On Graphically Checking Goodness-of-fit of Binary Logistic Regression Models

OBJECTIVES: This paper is concerned with checking goodness-of-fit of binary logistic regression models. For the practitioners of data analysis, the broad classes of procedures for checking goodness-of-fit available in the literature are described. The challenges of model checking in the context of binary logistic regression are reviewed. As a viable solution, a simple graphical procedure for checking goodness-of-fit is proposed. METHODS: The graphical procedure proposed relies on pieces of information available from any logistic analysis; the focus is on combining and presenting these in an informative way. RESULTS: The information gained using this approach is presented with three examples. In the discussion, the proposed method is put into context and compared with other graphical procedures for checking goodness-of-fit of binary logistic models available in the literature. CONCLUSION: A simple graphical method can significantly improve the understanding of any logistic regression analysis and help to prevent faulty conclusions.

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.

Daily Physical Activities and Sports in Adult Survivors of Childhood Cancer and Healthy Controls: A Population-Based Questionnaire Survey

Background Healthy lifestyle including sufficient physical activity may mitigate or prevent adverse long-term effects of childhood cancer. We described daily physical activities and sports in childhood cancer survivors and controls, and assessed determinants of both activity patterns. Methodology/Principal Findings The Swiss Childhood Cancer Survivor Study is a questionnaire survey including all children diagnosed with cancer 1976–2003 at age 0–15 years, registered in the Swiss Childhood Cancer Registry, who survived ≥5years and reached adulthood (≥20years). Controls came from the population-based Swiss Health Survey. We compared the two populations and determined risk factors for both outcomes in separate multivariable logistic regression models. The sample included 1058 survivors and 5593 controls (response rates 78% and 66%). Sufficient daily physical activities were reported by 52% (n = 521) of survivors and 37% (n = 2069) of controls (p<0.001). In contrast, 62% (n = 640) of survivors and 65% (n = 3635) of controls reported engaging in sports (p = 0.067). Risk factors for insufficient daily activities in both populations were: older age (OR for ≥35years: 1.5, 95CI 1.2–2.0), female gender (OR 1.6, 95CI 1.3–1.9), French/Italian Speaking (OR 1.4, 95CI 1.1–1.7), and higher education (OR for university education: 2.0, 95CI 1.5–2.6). Risk factors for no sports were: being a survivor (OR 1.3, 95CI 1.1–1.6), older age (OR for ≥35years: 1.4, 95CI 1.1–1.8), migration background (OR 1.5, 95CI 1.3–1.8), French/Italian speaking (OR 1.4, 95CI 1.2–1.7), lower education (OR for compulsory schooling only: 1.6, 95CI 1.2–2.2), being married (OR 1.7, 95CI 1.5–2.0), having children (OR 1.3, 95CI 1.4–1.9), obesity (OR 2.4, 95CI 1.7–3.3), and smoking (OR 1.7, 95CI 1.5–2.1). Type of diagnosis was only associated with sports. Conclusions/Significance Physical activity levels in survivors were lower than recommended, but comparable to controls and mainly determined by socio-demographic and cultural factors. Strategies to improve physical activity levels could be similar as for the general population.

Response surface modeling of the interaction between propofol and sevoflurane

BACKGROUND: Propofol and sevoflurane display additivity for gamma-aminobutyric acid receptor activation, loss of consciousness, and tolerance of skin incision. Information about their interaction regarding electroencephalographic suppression is unavailable. This study examined this interaction as well as the interaction on the probability of tolerance of shake and shout and three noxious stimulations by using a response surface methodology. METHODS: Sixty patients preoperatively received different combined concentrations of propofol (0-12 microg/ml) and sevoflurane (0-3.5 vol.%) according to a crisscross design (274 concentration pairs, 3 to 6 per patient). After having reached pseudo-steady state, the authors recorded bispectral index, state and response entropy and the response to shake and shout, tetanic stimulation, laryngeal mask airway insertion, and laryngoscopy. For the analysis of the probability of tolerance by logistic regression, a Greco interaction model was used. For the separate analysis of bispectral index, state and response entropy suppression, a fractional Emax Greco model was used. All calculations were performed with NONMEM V (GloboMax LLC, Hanover, MD). RESULTS: Additivity was found for all endpoints, the Ce(50, PROP)/Ce(50, SEVO) for bispectral index suppression was 3.68 microg. ml(-1)/ 1.53 vol.%, for tolerance of shake and shout 2.34 microg . ml(-1)/ 1.03 vol.%, tetanic stimulation 5.34 microg . ml(-1)/ 2.11 vol.%, laryngeal mask airway insertion 5.92 microg. ml(-1) / 2.55 vol.%, and laryngoscopy 6.55 microg. ml(-1)/2.83 vol.%. CONCLUSION: For both electroencephalographic suppression and tolerance to stimulation, the interaction of propofol and sevoflurane was identified as additive. The response surface data can be used for more rational dose finding in case of sequential and coadministration of propofol and sevoflurane.

Temporal trends in the characteristics of children at antiretroviral therapy initiation in southern Africa: the IeDEA-SA Collaboration

BACKGROUND Since 2005, increasing numbers of children have started antiretroviral therapy (ART) in sub-Saharan Africa and, in recent years, WHO and country treatment guidelines have recommended ART initiation for all infants and very young children, and at higher CD4 thresholds for older children. We examined temporal changes in patient and regimen characteristics at ART start using data from 12 cohorts in 4 countries participating in the IeDEA-SA collaboration. METHODOLOGY/PRINCIPAL FINDINGS Data from 30,300 ART-naïve children aged <16 years at ART initiation who started therapy between 2005 and 2010 were analysed. We examined changes in median values for continuous variables using the Cuzick's test for trend over time. We also examined changes in the proportions of patients with particular disease severity characteristics (expressed as a binary variable e.g. WHO Stage III/IV vs I/II) using logistic regression. Between 2005 and 2010 the number of children starting ART each year increased and median age declined from 63 months (2006) to 56 months (2010). Both the proportion of children <1 year and ≥10 years of age increased from 12 to 19% and 18 to 22% respectively. Children had less severe disease at ART initiation in later years with significant declines in the percentage with severe immunosuppression (81 to 63%), WHO Stage III/IV disease (75 to 62%), severe anemia (12 to 7%) and weight-for-age z-score<-3 (31 to 28%). Similar results were seen when restricting to infants with significant declines in the proportion with severe immunodeficiency (98 to 82%) and Stage III/IV disease (81 to 63%). First-line regimen use followed country guidelines. CONCLUSIONS/SIGNIFICANCE Between 2005 and 2010 increasing numbers of children have initiated ART with a decline in disease severity at start of therapy. However, even in 2010, a substantial number of infants and children started ART with advanced disease. These results highlight the importance of efforts to improve access to HIV diagnostic testing and ART in children.

Why do individuals behave differently in commons dilemmas?: The case of alpine farmers using common property pastures in Grindelwald, Switzerland

The sustainable use of common-pool resources depends on users’ behaviour with regards to appropriation and provision. Most knowledge about behaviour in such situations comes from experimental research. As experiments take place in confined environments, motivational drivers and actions in the field might differ. This paper analyses farmers’ use of common property pastures in Grindelwald, Switzerland. Binary logistic regression is applied to survey data to explore the effect of farmers’ attributes on livestock endowment, appropriation and provision behaviour. Furthermore, Q methodology is used to assess the impact of broader contextual variables on the sustainability of common property pastures. It is shown that the strongest associations exist between (a) socio-economic attributes and change in livestock endowment; (b) norms and appropriation behaviour; and (c) area and pay-off and provision behaviour. Relevant contextual variables are the economic value of the resource units, off-farm income opportunities, and the subsidy structure. We conclude that with increasing farm size farmers reduce the use and maintenance of common property. Additionally, we postulate that readiness to maintain a resource increases with appropriation activities and the net returns generated from appropriation.

Systematic analysis of factors associated with progression and regression of ulcerative colitis in 918 patients.

BACKGROUND Studies that systematically assess change in ulcerative colitis (UC) extent over time in adult patients are scarce. AIM To assess changes in disease extent over time and to evaluate clinical parameters associated with this change. METHODS Data from the Swiss IBD cohort study were analysed. We used logistic regression modelling to identify factors associated with a change in disease extent. RESULTS A total of 918 UC patients (45.3% females) were included. At diagnosis, UC patients presented with the following disease extent: proctitis [199 patients (21.7%)], left-sided colitis [338 patients (36.8%)] and extensive colitis/pancolitis [381 (41.5%)]. During a median disease duration of 9 [4-16] years, progression and regression was documented in 145 patients (15.8%) and 149 patients (16.2%) respectively. In addition, 624 patients (68.0%) had a stable disease extent. The following factors were identified to be associated with disease progression: treatment with systemic glucocorticoids [odds ratio (OR) 1.704, P = 0.025] and calcineurin inhibitors (OR: 2.716, P = 0.005). No specific factors were found to be associated with disease regression. CONCLUSIONS Over a median disease duration of 9 [4-16] years, about two-thirds of UC patients maintained the initial disease extent; the remaining one-third had experienced either progression or regression of the disease extent.