1998
DOI: 10.1016/s0895-4356(98)00066-3
|View full text |Cite
|
Sign up to set email alerts
|

Using Binary Logistic Regression Models for Ordinal Data with Non-proportional Odds

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
143
0
2

Year Published

2000
2000
2019
2019

Publication Types

Select...
9
1

Relationship

1
9

Authors

Journals

citations
Cited by 169 publications
(146 citation statements)
references
References 21 publications
1
143
0
2
Order By: Relevance
“…To assess the simultaneous influence of factors on adherence two logistic regression models were fitted as odds were not proportional between adherence groups and thus did not allow for ordinal logistic regression (Le 1998;Bender and Grouven 1998). Linearity was checked graphically.…”
Section: Discussionmentioning
confidence: 99%
“…To assess the simultaneous influence of factors on adherence two logistic regression models were fitted as odds were not proportional between adherence groups and thus did not allow for ordinal logistic regression (Le 1998;Bender and Grouven 1998). Linearity was checked graphically.…”
Section: Discussionmentioning
confidence: 99%
“…Two separate binary logistic regression models were designed for representing factors related to (1) at least optimal maternal weight gain and (2) excessive weight gain Maternal diet in pregnancy and weight gain AS Olafsdottir et al during pregnancy. 39 The odds of gaining at least optimal or excessive weight during pregnancy was calculated with 95% confidence intervals (95% CI), adjusting for gestational length, maternal age and smoking. Stepwise backward elimination was used for selecting dietary factors and other possible sources of confounding, after comparing the differences between the three weight gain groups (i.e., suboptimal, optimal or excessive weight gain) with ANOVA.…”
Section: Discussionmentioning
confidence: 99%
“…However, the ordinal regression did not meet the assumption even after the complementary log-log function was used. A simple approach to analyse ordinal data with non-proportional odds is to dichotomize the ordinal response variable by means of several cut-off points and use separate binary logistic regression models for each dichotomized response (Bender and Grouven 1998). For subsequent analysis, therefore, the life satisfaction dependent variable was dichotomised into two cut-off points: level 7 and level 6 or above.…”
Section: Methodsmentioning
confidence: 99%