An ordinal logistic regression model with misclassification of the outcome variable and categorical covariate

Ordinal outcomes are frequently employed in diagnosis and clinical trials. Clinical trials of Alzheimer's disease (AD) treatments are a case in point using the status of mild, moderate or severe disease as outcome measures. As in many other outcome oriented studies, the disease status may be misclassified. This study estimates the extent of misclassification in an ordinal outcome such as disease status. Also, this study estimates the extent of misclassification of a predictor variable such as genotype status. An ordinal logistic regression model is commonly used to model the relationship between disease status, the effect of treatment, and other predictive factors. A simulation study was done. First, data based on a set of hypothetical parameters and hypothetical rates of misclassification was created. Next, the maximum likelihood method was employed to generate likelihood equations accounting for misclassification. The Nelder-Mead Simplex method was used to solve for the misclassification and model parameters. Finally, this method was applied to an AD dataset to detect the amount of misclassification present. The estimates of the ordinal regression model parameters were close to the hypothetical parameters. β1 was hypothesized at 0.50 and the mean estimate was 0.488, β2 was hypothesized at 0.04 and the mean of the estimates was 0.04. Although the estimates for the rates of misclassification of X1 were not as close as β1 and β2, they validate this method. X 1 0-1 misclassification was hypothesized as 2.98% and the mean of the simulated estimates was 1.54% and, in the best case, the misclassification of k from high to medium was hypothesized at 4.87% and had a sample mean of 3.62%. In the AD dataset, the estimate for the odds ratio of X 1 of having both copies of the APOE 4 allele changed from an estimate of 1.377 to an estimate 1.418, demonstrating that the estimates of the odds ratio changed when the analysis includes adjustment for misclassification. ^

Attitudes of dental students to hand hygiene practices at a dental school

Objectives. The purpose of this study was to elucidate behavioral determinants (prevailing attitudes and beliefs) of hand hygiene practices among undergraduate dental students in a dental school. ^ Methods. Statistical modeling using the Integrative Behavioral Model (IBM) prediction was utilized to develop a questionnaire for evaluating behavioral perceptions of hand hygiene practices by dental school students. Self-report questionnaires were given to second, third and fourth year undergraduate dental students. Models representing two distinct hand hygiene practices, termed "elective in-dental school hand hygiene practice" and "inherent in-dental school hand hygiene practice" were tested using linear regression analysis. ^ Results. 58 responses were received (24.5%); the sample mean age was 26.6 years old and females comprised 51%. In our models, elective in-dental school hand hygiene practice and inherent in-dental school hand hygiene practice, explained 40% and 28%, respectively, of the variance in behavioral intention. Translation of community hand hygiene practice to the dental school setting is the predominant driver of elective hand hygiene practice. Intended elective in-school hand hygiene practice is further significantly predicted by students' self-efficacy. Students' attitudes, peer pressure of other dental students and clinic administrators, and role modeling had minimal effects. Inherent hand hygiene intent was strongly predicted by students' beliefs in the benefits of the activity and, to a lesser extent, role modeling. Inherent and elective community behaviors were insignificant. ^ Conclusions. This study provided significant insights into dental student's hand hygiene behavior and can form the basis for an effective behavioral intervention program designed to improve hand hygiene compliance.^

Estimating the mean and standard deviation of concentration distributions using censored samples

Environmental data sets of pollutant concentrations in air, water, and soil frequently include unquantified sample values reported only as being below the analytical method detection limit. These values, referred to as censored values, should be considered in the estimation of distribution parameters as each represents some value of pollutant concentration between zero and the detection limit. Most of the currently accepted methods for estimating the population parameters of environmental data sets containing censored values rely upon the assumption of an underlying normal (or transformed normal) distribution. This assumption can result in unacceptable levels of error in parameter estimation due to the unbounded left tail of the normal distribution. With the beta distribution, which is bounded by the same range of a distribution of concentrations, $\rm\lbrack0\le x\le1\rbrack,$ parameter estimation errors resulting from improper distribution bounds are avoided. This work developed a method that uses the beta distribution to estimate population parameters from censored environmental data sets and evaluated its performance in comparison to currently accepted methods that rely upon an underlying normal (or transformed normal) distribution. Data sets were generated assuming typical values encountered in environmental pollutant evaluation for mean, standard deviation, and number of variates. For each set of model values, data sets were generated assuming that the data was distributed either normally, lognormally, or according to a beta distribution. For varying levels of censoring, two established methods of parameter estimation, regression on normal ordered statistics, and regression on lognormal ordered statistics, were used to estimate the known mean and standard deviation of each data set. The method developed for this study, employing a beta distribution assumption, was also used to estimate parameters and the relative accuracy of all three methods were compared. For data sets of all three distribution types, and for censoring levels up to 50%, the performance of the new method equaled, if not exceeded, the performance of the two established methods. Because of its robustness in parameter estimation regardless of distribution type or censoring level, the method employing the beta distribution should be considered for full development in estimating parameters for censored environmental data sets. ^

