LOGITCPRPLOT: Stata module to graph component-plus-residual plot for logistic regression

logitcprplot can be used after logistic regression for graphing a component-plus-residual plot (a.k.a. partial residual plot) for a given predictor, including a lowess, local polynomial, restricted cubic spline, fractional polynomial, penalized spline, regression spline, running line, or adaptive variable span running line smooth

RRLOGIT: Stata module to estimate logistic regression for randomized response data

rrlogit fits a maximum-likelihood logistic regression for randomized response data.

A review of two journals found that articles using multivariable logistic regression frequently did not report commonly recommended assumptions

Background and Objective: To examine if commonly recommended assumptions for multivariable logistic regression are addressed in two major epidemiological journals. Methods: Ninety-nine articles from the Journal of Clinical Epidemiology and the American Journal of Epidemiology were surveyed for 10 criteria: six dealing with computation and four with reporting multivariable logistic regression results. Results: Three of the 10 criteria were addressed in 50% or more of the articles. Statistical significance testing or confidence intervals were reported in all articles. Methods for selecting independent variables were described in 82%, and specific procedures used to generate the models were discussed in 65%. Fewer than 50% of the articles indicated if interactions were tested or met the recommended events per independent variable ratio of 10: 1. Fewer than 20% of the articles described conformity to a linear gradient, examined collinearity, reported information on validation procedures, goodness-of-fit, discrimination statistics, or provided complete information on variable coding. There was no significant difference (P >.05) in the proportion of articles meeting the criteria across the two journals. Conclusion: Articles reviewed frequently did not report commonly recommended assumptions for using multivariable logistic regression. (C) 2004 Elsevier Inc. All rights reserved.

Optimal crossover designs for logistic regression models in pharmacodynamics

Pharmacodynamics (PD) is the study of the biochemical and physiological effects of drugs. The construction of optimal designs for dose-ranging trials with multiple periods is considered in this paper, where the outcome of the trial (the effect of the drug) is considered to be a binary response: the success or failure of a drug to bring about a particular change in the subject after a given amount of time. The carryover effect of each dose from one period to the next is assumed to be proportional to the direct effect. It is shown for a logistic regression model that the efficiency of optimal parallel (single-period) or crossover (two-period) design is substantially greater than a balanced design. The optimal designs are also shown to be robust to misspecification of the value of the parameters. Finally, the parallel and crossover designs are combined to provide the experimenter with greater flexibility.

Logistic Regression in Modelling Data for CVC - Related Infection

2000 Mathematics Subject Classification: 62J12, 62P10.

Modeling Data for Complications in Diabetics Using Logistic Regression

2010 Mathematics Subject Classification: 62P10.

Sequential Logistic Regression: A Method to Reveal Subtlety in Self-Efficacy

This paper uses self-efficacy to predict the success of women in introductory physics. We show how sequential logistic regression demonstrates the predictive ability of self-efficacy, and reveals variations with type of physics course. Also discussed are the sources of self-efficacy that have the largest impact on predictive ability.

Use of posterior predictive assessments to evaluate model fit in multilevel logistic regression

Assessing the fit of a model is an important final step in any statistical analysis, but this is not straightforward when complex discrete response models are used. Cross validation and posterior predictions have been suggested as methods to aid model criticism. In this paper a comparison is made between four methods of model predictive assessment in the context of a three level logistic regression model for clinical mastitis in dairy cattle; cross validation, a prediction using the full posterior predictive distribution and two “mixed” predictive methods that incorporate higher level random effects simulated from the underlying model distribution. Cross validation is considered a gold standard method but is computationally intensive and thus a comparison is made between posterior predictive assessments and cross validation. The analyses revealed that mixed prediction methods produced results close to cross validation whilst the full posterior predictive assessment gave predictions that were over-optimistic (closer to the observed disease rates) compared with cross validation. A mixed prediction method that simulated random effects from both higher levels was best at identifying the outlying level two (farm-year) units of interest. It is concluded that this mixed prediction method, simulating random effects from both higher levels, is straightforward and may be of value in model criticism of multilevel logistic regression, a technique commonly used for animal health data with a hierarchical structure.

