Magnitude and direction of missing confounders had different consequences on treatment effect estimation in propensity score analysis
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Magnitude and direction of missing confounders had different consequences on treatment effect estimation in propensity score analysis. / Nguyen, Tri Long; Collins, Gary S.; Spence, Jessica; Fontaine, Charles; Daurès, Jean Pierre; Devereaux, Philip J.; Landais, Paul; Le Manach, Yannick.
I: Journal of Clinical Epidemiology, Bind 87, 2017, s. 87-97.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Magnitude and direction of missing confounders had different consequences on treatment effect estimation in propensity score analysis
AU - Nguyen, Tri Long
AU - Collins, Gary S.
AU - Spence, Jessica
AU - Fontaine, Charles
AU - Daurès, Jean Pierre
AU - Devereaux, Philip J.
AU - Landais, Paul
AU - Le Manach, Yannick
PY - 2017
Y1 - 2017
N2 - Objective Propensity score (PS) analysis allows an unbiased estimate of treatment effects but assumes that all confounders are measured. We assessed the impact of omitting confounders from a PS analysis on clinical decision making. Study Design and Setting We conducted Monte Carlo simulations on hypothetical observational studies based on virtual populations and on the population from a large randomized trial (CRASH-2). In both series of simulations, PS analysis was conducted with all confounders and with omitted confounders, which were defined to have different strengths of association with the outcome and treatment exposure. After inverse probability of treatment weighting, we calculated the absolute risk differences and numbers needed to treat (NNT). Results In both series of simulations, omitting a confounder that was moderately associated with the outcome and exposure led to negligible bias on the NNT scale. The bias induced by omitting strongly positive confounding variables remained less than 15 patients to treat. Major bias and reversed effects were found only when omitting highly prevalent, strongly negative confounders that were similarly associated with the outcome and exposure with odds ratios greater than 4.00 (or <0.25). This omission was accompanied by a substantial decrease in analysis power. Conclusion The omission of strongly negative confounding variables from a PS analysis can lead to incorrect clinical decision making. However, omitting these variables also decreases the analysis power, which may prevent the reporting of significant but misleading effects.
AB - Objective Propensity score (PS) analysis allows an unbiased estimate of treatment effects but assumes that all confounders are measured. We assessed the impact of omitting confounders from a PS analysis on clinical decision making. Study Design and Setting We conducted Monte Carlo simulations on hypothetical observational studies based on virtual populations and on the population from a large randomized trial (CRASH-2). In both series of simulations, PS analysis was conducted with all confounders and with omitted confounders, which were defined to have different strengths of association with the outcome and treatment exposure. After inverse probability of treatment weighting, we calculated the absolute risk differences and numbers needed to treat (NNT). Results In both series of simulations, omitting a confounder that was moderately associated with the outcome and exposure led to negligible bias on the NNT scale. The bias induced by omitting strongly positive confounding variables remained less than 15 patients to treat. Major bias and reversed effects were found only when omitting highly prevalent, strongly negative confounders that were similarly associated with the outcome and exposure with odds ratios greater than 4.00 (or <0.25). This omission was accompanied by a substantial decrease in analysis power. Conclusion The omission of strongly negative confounding variables from a PS analysis can lead to incorrect clinical decision making. However, omitting these variables also decreases the analysis power, which may prevent the reporting of significant but misleading effects.
KW - Causal inference
KW - Confounding bias
KW - Observational study
KW - Propensity score
KW - Simulation
KW - Unmeasured confounders
U2 - 10.1016/j.jclinepi.2017.04.001
DO - 10.1016/j.jclinepi.2017.04.001
M3 - Journal article
C2 - 28412467
AN - SCOPUS:85019103930
VL - 87
SP - 87
EP - 97
JO - Journal of Clinical Epidemiology
JF - Journal of Clinical Epidemiology
SN - 0895-4356
ER -
ID: 218396636