scholarly journals PNL26 EXTENDING MATCHING ESTIMATORS OF CAUSAL EFFECTS TO CONSIDER UNOBSERVED VARIABLE BIAS: AN APPLICATION OF SENSITIVITY ANALYSIS

2006 ◽  
Vol 9 (3) ◽  
pp. A87
Author(s):  
JW Devine ◽  
RS Hadsall ◽  
JF Farley
Keyword(s):  
Sensitivity Analysis ◽  
Causal Effects ◽  
Matching Estimators ◽  
Variable Bias ◽  
Unobserved Variable

scholarly journals The Impossible Mediation Test: A Method for Dealing with Plausibly Confounded Mediation

2017 ◽  
Author(s):  
David Scott Yeager ◽  
Jon Krosnick
Keyword(s):  
Sensitivity Analysis ◽  
Correlational Analysis ◽  
Causal Process ◽  
Psychology Research ◽  
Strong Basis ◽  
Spurious Association ◽  
Omitted Variable Bias ◽  
Variable Bias ◽  
As If

In much psychology research, mediators are measured, not manipulated. Therefore, the paths from mediators to outcomes—the so-called b paths—can be confounded by omitted variable bias, as in any other correlational analysis. The present research builds on the logic of falsification tests in econometrics and sensitivity analysis in statistics to propose the impossible mediation test, which can quantify the amount of confounded mediation. Researchers can add to an experiment a condition in which the dependent variable is measured first, then the manipulation is implemented, and finally, the posited mediator is measured. This allows for assessment of the spurious association between the dependent variable and the mediator, and statistics can be estimated as if the dependent variable was measured after the manipulation was implemented, to assess whether the spurious association is sufficiently strong to yield the false appearance of mediation. This estimate of “impossible” mediation can be compared to the results obtained from data where the dependent variable is actually measured in the conventional order after the mediator, to determine whether evidence of mediation is stronger in the latter case than the former. Evidence of mediation that survives the impossible mediation test constitutes a strong basis for a claim about mediation of a causal process. The paper illustrates this procedure with an empirical example.

scholarly journals A Selection Bias Approach to Sensitivity Analysis for Causal Effects

2014 ◽  
Vol 22 (2) ◽  
pp. 169-182 ◽  
Author(s):  
Matthew Blackwell
Keyword(s):  
Sensitivity Analysis ◽  
Causal Inference ◽  
Political Science ◽  
Selection Bias ◽  
Large Volume ◽  
Quantitative Approach ◽  
Causal Effects ◽  
Omitted Variables ◽  
Fundamental Fact ◽  
Unmeasured Confounders

The estimation of causal effects has a revered place in all fields of empirical political science, but a large volume of methodological and applied work ignores a fundamental fact: most people are skeptical of estimated causal effects. In particular, researchers are often worried about the assumption of no omitted variables or no unmeasured confounders. This article combines two approaches to sensitivity analysis to provide researchers with a tool to investigate how specific violations of no omitted variables alter their estimates. This approach can help researchers determine which narratives imply weaker results and which actually strengthen their claims. This gives researchers and critics a reasoned and quantitative approach to assessing the plausibility of causal effects. To demonstrate the approach, I present applications to three causal inference estimation strategies: regression, matching, and weighting.

Matching Estimators of Causal Effects

2014 ◽  
pp. 140-187
Author(s):  
Stephen L. Morgan ◽  
Christopher Winship
Keyword(s):  
Causal Effects ◽  
Matching Estimators

scholarly journals Identification of average effects under magnitude and sign restrictions on confounding

10.3982/qe689 ◽  
2019 ◽  
Vol 10 (4) ◽  
pp. 1619-1657 ◽  
Author(s):  
Karim Chalak
Keyword(s):  
Sensitivity Analysis ◽  
Direct Effect ◽  
Instrumental Variables ◽  
Average Treatment Effect ◽  
Structural Systems ◽  
Omitted Variables ◽  
Average Effect ◽  
Omitted Variable Bias ◽  
Marginal Effects ◽  
Variable Bias

This paper studies measuring various average effects of X on Y in general structural systems with unobserved confounders U, a potential instrument Z, and a proxy W for U. We do not require X or Z to be exogenous given the covariates or W to be a perfect one‐to‐one mapping of U. We study the identification of coefficients in linear structures as well as covariate‐conditioned average nonparametric discrete and marginal effects (e.g., average treatment effect on the treated), and local and marginal treatment effects. First, we characterize the bias, due to the omitted variables U, of (nonparametric) regression and instrumental variables estimands, thereby generalizing the classic linear regression omitted variable bias formula. We then study the identification of the average effects of X on Y when U may statistically depend on X and Z. These average effects are point identified if the average direct effect of U on Y is zero, in which case exogeneity holds, or if W is a perfect proxy, in which case the ratio (contrast) of the average direct effect of U on Y to the average effect of U on W is also identified. More generally, restricting how the average direct effect of U on Y compares in magnitude and/or sign to the average effect of U on W can partially identify the average effects of X on Y. These restrictions on confounding are weaker than requiring benchmark assumptions, such as exogeneity or a perfect proxy, and enable a sensitivity analysis. After discussing estimation and inference, we apply this framework to study earnings equations.

scholarly journals Spillover Effects in the Presence of Unobserved Networks

2020 ◽  
pp. 1-30
Author(s):  
Naoki Egami
Keyword(s):  
Sensitivity Analysis ◽  
Spillover Effect ◽  
Spillover Effects ◽  
Unbiased Estimation ◽  
Potential Influence ◽  
Face To Face ◽  
Multiple Networks ◽  
Omitted Variable Bias ◽  
Experimental Subjects ◽  
Variable Bias

Abstract When experimental subjects can interact with each other, the outcome of one individual may be affected by the treatment status of others. In many social science experiments, such spillover effects may occur through multiple networks, for example, through both online and offline face-to-face networks in a Twitter experiment. Thus, to understand how people use different networks, it is essential to estimate the spillover effect in each specific network separately. However, the unbiased estimation of these network-specific spillover effects requires an often-violated assumption that researchers observe all relevant networks. We show that, unlike conventional omitted variable bias, bias due to unobserved networks remains even when treatment assignment is randomized and when unobserved networks and a network of interest are independently generated. We then develop parametric and nonparametric sensitivity analysis methods, with which researchers can assess the potential influence of unobserved networks on causal findings. We illustrate the proposed methods with a simulation study based on a real-world Twitter network and an empirical application based on a network field experiment in China.

Sign in / Sign up

Export Citation Format

Share Document