Obtaining environmental favourability functions from logistic regression

Logistic regression is a statistical tool widely used for predicting species’ potential distributions starting from presence/absence data and a set of independent variables. However, logistic regression equations compute probability values based not only on the values of the predictor variables but also on the relative proportion of presences and absences in the dataset, which does not adequately describe the environmental favourability for or against species presence. A few strategies have been used to circumvent this, but they usually imply an alteration of the original data or the discarding of potentially valuable information. We propose a way to obtain from logistic regression an environmental favourability function whose results are not affected by an uneven proportion of presences and absences. We tested the method on the distribution of virtual species in an imaginary territory. The favourability models yielded similar values regardless of the variation in the presence/absence ratio. We also illustrate with the example of the Pyrenean desman’s (Galemys pyrenaicus) distribution in Spain. The favourability model yielded more realistic potential distribution maps than the logistic regression model. Favourability values can be regarded as the degree of membership of the fuzzy set of sites whose environmental conditions are favourable to the species, which enables applying the rules of fuzzy logic to distribution modelling. They also allow for direct comparisons between models for species with different presence/absence ratios in the study area. This makes themmore useful to estimate the conservation value of areas, to design ecological corridors, or to select appropriate areas for species reintroductions.

Impacto da adequação da oferta energética sobre a mortalidade em pacientes de UTI recebendo nutrição enteral

OBJETIVO: Investigar a relação entre adequação da oferta energética e mortalidade na unidade de terapia intensiva em pacientes sob terapia nutricional enteral exclusiva. MÉTODOS: Estudo observacional prospectivo conduzido em uma unidade de terapia intensiva em 2008 e 2009. Foram incluídos pacientes >18 anos que receberam terapia nutricional enteral por >72h. A adequação da oferta de energia foi estimada pela razão administrado/prescrito. Para a investigação da relação entre variáveis preditoras (adequação da oferta energética, escore APACHE II, sexo, idade e tempo de permanência na unidade de terapia intensiva e o desfecho mortalidade na unidade de terapia intensiva, utilizou-se o modelo de regressão logística não condicional. RESULTADOS: Foram incluídos 63 pacientes (média 58 anos, mortalidade 27%), 47,6% dos quais receberam mais de 90% da energia prescrita (adequação média 88,2%). O balanço energético médio foi de -190 kcal/dia. Observou-se associação significativa entre ocorrência de óbito e as variáveis idade e tempo de permanência na unidade de terapia intensiva, após a retirada das variáveis adequação da oferta energética, APACHE II e sexo durante o processo de modelagem. CONCLUSÃO: A adequação da oferta energética não influenciou a taxa de mortalidade na unidade de terapia intensiva. Protocolos de infusão de nutrição enteral seguidos criteriosamente, com adequação administrado/prescrito acima de 70%, parecem ser suficientes para não interferirem na mortalidade. Dessa forma, pode-se questionar a obrigatoriedade de atingir índices próximos a 100%, considerando a elevada frequência com que ocorrem interrupções no fornecimento de dieta enteral devido a intolerância gastrointestinal e jejuns para exames e procedimentos. Pesquisas futuras poderão identificar a meta ideal de adequação da oferta energética que resulte em redução significativa de complicações, mortalidade e custos.

Increased MMA concentration and body mass index are associated with spontaneous abortion in Brazilian women A pilot study

