3

What is the difference between "conditional analysis" and "conditional logistic regression"?

It is also really hard to find out an easy example of that "conditional" means in this case...

Randel
  • 6,199
  • 4
  • 39
  • 65
eXpander
  • 524
  • 1
  • 6
  • 15
  • 3
    Welcome user1261558, maybe you could be a bit more specific about the context in which you've encountered both type of analysis, it would make it easier to answer your question. You can also have a look at the [faq](http://stats.stackexchange.com/faq) on what to put in a question to maximize the chances of getting an answer. Conditional logistic regression is usually used to model choice between several alternatives (e.g. brand A or B at different prices), or in the context of a case/control situation assess characteristics found in the cases but not in the controls. – Antoine Vernet Mar 11 '13 at 11:01

1 Answers1

1

In addition to the comments by Antoine above, a conditional logistic regression is often used when the cases and controls are matched. A conditional logistic regression can account for the fact that there is a dependence between how the patients were selected. Another example of when conditional logistic regression would be helpful is in the context of a dataset that has levels of strata or centers. In this context estimating the association between exposure (within a center or center) and an outcome is the goal.

A conditional analysis can have many meanings. I would need additional information to address this point. You may referring to doing analysis under a condition such as doing an analysis on people above the age of 60, or female patients in a data set. People often refer to these as subgroup analyses, if your study was not originally powered for investigating these associations.

SniperBro2000
  • 720
  • 1
  • 6
  • 8