Estimation of average treatment effects based on parametric propensity score model

In this paper, the estimation of average treatment effects is examined given that the propensity score is of a parametric form with some unknown parameters. Under the assumption that the treatment is ignorable given some observed characteristics, the MLEs for those unknown parameters in the probability assignment model have been achieved firstly and then three estimators have been defined by the inverse probability weighted, regression and imputation methods, respectively. All the estimators are shown asymptotically normal and more importantly, the substantial efficiency gains of the first two estimates have been obtained theoretically compared with the existing estimators in Hahn (1998) and Hirano et al. (2003), i.e., the inverse weighted probability estimator and the regression estimator have smaller asymptotic variances. Our simulation analysis verifies the theoretical results in terms of biases, SEs and MSEs.     

On the inefficiency of propensity score matching

Propensity score matching is now widely used in empirical applications for estimating treatment effects. Propensity score matching (PSM) is preferred to matching on X because of the lower dimension of the estimation problem. In this note, however, it is shown that PSM is inefficient compared to matching on X. Hence, matching on X should be considered as a serious alternative.     

Comparing different propensity score estimation methods for estimating the marginal causal effect through standardization to propensity scores

Hernan and Robins proposed a method for calculating marginal causal effect of treatment using standardization to propensity scores.

?Data adaptive methods have been suggested as alternatives to logistic regression for the estimation of propensity scores. We examined the performance of various data mining methods using simulated data. The estimators' performance was evaluated in terms of relative bias, 95% CI coverage rate, and mean squared error.

?All methods (except CART and GBM) displayed generally acceptable performance. However, under the conditions of moderate non-additivity and moderate nonlinearity, ANN and SL outperformed logistic regression with better bias reduction and more consistent 95% CI coverage.     

Propensity score model specification for estimation of average treatment effects

Treatment effect estimators that utilize the propensity score as a balancing score, e.g., matching and blocking estimators are robust to misspecifications of the propensity score model when the misspecification is a balancing score. Such misspecifications arise from using the balancing property of the propensity score in the specification procedure. Here, we study misspecifications of a parametric propensity score model written as a linear predictor in a strictly monotonic function, e.g. a generalized linear model representation. Under mild assumptions we show that for misspecifications, such as not adding enough higher order terms or choosing the wrong link function, the true propensity score is a function of the misspecified model. Hence, the latter does not bring bias to the treatment effect estimator. It is also shown that a misspecification of the propensity score does not necessarily lead to less efficient estimation of the treatment effect. The results of the paper are highlighted in simulations where different misspecifications are studied.     

Comparison of Type I error rates and statistical power of different propensity score methods

Propensity score analysis (PSA) is a technique to correct for potential confounding in observational studies. Covariate adjustment, matching, stratification, and inverse weighting are the four most commonly used methods involving propensity scores. The main goal of this research is to determine which PSA method performs the best in terms of protecting against spurious association detection, as measured by Type I error rate, while maintaining sufficient power to detect a true association, if one exists. An examination of these PSA methods along with ordinary least squares regression was conducted under two cases: correct PSA model specification and incorrect PSA model specification. PSA covariate adjustment and PSA matching maintain the nominal Type I error rate, when the PSA model is correctly specified, but only PSA covariate adjustment achieves adequate power levels. Other methods produced conservative Type I Errors in some scenarios, while liberal Type I error rates were observed in other scenarios.     

Estimating and using propensity score in presence of missing background data: an application to assess the impact of childbearing on wellbeing

