Confounding

The issue of confounding is of central importance in any analytic epidemiological study, especially in the case of observational studies. Confounding results from non-random differences between the groups of animals being compared in relation to a second, 'confounding' exposure which is independently associated with both the exposure of interest (although not a consequence of this) and the outcome of interest (although not an effect of this). This results in the effect of the exposure of interest is 'mixed up' with the effect of the confounding exposure, and therefore an incorrect estimate of the true association. As such, confounding is viewed by many authors as a form of bias - however, unlike forms of selection and information bias, it is a natural feature of the data (in the case of an observational study), and techniques are available to account for it during analysis.

An example of confounding

As the concept of confounding can be difficult to understand, an example is given here. Consider a cross sectional study investigating the association between the use of (moderately effective) anthelmintics and infection with Echinococcus granulosus tapeworm in a sheep farming area where the parasite is known to exist. Initial results show that animals which were not dosed recently with anthelmintics were more likely to be infected with the tapeworm; however, further investigation shows that these dogs were also more likely to have free access to roam on the surrounding fields. In this example, free roaming is confounding the association between anthelmintic use and infection: dogs which are allowed to roam freely are both more likely to not have been dosed with anthelmintics (because their owners have more trouble restraining them for dosing) and are more likely to acquire infection (from infected dead sheep they find whilst roaming). Roaming freely is not a consequence of failure of having been dosed with anthelmintics (i.e. it does not lie on the causal pathway between anthelmintic use and infection), nor is it a consequence of having become infected with the tapeworm. If the effect of roaming was removed, the expected association between infection and recent use of anthelmintics would be expected to be reduced (although it would still be expected to be present to some degree). A common example of confounding used in human epidemiology is the association between alcohol consumption and lung cancer, which is confounded by cigarette smoking (i.e. people who drink more are more likely to also smoke cigarettes, which are also known to be associated with development of lung cancer).

Identifying counfounding

The first step in identifying confounding should be based on logical consideration of the suspected association:

• is there a plausible confounding effect?
• is the suspected confounding variable a direct consequence of the exposure of interest? For example, in the example given above, access to dead sheep could not be considered as a confounding variable for the association between roaming and infection, as it is the main presumed mechanism of action of roaming. That is, dogs which roam more have greater access to dead sheep, and dogs which are not allowed to roam would be expected to have minimal access to dead sheep.
• is the suspected confounding variable a direct consequence of the outcome of interest?

Dealing with confounding

Although the presence of confounding is a characteristic of the data, it needs to be accounted for in order to develop conclusions regarding true risk factors for the outcome of interest.

number of techniques are available to deal with confounding in an analytic study. These can be broadly classified as