China
Africa
Explore chapters and articles related to this topic
What are effect measures for dichotomous outcomes?
Published in Debra Evans, Making Sense of Evidence-based Practice for Nursing, 2023
An odds ratio greater than 1 indicates greater odds of the event/outcome in the experimental group, an odds ratio less than 1 indicates smaller odds of the event/outcome in the experimental group, and an odds ratio = 1 indicates no difference in odds for the event/outcome between the two groups.
Meta-Analyses and Systematic Reviews
Published in Charles E. Dean, The Skeptical Professional's Guide to Rational Prescribing, 2022
When the outcome is couched in terms of a dichotomous variable, a research question that can be answered yes or no (how many patients relapsed or died after an event?), one can use an odds ratio (OR). The odds ratio is simply a measure of the association between an event and an outcome, divided by the association between those not exposed to the event and an outcome. Let’s say we are investigating the number of people who became ill after eating ice cream (13/17) vs the number who did not become ill (32/23). We divide the two results (13/17) divide by 32/33 and find an OR of 0.55. Another term is relative risk (RR), wherein the number of patients who relapsed or died is divided by the total number of patients in the study. Note that statisticians state that the OR can be similar to the RR. This can occur when the incidence of the disease is less than 10%. If higher than 10%, the OR will exaggerate the RR. One can further assess the results of studies via two models, one being a fixed effects model. This model assumes that among all of the groups being studied, there is a true mean ES. The other is a random effects model, a model which assumes that each study can have a true mean ES that differs from the others, perhaps due to study conditions.
Probability
Published in Marcello Pagano, Kimberlee Gauvreau, Heather Mattie, Principles of Biostatistics, 2022
Marcello Pagano, Kimberlee Gauvreau, Heather Mattie
These data imply that females with breast cancer have an odds of using oral contraceptives that is 1.05 times the odds of those without breast cancer. However – because of the mathematical equivalence of the two formulas for the odds ratio – we are also able to say that individuals who have used oral contraceptives have an odds of developing breast cancer that is 1.05 times the odds of nonusers. As with the relative risk, an odds ratio of 1.0 indicates that exposure does not have an effect on the probability of the outcome. An odds ratio greater than 1.0 means that there is an increased risk of the outcome among exposed individuals, and an odds ratio less than 1.0 means that there is a decreased risk of the outcome among the exposed.
Understanding dropout and non-participation in follow-up evaluation for the benefit of patients and research: evidence from a longitudinal observational study on patients with eating disorders
Published in Eating Disorders, 2023
Patrizia Todisco, Paolo Meneguzzo, Alice Garolla, Eva Diomidous, Athos Antoniades, Paris Vogazianos, Federica Tozzi
The output of the RF was used to identify the most important variables for focusing the statistical analyses. Logistic regression analysis was used to calculate the effect of the independent variable (IV) on the dependent variable (DV)—dropout (Pourhoseingholi et al., 2012). In the simple logistic model, the effect of x on y is given by the size of the parameter, β1, or the odds ratio (OR) between p1 = the probability of an event under H0 and p2 = the probability of an event under H1, where β1 = log [OR]. The odds of dropping out are given by the number of patients that dropped out divided by the number of patients that did not drop out. The Odds Ratio is the ratio of the odds under two different conditions of the predictor variable. In logistic regression, the Odds Ratio (OR) is the expected change in the odds of having the outcome per unit change in the predictor variable. So, for example, for the Anger-Hostility subscale which gave us an OR of 2.02, this tells us how much the odds of dropping out will change for each 1 unit change in the predictor Anger-Hostility subscale, that is, an increase of 1 unit in Anger-Hostility subscale multiplies the odds of dropping out by 2.02 or in other words an increase of 1 unit in Anger-Hostility subscale is associated with an increase of 102% in the odds of dropping out. The alpha was set at p < .05 for all analyses.
Homogeneity test of relative risk ratios for stratified bilateral data under different algorithms
Published in Journal of Applied Statistics, 2023
Ke-Yi Mou, Chang-Xing Ma, Zhi-Ming Li
In medical clinical studies, observations from patients' paired parts (e.g. eyes, ears, and arms) are usually collected as paired data. The paired outcomes for each patient will be no, unilateral or bilateral response(s). Data from all patients can be summarized in a contingency table. The correlation between responses from paired parts should be taken into account to avoid biased or misleading results. In clinical practice, research subjects often can be distinguished by some control variables (e.g. age, gender), which contribute to stratified data. Although the questions involving treatment-by-stratum interaction are often secondary in most multi-center trials, they are still important as preparatory work for the overall and subgroup analyses. For a stratified bilateral design with two groups, the interaction can be tested by comparing different ratios across strata. If the ratios are not significantly different, the effect of stratum is negligible. Relative risk ratio, odds ratio and risk difference are often used to quantify the strength of the association. Generally, relative risk ratio is more visual than odds ratio. Walter [22] pointed out the population risks of some diseases were rather small such that risk differences between groups were less dramatic. Thus, risk relative ratio can be effectively used to study the homogeneity test in stratified bilateral data.
Factors affecting severe pedestrian crash percentages at intersections in Colorado 2006–2018
Published in International Journal of Injury Control and Safety Promotion, 2023
Bruce Janson, Mohamed Mesbah, Wesley Marshall
Column 6 shows the unadjusted (or independent) odds ratio for each factor level compared to the base level listed first with no odds ratio shown. All variables in Table 1 are listed with the second factor level associated with greater severity. Thus, the odds ratios are all greater than 1. The null hypothesis of the odds ratio is that it is not significantly different from 1 based on the data, which is rejected if its confidence interval excludes 1 at the 95% level of confidence. Variables not listed had p-values above 5%. Columns 7–9 show the confidence interval bounds and z-statistic of each odds ratio, and column 10 shows the p-value of the z-statistic. Only vehicle type (with an unadjusted p-value of 13.9%) is still shown because it does become significant in logistic regression as shown later.