Search

In certain indications, it is well understood that randomized controlled trials lead to slow enrollment and high differential drop-out rate in the standard of care control arm when the standard of care is undesirable to patients. This not only impacts the pace of drug development but may also render a randomized trial uninterpretable if drop-out from the control arm is common. Single-arm trials are common in such indications. An external control arm (ECA) built using a propensity score method (Rosenbaum and Rubin, Biometrika 70:41–55, 1983) from subjects outside the current trial but who meet the same eligibility criteria as the subjects of the current trial, is valuable in assessing treatment effect of a new drug that cannot be otherwise assessed with a single-arm trial, or an unintentionally under-powered and arguably biased randomized controlled trial. Propensity score methods have increasingly gained importance in observational medical research, paving the way for the use of these methods in non-randomized clinical trials. In this paper, we describe our experience with building an ECA for drug development related to regulatory activities associated with a new molecular entity (NME). Through analysis of a phase 2 study, we show how best practices from causal statistical methods can be used to build an ECA for a non-randomized drug trial—a novel application of a well-studied method. To prevent selection bias, the selection of subjects for the ECA was carried out by an independent group of statisticians who were blinded to all patient outcome data. We share lessons learnt from our regulatory interactions that provide helpful suggestions on how to advance ECA-based drug development. There has been interest in confirmatory trials that use reduced control arm randomization along with an ECA. We present a design for such a hybrid trial using a propensity score weighting method and describe how a standard propensity score analysis can be used to analyze data resulting from a composite hybrid randomized and external control arm. [ABSTRACT FROM AUTHOR]

Recent years have seen increasing interest in and attention to evidence-based practices, where the 'evidence' generally comes from well-conducted randomized trials. However, while those trials yield accurate estimates of the effect of the intervention for the participants in the trial (known as 'internal validity'), they do not always yield relevant information about the effects in a particular target population (known as 'external validity'). This may be due to a lack of specification of a target population when designing the trial, difficulties recruiting a sample that is representative of a prespecified target population, or to interest in considering a target population somewhat different from the population directly targeted by the trial. This paper first provides an overview of existing design and analysis methods for assessing and enhancing the ability of a randomized trial to estimate treatment effects in a target population. It then provides a case study using one particular method, which weights the subjects in a randomized trial to match the population on a set of observed characteristics. The case study uses data from a randomized trial of school-wide positive behavioral interventions and supports (PBIS); our interest is in generalizing the results to the state of Maryland. In the case of PBIS, after weighting, estimated effects in the target population were similar to those observed in the randomized trial. The paper illustrates that statistical methods can be used to assess and enhance the external validity of randomized trials, making the results more applicable to policy and clinical questions. However, there are also many open research questions; future research should focus on questions of treatment effect heterogeneity and further developing these methods for enhancing external validity. Researchers should think carefully about the external validity of randomized trials and be cautious about extrapolating results to specific populations unless they are confident of the similarity between the trial sample and that target population. [ABSTRACT FROM AUTHOR]

The current kidney allocation system in the United States fails to match donors and recipients well. In an effort to improve the allocation system, the United Network of Organ Sharing (UNOS) defined factors that should determine a new allocation policy, and particularly patients' potential remaining lifetime without a transplant (pre-transplant survival rates). Estimating pre-transplant survival rates is challenging because the data available on candidates and organ recipients is already 'contaminated' by the current allocation policy. In particular, the selection of patients who are offered (and decide to accept) a kidney is not random. We therefore expect differences in mortality-related characteristics of organ recipients and of candidates who have not received transplant. Such differences introduce bias into survival models. Existing approaches for tackling this selection bias either ignore the difference between candidates and recipients or assume that selection to transplant is based solely on patients' pre-transplant information, irrespective of the potential allocation outcome. We argue that in practice the allocation is dependent on the anticipated allocation outcome, which is a major factor in selection to transplant. Moreover, we show that ignoring the anticipated outcome increases model bias rather than decreases it. In this paper, we propose a novel simulator-based approach (SimBa) that adjusts for the selection bias by taking into account both pre-transplant and anticipated outcome information using simulation. We then fit survival models to kidney transplant waitlist data and compare the different adjustment methods. We find that SimBa not only fits the data best, but also captures a key aspect of the current allocation policy, namely, that the probability of kidney allocation increases in the expected pre-transplant life years. [ABSTRACT FROM AUTHOR]