Propensity score methods are an increasingly popular technique for causal inference. To estimate propensity scores, we must model the distribution of the treatment indicator given a vector of covariates. Much work has been done in the case where the covariates are fully observed. Unfortunately, many large scale and complex surveys, such as longitudinal surveys, suffer from missing covariate values. In this paper, we compare three different approaches and their underlying assumptions of handling missing background data in the estimation and use of propensity scores: a complete-case analysis, a pattern-mixture model based approach developed by Rosenbaum and Rubin (J Am Stat Assoc79:516–524, 1984), and a multiple imputation approach. We apply these methods to assess the impact of childbearing events on individuals’ wellbeing in Indonesia, using a sample of women from the Indonesia Family Life Survey. I am grateful to all the participants at the project “Poverty Dynamics and Fertility in Developing Countries” for their support and encouragement. Special thanks are due to Fabrizia Mealli for her insightful suggestions and discussions. I also thank Jungho Kim, who is the main author of the STATA code to produce Indonesia consumption expenditure. Finally, I thank Arnstein Aassve, and Letizia Mencarini for help working with the data and their very useful discussions, and Alexia Fuernkranz-Prskawetz, and Henriette Engelhardt for detailed comments and suggestions which have improved the paper. Financial support from CNR-EFS and COFIN 2005 is gratefully acknowledged.     

Performance evaluation of propensity score methods for estimating average treatment effects with multi-level treatments*

The propensity score (PS) method is widely used to estimate the average treatment effect (TE) in observational studies. However, it is generally confined to the binary treatment assignment. In an extension to the settings of a multi-level treatment, Imbens proposed a generalized propensity score which is the conditional probability of receiving a particular level of the treatment given pre-treatment variables. The average TE can then be estimated by conditioning solely on the generalized PS under the assumption of weak unconfoundedness. In the present work, we adopted this approach and conducted extensive simulations to evaluate the performance of several methods using the generalized PS, including subclassification, matching, inverse probability of treatment weighting (IPTW), and covariate adjustment. Compared with other methods, IPTW had the preferred overall performance. We then applied these methods to a retrospective cohort study of 228,876 pregnant women. The impact of the exposure to different types of the antidepressant medications (no exposure, selective serotonin reuptake inhibitor (SSRI) only, non-SSRI only, and both) during pregnancy on several important infant outcomes (birth weight, gestation age, preterm labor, and respiratory distress) were assessed.     

Maximum entropy in the mean methods in propensity score matching for interval and noisy data

Abstract

In this paper, we propose maximum entropy in the mean methods for propensity score matching classification problems. We provide a new methodological approach and estimation algorithms to handle explicitly cases when data is available: (i) in interval form; (ii) with bounded measurement or observational errors; or (iii) both as intervals and with bounded errors. We show that entropy in the mean methods for these three cases generally outperform benchmark error-free approaches.     

Estimation of average causal effect using the restricted mean residual lifetime as effect measure

Although mean residual lifetime is often of interest in biomedical studies, restricted mean residual lifetime must be considered in order to accommodate censoring. Differences in the restricted mean residual lifetime can be used as an appropriate quantity for comparing different treatment groups with respect to their survival times. In observational studies where the factor of interest is not randomized, covariate adjustment is needed to take into account imbalances in confounding factors. In this article, we develop an estimator for the average causal treatment difference using the restricted mean residual lifetime as target parameter. We account for confounding factors using the Aalen additive hazards model. Large sample property of the proposed estimator is established and simulation studies are conducted in order to assess small sample performance of the resulting estimator. The method is also applied to an observational data set of patients after an acute myocardial infarction event.     

Comparison of causal effect estimators under exposure misclassification

Over the past decades, various principles for causal effect estimation have been proposed, all differing in terms of how they adjust for measured confounders: either via traditional regression adjustment, by adjusting for the expected exposure given those confounders (e.g., the propensity score), or by inversely weighting each subject's data by the likelihood of the observed exposure, given those confounders. When the exposure is measured with error, this raises the question whether these different estimation strategies might be differently affected and whether one of them is to be preferred for that reason. In this article, we investigate this by comparing inverse probability of treatment weighted (IPTW) estimators and doubly robust estimators for the exposure effect in linear marginal structural mean models (MSM) with G-estimators, propensity score (PS) adjusted estimators and ordinary least squares (OLS) estimators for the exposure effect in linear regression models. We find analytically that these estimators are equally affected when exposure misclassification is independent of the confounders, but not otherwise. Simulation studies reveal similar results for time-varying exposures and when the model of interest includes a logistic link.     

