Cochran-Mantel-Haenszel Method

Question 1

Cochran-Mantel-Haenszel Method

Answer 1

technique used to estimate the association between risk factors and outcome; while accounting for confounding

data are organized into stratum and associations are estimated in each stratum and combined

is used with dichotmous outcome variables and dichotomous risk factors.

produces a single number summary of association that accounts for the different associations found in each stratum

produces “adjusted” estimates such as adjusted RR and adusted OR estimates

Question 2

Dichotomous viariables

Answer 2

are nominal variables which have only two categories or levels.

For example, if we were looking at gender, we would most probably categorize somebody as either “male” or “female”. This is an example of a dichotomous variable (and also a nominal variable).

Another example might be if we asked a person if they owned a mobile phone. Here, we may categorise mobile phone ownership as either “Yes” or “No”.

Question 3

Counfounding

Answer 3

can be continouous, partial, or complete and must also be categorized into stratum

is the distortion of the effect of a risk factor on an outcome

present when the r/s b/w the risk factor or independent variable and the outcome is modified by a 3rd variable

is r/t the risk factor or independent variable (X) and also to the outcome (Y)

exist when meaningfully different interpretations of the r/s b/w X and Y result when an extraneous variable (aka covariate) is ignored or included in the analysis

assessment requires comparing a crude(unadjusted) estimate of association and an adjusted estimate (one that takes the extraneous variable into account)

Question 4

Complete confounding

Answer 4

Assessment of the r/s b/w the risk factors independent variable and the outcome is inseparable from the r/s b/w the confounder and the outcome

the effects of the risk factor and the confounder on the outome cannot be distinguished from one another

most situations involve partial confounding b/w the risk factor and the confounder

in epidemiological and observational studies, this often occurs when there is an imbalance in the risk factor, with respect to the confounder