This paper builds upon two prior papers by Haviland and Nagin (Psychometrika 70:1–22, 2005) and Haviland, Nagin, and Rosenbaum (Working paper, 2006) that attempt to bring the key attributes of an experiment to the analysis of non-experimental longitudinal data. Using a case study of the facilitation effect of gang membership on violence, it systematically examines the contribution of group-based trajectory modeling to the achievement of covariate balance in observational data. In this case study, inclusion of the posterior probabilities of group membership (PPGM), from a model on the pre-treatment measures of the outcome variable, created closer balance on these key covariates than did analyses that did not include them. Still closer balance was obtained on these key covariates by stratifying the analysis by trajectory group. This stratification was achieved by fitting separate propensity score models and matching gang joiners to gang abstainers within trajectory group. In addition, we demonstrated that further balance could be obtained on additional covariates by including PPGM from a model on pre-treatment longitudinal data of these covariates. While this case study is only one empirical example, we believe that it provides useful empirical evidence on the value of performing within trajectory group causal inference in observational longitudinal data and on the use of the PPGM in achieving balance in propensity score-based causal inference. [ABSTRACT FROM AUTHOR]

Whether work is performed for household members’ consumption (subsistence work) or for sale to others (market work), it may be an enabling resource for women’s agency, or their capacity to define and act upon their goals. The present paper asks: Do women who engage in market work have higher agency in the three domains of economic decision-making, freedom of movement, and equitable gender role attitudes, compared to those who engage in subsistence work and those who do not work? To address this question, we leverage data from a probability sample of ever-married women in rural Minya, Egypt (N = 600). We use structural equation models with propensity score adjustment to estimate the relationship between women’s work and three domains of their agency. We find no effect on gender attitudes or decision making. However, women’s subsistence and market work are associated with increasingly higher factor means for freedom of movement, compared to not working. We conclude that in rural Minya, the relationship between women’s work and their agency depends on the type of work they perform and the dimension of agency under consideration, with the rewards of market work exceeding those of subsistence work in the domain of freedom of movement alone. [ABSTRACT FROM AUTHOR]

Despite growing recognition of the important role implementation plays in successful prevention efforts, relatively little work has sought to demonstrate a causal relationship between implementation factors and participant outcomes. In turn, failure to explore the implementation-to-outcome link limits our understanding of the mechanisms essential to successful programming. This gap is partially due to the inability of current methodological procedures within prevention science to account for the multitude of confounders responsible for variation in implementation factors (i.e., selection bias). The current paper illustrates how propensity and marginal structural models can be used to improve causal inferences involving implementation factors not easily randomized (e.g., participant attendance). We first present analytic steps for simultaneously evaluating the impact of multiple implementation factors on prevention program outcome. Then, we demonstrate this approach for evaluating the impact of enrollment and attendance in a family program, over and above the impact of a school-based program, within PROSPER, a large-scale real-world prevention trial. Findings illustrate the capacity of this approach to successfully account for confounders that influence enrollment and attendance, thereby more accurately representing true causal relations. For instance, after accounting for selection bias, we observed a 5 % reduction in the prevalence of 11th grade underage drinking for those who chose to receive a family program and school program compared to those who received only the school program. Further, we detected a 7 % reduction in underage drinking for those with high attendance in the family program. [ABSTRACT FROM AUTHOR]

In this paper, we address the Bayesian classification with incomplete data. The common approach in the literature is to simply ignore the samples with missing values or impute missing values before classification. However, these methods are not effective when a large portion of the data have missing values and the acquisition of samples is expensive. Motivated by these limitations, the expectation maximization algorithm for learning a multivariate Gaussian mixture model and a multiple kernel density estimator based on the propensity scores are proposed to avoid listwise deletion (LD) or mean imputation (MI) for solving classification tasks with incomplete data. We illustrate the effectiveness of our proposed algorithms on some artificial and benchmark UCI data sets by comparing with LD and MI methods. We also apply these algorithms to solve the practical classification tasks on the lithology identification of hydrothermal minerals and license plate character recognition. The experimental results demonstrate their good performance with high classification accuracies. [ABSTRACT FROM AUTHOR]

This paper examines the impact of three components of an HIV prevention program (mid-media, interpersonal communication, and project-run clinics) on consistent condom use by long distance truckers with paid and non-paid female partners in India. Data from 2,723 long distance truckers were analyzed using the propensity score matching approach. Based on utilization of services, the following categories of intervention exposure were derived: no exposure, exposure only to mid-media, exposure only to mid-media and interpersonal communication, exposure only to mid-media and project-run clinics, and exposure to all three intervention components. Compared to those who were not exposed to any intervention, exposure to mid-media alone increased consistent condom use with paid female partners by about ten percent. Exposure to mid-media and visits to project-run clinics increased consistent condom use with non-paid female partners by 26 %. These findings suggest that mid-media events and clinics were the most effective package of services to increase consistent condom use among the long distance truckers. [ABSTRACT FROM AUTHOR]

