Contents
What do you need to know about the propensity score?
Description Propensity score analysis (PSA) arose as a way to achieve exchangeability between exposed and unexposed groups in observational studies without relying on traditional model building. Exchangeability is critical to our causal inference. In experimental studies (e.g. randomized control trials), the probability of being exposed is 0.5.
How is propensity score matching used in observational studies?
2 To explain further, IF propensity score matching was used in a randomized experiment comparing two groups, then the propensity score for each participant in the study would be 0.50. This is because each participant would be randomly assigned to either the treatment or the control group with a 50% probability.
How many covariates should be included in a propensity score?
A commonly cited concern is that such models might be overfitted when the number of covariates is large compared with the number of patients or outcome events. Although a rule of thumb is to have at least 10 events per covariate included in the model (2), more recent opinions favor relaxing this rule (3).
How are Propensity scores used in social epidemiology?
Propensity score matching for social epidemiology in Methods in Social Epidemiology (eds. JM Oakes and JS Kaufman), Jossey-Bass, San Francisco, CA. Simple and clear introduction to PSA with worked example from social epidemiology.
Which is the nearest neighbor to a PS score?
Most common is the nearest neighbor within calipers. The nearest neighbor would be the unexposed subject that has a PS nearest to the PS for our exposed subject. We may not be able to find an exact match, so we say that we will accept a PS score within certain caliper bounds.
What are the limitations of the PSA score?
The most serious limitation is that PSA only controls for measured covariates. Group overlap must be substantial (to enable appropriate matching). Matching on observed covariates may open backdoor paths in unobserved covariates and exacerbate hidden bias.
How are Propensity scores used to reduce selection bias?
Propensity matching with large samples has been shown to reduce selection bias that may be present in evaluation designs (Rubin, 1979). It has been noted that with small samples there may be insufficient power to produce meaningful results (Quigley, 2003).
Which is the second step of propensity score matching?
Recall, that the second step of propensity score matching, is the “matching” phase in which an analyst uses an algorithm to identify pairs of one observed and one unobserved individual, in order to subsequently compare each pair’s outcomes while holding their propensity scores constant.
When to use propensity score for causal inference?
As is common with many causal inference techniques, an analyst must be cautious when estimating a causal effect using propensity score matching.
Is there a way to match a PS score?
Several methods for matching exist. Most common is the nearest neighbor within calipers. The nearest neighbor would be the unexposed subject that has a PS nearest to the PS for our exposed subject. We may not be able to find an exact match, so we say that we will accept a PS score within certain caliper bounds.