2017
DOI: 10.3389/fvets.2017.00193
|View full text |Cite
|
Sign up to set email alerts
|

Odds Ratio or Prevalence Ratio? An Overview of Reported Statistical Methods and Appropriateness of Interpretations in Cross-sectional Studies with Dichotomous Outcomes in Veterinary Medicine

Abstract: One of the most commonly observational study designs employed in veterinary is the cross-sectional study with binary outcomes. To measure an association with exposure, the use of prevalence ratios (PR) or odds ratios (OR) are possible. In human epidemiology, much has been discussed about the use of the OR exclusively for case–control studies and some authors reported that there is no good justification for fitting logistic regression when the prevalence of the disease is high, in which OR overestimate the PR. … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

2
114
0
1

Year Published

2019
2019
2024
2024

Publication Types

Select...
7
2
1

Relationship

0
10

Authors

Journals

citations
Cited by 163 publications
(128 citation statements)
references
References 44 publications
2
114
0
1
Order By: Relevance
“…Binomial models were preferred because they provide prevalence ratios directly. Secondly unlike the alternative logistic regression log binomial models do not overestimate their coefficients when the outcome of interest is a common occurrence[28, 29] although they also have problems of lack of convergence[19]. In the few times non-convergence occurred we used modified Poisson regression which solves the problem but it is not also perfect since it produces inconsistent variances[19].…”
Section: Methodsmentioning
confidence: 99%
“…Binomial models were preferred because they provide prevalence ratios directly. Secondly unlike the alternative logistic regression log binomial models do not overestimate their coefficients when the outcome of interest is a common occurrence[28, 29] although they also have problems of lack of convergence[19]. In the few times non-convergence occurred we used modified Poisson regression which solves the problem but it is not also perfect since it produces inconsistent variances[19].…”
Section: Methodsmentioning
confidence: 99%
“…We examined the associations between unmet needs and each independent variable by calculating the prevalence ratio (PR) using a log-binomial regression model which is preferable for the outcome variable with high prevalence. 43 Variables with p-value of ≤0.25 in the bivariate analysis were considered in the multivariable analysis and adjusted PR (APR) along with 95% CIs were estimated and a p-value <0.05 was used to declare the statistical significance. Log-likelihood ratio test and Akaike's and Bayesian information criterion were used to select the final model.…”
Section: Data Management and Analysismentioning
confidence: 99%
“…The output of the model was the Prevalence Ratio (PR). A log‐binomial regression was chosen owing to the high frequency of occurrence of mediastinal lymphoma, because using logistic regression would overestimate the PR . The variable age was categorized as ‘young’ (less than 36 months), ‘adult’ (more or equal to 36 months and less than 96 months) and ‘aged’ (more than 96 months).…”
Section: Methodsmentioning
confidence: 99%