Two major statistical issues confronting comparative analyses of hospital outcomes are adequacy of case-mix adjustment and proper accounting for random variation. Hierarchical modeling has been proposed to improve precision and reduce the impact of random variation but becomes difficult to implement when there are numerous case-mix factors to control. In this paper we formulate the problem of hospital performance comparisons within the framework of potential outcomes and illustrate an approach to hospital comparisons which combines multiple category propensity score methods for the control of case-mix variations with hierarchical Bayesian modeling of case-mix adjusted summaries. The approach is similar to that proposed by Huang et al. (Health Serv Res 40:253-278, ) but extends their approach by using a Bayesian model to accommodate hospital level attributes and to facilitate joint modeling of performance for multiple outcomes. The analytical approach is illustrated by a comparison of 30 day post admission mortality risks for patients treated for acute myocardial infarction, pneumonia or stroke in 34 New Zealand public hospitals. In a small simulation study, reported in electronic supplementary material, hierarchical models outperformed non-hierarchical models, achieving both better credible interval coverage and shorter average interval lengths for measures of between hospital variation based on contrasts between the 90th and 10th percentiles of the mortality risk distribution. Simulation performance of hierarchical and non-hierarchical models in detecting unusual performance was similar. [ABSTRACT FROM AUTHOR]

Obesity among U.S. adolescents ages 12–19 rose from 4.6% in 1963–1965 to 17.4% in 2003–2004. This paper contributes to the literature on the impact of unhealthy body mass index (BMI) on health (e.g., obesity) and human capital (e.g., schooling) investments of adolescents. We use the propensity score method to study 8,388 individuals who responded to survey Waves I through III of the National Longitudinal Study of Adolescent Health (Add Health), for students in grades 7–12. We estimate an economic model that captures longer-term effects of BMI categories (obesity and overweight separately) on on-time (dichotomous) high school graduation. We control for characteristics at the individual, household, and community levels. Baseline probit regression estimates were improved upon by using matching estimators (propensity scores yield consistent estimate of the average treatment on the treated) based on the nearest neighbor and the more robust kernel density weighting schemes. Results from both full and reduced models suggest no adverse impact of overweight or obesity on timely high school completion for males, but a significant average negative effect on females. Investigating disparities in effects across both gender and race, we isolate the adverse effects primarily to white and Asian females. No significant effects were found for African-Americans. One of the novel contributions of our research is that the significant effects of gender- and race- specific adolescent obesity and overweight conditions reach beyond high school GPA standing to also impact on-time high school graduation status. [ABSTRACT FROM AUTHOR]

In this paper, we re-analyze data used to study the role of race in capital cases in the state of Maryland. We show that when alternative, and arguably more appropriate, statistical procedures are applied, the racial effects reported in early work turn out to be very fragile. The methodological point is more general: conventional causal modeling with observational data is not likely to produce robust results for a variety of criminal justice applications. [ABSTRACT FROM AUTHOR]

A central theme of research on human development and psychopathology is whether a therapeutic intervention or a turning-point event, such as a family break-up, alters the trajectory of the behavior under study. This paper lays out and applies a method for using observational longitudinal data to make more confident causal inferences about the impact of such events on developmental trajectories. The method draws upon two distinct lines of research: work on the use of finite mixture modeling to analyze developmental trajectories and work on propensity scores. The essence of the method is to use the posterior probabilities of trajectory group membership from a finite mixture modeling framework, to create balance on lagged outcomes and other covariates established prior to t for the purpose of inferring the impact of first-time treatment at t on the outcome of interest. The approach is demonstrated with an analysis of the impact of gang membership on violent delinquency based on data from a large longitudinal study conducted in Montreal. [ABSTRACT FROM AUTHOR]

In many health services applications, research to determine the effectiveness of a particular treatment cannot be carried out using a controlled clinical trial. In settings such as these, observational studies must be used. Propensity score methods are useful tools to employ in order to balance the distribution of covariates between treatment groups and hence reduce the potential bias in treatment effect estimates in observational studies. A challenge in many health services research studies is the presence of missing data among the covariates that need to be balanced. In this paper, we compare three simple propensity models using data that examine the effectiveness of self-monitoring of blood glucose (SMBG) in reducing hemoglobin A1c in a cohort of 10,566 type 2 diabetics. The first propensity score model uses only subjects with complete case data ( n=6,687), the second incorporates missing value indicators into the model, and the third fits separate propensity scores for each pattern of missing data. We compare the results of these methods and find that incorporating missing data into the propensity score model reduces the estimated effect of SMBG on hemoglobin A1c by more than 10%, although this reduction was not clinically significant. In addition, beginning with the complete data, we artificially introduce missing data using a nonignorable missing data mechanism and compare treatment effect estimates using the three propensity score methods and a simple analysis of covariance (ANCOVA) method. In these analyses, we find that the complete case analysis and the ANCOVA method both perform poorly, the missing value indicator model performs moderately well, and the pattern mixture model performs even better in estimating the original treatment effect observed in the␣complete data prior to the introduction of artificial missing data. We conclude that in observational studies one␣must not only adjust for potentially confounding variables using methods such as propensity scores, but one␣should also account for missing data in these models in order to allow for causal inference more appropriately to be applied. [ABSTRACT FROM AUTHOR]