Background: The pathophysiology of spontaneous abortion is complex and may involve the interaction of genetic and environmental factors. We evaluated the predictors of spontaneous abortion in Brazilian pregnant women. The effects of age, gestational age. body mass index (BMI), cigarette smoking, alcohol ingestion, use of multivitamins and concentrations of vitamins (folate, cobalamin and vitamin 136) and vitamin-dependent metabolites were analyzed. Methods: Study population included 100 healthy women that attended pre-natal care in 2 health centers of Sao Paulo, Brazil, and in whom pregnancy outcome was known. Folate and cobalamin status was measured in blood specimens collected between 4 and 16 weeks. The genotypes for 8 gene polymorphisms were evaluated by PCR-RFLP. Results: Eighty-eight women had normal pregnancy outcome (Group 1), while 12 experienced a miscarriage after blood collection (Group 2). Increased methylmalonic acid (MMA) concentrations were found in Group 2 (median [25th-75th percentile]=274 [149-425] nmol/l) relative to Group 1 (138 [98-185]) (P<0.01). No differences between the groups were observed for serum cobalamin, serum or red cell folate, and serum total homocysteine or allele frequencies for 8 polymorphisms. In a conditional logistic regression analysis including age, gestational age, serum creatinine, MMA, cystathionine, body mass index (BMI), cigarette smoking, alcohol ingestion and use of multivitamins the risk of abortion was significantly associated with MMA (OR [95% CI] = 3.80 [1.36, 10.62] per quartile increase in MMA), BMI (OR [95% CI] = 5.49 [1.29,23.39] per quartile) and gestational age (OR [95% CI] = 0.10 [0.01, 0.77] per increase of interval in gestational age). Conclusions: Increased serum MMA and BMI concentrations are associated with spontaneous abortion in Brazilian women. (C) 2009 Elsevier B.V. All rights reserved.

Environmental Risk Factors for Parkinson's Disease

Parkinson’s disease (PD) is a progressive, degenerative, neurological disease. The progressive disability associated with PD results in substantial burdens for those with the condition, their families and society in terms of increased health resource use, earnings loss of affected individuals and family caregivers, poorer quality of life, caregiver burden, disrupted family relationships, decreased social and leisure activities, and deteriorating emotional well-being. Currently, no cure is available and the efficacy of available treatments, such as medication and surgical interventions, decreases with longer duration of the disease. Whilst the cause of PD is unknown, genetic and environmental factors are believed to contribute to its aetiology. Descriptive and analytical epidemiological studies have been conducted in a number of countries in an effort to elucidate the cause, or causes, of PD. Rural residency, farming, well water consumption, pesticide exposure, metals and solvents have been implicated as potential risk factors for PD in some previous epidemiological studies. However, there is substantial disagreement between the results of existing studies. Therefore, the role of environmental exposures in the aetiology of PD remains unclear. The main component of this thesis consists of a case-control study that assessed the contribution of environmental exposures to the risk of developing PD. An existing, previously unanalysed, dataset from a local case-control study was analysed to inform the design of the new case-control study. The analysis results suggested that regular exposure to pesticides and head injury were important risk factors for PD. However, due to the substantial limitations of this existing study, further confirmation of these results was desirable with a more robustly designed epidemiological study. A new exposure measurement instrument (a structured interviewer-delivered questionnaire) was developed for the new case-control study to obtain data on demographic, lifestyle, environmental and medical factors. Prior to its use in the case-control study, the questionnaire was assessed for test-retest repeatability in a series of 32 PD cases and 29 healthy sex-, age- and residential suburb-matched electoral roll controls. High repeatability was demonstrated for lifestyle exposures, such as smoking and coffee/tea consumption (kappas 0.70-1.00). The majority of environmental exposures, including use of pesticides, solvents and exposure to metal dusts and fumes, also showed high repeatability (kappas >0.78). A consecutive series of 163 PD case participants was recruited from a neurology clinic in Brisbane. One hundred and fifty-one (151) control participants were randomly selected from the Australian Commonwealth Electoral Roll and individually matched to the PD cases on age (± 2 years), sex and current residential suburb. Participants ranged in age from 40-89 years (mean age 67 years). Exposure data were collected in face-to-face interviews. Odds ratios and 95% confidence intervals were calculated using conditional logistic regression for matched sets in SAS version 9.1. Consistent with previous studies, ever having been a regular smoker or coffee drinker was inversely associated with PD with dose-response relationships evident for packyears smoked and number of cups of coffee drunk per day. Passive smoking from ever having lived with a smoker or worked in a smoky workplace was also inversely related to PD. Ever having been a regular tea drinker was associated with decreased odds of PD. Hobby gardening was inversely associated with PD. However, use of fungicides in the home garden or occupationally was associated with increased odds of PD. Exposure to welding fumes, cleaning solvents, or thinners occupationally was associated with increased odds of PD. Ever having resided in a rural or remote area was inversely associated with PD. Ever having resided on a farm was only associated with moderately increased odds of PD. Whilst the current study’s results suggest that environmental exposures on their own are only modest contributors to overall PD risk, the possibility that interaction with genetic factors may additively or synergistically increase risk should be considered. The results of this research support the theory that PD has a multifactorial aetiology and that environmental exposures are some of a number of factors to contribute to PD risk. There was also evidence of interaction between some factors (eg smoking and welding) to moderate PD risk.

