Multinomial goodness-of-fit: large sample tests with survey design correction and exact tests for small samples

I introduce the new mgof command to compute distributional tests for discrete (categorical, multinomial) variables. The command supports largesample tests for complex survey designs and exact tests for small samples as well as classic large-sample x2-approximation tests based on Pearson’s X2, the likelihood ratio, or any other statistic from the power-divergence family (Cressie and Read, 1984, Journal of the Royal Statistical Society, Series B (Methodological) 46: 440–464). The complex survey correction is based on the approach by Rao and Scott (1981, Journal of the American Statistical Association 76: 221–230) and parallels the survey design correction used for independence tests in svy: tabulate. mgof computes the exact tests by using Monte Carlo methods or exhaustive enumeration. mgof also provides an exact one-sample Kolmogorov–Smirnov test for discrete data.

Consistent estimation of the fixed effects ordered logit model

The paper considers panel data methods for estimating ordered logit models with individual-specific correlated unobserved heterogeneity. We show that a popular approach is inconsistent, whereas some consistent and efficient estimators are available, including minimum distance and generalized method-of-moment estimators. A Monte Carlo study reveals the good properties of an alternative estimator that has not been considered in econometric applications before, is simple to implement and almost as efficient. An illustrative application based on data from the German Socio-Economic Panel confirms the large negative effect of unemployment on life satisfaction that has been found in the previous literature.

Identification and estimation of thresholds in the fixed effects ordered logit model

This paper proposes a new estimator for the fixed effects ordered logit model. In contrast to existing methods, the new procedure allows estimating the thresholds. The empirical relevance and simplicity of implementation is illustrated in an application on the effect of unemployment on life satisfaction.

MGOF: Stata module to perform goodness-of-fit tests for multinomial data

mgof computes goodness-of-fit tests for the distribution of a discrete (categorical, multinomial) variable. The default is to perform classical large sample chi-squared approximation tests based on Pearson's X2 statistic and the log likelihood ratio (G2) statistic or a statistic from the Cressie-Read family. Alternatively, mgof computes exact tests using Monte Carlo methods or exhaustive enumeration. A Kolmogorov-Smirnov test for discrete data is also provided. The moremata package, also available from SSC, is required.

Multinomial goodness-of-fit: large sample tests with survey design correction and exact tests for small samples

A new Stata command called -mgof- is introduced. The command is used to compute distributional tests for discrete (categorical, multinomial) variables. Apart from classic large sample $\chi^2$-approximation tests based on Pearson's $X^2$, the likelihood ratio, or any other statistic from the power-divergence family (Cressie and Read 1984), large sample tests for complex survey designs and exact tests for small samples are supported. The complex survey correction is based on the approach by Rao and Scott (1981) and parallels the survey design correction used for independence tests in -svy:tabulate-. The exact tests are computed using Monte Carlo methods or exhaustive enumeration. An exact Kolmogorov-Smirnov test for discrete data is also provided.

Renal insufficiency is independently associated with a distal distribution pattern of symptomatic lower-limb atherosclerosis

Objectives The purpose of this study was to assess the impact of renal insufficiency (RI) on the distribution pattern of peripheral arterial disease (PAD). We hypothesised that RI is associated with a distally accentuated involvement of the peripheral arterial tree. Design This is a retrospective analysis. Materials and Methods Analysis was based on a consecutive series of 2709 patients with chronic PAD of atherosclerotic origin undergoing primary endovascular treatment of lower-extremity arteries. Atherosclerotic pattern was grouped into femoropopliteal (n = 2085) and infragenicular (n = 892) disease according to target lesions treated while using iliac disease (n = 1133) as reference. Univariable and multivariable multinomial regression analyses were performed to assess relation with RI. Results are shown as relative risk ratio (RRRs) with 95% confidence intervals (95% CIs). A p < 0.05 was considered statistically significant. RI was defined as glomerular filtration rate (GFR) < 60 ml min−1 1.73 m−2. Results Presence of RI was an independent risk factor for a centrifugal lesion pattern (RRR 1.48, 95% CI: 1.17–1.86, p = 0.001). Moreover, a decrease in GFR by 10 ml min−1 1.73 m−2 was associated with an RRR of 1.08 for below-the-knee arterial disease (95% CI: 1.03–1.13, p = 0.003). Conclusion Presence and severity of RI are independent predictors of a distal obstructive pattern in patients with symptomatic PAD.