The purpose of this study was to illustrate the use of propensity scores for creating comparison groups, partially controlling for pretreatment course selection bias, and estimating the treatment effects of selected courses on the development of moral reasoning in undergraduate students. Specifically, we used a sample of convenience for comparing differences in moral reasoning development scores among students enrolled in intergroup dialogue, service learning, psychology and philosophy courses with those of an introductory sociology course. Adopting a propensity score approach included reviewing the empirical literature for its guidance in substantiating the reasons for including pretreatment variables (i.e., pretreatment course-taking behaviors, race, sex, political identification, need for cognition, major, age, pretreatment moral reasoning scores) in our analysis, measuring these variables, and reducing them into a single composite propensity score for each student in our analytic sample. This score then served as the basis for creating a new comparison group and for allowing us to estimate unbiased (or less biased) course-related treatment effects on moral reasoning development. Implications for higher education researchers are discussed. [ABSTRACT FROM AUTHOR]

Background: It is not uncommon for medical specialists to predominantly care for patients with certain chronic conditions rather than primary care physicians (PCPs), yet the resource implications from such patterns of care are not well understood. Objective: To assess resource use of diabetes patients who predominantly visit a PCP versus a medical specialist. Design: Retrospective cohort study of diabetes patients aging into the traditional Medicare program. Patients were attributed to a PCP or medical specialist annually based on a preponderance of ambulatory care visits and categorized according to whether attribution changed year to year. Propensity score weighting was used to balance baseline demographic characteristics, diabetes complications, and underlying health conditions between patients attributed to PCPs and to medical specialists. Spending and utilization were measured up to 3 patient-years. Subjects: A total of 141,558 patient-years. Main Measures: Total visits, unique physicians, hospital admissions, emergency department visits, procedures, imaging, and tests. Key Results: Each year, roughly 70% of patients maintained attribution to a PCP and 15% to a medical specialist relative to the previous year. After propensity weighting, patients continuously attributed to a PCP versus medical specialist from 1 year to the next had lower average total payer payments ($10,326 [SD $57,386] versus $14,971 [SD $74,112], P<0.0001) and lower total patient out-of-pocket payments ($1,707 [SD $6,020] versus $2,443 [SD $7,984], P<0.0001). Rates of hospitalization, emergency department visits, procedures, imaging, and tests were lower among patients attributed to PCPs as well. Conclusions: Older adults with diabetes who receive more of their ambulatory care from a PCP instead of a medical specialist show evidence of lower resource use. [ABSTRACT FROM AUTHOR]

In medical product development, there has been a growing interest in utilizing real-world data which have become abundant owing to advances in biomedical science, information technology and engineering. High-quality real-world data may be utilized to generate real-world evidence for regulatory or healthcare decision-making. We discuss propensity score-based approaches for leveraging patients from a real-world data source to construct a control group for a non-randomized comparative study or to augment a single-arm or randomized prospective investigational clinical study. The proposed propensity score-based approaches leverage real-world patients that are similar to those prospectively enrolled into the investigational clinical study in terms of baseline characteristics. Either frequentist or Bayesian inference can then be applied for outcome data analysis, with the option of down-weighting information from the real-world data source. Examples based on pre-market regulatory review experience are provided to illustrate the implementation of the proposed approaches. [ABSTRACT FROM AUTHOR]

Objective: Previous studies have shown that high workload affects health negatively. However, studies are lacking among home care workers. The aim of this study is to examine the burden of perceived workload on health-related quality of life (HRQoL) among home care workers and to determine whether psychosocial factors modify such a relationship. Methods: A cross-sectional study was conducted in which 1162 (58% response rate) home care workers participated. The psychosocial factors were measured by QPSnordic. HRQoL was measured by EuroQol 5 dimensions, from which responses were translated into quality-adjusted life year scores (QALY). Propensity scores were used with absolute risk differences (RD). Stratified analysis was used to test the buffer hypothesis of the demand–control–support model. Results: Personnel with a high workload had a statistically significant 0.035 lower QALY than personnel with a normal workload. This difference was also statistically significant for the Visual Analogue Scale (RD 5.0) and the mobility (RD 0.033) and anxiety/depression scales (RD 0.20) dimensions of EQ-5D. For QALY, the effect of a high workload compared to a normal workload was higher, with low (RD 0.045, significant) compared with high (RD 0.015, non-significant) social support; while it was similar, and non-significant results, for low and high control. Conclusions: Our study shows that lowered work burden would be beneficial for home care personnel. Furthermore, our results suggest that interventions aimed at increasing social support could reduce work-related illness. [ABSTRACT FROM AUTHOR]

