[Odds ratio or prevalence ratio? Their use in cross-sectional studies].
ABSTRACT The most commonly used measures of association in cross-sectional studies are the odds ratio (OR) and the prevalence ratio (PR). Some cross-sectional epidemiologic studies describe their results as OR but use the definition of PR. The main aim of this study was to describe and compare different calculation methods for PR described in literature using two situations (prevalence < 20% and prevalence > 20%).
A literature search was carried out to determine the most commonly used techniques for estimating the PR. The four most frequent methods were: 1) obtaining the OR using non-conditional logistic regression but using the correct definition; 2) using Breslow-Cox regression; 3) using a generalized linear model with logarithmic transformation and binomial family, and 4) using the conversion formula from OR into PR. The models found were replicated for both situations (prevalence less than 20% and greater than 20%) using real data from the 1994 Catalan Health Interview Survey.
When prevalence was low, no substantial differences were observed in either the estimators or standard errors obtained using the four procedures. When prevalence was high, differences were found between estimators and confidence intervals although all the measures maintained statistical significance.
All the methods have advantages and disadvantages. Individual researchers should decide which technique is the most appropriate for their data and should be consistent when using an estimator and interpreting it.
SourceAvailable from: Maria Rita Donalisio[Show abstract] [Hide abstract]
ABSTRACT: The objective for this paper was to present and discuss the use of odds ratios and prevalence ratios using real data with a complex sampling design. We carried out a cross-sectional study using data obtained from a two-stage stratified cluster sample from a study conducted in 2001-2002 (n = 1,958). Odds ratios and prevalence ratios were obtained by unconditional logistic regression and Poisson regression, respectively, for later comparison using the Stata statistical package (v. 7.0). Confidence intervals and design effects were considered in the evaluation of the precision of estimates. Two outcomes of a cross-sectional study with different prevalences were evaluated: vaccination against influenza (66.1%) and self-referred lung disease (6.9%). In the high-prevalence scenario, using prevalence ratios the estimates were more conservative and we found narrower confidence intervals. In the low-prevalence scenario, we found no important numeric differences between the estimates and standard errors obtained using the two techniques. A design effect greater than one indicates that the sample design has increased the variance of the estimate. However, it is the researcher's task to choose which technique and measure to use for each data set, since this choice must remain within the scope of epidemiology.Revista Brasileira de Epidemiologia 09/2008; 11(3):347-355.
[Show abstract] [Hide abstract]
ABSTRACT: To describe the second version of the Spanish Copenhagen Psychosocial Questionnaire and to present evidence of its validity and reliability. The original Danish long COPSOQ II questionnaire was adapted to the labor market, cultural, and linguistic setting of Spain and included in the 2010 Spanish Psychosocial Risks Survey. Analysis involved the assessment of psychometric characteristics and associations among psychosocial scales and health scales. Medium and short versions were derived from the long one. The long questionnaire was configured with 24 dimensions (92 items); medium-length questionnaire with 20 dimensions (69 items); and short questionnaire with 14 dimensions (28 items). All scales showed acceptable reliability and concordance between versions. Most associations among psychosocial scales and Mental Health, Stress, and Burnout scales were in the expected direction, except the scale of Influence, that showed some incongruent associations. Results support the validity and reliability of Spanish COPSOQ II questionnaires as tools for psychosocial risk assessment at the workplace, however, better scales should be developed specially for the dimension of Influence. Am. J. Ind. Med. 9999:1-11, 2013. © 2013 Wiley Periodicals, Inc.American Journal of Industrial Medicine 01/2014; 57(1). DOI:10.1002/ajim.22238 · 1.59 Impact Factor
[Show abstract] [Hide abstract]
ABSTRACT: Objective To analyze the perception of the Spanish population of risk factors for cancer. Methods Data were extracted from the OncoBarometro 2010 survey. Multivariate logistic models were applied to analyze the perception of the population on the importance of various risk factors: smoking, alcohol, sun, food, weight, sexually transmitted diseases, family history, radiation exposure, exposure to toxic substances and air pollution. The answers were rated on a 0 to 10 scale and were converted to low (0-6) and high (7-10) categories. The measure of association used was the prevalence ratio (PR). Results The greatest importance was assigned to smoking (high importance: 83.1%), whereas the least importance was assigned to weight (26.5%). In general, the probability of perceiving risk factors as important was lower among men (PR sun: 0.87; PR sexually transmitted diseases: 0.78) and increased among people who received professional advice on cancer prevention (PR alcohol: 1.11; PR sun: 1.18; PR food; 1.31; PR weight: 1.92). In particular, knowledge of symptoms and extreme fear of cancer were associated with perceiving smoking as an important risk factor, whereas a high perceived vulnerability to cancer was associated with perceiving exposure to toxic substances, pollution and smoking as important risk factors. Conclusions Greater awareness is required of the association of cancer with overweight and sexually transmitted diseases. The recommendations given by health professionals on cancer prevention are key to increasing the population's awareness of risk factors for cancer.Gaceta Sanitaria 01/2013; DOI:10.1016/j.gaceta.2013.10.008 · 1.25 Impact Factor