Reporting of research quality characteristics of studies published in 6 major clinical dental specialty journals

The objective of this article was to record reporting characteristics related to study quality of research published in major specialty dental journals with the highest impact factor (Journal of Endodontics, Journal of Oral and Maxillofacial Surgery, American Journal of Orthodontics and Dentofacial Orthopedics; Pediatric Dentistry, Journal of Clinical Periodontology, and International Journal of Prosthetic Dentistry). The included articles were classified into the following 3 broad subject categories: (1) cross-sectional (snap-shot), (2) observational, and (3) interventional. Multinomial logistic regression was conducted for effect estimation using the journal as the response and randomization, sample calculation, confounding discussed, multivariate analysis, effect measurement, and confidence intervals as the explanatory variables. The results showed that cross-sectional studies were the dominant design (55%), whereas observational investigations accounted for 13%, and interventions/clinical trials for 32%. Reporting on quality characteristics was low for all variables: random allocation (15%), sample size calculation (7%), confounding issues/possible confounders (38%), effect measurements (16%), and multivariate analysis (21%). Eighty-four percent of the published articles reported a statistically significant main finding and only 13% presented confidence intervals. The Journal of Clinical Periodontology showed the highest probability of including quality characteristics in reporting results among all dental journals.

Association of cardiovascular risk factors with pattern of lower limb atherosclerosis in 2659 patients undergoing angioplasty

OBJECTIVES: Aim of this study is to correlate distribution pattern of lower limb atherosclerosis with cardiovascular risk factor profile of patients with peripheral arterial occlusive disease (PAD). PATIENTS AND METHODS: Analysis is based on a consecutive series of 2659 patients (1583 men, 1076 women, 70+/-11 years) with chronic PAD of atherosclerotic origin undergoing primary endovascular treatment of lower extremity arteries. Pattern of atherosclerosis was grouped into iliac (n=1166), femoropopliteal (n=2151) and infrageniculate (n=888) disease defined according to target lesions treated. A multivariable multinomial logistic regression analysis was performed to assess relation with age, gender and classical cardiovascular risk factors (diabetes mellitus, arterial hypertension, hypercholesterolemia, cigarette smoking) using femoropopliteal disease as reference. RESULTS: Iliac disease was associated with younger age (RRR 0.95 per year of age, 95%-CI 0.94-0.96, p<0.001), male gender (RRR 1.32, 95%-CI 1.09-1.59, p=0.004) and cigarette smoking (RRR 2.02, 95%-CI 1.68-2.42, p<0.001). Infrageniculate disease was associated with higher age (RRR 1.02, 95%-CI 1.01-1.02, p<0.001), male gender (RRR 1.23, 95%-CI 1.06-1.41, p=0.005) and diabetes mellitus (RRR 1.68, 95%-CI 1.47-1.92, p<0.001). Hypercholesterolemia was less prevalent in patients with lesions below the knee (RRR 0.82, 95%-CI 0.71-0.94, p=0.006), whereas no distinct pattern was apparent related to arterial hypertension. CONCLUSION: Clinical phenotype of peripheral atherosclerosis varies with prevalence of cardiovascular risk factors suggesting differences in mechanisms involved in iliac as compared with infrageniculate lesions. Identification of molecular mechanism might have influence on future therapeutic strategies in PAD patients.

Discordant responses to potent antiretroviral treatment in previously naive HIV-1-infected adults initiating treatment in resource-constrained countries: the antiretroviral therapy in low-income countries (ART-LINC) collaboration

OBJECTIVES: To assess the frequency of and risk factors for discordant responses at 6 months on highly active antiretroviral therapy (HAART) in previously treatment-naive HIV patients from resource-limited countries. METHODS: The Antiretroviral Therapy in Low-Income Countries Collaboration is a network of clinics providing care and treatment to HIV-infected patients in Africa, Latin America, and Asia. Patients who initiated therapy between 1996 and 2004, were aged 16 years or older, and had a baseline CD4 cell count were included in this analysis. Responses were defined based on plasma viral load (PVL) and CD4 cell count at 6 months as complete virologic and immunologic (VR(+)IR(+)), virologic only (VR(+)IR(-)), immunologic only (VR(-)IR(+)), and nonresponse (VR(-)IR(-)). Multinomial logistic regression was used to assess the association between therapy responses and clinical and demographic variables. RESULTS: Of the 3111 patients eligible for analysis, 1914 had available information at 6 months of therapy: 1074 (56.1%) were VR(+)IR(+), 364 (19.0%) were VR(+)IR(-), 283 (14.8%) were (VR(-)IR(+)), and 193 (10.1%) were VR(-)IR(-). OF THE 3111 patients eligible for analysis, 1914 had available information at 6 months of therapy: 1074 (56.1%) were VRIR, 364 (19.0%) were VRIR, 283 (14.8%) were (VRIR), and 193 (10.1%) were VRIR. Compared with complete responders, virologic-only responders were older, had a higher baseline CD4 cell count, had a lower baseline PVL, and were more likely to have received a nonstandard HAART regimen; immunologic-only responders were younger, had a lower baseline CD4 cell count, had a higher baseline PVL, and were more likely to have received a protease inhibitor-based regimen. CONCLUSIONS: The frequency of and risk factors for discordant responses were comparable to those observed in developed countries. Longer follow-up is needed to assess the long-term impact of discordant responses on mortality in these resource-limited settings.