Family-based prevention programs increasingly are being disseminated and can be effective for an array of adolescent problem behaviors, including substance use initiation. Yet, we continue to have little understanding of how and why these programs work. Increased specificity in our understanding of what components drive program effects can facilitate refinement of programs, with potential for greater impact at a lower cost. Using attendance data, previously coded intervention components, and a previously developed propensity model to adjust for potential bias, this study evaluated content component-specific dosage effects of the Strengthening Families Program: for Parents and Youth Ages 10-14 on three substance use initiation outcomes by grade 12. Results indicated that greater dosages of program content related to (a) parental monitoring and behavior management strategies and (b) promoting positive family relationships had potent and robust effects on reduction of risk for initiating drunkenness and marijuana use and (c) self-regulation and stress management had potent and robust effects on reduction of risk for initiating cigarette and marijuana use. Results indicate potential critical components within SFP 10-14 and offer a path forward for continuing work in efforts to optimize this widely disseminated program. [ABSTRACT FROM AUTHOR]

Covariate-adjusted treatment effects are commonly estimated in non-randomized studies. It has been shown that measurement error in covariates can bias treatment effect estimates when not appropriately accounted for. So far, these delineations primarily assumed a true data generating model that included just one single covariate. It is, however, more plausible that the true model consists of more than one covariate. We evaluate when a further covariate may reduce bias due to measurement error in another covariate and in which cases it is not recommended to include a further covariate. We analytically derive the amount of bias related to the fallible covariate's reliability and systematically disentangle bias compensation and amplification due to an additional covariate. With a fallible covariate, it is not always beneficial to include an additional covariate for adjustment, as the additional covariate can extensively increase the bias. The mechanisms for an increased bias due to an additional covariate can be complex, even in a simple setting of just two covariates. A high reliability of the fallible covariate or a high correlation between the covariates cannot in general prevent from substantial bias. We show distorting effects of a fallible covariate in an empirical example and discuss adjustment for latent covariates as a possible solution. [ABSTRACT FROM AUTHOR]

Latent class analysis (LCA) has proven to be a useful tool for identifying qualitatively different population subgroups who may be at varying levels of risk for negative outcomes. Recent methodological work has improved techniques for linking latent class membership to distal outcomes; however, these techniques do not adjust for potential confounding variables that may provide alternative explanations for observed relations. Inverse propensity score weighting provides a way to account for many confounders simultaneously, thereby strengthening causal inference of the effects of predictors on outcomes. Although propensity score weighting has been adapted to LCA with covariates, there has been limited work adapting it to LCA with distal outcomes. The current study proposes a step-by-step approach for using inverse propensity score weighting together with the "Bolck, Croon, and Hagenaars" approach to LCA with distal outcomes (i.e., the BCH approach), in order to estimate the causal effects of reasons for alcohol use latent class membership during the year after high school (at age 19) on later problem alcohol use (at age 35) with data from the longitudinal sample in the Monitoring the Future study. A supplementary appendix provides evidence for the accuracy of the proposed approach via a small-scale simulation study, as well as sample programming code to conduct the step-by-step approach. [ABSTRACT FROM AUTHOR]

Guided by Vygotsky's social learning theory, this study reports a 24-week investigation on whether regular use of Istation, an integrated learning system used by approximately 4 million students in the United States, had an effect on the early literacy achievement of children in twelve kindergarten classrooms. A mixed-method, quasi-experimental design was constructed using propensity scores. Also investigated were the effects of the level of teacher literacy support on early literacy achievement and the interaction between Istation use and the level of teacher literacy support. A descriptive discriminant analysis was performed to determine the main effect of Istation. The level of teacher support and the interaction effect was then tested using a multivariate between-subject analysis. Results indicated that Istation did have a statistically significant effect on the early literacy skills of the kindergarten students studied and could explain 17.7% of the variance in group differences. Teacher literacy support and the interaction between teacher support and Istation were not significant. This study considers the relationship between technology and early literacy and concludes that Istation can serve as a more knowledgeable other as students develop some early literacy skills; however, teachers are still needed to provide complete literacy instruction for young students. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate with an ex post facto quasi-experimental design the impact of tactical police response on residential theft from vehicle crime in micro-time hot spots as well as whether spatial displacement occurs. Methods: The evaluation uses 5 years of data from one police agency that responded to micro-time hot spots as part of its normal crime reduction efforts. To determine the experimental comparison group, propensity scores were computed using logistic regression. Cases were matched using greedy 1-1 matching with a caliper of 0.10 of the standard deviation of the logit of the propensity score and resulted in 86 pairs. t Tests were used to examine the effect of the treatment and whether spatial displacement of crime occurred as a result. Results: Results showed that when police responded with about seven responses per day and for between 2 and 3 weeks, there was nearly a 20 % reduction in residential theft from vehicle crimes, and the micro-time hot spots with response did not last as long as those that did not. Results also showed no spatial displacement of crime as a result of the response. Conclusions: This evaluation is first to examine tactical police strategies for property crimes occurring at micro-places in micro-time. Findings support the hypothesis that micro-time hot spots are less severe and 'cool off' more quickly after a response. Thus, police should consider responding to property crime occurring in micro-places at a smaller temporal unit. Future research should further explore this unit of police response to corroborate these results. [ABSTRACT FROM AUTHOR]

