Logistic regression analysis of sample survey data

Roberts, Glyn; Rao, Naresh Krishna; Kumar, S.

doi:10.1093/biomet/74.1.1

Cited by 110 publications

(31 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We also computed a multivariable survey logistic regression model for explaining the variation in HIV taking the complex sampling design features into account as explained in [22]. The logistic regression models fall into a broader class of models referred to as generalized linear models (GLMs).…”

Section: Methodsmentioning

confidence: 99%

Estimating HIV Prevalence in Zimbabwe Using Population-Based Survey Data

Chinomona

Mwambi

2015

PLoS ONE

View full text Add to dashboard Cite

Estimates of HIV prevalence computed using data obtained from sampling a subgroup of the national population may lack the representativeness of all the relevant domains of the population. These estimates are often computed on the assumption that HIV prevalence is uniform across all domains of the population. Use of appropriate statistical methods together with population-based survey data can enhance better estimation of national and subgroup level HIV prevalence and can provide improved explanations of the variation in HIV prevalence across different domains of the population. In this study we computed design-consistent estimates of HIV prevalence, and their respective 95% confidence intervals at both the national and subgroup levels. In addition, we provided a multivariable survey logistic regression model from a generalized linear modelling perspective for explaining the variation in HIV prevalence using demographic, socio-economic, socio-cultural and behavioural factors. Essentially, this study borrows from the proximate determinants conceptual framework which provides guiding principles upon which socio-economic and socio-cultural variables affect HIV prevalence through biological behavioural factors. We utilize the 2010–11 Zimbabwe Demographic and Health Survey (2010–11 ZDHS) data (which are population based) to estimate HIV prevalence in different categories of the population and for constructing the logistic regression model. It was established that HIV prevalence varies greatly with age, gender, marital status, place of residence, literacy level, belief on whether condom use can reduce the risk of contracting HIV and level of recent sexual activity whereas there was no marked variation in HIV prevalence with social status (measured using a wealth index), method of contraceptive and an individual’s level of education.

show abstract

Section: Methodsmentioning

confidence: 99%

Estimating HIV Prevalence in Zimbabwe Using Population-Based Survey Data

Chinomona

Mwambi

2015

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…These procedures incorporate the sampling design attributes and weighting into the analyses (Roberts et al, 1987). For descriptive analyses, SurveyMeans, and Survey-Freq, with corrected standard errors for mean estimation, 95% confidence intervals (95% CIs), weighted frequency, and percent, were calculated.…”

Section: Covariatesmentioning

confidence: 99%

Independent Effects of Sleep Duration and Body Mass Index on the Risk of a Work-Related Injury: Evidence From the US National Health Interview Survey (2004–2010)

Lombardi

Wirtz²,

Willetts

et al. 2012

Chronobiology International

View full text Add to dashboard Cite

Fatigue has been linked to adverse safety outcomes, and poor quality or decreased sleep has been associated with obesity (higher body mass index, BMI). Additionally, higher BMI is related to an increased risk for injury; however, it is unclear whether BMI modifies the effect of short sleep or has an independent effect on work-related injury risk. To answer this question, the authors examined the risk of a work-related injury as a function of total daily sleep time and BMI using the US National Health Interview Survey (NHIS). The NHIS is an in-person household survey using a multistage, stratified, clustered sample design representing the US civilian population. Data were pooled for the 7-yr survey period from 2004 to 2010 for 101 891 "employed" adult subjects (51.7%; 41.1 ± yrs of age [mean ± SEM]) with data on both sleep and BMI. Weighted annualized work-related injury rates were estimated across a priori defined categories of BMI: healthy weight (BMI: <25), overweight (BMI: 25-29.99), and obese (BMI: ≥30) and also categories of usual daily sleep duration: <6, 6-6.99, 7-7.99, 8-8.99, and ≥9 h. To account for the complex sampling design, including stratification, clustering, and unequal weighting, weighted multiple logistic regression was used to estimate the risk of a work-related injury. The initial model examined the interaction among daily sleep duration and BMI, controlling for weekly working hours, age, sex, race/ethnicity, education, type of pay, industry, and occupation. No significant interaction was found between usual daily sleep duration and BMI (p = .72); thus, the interaction term of the final logistic model included these two variables as independent predictors of injury, along with the aforementioned covariates. Statistically significant covariates (p ≤ .05) included age, sex, weekly work hours, occupation, and if the worker was paid hourly. The lowest categories of usual sleep duration (<6 and 6-6.9 h) showed significantly (p ≤ .05) elevated injury risks than the referent category (7-8 h sleep), whereas sleeping >7-8 h did not significantly elevate risk. The adjusted injury risk odds ratio (OR) for a worker with a usual daily sleep of <6 h was 1.86 (95% confidence interval [CI]: 1.37-2.52), and for 6-6.9 h it was 1.46 (95% CI: 1.18-1.80). With regards to BMI, the adjusted injury risk OR comparing workers who were obese (BMI: ≥30) to healthy weight workers (BMI: <25) was 1.34 (95% CI: 1.09-1.66), whereas the risk in comparing overweight workers (BMI: 25-29.99) to healthy weight risk was elevated, but not statistically significant (OR = 1.08; 95% CI: .88-1.33). These results from a large representative sample of US workers suggest increase in work-related injury risk for reduced sleep regardless of worker's body mass. However, being an overweight worker also increases work-injury risk regardless of usual daily sleep duration. The independent additive risk of these factors on work-related injury suggests a substantial, but at least partially preventable, risk.

show abstract

“…Koehler and Wilson (1986) extend the results of Brier (1980) for a Dirichlet-multinomial model and study statistics for loglinear models in general survey designs that use some knowledge of this sampling design. A variety of corrections to X 2 and G 2 have been proposed in the papers cited here; other corrections include those of Bedrick (1983), Fay (1985) (using the jackknife), Rao and Scott (1984), and Roberts et al (1987). Thomas and Rao (1987) study the small-sample properties of some of these corrected statistics under simulated cluster sampling.…”

Section: Serially Dependent Data and Cluster Samplingmentioning

confidence: 99%