Electronic medical record systems, data quality and loss to follow-up: survey of antiretroviral therapy programmes in resource-limited settings

OBJECTIVE: To describe the electronic medical databases used in antiretroviral therapy (ART) programmes in lower-income countries and assess the measures such programmes employ to maintain and improve data quality and reduce the loss of patients to follow-up. METHODS: In 15 countries of Africa, South America and Asia, a survey was conducted from December 2006 to February 2007 on the use of electronic medical record systems in ART programmes. Patients enrolled in the sites at the time of the survey but not seen during the previous 12 months were considered lost to follow-up. The quality of the data was assessed by computing the percentage of missing key variables (age, sex, clinical stage of HIV infection, CD4+ lymphocyte count and year of ART initiation). Associations between site characteristics (such as number of staff members dedicated to data management), measures to reduce loss to follow-up (such as the presence of staff dedicated to tracing patients) and data quality and loss to follow-up were analysed using multivariate logit models. FINDINGS: Twenty-one sites that together provided ART to 50 060 patients were included (median number of patients per site: 1000; interquartile range, IQR: 72-19 320). Eighteen sites (86%) used an electronic database for medical record-keeping; 15 (83%) such sites relied on software intended for personal or small business use. The median percentage of missing data for key variables per site was 10.9% (IQR: 2.0-18.9%) and declined with training in data management (odds ratio, OR: 0.58; 95% confidence interval, CI: 0.37-0.90) and weekly hours spent by a clerk on the database per 100 patients on ART (OR: 0.95; 95% CI: 0.90-0.99). About 10 weekly hours per 100 patients on ART were required to reduce missing data for key variables to below 10%. The median percentage of patients lost to follow-up 1 year after starting ART was 8.5% (IQR: 4.2-19.7%). Strategies to reduce loss to follow-up included outreach teams, community-based organizations and checking death registry data. Implementation of all three strategies substantially reduced losses to follow-up (OR: 0.17; 95% CI: 0.15-0.20). CONCLUSION: The quality of the data collected and the retention of patients in ART treatment programmes are unsatisfactory for many sites involved in the scale-up of ART in resource-limited settings, mainly because of insufficient staff trained to manage data and trace patients lost to follow-up.

Evaluation of a Bayesian MCMC Random Effects Inference Methodology for Capture-Mark-Recapture Data

Monte Carlo simulation was used to evaluate properties of a simple Bayesian MCMC analysis of the random effects model for single group Cormack-Jolly-Seber capture-recapture data. The MCMC method is applied to the model via a logit link, so parameters p, S are on a logit scale, where logit(S) is assumed to have, and is generated from, a normal distribution with mean μ and variance σ2 . Marginal prior distributions on logit(p) and μ were independent normal with mean zero and standard deviation 1.75 for logit(p) and 100 for μ ; hence minimally informative. Marginal prior distribution on σ2 was placed on τ2=1/σ2 as a gamma distribution with α=β=0.001 . The study design has 432 points spread over 5 factors: occasions (t) , new releases per occasion (u), p, μ , and σ . At each design point 100 independent trials were completed (hence 43,200 trials in total), each with sample size n=10,000 from the parameter posterior distribution. At 128 of these design points comparisons are made to previously reported results from a method of moments procedure. We looked at properties of point and interval inference on μ , and σ based on the posterior mean, median, and mode and equal-tailed 95% credibility interval. Bayesian inference did very well for the parameter μ , but under the conditions used here, MCMC inference performance for σ was mixed: poor for sparse data (i.e., only 7 occasions) or σ=0 , but good when there were sufficient data and not small σ .