Neuroimaging research is usually conducted in volunteers who meet a priori selection criteria. Selection/volunteer bias is assumed but cannot be assessed. During an ongoing population-based cohort study of 1982 older adults, we asked 1702 active participants about their interest in undergoing a research brain scan. Compared with those not interested, the 915 potentially interested individuals were significantly younger, more likely to be male, better educated, generally healthier, and more likely to be cognitively intact and dementia-free. In 48 of the interested individuals, we conducted a previously reported pilot structural magnetic resonance imaging (sMRI) study modelling mild cognitive impairment (MCI) vs. normal cognition, and Clinical Dementia Rating (CDR) = 0.5 vs. CDR = 0, as a function of sMRI atrophy ratings. We now compare these 48 individuals (1) with all interested participants, to assess selection bias; (2) with all who had been asked about their interest, to assess volunteer bias; and (3) with the entire study cohort, to assess attrition bias from those who had dropped out before the question was asked. Using these data in propensity score models, we generated weights which we applied to logistic regression models reanalyzing the data from the pilot sMRI study. These weighted models adjusted, in turn, for selection bias, interest/volunteer bias, and attrition bias. They show fewer regions of interest to be associated with MCI/ CDR than were in the original unweighted models. When study participants are drawn from a well-characterized population, they can be compared with non-participants, and the information used to correct study results for potential bias and thus provide more generalizable estimates. [ABSTRACT FROM AUTHOR]

This longitudinal study aims to explore the potential causal relationship between parental knowledge and youth risky behavior among a sample of rural, early adolescents (84 % White, 47 % male). Using inverse propensity weighting, the sample was adjusted by controlling for 33 potential confounding variables. Confounding variables include other aspects of the parent-child relationship, parental monitoring, demographic variables, and earlier levels of problem behavior. The effect of parental knowledge was significant for youth substance and polysubstance use initiation, alcohol and cigarette use, attitudes towards substance use, and delinquency. Our results suggest that parental knowledge may be causally related to substance use during middle school, as the relationship between knowledge and youth outcomes remained after controlling for 33 different confounding variables. The discussion focuses on understanding issues of causality in parenting and intervention implications. [ABSTRACT FROM AUTHOR]

Confounding is widely recognized in settings where all variables are fully observed, yet recognition of and statistical methods to address confounding in the context of latent class regression are slowly emerging. In this study we focus on confounding when regressing a distal outcome on latent class; extending standard confounding methods is not straightforward when the treatment of interest is a latent variable. We describe a recent 1-step method, as well as two 3-step methods (modal and pseudoclass assignment) that incorporate propensity score weighting. Using simulated data, we compare the performance of these three adjusted methods to an unadjusted 1-step and unadjusted 3-step method. We also present an applied example regarding adolescent substance use treatment that examines the effect of treatment service class on subsequent substance use problems. Our simulations indicated that the adjusted 1-step method and both adjusted 3-step methods significantly reduced bias arising from confounding relative to the unadjusted 1-step and 3-step approaches. However, the adjusted 1-step method performed better than the adjusted 3-step methods with regard to bias and 95 % CI coverage, particularly when class separation was poor. Our applied example also highlighted the importance of addressing confounding-both unadjusted methods indicated significant differences across treatment classes with respect to the outcome, yet these class differences were not significant when using any of the three adjusted methods. Potential confounding should be carefully considered when conducting latent class regression with a distal outcome; failure to do so may results in significantly biased effect estimates or incorrect inferences. [ABSTRACT FROM AUTHOR]

In this article, we investigated the effects of marriage and spousal characteristics on the use of preventive care. We accounted for the endogeneity of marriage by combining propensity score estimation techniques with marriage transitions observed in longitudinal data. Results indicated that marriage increases the probability of dental check-ups and physical examinations for both sexes and mammograms and Pap smears for women. Next, we examined whether spousal characteristics affect the use of preventive care. Spousal education, income, health conditions, and preferences for risk and health care all affected use of preventive care in expected directions. Taken together, we conclude that marriage increases the use of preventive care; however, the net marital effect masks a heterogeneity that results from the characteristics of the spouse an individual marries. [ABSTRACT FROM AUTHOR]

Prevention scientists use latent class analysis (LCA) with increasing frequency to characterize complex behavior patterns and profiles of risk. Often, the most important research questions in these studies involve establishing characteristics that predict membership in the latent classes, thus describing the composition of the subgroups and suggesting possible points of intervention. More recently, prevention scientists have begun to adopt modern methods for drawing causal inference from observational data because of the bias that can be introduced by confounders. This same issue of confounding exists in any analysis of observational data, including prediction of latent class membership. This study demonstrates a straightforward approach to causal inference in LCA that builds on propensity score methods. We demonstrate this approach by examining the causal effect of early sex on subsequent delinquency latent classes using data from 1,890 adolescents in 11th and 12th grade from wave I of the National Longitudinal Study of Adolescent Health. Prior to the statistical adjustment for potential confounders, early sex was significantly associated with delinquency latent class membership for both genders ( p = 0.02). However, the propensity score adjusted analysis indicated no evidence for a causal effect of early sex on delinquency class membership ( p = 0.76) for either gender. Sample R and SAS code is included in an Appendix in the ESM so that prevention scientists may adopt this approach to causal inference in LCA in their own work. [ABSTRACT FROM AUTHOR]

