Pseudorandomization using an instrumental variable: a strong tool to break through selection bias

2012 ◽  
Vol 76 (5) ◽  
pp. 1079-1080 ◽  
Author(s):  
Tsuyoshi Hamada ◽  
Takeshi Tsujino ◽  
Hiroyuki Isayama ◽  
Kazuhiko Koike
Keyword(s):  
Selection Bias ◽  
Instrumental Variable

scholarly journals Selection bias in instrumental variable analyses

2017 ◽  
Author(s):  
Rachael A. Hughes ◽  
Neil M. Davies ◽  
George Davey Smith ◽  
Kate Tilling
Keyword(s):  
Confidence Interval ◽  
Selection Bias ◽  
Instrumental Variable ◽  
Causal Effect ◽  
Major Effect ◽  
Directed Acyclic Graphs ◽  
Factors Affecting ◽  
Exposure Effect ◽  
Using Data ◽  
The Uk

AbstractParticipants in epidemiological and genetic studies are rarely true random samples of the populations they are intended to represent, and both known and unknown factors can influence participation in a study (known as selection into a study). The circumstances in which selection causes bias in an instrumental variable (IV) analysis are not widely understood by practitioners of IV analyses. We use directed acyclic graphs (DAGs) to depict assumptions about the selection mechanism (factors affecting selection) and show how DAGs can be used to determine when a two-stage least squares (2SLS) IV analysis is biased by different selection mechanisms. Via simulations, we show that selection can result in a biased IV estimate with substantial confidence interval undercoverage, and the level of bias can differ between instrument strengths, a linear and nonlinear exposure-instrument association, and a causal and noncausal exposure effect. We present an application from the UK Biobank study, which is known to be a selected sample of the general population. Of interest was the causal effect of education on the decision to smoke. The 2SLS exposure estimates were very different between the IV analysis ignoring selection and the IV analysis which adjusted for selection (e.g., 1.8 [95% confidence interval −1.5, 5.0] and −4.5 [−6.6, −2.4], respectively). We conclude that selection bias can have a major effect on an IV analysis and that statistical methods for estimating causal effects using data from nonrandom samples are needed.

scholarly journals Selection Bias When Using Instrumental Variable Methods to Compare Two Treatments But More Than Two Treatments Are Available

2016 ◽  
Vol 12 (1) ◽  
pp. 219-232 ◽  
Author(s):  
Ashkan Ertefaie ◽  
Dylan Small ◽  
James Flory ◽  
Sean Hennessy
Keyword(s):  
Selection Bias ◽  
Treatment Effect ◽  
Instrumental Variable ◽  
Treatment Effects ◽  
Health Improvement ◽  
Effect Estimate ◽  
Diabetic Patients ◽  
Data Set ◽  
The Health Improvement Network ◽  
Theoretical Evidence

Abstract Instrumental variable (IV) methods are widely used to adjust for the bias in estimating treatment effects caused by unmeasured confounders in observational studies. It is common that a comparison between two treatments is focused on and that only subjects receiving one of these two treatments are considered in the analysis even though more than two treatments are available. In this paper, we provide empirical and theoretical evidence that the IV methods may result in biased treatment effects if applied on a data set in which subjects are preselected based on their received treatments. We frame this as a selection bias problem and propose a procedure that identifies the treatment effect of interest as a function of a vector of sensitivity parameters. We also list assumptions under which analyzing the preselected data does not lead to a biased treatment effect estimate. The performance of the proposed method is examined using simulation studies. We applied our method on The Health Improvement Network (THIN) database to estimate the comparative effect of metformin and sulfonylureas on weight gain among diabetic patients.

scholarly journals Methodological Challenges When Studying Distance to Care as an Exposure in Health Research

2019 ◽  
Vol 188 (9) ◽  
pp. 1674-1681 ◽  
Author(s):  
Ellen C Caniglia ◽  
Rebecca Zash ◽  
Sonja A Swanson ◽  
Kathleen E Wirth ◽  
Modiegi Diseko ◽  
...  
Keyword(s):  
Measurement Error ◽  
Causal Inference ◽  
Selection Bias ◽  
Birth Outcomes ◽  
Health Research ◽  
Instrumental Variable ◽  
Sensitivity Analyses ◽  
Unmeasured Confounding ◽  
Instrument Selection ◽  
Distance To Care

Abstract Distance to care is a common exposure and proposed instrumental variable in health research, but it is vulnerable to violations of fundamental identifiability conditions for causal inference. We used data collected from the Botswana Birth Outcomes Surveillance study between 2014 and 2016 to outline 4 challenges and potential biases when using distance to care as an exposure and as a proposed instrument: selection bias, unmeasured confounding, lack of sufficiently well-defined interventions, and measurement error. We describe how these issues can arise, and we propose sensitivity analyses for estimating the degree of bias.

scholarly journals Returns to Investment in University Education - Economics Career at Continental University

2021 ◽  
Vol 12 (1) ◽  
pp. 166
Author(s):  
Gustavo Ilich Loayza Acosta ◽  
Naisha Alyssa Bernardo Reyes ◽  
Margarita Elluz Calle Arancibia
Keyword(s):  
Labor Market ◽  
Selection Bias ◽  
Instrumental Variable ◽  
Geographic Location ◽  
Direct Costs ◽  
University Education ◽  
Education Economics ◽  
Cross Sectional ◽  
Returns To Investment ◽  
Years Of Schooling

The present work analyzes the returns to the years of superior schooling of graduates of Economics Career at Continental University within the labor market of the region Junín of the period 2019. For this purpose, the returns to education are investigated under the normal assumptions of Mincer's equation, and later the incorporation of the instrumental variable: school of origin is proposed, in order to correct the problem of endogeneity. Finally, to correct the problem of selection bias, Heckman's technique is used: two-stage regression. This consists of first analyzing the probability of accessing the labor market in the Junín region in terms of variables such as: geographic location, school of origin, age, direct costs. Subsequently, analyzing the return to years of schooling. Likewise, it is important to specify that in the modeling of the probability a second regression is estimated incorporating the variable Academic Grade in order to be able to study the Sheepskin Effect. The results obtained showed that the return to years of schooling is 0.8%, which is not significant and is not corrected for Heckman's selection bias. We also have that the R2 is 10.11% which is very low for this type of cross-sectional data. This result is explained by the degree of rootedness of the graduates in staying in the Huancayo province and the low migration to other labor markets. In addition, this means that they do not have better working conditions that can be transformed into higher income.

Sign in / Sign up

Export Citation Format

Share Document