Exploring the periodicity of cardiovascular events in Switzerland: Variation in deaths and hospitalizations across seasons, day of the week and hour of the day

Purpose The purpose of this study is to explore the periodical patterns of events and deaths related to cardiovascular disease (CVD), acute myocardial infarction (AMI) and stroke in Swiss adults (≥18years). Methods Mortality data for period 1969–2007 (N=869,863 CVD events) and hospitalization data for period 1997–2008 (N=959,990 CVD events) were used. The annual, weekly and circadian distribution of CVD-related deaths and events were assessed. Multivariate analysis was conducted using multinomial logistic regression adjusting for age, gender and calendar year and considering deaths from respiratory diseases, accidents or other causes as competitive events. Results CVD deaths and hospitalizations occurred less frequently in the summer months. Similar patterns were found for AMI and stroke. No significant weekly variation for CVD deaths was found. Stratification by age and gender showed subjects aged <65years to present a higher probability of dying on Mondays and Saturday, only for men. This finding was confirmed after multivariate adjustment. Finally, a circadian variation in CVD mortality was observed, with a first peak in the morning (8–12am) and a smaller second peak in the late afternoon (2–6pm). This pattern persisted after multivariate adjustment and was more pronounced for AMI than for stroke. Conclusion There is a periodicity of hospitalizations and deaths related to CVD, AMI and stroke in Switzerland. This pattern changes slightly according to the age and sex of the subjects. Although the underlying mechanisms are not fully identified, preventive measures should take into account these aspects to develop better strategies of prevention and management of CVD.

Adult parent-child relationships: Relationship quality, support, and reciprocity

In accordance with Bengtson's model of intergenerational solidarity (e.g. Bengtson & Roberts, 1991), the interrelations between adult daughters' family values, their perception of the relationship quality with their parents, the support they reported to give to and to receive from their parents, and their perception of reciprocity in intergenerational support exchange were investigated for N = 265 middle-aged women in Germany. It was also asked whether the support given to parents and perceived reciprocity are related to daughters' felt burden as a result of their support. Cross-sectional, self-report data were examined with multiple and multinomial logistic regression analyses. The analyses revealed positive relations between family values, relationship quality, and support to parents. Perceived reciprocity was associated with the exchange of intergenerational support and imbalance in support had negative effects on the relationship quality. Felt burden was predicted by the extent of support and the perceived reciprocity. However, specific correlational patterns depending on the kind of support as well as differences in the importance of mother and father occurred. The findings are discussed against the background of the meaning of family obligations and reciprocity in a Western culture.

Genotype-specific risk factors for Staphylococcus aureus in Swiss dairy herds with an elevated yield-corrected herd somatic cell count

Bovine mastitis is a frequent problem in Swiss dairy herds. One of the main pathogens causing significant economic loss is Staphylococcus aureus. Various Staph. aureus genotypes with different biological properties have been described. Genotype B (GTB) of Staph. aureus was identified as the most contagious and one of the most prevalent strains in Switzerland. The aim of this study was to identify risk factors associated with the herd-level presence of Staph. aureus GTB and Staph. aureus non-GTB in Swiss dairy herds with an elevated yield-corrected herd somatic cell count (YCHSCC). One hundred dairy herds with a mean YCHSCC between 200,000 and 300,000cells/mL in 2010 were recruited and each farm was visited once during milking. A standardized protocol investigating demography, mastitis management, cow husbandry, milking system, and milking routine was completed during the visit. A bulk tank milk (BTM) sample was analyzed by real-time PCR for the presence of Staph. aureus GTB to classify the herds into 2 groups: Staph. aureus GTB-positive and Staph. aureus GTB-negative. Moreover, quarter milk samples were aseptically collected for bacteriological culture from cows with a somatic cell count ≥150,000cells/mL on the last test-day before the visit. The culture results allowed us to allocate the Staph. aureus GTB-negative farms to Staph. aureus non-GTB and Staph. aureus-free groups. Multivariable multinomial logistic regression models were built to identify risk factors associated with the herd-level presence of Staph. aureus GTB and Staph. aureus non-GTB. The prevalence of Staph. aureus GTB herds was 16% (n=16), whereas that of Staph. aureus non-GTB herds was 38% (n=38). Herds that sent lactating cows to seasonal communal pastures had significantly higher odds of being infected with Staph. aureus GTB (odds ratio: 10.2, 95% CI: 1.9-56.6), compared with herds without communal pasturing. Herds that purchased heifers had significantly higher odds of being infected with Staph. aureus GTB (rather than Staph. aureus non-GTB) compared with herds without purchase of heifers. Furthermore, herds that did not use udder ointment as supportive therapy for acute mastitis had significantly higher odds of being infected with Staph. aureus GTB (odds ratio: 8.5, 95% CI: 1.6-58.4) or Staph. aureus non-GTB (odds ratio: 6.1, 95% CI: 1.3-27.8) than herds that used udder ointment occasionally or regularly. Herds in which the milker performed unrelated activities during milking had significantly higher odds of being infected with Staph. aureus GTB (rather than Staph. aureus non-GTB) compared with herds in which the milker did not perform unrelated activities at milking. Awareness of 4 potential risk factors identified in this study guides implementation of intervention strategies to improve udder health in both Staph. aureus GTB and Staph. aureus non-GTB herds.