The sensitivity of linear regression coefficients' confidence limits to the omission of a confounder

Archived Abstract of Former PSC Researcher

Hosman, Carrie A., Ben Hansen, and Paul W. Holland. 2010. "The sensitivity of linear regression coefficients' confidence limits to the omission of a confounder." Annals of Applied Statistics, 4(2): 849-870.

Omitted variable bias can affect treatment effect estimates obtained from observational data due to the lack of random assignment to treatment groups. Sensitivity analyses adjust these estimates to quantify the impact of potential omitted variables. This paper presents methods of sensitivity analysis to adjust interval estimates of treatment effect both the point estimate and standard error obtained using multiple linear regression. Central to our approach is what we term benchmarking, the use of data to establish reference points for speculation about omitted confounders. The method adapts to treatment effects that may differ by subgroup, to scenarios involving omission of multiple variables, and to combinations of covariance adjustment with propensity score stratification. We illustrate it using data from an influential study of health outcomes of patients admitted to critical care.

DOI:10.1214/09-AOAS315 (Full Text)

Country of focus: United States of America.

Browse | Search : All Pubs | Next

PSC In The News

RSS Feed icon

After a baby, 28% of new parents leave full-time STEM work, reports Erin Cech

Owen-Smith considers research team size and support of diversity of the research enterprise

Thompson says it is easier for police to seize assets from a black person than a white person

More News

Highlights

Meghan O'Neil's work on "Housing Policy, Race, Inequality, and Disparate Impact" published in Phlyon's Du Bois King Anniversary issue

Morenoff elected Secretary of APC Association of Population Centers for 2019

More Highlights


Connect with PSC follow PSC on Twitter Like PSC on Facebook