C. Zocchetti et al., RELATIONSHIP BETWEEN PREVALENCE RATE RATIOS AND ODDS RATIOS IN CROSS-SECTIONAL STUDIES, International journal of epidemiology, 26(1), 1997, pp. 220-223
Background. Cross-sectional data are frequently encountered in epidemi
ology and published results are predominantly presented in terms of pr
evalence odds ratios (FOR), A recent debate suggested a switch from FO
R, which is easily obtained via logistic regression analysis available
in many statistical packages, to prevalence rate ratios (PRR). We tho
ught it useful to explore the mathematical relationship between PRR an
d FOR and to evaluate the degree of divergence of the two measures as
a function of the prevalence of disease and exposure. Methods. With th
e use of some algebra and the common definitions of prevalence of the
disease (Pr(D)), prevalence of the exposure (Pr(E)), PRR, and FOR in a
2x2 table, we have identified a useful formula that represents the ma
thematical relationship between these four quantities. Plots of FOR ve
rsus PRR for selected values of Pr(D) and Pr(E) are reported. Results.
Mathematically speaking the general relationship takes the form of a
second order curve which can change curvature and/or rotate around the
point FOR = PRR = 1 according to the values of Pr(D) and Pr(E), with
FOR being always further from the null value than is PRR. The discrepa
ncies are much more influenced by variations in Pr(D) than in Pr(E). C
onclusions. We think that the choice between FOR or PRR in a cross-sec
tional study ought to be based on epidemiological grounds and not on t
he availability of software tools. The paper offers a formula and some
examples for a better understanding of the relationship between PRR a
nd FOR as a function of the prevalence of the disease and the prevalen
ce of the exposure.