On the effect of misspecifying the error density in a deconvolution problem

The author studies the effect of a misspecification of the error density on the mean integrated squared error (MISE) of the deconvolution estimator. He shows that the MISE converges to a certain functional which he defines. He also illustrates the fact that the limit can sometimes be infinite. Finally, he derives some guidelines for selecting the error density in order to ensure robustness properties of the procedure.     

Controlling for confounding via propensity score methods can result in biased estimation of the conditional AUC: A simulation study

In the medical literature, there has been an increased interest in evaluating association between exposure and outcomes using nonrandomized observational studies. However, because assignments to exposure are not random in observational studies, comparisons of outcomes between exposed and nonexposed subjects must account for the effect of confounders. Propensity score methods have been widely used to control for confounding, when estimating exposure effect. Previous studies have shown that conditioning on the propensity score results in biased estimation of conditional odds ratio and hazard ratio. However, research is lacking on the performance of propensity score methods for covariate adjustment when estimating the area under the ROC curve (AUC). In this paper, AUC is proposed as measure of effect when outcomes are continuous. The AUC is interpreted as the probability that a randomly selected nonexposed subject has a better response than a randomly selected exposed subject. A series of simulations has been conducted to examine the performance of propensity score methods when association between exposure and outcomes is quantified by AUC; this includes determining the optimal choice of variables for the propensity score models. Additionally, the propensity score approach is compared with that of the conventional regression approach to adjust for covariates with the AUC. The choice of the best estimator depends on bias, relative bias, and root mean squared error. Finally, an example looking at the relationship of depression/anxiety and pain intensity in people with sickle cell disease is used to illustrate the estimation of the adjusted AUC using the proposed approaches.     

Survival analysis using inverse probability of treatment weighted methods based on the generalized propensity score

In survival analysis, treatment effects are commonly evaluated based on survival curves and hazard ratios as causal treatment effects. In observational studies, these estimates may be biased due to confounding factors. The inverse probability of treatment weighted (IPTW) method based on the propensity score is one of the approaches utilized to adjust for confounding factors between binary treatment groups. As a generalization of this methodology, we developed an exact formula for an IPTW log‐rank test based on the generalized propensity score for survival data. This makes it possible to compare the group differences of IPTW Kaplan–Meier estimators of survival curves using an IPTW log‐rank test for multi‐valued treatments. As causal treatment effects, the hazard ratio can be estimated using the IPTW approach. If the treatments correspond to ordered levels of a treatment, the proposed method can be easily extended to the analysis of treatment effect patterns with contrast statistics. In this paper, the proposed method is illustrated with data from the Kyushu Lipid Intervention Study (KLIS), which investigated the primary preventive effects of pravastatin on coronary heart disease (CHD). The results of the proposed method suggested that pravastatin treatment reduces the risk of CHD and that compliance to pravastatin treatment is important for the prevention of CHD. Copyright © 2009 John Wiley & Sons, Ltd.     

Efficient Estimation of Data Combination Models by the Method of Auxiliary-to-Study Tilting (AST)

We propose a locally efficient estimator for a class of semiparametric data combination problems. A leading estimand in this class is the average treatment effect on the treated (ATT). Data combination problems are related to, but distinct from, the class of missing data problems with data missing at random (of which the average treatment effect (ATE) estimand is a special case). Our estimator also possesses a double robustness property. Our procedure may be used to efficiently estimate, among other objects, the ATT, the two-sample instrumental variables model (TSIV), counterfactual distributions, poverty maps, and semiparametric difference-in-differences. In an empirical application, we use our procedure to characterize residual Black–White wage inequality after flexibly controlling for “premarket” differences in measured cognitive achievement. Supplementary materials for this article are available online.     

An empirical investigation into the effect of childbearing on economic wellbeing in Europe

This paper investigates the extent childbearing among couples in Europe affects their level of economic well being. We do so by implementing a propensity score matching procedure in combination with a difference-in-difference estimator. Using data from European Community Household Panel Survey (ECHP), we compare how the impact of childbearing on wellbeing varies among countries. We use several measures for wellbeing, including poverty status and various deprivation indices that take into account the multidimensionality of individuals‘ assessment of wellbeing. Not unexpected we find childbearing tend to worsen the economic wellbeing of households, but with important differences in magnitude across countries. In Scandinavian countries the effect is small and rarely significant, it is strong in the UK and also significant in Mediterranean countries. Depending on the measure of wellbeing, we find important differences among countries that are similar in terms of welfare provision.     

