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.

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.

Coronary Artery Stenoses: Accuracy of 64-Detector Row CT Angiography in Segments with Mild, Moderate, or Severe Calcification-A Subanalysis of the CORE-64 Trial

Purpose: To evaluate the influence of cross-sectional arc calcification on the diagnostic accuracy of computed tomography (CT) angiography compared with conventional coronary angiography for the detection of obstructive coronary artery disease (CAD). Materials and Methods: Institutional Review Board approval and written informed consent were obtained from all centers and participants for this HIPAA-compliant study. Overall, 4511 segments from 371 symptomatic patients (279 men, 92 women; median age, 61 years [interquartile range, 53-67 years]) with clinical suspicion of CAD from the CORE-64 multi-center study were included in the analysis. Two independent blinded observers evaluated the percentage of diameter stenosis and the circumferential extent of calcium (arc calcium). The accuracy of quantitative multidetector CT angiography to depict substantial (>50%) stenoses was assessed by using quantitative coronary angiography (QCA). Cross-sectional arc calcium was rated on a segment level as follows: noncalcified or mild (<90 degrees), moderate (90 degrees-180 degrees), or severe (>180 degrees) calcification. Univariable and multivariable logistic regression, receiver operation characteristic curve, and clustering methods were used for statistical analyses. Results: A total of 1099 segments had mild calcification, 503 had moderate calcification, 338 had severe calcification, and 2571 segments were noncalcified. Calcified segments were highly associated (P < .001) with disagreement between CTA and QCA in multivariable analysis after controlling for sex, age, heart rate, and image quality. The prevalence of CAD was 5.4% in noncalcified segments, 15.0% in mildly calcified segments, 27.0% in moderately calcified segments, and 43.0% in severely calcified segments. A significant difference was found in area under the receiver operating characteristic curves (noncalcified: 0.86, mildly calcified: 0.85, moderately calcified: 0.82, severely calcified: 0.81; P < .05). Conclusion: In a symptomatic patient population, segment-based coronary artery calcification significantly decreased agreement between multidetector CT angiography and QCA to detect a coronary stenosis of at least 50%.

Common mental disorders during pregnancy and adverse obstetric outcomes

Methods. A prospective cohort study was conducted with 831 pregnant women from antenatal clinics in primary healthcare in Sao Paulo, Brazil. The clinical interview schedule-revised and demographic questionnaires were administered between the 20th and 30th weeks of gestation. Information on infant weight and gestational age at birth were obtained from hospital records. Univariate analyses were used to examine the association between the main exposure and main outcomes. Statistical associations were examined with chimultivariable logistic regression model. Results. The prevalence of CMD during gestation was 33.6 (95% CI: 30.4-36.9). The follow-up rate was 99.5%. Sixty three (7.6%) newborns were classified as LBW and 56 (6.9%) were classified as PTB. CMD during pregnancy was not associated with risk of PTB (adjusted OR:1.03, 95% CI: 0.57-1.88) or LBW (adjusted OR:1.09, 95% CI: 0.62-1.91). Conclusions. CMD prevalence is high among low-income and low-risk pregnant women attended by public health services in a middle-income country, but not confer an increased risk for adverse obstetric outcome.

Cigarette smoking and risk of epithelial ovarian cancer (Australia)

Objectives: We studied the association between cigarette smoking and ovarian cancer in a population-based case-control study. Methods: A total of 794 women with histologically confirmed epithelial ovarian cancer who were aged 18-79 years and resident in one of three Australian states were interviewed, together with 855 controls aged 18-79 years selected at random from the electoral roll from the same states. Information was obtained about cigarette smoking and other factors including age, parity, oral contraceptive use, and reproductive factors. We estimated the relative risk of ovarian cancer associated with cigarette smoking, accounting for histologic type, using multivariable logistic regression to adjust for confounding factors. Results: Women who had ever smoked cigarettes were more likely to develop ovarian cancer than women who had never smoked (adjusted odds ratio (OR) = 1.5; 95% confidence interval (CI) = 1.2-1.9). Risk was greater for ovarian cancers of borderline malignancy (OR = 2.4; 95% CI = 1.4-4.1) than for invasive tumors (OR = 1.7; 95% CI = 1.2-2.4) and the histologic subtype most strongly associated overall was the mucinous subtype among both current smokers (OR = 3.2; 95% CI = 1.8-5.7) and past smokers (OR = 2.3; 95% CI = 1.3-3.9). Conclusions: These data extend recent findings and suggest that cigarette smoking is a risk factor for ovarian cancer, especially mucinous and borderline mucinous types. From a public health viewpoint, this is one of the few reports of a potentially avoidable risk factor for ovarian cancer.

