adjust for the non-response bias‎. ‎Therefore a number of methods ...

متن کامل

An Application of Non-response Bias Reduction Using Propensity Score Methods

‎Normal distribution is widely used in many applications‎. ‎The problem of testing whether observations come from a normal distribution has been studied extensively by many researchers‎. ‎Our main goal in this article is to present a simple test procedure for testing multivariate ‎normality‎‎.

متن کامل

Propensity Score Application in the Relationship of Screen Time and Metabolic Syndrome in Adolescents: the CASPIAN-III Study

Aim: This study aimed to assess the relationship of screen time and metabolic syndrome (MetS) among Iranian adolescents. Materials and Methods  In this nationwide study, the propensity score (PS) was used in a matched case-control study design. The data was obtained from 5,625 students aged 10-18 years, who participated in a national school-based surveillance program. MetS was defined accordi...

متن کامل

The Effect of Inflation Targeting on Indirect Tax Performance in Selected Countries Using Propensity Score Matching Model

Inflation targeting framework has become a predominant monetary approach across the globe. Williams (2015) believes that in a very real sense, almost all economies are inflation targeters -either explicit or implicit- now.(1) Due to the increasing spread of this policy, it is necessary to consider the way it affects macroeconomic variables. using prevalent economic models for evaluating the eff...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2005