Community colleges have increased post-secondary educational access for disadvantaged youth, but it is unknown how community college degrees fit into the educational gradient of health status disparities. Using data from high school graduates in the National Longitudinal Study of Adolescent Health, we compared young adults ages 26-31 whose highest degrees were high school diplomas ( n = 5,584), sub-baccalaureate credentials (sub-BAs include community college certificates and associate's degrees) ( n = 2,415), and baccalaureate degrees (BAs) ( n = 3,303) on measures of hypertension, obesity, smoking, sleep problems, dyslipidemia, and depression. Comparisons used multivariate Poisson regression with robust standard errors after exact and nearest-neighbor Mahalanobis matching within propensity score calipers on 23 baseline factors measured in 1995. High school graduates and sub-BAs differed significantly on 3 of 23 baseline factors. After matching, sub-BAs were 16 % less likely to smoke daily than if they had only a high school diploma but did not differ in other health status measures. Sub-BAs and BAs differed significantly on 14 of 23 baseline factors. After matching, BAs were 60 % less likely to smoke daily, 14 % less likely to be obese, and 38 % less likely to have been diagnosed with depression. Sub-BA degrees are accessible to high school graduates irrespective of academic backgrounds and predict lower smoking prevalence. BAs are less accessible to high school graduates and predict lower chances of smoking, depression, and obesity. [ABSTRACT FROM AUTHOR]

Researchers investigated the impact that a first-year college experience course had on students' first-year grade point averages (GPAs) and retention rates. A sample of 109 first-year students enrolled in the course was compared to a sample of 326 students from the same university who had not taken the course. The goals of the experience course were to reduce attrition, increase grade point averages, and enhance academic skills. Without accounting for selection bias, those who took the course had similar retention rates and lower GPAs than those who did not take the course. After matching on propensity scores, the negative effects of the program on GPA were nullified and those in the program were more likely to enroll for a second year. Although the benefits from the course were weak, the positive impact of the program was more apparent after accounting for individual differences. [ABSTRACT FROM AUTHOR]

Prior research indicates that adolescent offenders transferred to adult court are more likely to recidivate than those retained in the juvenile system. The studies supporting this conclusion, however, are limited in addressing the issue of heterogeneity among transferred adolescents. This study estimates the effect of transfer on later crime using a sample of 654 serious juvenile offenders, 29% of whom were transferred. We use propensity score matching to reduce potential selection bias, and we partition the sample on legal characteristics to examine subgroup effects. We find an overall null effect of transfer on re-arrest, but evidence of differential effects of transfer for adolescents with different offending histories. These results suggest that evaluating the effects of transfer for all transferred adolescents together may lead to misguided policy conclusions. [ABSTRACT FROM AUTHOR]

This study uses longitudinal official record data on adult offenders in The Netherlands ( n = 4,246) to compare recidivism after community service to that after short-term imprisonment. To account for possible bias due to selection of offenders into these types of sanctions, we control for a large set of confounding variables using a combined method of ‘matching by variable’ and ‘propensity score matching’. Our findings demonstrate that offenders recidivate significantly less after having performed community service compared to after having been imprisoned. This finding holds for both the short- and long-term. Furthermore, using the Rosenbaum bounds method, we show that the results are robust for hidden bias. [ABSTRACT FROM AUTHOR]

Using data from the Netherlands-based Criminal Career and Life-course Study the effect of first-time imprisonment between age 18–38 on the conviction rates in the 3 years immediately following the year of the imprisonment was examined. Unadjusted comparisons of those imprisoned and those not imprisoned will be biased because imprisonment is not meted out randomly. Selection processes will tend to make the imprisoned group disproportionately crime prone compared to the not imprisoned group. In this study group-based trajectory modeling was combined with risk set matching to balance a variety of measurable indicators of criminal propensity. Findings indicate that first-time imprisonment is associated with an increase in criminal activity in the 3 years following release. The effect of imprisonment is similar across offence types. [ABSTRACT FROM AUTHOR]

I use diagrams to illustrate the sources of potential selection bias in observational studies of comparative effectiveness. I adapt these diagrams for three hypothetical scenarios that clarify the strengths and weaknesses of two prominent methods used to account for potential selection bias: propensity scores and instrumental variables. After reviewing the fundamentals of how to apply each method, including new developments that make implementation easier, I refer to some recent studies that illustrate how choice of method can affect estimates. I conclude by emphasizing that many studies with apparently rich sources of data are nevertheless unlikely to produce unbiased estimates and that conceptual modeling can help identify these problems in advance. [ABSTRACT FROM AUTHOR]

