Choice among the Link Function in Ordinal Regression in SPSS

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

Which link function should we choose when we do ordinal regression in SPSS? Thanks!

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：regression regressio function ordinal regress SPSS regression ordinal Choice among

Logit: Evenly Distributed Categories

Complementary Log-Log: Higher Categories More Probable;

Negative Log-Log:Lower Categories More Probable

Probit: Analysis with Explicitly Normally Distributed Latent Variable;

Cauchit: Outcome With Many Extreme Value

Probit and logit models are reasonable choices when the changes in the cumulative probabilities are gradual. If there are abrupt changes, other link functions should be used. The complementary log- log link may be a good model when the cumulative probabilities increase from 0 fairly slowly and then rapidly approach 1. If the opposite is true, namely that the cumulative probability for lower scores is high and the approach to 1 is slow, the negative log- log link may describe the data. If the complementary log- log model describes the probability of an event occurring, the loglog model describes the probability of the event not occurring.

-------------------------------------------------------

SPSS 14.0 Advanced Statistical Procedures Companion
by Marija J. Norušis
ISBN 0-13-174700-2
Prentice Hall
Pages 368