Gender differences in the association between tooth loss and obesity among older adults in Brazil

OBJECTIVE To analyze if differences according to gender exists in the association between tooth loss and obesity among older adults.METHODS We analyzed data on 1,704 older adults (60 years and over) from the baseline of a prospective cohort study conducted in Florianopolis, SC, Southern Brazil. Multivariable logistic regression models were used to assess the association between tooth loss and general and central obesity after adjustment for confounders (age, gender, skin color, educational attainment, income, smoking, physical activity, use of dentures, hypertension, and diabetes). Linear regressions were also assessed with body mass index and waist circumference as continuous outcomes. Interaction between gender and tooth loss was further assessed.RESULTS Overall mean body mass index was 28.0 kg/m2. Mean waist circumference was 96.8 cm for males and 92.6 cm for females. Increasing tooth loss was positively associated with increased body mass index and waist circumference after adjustment for confounders. Edentates had 1.4 (95%CI 1.1;1.9) times higher odds of being centrally obese than individuals with a higher number of teeth; however, the association lost significance after adjustment for confounders. In comparison with edentate males, edentate females presented a twofold higher adjusted prevalence of general and central obesity. In the joint effects model, edentate females had a 3.8 (95%CI 2.2;6.6) times higher odds to be centrally obese in comparison with males with more than 10 teeth present in both the arches. Similarly, females with less than 10 teeth in at least one arch had a 2.7 (95%CI 1.6;4.4) times higher odds ratio of having central obesity in comparison with males with more than 10 teeth present in both the arches.CONCLUSIONS Central obesity was more prevalent than general obesity among the older adults. We did not observe any association between general obesity and tooth loss. The association between central obesity and tooth loss depends on gender – females with tooth loss had greater probability of being obese.

ASSOCIATION BETWEEN SMOKING, CRACK COCAINE ABUSE AND THE DISCONTINUATION OF COMBINATION ANTIRETROVIRAL THERAPY IN RECIFE, PERNAMBUCO, BRAZIL

Despite the effectiveness of combination antiretroviral therapy in the treatment of people living with HIV/AIDS (PLWHA), nonadherence to medication has become a major threat to its effectiveness. This study aimed to estimate the prevalence of self-reported irregular use of antiretroviral therapy and the factors associated with such an irregularity in PLWHA. A cross-sectional study of PLWHA who attended two referral centers in the city of Recife, in Northeastern Brazil, between June 2007 and October 2009 was carried out. The study analyzed socioeconomic factors, social service support and personal habits associated with nonadherence to antiretroviral therapy, adjusted by multivariable logistic regression analysis. The prevalence of PLWHA who reported irregular use of combination antiretroviral therapy (cART) was 25.7%. In the final multivariate model, the irregular use of cART was associated with the following variables: being aged less than 40 years (OR = 1.66, 95%-CI: 1.29-2.13), current smokers (OR = 1.76, 95%-CI: 1.31-2.37) or former smokers (OR = 1.43, 95%-CI: 1.05-1.95), and crack cocaine users (OR = 2.79, 95%-CI: 1.24-6.32). Special measures should be directed towards each of the following groups: individuals aged less than 40 years, smokers, former smokers and crack cocaine users. Measures for giving up smoking and crack cocaine should be incorporated into HIV-control programs in order to promote greater adherence to antiretroviral drugs and thus improve the quality of life and prolong life expectancy.