A simple method for estimating relative risk using logistic regression.

Grupo Latinoamericano de Investigaciones Epidemiológicas, Organización Latinoamericana para el Fomento de la Investigación en Salud, Bucaramanga, Colombia.
BMC Medical Research Methodology (Impact Factor: 2.21). 02/2012; 12:14. DOI: 10.1186/1471-2288-12-14
Source: PubMed

ABSTRACT Odds ratios (OR) significantly overestimate associations between risk factors and common outcomes. The estimation of relative risks (RR) or prevalence ratios (PR) has represented a statistical challenge in multivariate analysis and, furthermore, some researchers do not have access to the available methods. Objective: To propose and evaluate a new method for estimating RR and PR by logistic regression.
A provisional database was designed in which events were duplicated but identified as non-events. After, a logistic regression was performed and effect measures were calculated, which were considered RR estimations. This method was compared with binomial regression, Cox regression with robust variance and ordinary logistic regression in analyses with three outcomes of different frequencies.
ORs estimated by ordinary logistic regression progressively overestimated RRs as the outcome frequency increased. RRs estimated by Cox regression and the method proposed in this article were similar to those estimated by binomial regression for every outcome. However, confidence intervals were wider with the proposed method.
This simple tool could be useful for calculating the effect of risk factors and the impact of health interventions in developing countries when other statistical strategies are not available.

  • [Show abstract] [Hide abstract]
    ABSTRACT: To determine optimal treatment for recurrent or residual intraventricular neurocytomas (IVNs), a systematic review of PubMed and EMBASE was conducted comparing fractionated conventional radiotherapy (FCRT) versus stereotactic radiosurgery (SRS). Inclusion criteria included histological IVN documentation, at least 6 months of follow-up observation and described dose of FCRT or SRS administered. Descriptive statistical and Kaplan-Meier analyses were performed. The literature search yielded 451 articles. Sixteen studies met inclusion criteria. The local tumor control proportion was 93% and 88% in the SRS and FCRT subgroups, respectively. The relative risk (RR) of local recurrence was 0.57 less (95% CI: 0.21-1.57; log-rank p=0.85) and the RR of all-cause mortality was 0.23 less (95% CI: 0.05-1.05; log-rank p=0.22) in SRS subgroup compared to the FCRT subgroup but did not reach statistical significance. Recurrence was significantly associated with presence of histological atypia (log-rank p<0.001). Severe complications were lower in SRS subgroup (5.5% versus 7.5%, p=0.74); however, distant tumor recurrence was slightly lower in the FCRT subgroup (1.5% versus 5.5%, p=0.24). The role of SRS or FCRT in the management of residual or recurrent IVNs will continue to depend on the balance between the risks and benefits of SRS and FCRT until better quality data are available.
    Clinical neurology and neurosurgery 02/2014; 117C:55-64. · 1.30 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: To assess the prevalence of medicine use in adults of Brasilia and to elucidate the associated factors. A cross-sectional study was conducted with adults (18 to 65 years) living in Brasilia, who were selected using a two-stage probabilistic sampling and interviewed in their home, from February to May 2012. The primary outcome was the use of medicines in the last 7 days. A Poisson regression with robust variance was employed to adjust for covariates following a hierarchical model. The study included 1820 individuals (11% losses), 60% of which were women, and the mean age was 37 ± 12.6 years. The prevalence of drug consumption was 35.7% (95% confidence interval [95%CI]: 33.5%-37.9%). Medicine consumption was significantly higher in women (prevalence ratio [PR] = 1.54; 95%CI: 1.28-1.85); unemployed or retired people (PR = 1.35; 95%CI: 1.15-1.59); people with hypertension (PR = 2.33; 95%CI: 2.00-2.71), diabetes (PR = 1.46; 95%CI: 1.22-1.74), depression (PR = 1.32; 95%CI: 1.13-1.53), or other chronic diseases (PR = 1.50; 95%CI: 1.26-1.79); and study participants who had a recent medical consultation (PR = 1.49; 95%CI: 1.29-1.71). Medication use was significantly higher at older ages. The participants obtained about half of the drugs from the Brazilian public health system, but this access was significantly different according to the economic class. Medication use was common among adults living in Brasilia and is associated with sex, age, health conditions, and access to healthcare. Copyright © 2014 John Wiley & Sons, Ltd.
    Pharmacoepidemiology and Drug Safety 02/2014; · 2.90 Impact Factor
  • Source

Full-text (2 Sources)

Available from
Jun 4, 2014