Another look into the effect of premarital cohabitation on duration of marriage: an approach based on matching

Summary.  The paper proposes an alternative approach to studying the effect of premarital cohabitation on subsequent duration of marriage on the basis of a strong ignorability assumption . The approach is called propensity score matching and consists of computing survival functions conditional on a function of observed variables (the propensity score), thus eliminating any selection that is derived from these variables. In this way, it is possible to identify a time varying effect of cohabitation without making any assumption either regarding its shape or the functional form of covariate effects. The output of the matching method is the difference between the survival functions of treated and untreated individuals at each time point. Results show that the cohabitation effect on duration of marriage is indeed time varying, being close to zero for the first 2–3 years and rising considerably in the following years.     

Evaluating the effect of education on earnings: models, methods and results from the National Child Development Survey

Summary.  Regression, matching, control function and instrumental variables methods for recovering the effect of education on individual earnings are reviewed for single treatments and sequential multiple treatments with and without heterogeneous returns. The sensitivity of the estimates once applied to a common data set is then explored. We show the importance of correcting for detailed test score and family background differences and of allowing for (observable) heterogeneity in returns. We find an average return of 27% for those completing higher education versus anything less. Compared with stopping at 16 years of age without qualifications, we find an average return to O-levels of 18%, to A-levels of 24% and to higher education of 48%.     

Estimates of the quantiles of kendall's partial rank correlation coefficient

The sampling distribution of kendall's partial rank correlation coefficient, J_xy?z, is not known for N>4, where N is the number of subjectts. Moran (1951) used a direcr conbinatorial method to obtain the distribution of J_xy?z forN=4; however, ten minor computationa; errors in his Table 2apparently resulted in how erroneous entries for his frequency table. Since the parctial limits of the direct combinatorial approach have been reached once N>4, the first main objective of this paper was to obtain the exact distribution of J_xy?z for N=f, 6, and 7 using an electronic computer. The second was to use the Monte Carlo method to obtain reliable estimates of the quantiles of J_xy?z for N=8,9,...,30     

On the application of statistical learning approaches to construct inverse probability weights in marginal structural Cox models: Hedging against weight-model misspecification

The marginal structural Cox model (MSCM) estimates can be highly sensitive to weight-model misspecification. We assess the performance of various popular statistical learners, such as LASSO, support vector machines, CART, bagged CART, and boosted CART, in estimating MSCM weights. When weight-models are misspecified, we find that the weights computed from boosted CART generally lead to less MSE and better coverage for the MSCM estimates. This study is motivated by the investigation of the impact of beta-interferon treatment on disability progression in subjects with multiple sclerosis from British Columbia, Canada (1995–2008).     

Addressing the effect of parameter estimation on phase II monitoring of multivariate multiple linear profiles via a new cluster-based approach

Abstract

Profile monitoring is applied when the quality of a product or a process can be determined by the relationship between a response variable and one or more independent variables. In most Phase II monitoring approaches, it is assumed that the process parameters are known. However, it is obvious that this assumption is not valid in many real-world applications. In fact, the process parameters should be estimated based on the in-control Phase I samples. In this study, the effect of parameter estimation on the performance of four Phase II control charts for monitoring multivariate multiple linear profiles is evaluated. In addition, since the accuracy of the parameter estimation has a significant impact on the performance of Phase II control charts, a new cluster-based approach is developed to address this effect. Moreover, we evaluate and compare the performance of the proposed approach with a previous approach in terms of two metrics, average of average run length and its standard deviation, which are used for considering practitioner-to-practitioner variability. In this approach, it is not necessary to know the distribution of the chart statistic. Therefore, in addition to ease of use, the proposed approach can be applied to other type of profiles. The superior performance of the proposed method compared to the competing one is shown in terms of all metrics. Based on the results obtained, our method yields less bias with small-variance Phase I estimates compared to the competing approach.