Summary Estimators: Mantel-Haenszel Method

Lead Author(s): Jeff Martin, MD

This is one method for calculating summary adjusted estimators when making adjustments in the measure of association.

Summary Estimators: Mantel-Haenszel Method

Given the Woolf's Method problem with cells of zero, the Mantel-Haenszel method is more widely used.

Data for Mantel-Haenszel's Method


Step 1 - Weight Using the Native Odds Ratio Scale

Here, we are working with the plain old native odds ratio scale.


In other words, the weight is related to the variance, but a special form of the variance, that is, when there is no association.

Example: Summary Adjusted Effect Using Mantel-Haenszel Method

In the example of AZT use we need to determine the summary adjusted effect, using the Mantel-Haenszel Method. We obtain an summary estimate for the association between AZT use and HIV seroconversion after adjusting for severity of needlestick.


The summary adjusted estimate is 0.3. The crude estimate was 0.6 and not even statistically significant.

Variance Associated with No Effect

Now, you might wonder why we using a variance associated with an odds ratio of no effect if indeed there is an effect in the stratum. Note: another intuitive approach to understanding the MH formula is to note that ad/n is a pretty good approximation of the numerator ad in an odds ratio and bc/N is a pretty good approximation of the denominator of the odds ratio.

Pros and Cons of Mantel-Haenszel's Methods

The Mantel-Haenszel technique, although not as straightforward conceptually as the Woolf technique, which directly uses stratum-specific variances, has many advantages: