A set of training materials for professionals working in intervention epidemiology, public health microbiology and infection control and hospital hygiene.
Need help with your investigation or report writing? Ask the Expert. Free advice from the professional community.
You can't make decissions on this page's approval status because you have not the owner or an admin on this page's Group.
Stratification is one of the pillars of epidemiological analysis. It allows investigators to familiarise with the distribution of data according to the variables of interest, to estimate the effect of a variable adjusted by the effect of covariates or confounding factors and to study interaction or effect modification between two factors.
However, stratification is limited in the number of variables to be examined simultaneously because the number of subjects in each stratum may drop to 0 or 1 thus even statistical methods for dealing with sparse data may not be applicable.
Regression analysis overcomes this limitation by estimating regression models to approximate the function describing the relationship between dependent and independent variables.
The different regression analysis techniques are very efficient estimating the independent effect of several covariates and for the study of interactions. On the other hand, modelling data encompasses underlying assumptions. Researchers should be familiar with regression techniques and the interpretation of results to assure that underlying model assumptions are realistic. Researchers using regression analysis may loss track of patterns of data distribution and the process may not be well understood by the target audience.
A combination of both techniques, stratification and regression, is probably the best approach for the analysis of epidemiological data.
In this chapter, we will focus on "logistic regression models", a regression analysis technique suited for the analysis of case-control data.
Topics covered in this chapter include:
Join the discussion about this article in the forum!
Fernando Simon posted on 6/18/2010 12:22:44 PM:
The FEM includes a chapter about Logistic regression and I accepted to be the editor for this chapter. It is the only chapter approaching multivariate analysis using regression models. It is OK for me and I think it will be very useful for many people. However, For future editions of the FEM would be better to have a different approach. Logistic regression should be part of a broader chapter or "hyperchapter" dealing with multivariate analysis in general and including at least the main regression models used in epidemiology depending on the question to be answerd, the characteristics of our data and the study design (logistic, conditional logistic, cox and poisson regression models).
May be the ECDC could bring this issue up in a near future.
Vladimir Prikazsky replied on 6/18/2010 12:39:09 PM:
that is for sure very relevant comment. And thank you for that. We will consider it for (near future) development of the FEM wiki and it should be the task of the advisory board to draw directions of the development.
Samuel replied on 6/26/2011 11:11:31 AM:
As I commented elsewhere I think it would be great to link to other resources within the chapters. An example for a great resource on categorical data analysis including logistic regression is the following lecture from UC Berkeley:
Arnold Bosman replied on 3/23/2015 11:58:36 AM:
Looking at this chapter of Logistic Regression and the discussion we had in 2010/2011, I propose we should look into this topic again and compare it with the explanatory approach we currently take in the MultiVariable Analysis module in EPIET.
What I consider useful in that curriculum, there is first a review of stratification and how this influences your bi-variable analysis (effect modification, confounding, both or none). Then to describe lineair regression analysis, and again describe how stratification influences your analysis.
This will then provide a good basis for understanding:
You need to be logged in to post comments.
You can log in here. You can register here if you haven't done so yet.