The method of modifying observations to account for external factors that may distort or skew associations in observations.

Adjusted Measure of Association

In the following case-control study of HIV seroconversion (Li 1997), we are looking at the effectiveness of AZT in preventing HIV seroconversion after a needlestick in health care workers. 0416_1HIV.JPG

The context is that needlesticks among health care workers from patients with HIV disease are unfortunately all too common. The question is whether taking the drug called AZT right after a needlestick can prevent the healthcare worker from becoming infected with HIV. So, the exposure in question is the use of AZT and the outcome is the occurrence of HIV. Cases were health care workers who had acquired HIV after a needlestick and controls were health care workers who did not acquire HIV after a needlestick. Well, this is a big difference in magnitude but note how few cases there are in the minor needlestick severity group. What would you want to do at this point?

Summary Estimate

To determine the adjusted measure of association for the effect modifier, we have to form a summary estimate of the two strata.

To do this, we will form a weighted average of the stratum-specific estimates.

In other words, we will assign weights to the various strata and then take an average of the strata using these weights. A simple mean is an example of a weighted average where all the weights are 1.

Methods for Calculating Summary Adjusted Estimators

In our example, we know that the weighted average is going to be somewhere between 0.0 and 0.35, but where exactly is it going to be? Two methods for calculating summary adjusted estimators:

Interpretation of the Adjusted Estimate

Is confounding present or is there a third variable?

In the example of AZT use:

1 - Compare adjusted estimate to crude estimate 2 - If adjusted measure differs meaningfully from crude estimate, then confounding is present What does differs meaningfully mean?


Li, R. W., & Wong, J. B. (1997). Postexposure treatment of HIV. N Engl J Med, 337(7), 499-500; author reply 501.

Jeff Martin, MD

See Also