Table 1.

Advantages and disadvantages of common strategies used to address confounding

MethodOverviewAdvantagesDisadvantages
Design phase
 RestrictionSetting criteria for study inclusionEasy to implementOnly removes or reduces confounding by the inclusion criteria
Reduces sample size
Cannot generalize findings to those excluded
 MatchingCreates matched sets of patients who have similar values of one or more confoundersIntuitiveDifficult to match on multiple confounders
Only removes or reduces confounding by the matching factors
Unmatched patients are excluded, reducing sample size, effect estimate precision, and generalizability
 Active comparatorComparing the treatment of interest to an active comparator rather than treatment nonuseMitigates confounding by indication
Clinically relevant head-to-head comparison of two or more treatments
Cannot be used when there is only one treatment option
Analysis phase
 Multivariable adjustmentPotential confounders are included as covariates in regression modelsEasy to implement in standard statistical software packagesOnly controls for measured confounders
The total number of confounders that can be included in regression models is contingent on the number of outcome events
 Propensity score matchingEach patient who received the treatment of interest is matched to one or more patients who received the comparator treatment with an equivalent propensity score, generating a matched cohort of treated and comparator patients that have similar baseline characteristicsPreferred in studies where there are relatively few outcome events compared with the number of potential confounders
Ability to check if covariate balance between the treated and comparator groups was achieved in the matched cohort
Only controls for measured confounders
Unmatched patients are excluded, reducing sample size, effect estimate precision, and generalizability
 Propensity score weightingThe propensity score is used to generate weights that are applied to the original study cohort to create a pseudo-population of treated and comparator patients that have similar baseline characteristicsPreferred in studies where there are relatively few outcome events compared with the number of potential confounders
Ability to check if covariate balance between the treated and comparator groups was achieved in the weighed cohort
Only controls for measured confounders
Less intuitive than propensity score matching
 G methodsComplex analytic methods that handle time-varying confounding in the setting of time-varying exposuresAppropriately handle time-varying confoundingOnly controls for measured confounders
Complex methods requiring advanced statistical expertise