Ordered logit
From Wikipedia, the free encyclopedia
In statistics, the ordered logit model, or ordered logistic regression, is a regression model for ordinal dependent variables. It can be thought of as an extension of the logistic regression model for dichotomous dependent variables. It is also known as the proportional odds model, as the model makes the proportional odds assumption: That the odds ratio for being in a chosen category or higher compared to being in a lower category is the same regardless of which category is chosen. In other words, it assumes that if the ordinal variable were dichotomised, the odds ratio would be the same regardless of the cut-off chosen for dichotomisation. The model is not equivalent to first dichotomising the outcome variable and then using logistic regression, however, as it makes use of the greater information available from the ordinal variable and is therefore more efficient.
[edit] See also
[edit] References
- Steve Simon (2004-09-22). Sample size for an ordinal outcome. STATS - STeve's Attempt to Teach Statistics. Retrieved on 2008-03-04.
[edit] Further reading
 |
Please expand this article using the suggested source(s) below. More information might be found in a section of the talk page. |
- Woodward, Mark (2005). Epidemiology: Study Design and Data Analysis, 2nd edition, Chapman & Hall/CRC. ISBN 978-1584884156.
- Hardin, James; Hilbe, Joseph (2007). Generalized Linear Models and Extensions, 2nd edition, College Station: Stata Press. ISBN 978-1-59718-014-6.