A case-control study of employment status and mortality in a cohort of Australian youth

Recent studies have demonstrated a link in young populations between unemployment and ill health. The purpose of this study is to correlate mortality with employment status in two cohorts of young Australian males, aged 17-25 years, from 1984 to 1988. Two youth cohorts consisting of an initially unemployed sample (n = 1424 males) and a population sample (n = 4573 males), were surveyed annually throughout the study period. Those lost to follow-up during the survey period were matched with death registries across Australia. Employment status was determined from weekly diaries and death certificates and was designated as: employed or student; unemployed; not in the work force (excluding students). Conditional logistic regression, using age- and cohort- matched cases (deaths) and controls (alive), was used to estimate the odds ratio (OR) of dying with regard to employment status, taking into account potential confounders such as ethnicity, aboriginality, educational attainment, pre-existing health problems, socio-economic status of parents, and other factors. Twenty three male survey respondents were positively matched to death registry records. Compared to those employed or students (referent group), significantly elevated ORs were found to be associated with neither being in the workforce nor a student for all cause, external cause, and external cause mortality other than suicide. Odds ratios were adjusted for age, survey cohort, ethnicity, pre-existing physical and mental health status, education level, and socio-economic status of parent(s). A statistically significant increasing linear trend in odds ratios of male mortality for most cause groups was found across the employment categories, from those employed or student (lowest ORs), through those unemployed; to those not in the workforce (highest ORs). Suicide was higher, but not statistically significantly, in those unemployed or not in the workforce. Suicide also was associated, though not significantly, with the respondent not living with their parents when they were 14 years of age. No association was found between mortality and past unemployment experience, as measured by length of time spent unemployed, or the number of spells of unemployment experienced during the survey. The results of this study underscore the elevated risk to survival in young males as a consequence of being neither employed nor a student. (C) 1999 Elsevier Science Ltd. All rights reserved.

Risk factors for basal cell carcinoma: a case-control study

A controlled trial was performed with the purpose of investigating which factors could be considered of significant risk for the development of basal cell carcinoma. A total of 259 cases of basal cell carcinoma diagnosed from July 1991 to July 1992 were compared with 518 controls matched for age and sex. All subjects in both groups were white. Protocol data were submitted to statistical analysis by the chi-square test and by multiple conditional logistic regression analysis and the following conclusions were reached: 1) light skin color (types I and II of the Fitzpatrick classification), odds ratio of 2.8; outdoor work under constant sunlight, odds ratio of 5.0; the presence of actinic lesions due to exposure to the sun, odds ratio of 4.9, are risk factors perse. 2) Type III skin in the Fitzpatrick classification only represents a risk factor when the patient reports a history of intense sunburns, but not in the absence of such a history. 3) Sunburns per se do not represent a risk factor althorig the point made in item 2 of these conclusions is valid. 4) Other suspected risk factors whose significance was not confirmed by multiple conditioned logistic regression analysis were: residence in rural areas, light eyes and blond hair color, extent of the awareness of the "sun x skin cancer" relationship, familial occurrence of skin cancer, excessive exposure to the sun, and freckles appearing in childhood.