Efficiency of the logistic regression and cox proportional hazards models in longitudinal studies

Annesi, I; Moreau, Thierry; Lellouch, J

doi:10.1002/sim.4780081211

Cited by 108 publications

(73 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…21,22 Logistic and Cox models give similar results when the overall event frequency is less than 10%. 23,24 Where the frequency of events is higher, ordinal data may be analyzed by time to event. 25,26 In the current dataset, the Cox model was slightly less efficient than bootstrapping, Mann-Whitney U, and ordinal logistic regression.…”

Section: Discussionmentioning

confidence: 99%

Use of Ordinal Outcomes in Vascular Prevention Trials

Bath

Geeganage

Gray

et al. 2008

Stroke

View full text Add to dashboard Cite

Background and Purpose-Vascular prevention trials mostly count "yes/no" (binary) outcome events, eg, stroke/no stroke. Analysis of ordered categorical vascular events (eg, fatal stroke/nonfatal stroke/no stroke) is clinically relevant and could be more powerful statistically. Although this is not a novel idea in the statistical community, ordinal outcomes have not been applied to stroke prevention trials in the past. Methods-Summary data on stroke, myocardial infarction, combined vascular events, and bleeding were obtained by treatment group from published vascular prevention trials. Data were analyzed using 10 statistical approaches which allow comparison of 2 ordinal or binary treatment groups. The results for each statistical test for each trial were then compared using Friedman 2-way analysis of variance with multiple comparison procedures. Results-Across 85 trials (335 305 subjects) the test results differed substantially so that approaches which used the ordinal nature of stroke events (fatal/nonfatal/no stroke) were more efficient than those which combined the data to form 2 groups (PϽ0.0001). The most efficient tests were bootstrapping the difference in mean rank, Mann-Whitney U test, and ordinal logistic regression; 4-and 5-level data were more efficient still. Similar findings were obtained for myocardial infarction, combined vascular outcomes, and bleeding. The findings were consistent across different types, designs and sizes of trial, and for the different types of intervention. Conclusions-When analyzing vascular events from prevention trials, statistical tests which use ordered categorical data are more efficient and are more likely to yield reliable results than binary tests. This approach gives additional information on treatment effects by severity of event and will allow trials to be smaller.

show abstract

Section: Discussionmentioning

confidence: 99%

Use of Ordinal Outcomes in Vascular Prevention Trials

Bath

Geeganage

Gray

et al. 2008

Stroke

View full text Add to dashboard Cite

show abstract

“…Comparisons of the theoretical basis of the Cox and logistic models have found that they should yield similar parameter and variance estimates and tests of inference when the underlying hazard rate is constant, follow-up time is short, the outcome is rare, and the relative risks associated with the risk factors in the models are not large [Green and Symons, 1983;Peduzzi et al, 1987;Annesi et al, 1989].…”

Section: Model Comparisonsmentioning

confidence: 96%

Empirical comparisons of proportional hazards, poisson, and logistic regression modeling of occupational cohort data

1998

View full text Add to dashboard Cite

“…The superiority of the Cox proportional hazards models over the logistic regression models in analyzing longitudinal data has been mathematically proven for models, which consider one dichotomous covariate 2 and models with multiple covariates. 3 A number of considerations regarding the generalizability of our results merit discussion. First, we simulated populations with a high risk of CHD, which implies that the absolute estimates of the statistical power of the different scenarios apply only to populations with similar disease risks.…”

Section: Discussionmentioning

confidence: 97%

“…example, the effect estimates will diverge when follow-up time is longer, 3,4 and effect estimates of logistic regression models are less precise, especially when the event is more common or when there is a strong relative risk. 13 This is in line with our findings in the empirical study, which showed that odds ratios tended to be more extreme than the hazard ratios.…”

Section: Discussionmentioning

confidence: 99%

“…1 If follow-up data are available, Cox proportional hazards models are the recommended models as they have more statistical power than logistic regression models. 2,3 This is due to the fact that the Cox proportional hazards models take account of the time until events occur. 4 However, these models have not been compared in cross-sectional genetic association studies.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cox proportional hazards models have more statistical power than logistic regression models in cross-sectional genetic association studies

et al. 2008

View full text Add to dashboard Cite

Cross-sectional genetic association studies can be analyzed using Cox proportional hazards models with age as time scale, if age at onset of disease is known for the cases and age at data collection is known for the controls. We assessed to what degree and under what conditions Cox proportional hazards models have more statistical power than logistic regression models in cross-sectional genetic association analyses. Analyses were conducted in an empirical study on the association of 65 polymorphisms and risk of coronary heart disease among 2400 familial hypercholesterolemia patients, and in a simulation study that considered various combinations of sample size, genotype frequency, and strength of association between the genotype and coronary heart disease. We applied Cox proportional hazards models and logistic regression models, and compared effect estimates (hazard ratios and odds ratios) and statistical power. In the empirical study, Cox proportional hazards models generally showed lower P-values for polymorphisms than logistic regression models. In the simulation study, Cox proportional hazards models had higher statistical power in all scenarios. Absolute differences in power did depend on the effect estimate, genotype frequency and sample size, and were most prominent for genotypes with minor effects. For example, when the genotype frequency was 30% in a sample with size n ¼ 2000 individuals, the absolute differences were the largest for effect estimates between 1.1 and 1.5. In conclusion, Cox proportional hazards models can increase statistical power in cross-sectional genetic association studies, especially in the range of effect estimates that are expected for genetic associations in common diseases.

show abstract

Efficiency of the logistic regression and cox proportional hazards models in longitudinal studies

Cited by 108 publications

References 4 publications

Use of Ordinal Outcomes in Vascular Prevention Trials

Use of Ordinal Outcomes in Vascular Prevention Trials

Empirical comparisons of proportional hazards, poisson, and logistic regression modeling of occupational cohort data

Cox proportional hazards models have more statistical power than logistic regression models in cross-sectional genetic association studies

Contact Info

Product

Resources

About