Evaluation of androgenicity, abdominal adiposity, blood pressure and types of ovulatory patterns in a sample of women with menstrual irregularities

Objective: To determine the prevalence of and the relationships between the degree and source of hyperandrogenemia, ovulatory patterns and cardiovascular disease risk indicators (blood pressure, indices or amount of obesity and fat distribution) in women with menstrual irregularities seen at endocrinologists' clinic. Design: A cross-sectional study design. Participants: A sample of 159 women with menstrual irregularities, aged 15-44, seen at endocrinologists' clinic. Main Outcome Measures: androgen levels, body mass index (BMI), waist-hip ratio (WHR), systolic and diastolic blood pressure (SBP & DBP), source of androgens, ovulatory activity. Results: The prevalence of hyperandrogenemia was 54.7% in this study sample. As expected, women with acne or hirsutism had an odds ratio 12.5 (95%CI = 5.2-25.5) times and 36 (95%CI = 12.9-99.5) times more likely to have hyperandrogenemia than those without acne or hirsutism. The main findings of this study were the following: Hyperandrogenemic women were more likely to have oligomenorrheic cycles (OR = 3.8, 95%CI = 1.5-9.9), anovulatory cycles (OR = 6.6, 95%CI = 2.8-15.4), general obesity (BMI $\ge$ 27) (OR = 6.8, 95%CI = 2.2-27.2) and central obesity (WHR $\ge$ 127) (OR = 14.5, 95%CI = 6.1-38.7) than euandrogenemic women. Hyperandrogenemic women with non-suppressible androgens had a higher mean BMI (29.3 $\pm$ 8.9) than those with suppressible androgens (27.9 $\pm$ 7.9); the converse was true for abdominal adiposity (WHR). Hyperandrogenemic women had a 2.4 odds ratio (95%CI = 1.0-6.2) for an elevated SBP and a 2.7 odds ratio (95%CI = 0.8-8.8) for elevated DBP. When age differences were accounted for, this relationship was strengthened and further strengthened when sources of androgens were controlled. When the differences in BMI were controlled, the odds ratio for elevated SBP in hyperandrogenemic women increased to 8.8 (95%CI = 1.1-69.9). When the age, the source of androgens, the amount of obesity and the type of obesity were controlled, hyperandrogenemic women had 13.5 (95%CI = 1.1-158.9) odds ratio for elevated SBP. Conclusions: In this study population, the presence of menstrual irregularities are highly predictive for the presence of elevated androgens. Women with elevated androgens have a high risk for obesity, more specifically for central obesity. The androgenemic status is an independent predictor of blood pressure elevation. It is probable that in the general population, the presence of menstrual irregularities are predictive of hyperandrogenemia. There is a great need for a population study of the prevalence of hyperandrogenemia and for longitudinal studies in hyperandrogenemic women (adrenarche to menopause) to investigate the evolution of these relationships. ^

The effect of yoga on cardiovascular health as measured by heart rate variability in a sample of breast cancer patients

The study is a three-armed randomized controlled trial comparing values for heart rate variability (HRV), a measure of cardiovascular health, throughout a yoga intervention of breast cancer patients undergoing radiotherapy. Patients attended either a yoga (n=45), stretch, (n=46), or control (n=42) condition 3 times per week for 6 weeks of radiation. Electrocardiograms (ECGs) were conducted on each participant to provide the values necessary for HRV analysis. Analyses focused on examining scores for those participants with HRV baseline values considered to be below the cutoff point for healthy HRV levels, defined by the authors as below the cutpoint of 68 ms. From the entire sample of 133 with available baselines, 26 yogis, 26 stretchers, and 23 controls were determined to be “pathologic” in terms of HRV, and selected for follow-up analysis at 3 weeks and then again at 6 weeks. Though no statistically significant differences were found between either group means at each timepoint or group change score means, the yoga group had consistently higher mean score and mean change scores. These findings are suggestive and indicate the need to refine the use of ECGs and HRV analysis programs to more accurately and comprehensively assess the effects of yoga on cardiovascular health in cancer patients.^