In response to community demands, case settlements, and state laws concerning racial profiling, police departments across the nation are collecting data on traffic stops. While the data collection is rapidly moving forward, there are few if any agreed upon methods for analyzing the data. Much of the attention has been on benchmarks for the race distribution of stops and searches. Little empirical work has advanced our understanding of the influence of race in the post-stop activities of police. The present study proposes a propensity score technique to determine the extent to which race bias affects citation rates, search rates, and the duration of the stop. Adjusting for confounding variables using the propensity score offers an alternative to multivariate regression that is more interpretable, less prone to errors in model assumptions, and ultimately easier to present to stakeholders in policing practices. An analysis of traffic stop data from the City of Oakland, California demonstrates the process, presentation, and interpretation of the results that the methodology produces. Ultimately, the study addresses the extent to which race plays a role in officers’ use of discretion. [ABSTRACT FROM AUTHOR]

We evaluated the costs and effectiveness of starting highly active antiretroviral therapy (HAART) at different points during the course of HIV infection, defined on the basis of CD4 T-lymphocytes counts. The study considered 3,250 HAART-naive patients of the Italian Cohort Naive Antiretrovirals (ICONA), enrolled and followed between 1997 and 2002. In correspondence to the thresholds of 500, 350, and 200 CD4 cells/mm3, we selected immediate and deferred groups accounting for lead-time bias. The effects of immediate vs. deferred treatment on AIDS-free survival and direct health costs were estimated stratifying on the propensity score of immediate HAART initiation. The incremental cost-effectiveness ratio (ICER) and the cost-effectiveness acceptability curve were also obtained. Although immediate HAART initiation did not affect incidence AIDS and death at high CD4 levels, starting HAART with 200–349 CD4 cells/mm3 rather than deferring it below 200 CD4 cells/mm3, proved to be cost-effective. [ABSTRACT FROM AUTHOR]

The study examines the effect of different types of antipsychotic treatment on the health related quality of life (HRQL) of people with schizophrenia under naturalistic outpatient treatment conditions. In a prospective study design, 307 schizophrenic patients were followed over a period of 2.5 years. HRQL, clinical characteristics, and type of antipsychotic medication were assessed five times every 6 months. HRQL was assessed by the SF-36. Random effect regression models were computed for the SF-36 mental (MCS) and physical (PCS) component scores. Propensity scores were included in the regression models to reduce a possible sample selection bias. Monotherapeutic treatment with new atypical neuroleptic drugs had a more positive effect on the mental health related quality of life (MCS) in comparison to treatment with polypharmacological treatment but not with oral conventional antipsychotics. Monopharmaceutical treatment with depot-antipsychotic drugs had a more positive effect on the physical health related quality of life (PCS) in comparison to polypharmacological treatment. Study results indicate that atypical antipsychotic drugs are not superior to conventional antipsychotics with regard to the effect on QOL. However, monopharmaceutical treatment can be assumed to be more effective in improving mental and physical related QOL than polypharmaceutical treatment. [ABSTRACT FROM AUTHOR]

The quality and outcomes of care provided by primary care physicians and specialists are increasingly important issues in health policy research. Estimating the effect of specialty care on patient outcomes however is complicated by the observational nature of the studies. Patients treated by specialists are often different in terms of observed and unobserved characteristics that can bias estimates of specialty effects. We illustrate and compare two different analytic approaches, propensity scores and instrumental variables, to infer the causal effect of cardiology care in the ambulatory setting on 18-month mortality among 5467 elderly patients who survived at least 3 months after being hospitalized for a myocardial infarction in New York state during 1994 and 1995. Using both approaches we found reductions in 18-month mortality associated with ambulatory cardiology care. However, reasonable deviations from the assumptions underlying each method led to estimated differences in mortality ranging from a 6% absolute reduction in mortality to a 2% increase among patients who received cardiology care. Choosing an analytic strategy depends on both available data and the policy question of interest. We believe that comparative analyses such as this one, with extensive assessment of the assumptions underlying each method, can provide valuable insights into important policy questions reliant on the analysis of observational data. [ABSTRACT FROM AUTHOR]

Analysis of a randomized trial is problematic when there is noncompliance with the treatment assignment. An intent-to-treat (ITT) analysis estimates the effect of randomization rather than the effect for those who actually receive the treatment. An alternative to the ITT is the “as treated” analysis, in which subjects are classified by the treatment actually received. However, the “as treated” analysis is also flawed since confounders are likely to be associated with switching treatment. We propose the use of an instrumental variable estimate (using the randomization as the instrument) in combination with propensity score adjustment. In addition, we consider the assumptions implicit in the instrumental variable methodology. These methods are illustrated with data from the Multimodal Treatment of ADHD (MTA) Study of treatment efficacy for children with attention deficit hyperactivity disorder. We show how the addition of the propensity score adjustment to the instrumental variable analysis uncovers some surprising results concerning the children who were assigned to behavioral therapy only but switched to medication. [ABSTRACT FROM AUTHOR]