Sas version 9.2 for windows

Sex differences in demographic and socioeconomic characteristics were evaluated by using χ² tests (categorical variables) and t-tests or Wilcoxon rank sum tests (continuous variables). Demographic, clinical and lifestyle factors across SES levels were compared using χ² tests (for categorical variables) or analysis of variance (ANOVA) (for continuous variables). Intensity of PA in METs were square root transformed to approximate normal distribution and then used to calculate lsmean and 95% confidence interval (CI) accounting for age and sex by SES levels. Trends in participation rates of PA by SES were evaluated by Cochran-Mantel-Haenszel χ² tests, while those in intensity of PA by SES were evaluated by ANOVA. Potential dose-response relationship of SEI score with PA intensity (METs) was evaluated using restricted cubic splines (RCS). Beta coefficients and 95% CIs for each SES component related to PA intensity (METs) were derived from generalized linear modeling (GLM). Tests for linear trend were performed by entering the categorical variables as continuous parameters in the adjusted models. All analyses were performed using SAS version 9.2 for windows (SAS Institute, Cary, North Carolina), and all tests of statistical significance were based on two-tailed probability.

Statistical analysis was performed using SAS version 9.2 for Windows (SAS Institute, Cary, North Carolina). Clinical and electrophysiological characteristics were expressed as means ± standard deviations (SD) for continuous data, or as frequency and percent for ordinal data. Comparisons between treatment responders and non-responders were made using the student’s t-test, the Wilcoxon rank-sum test, or the χ2-test, depending on the type and distribution of the variable. Normality was tested using the Shapiro-Wilk test. The number of criteria met for each of the EFNS/PNS, AAN, and study criteria definitions of CIDP were treated as ordinal variables, and univariable logistic regression models were run using responder status as the dependent variable, and “number of criteria met” as the independent variables. We report the regression coefficients, p-values, and odds ratios for each independent variable. Additionally, receiver operating characteristic (ROC) curves and the corresponding area-under-the-curve (AUC) using Responder Status as the gold-standard measure were generated for each independent variable. The analysis was completed for the entire cohort, as well as for the diabetes and non-diabetes subgroups. Significance was set at α-level of 0.05.

Categorical variables were compared between exposed and non-exposed children using χ²-tests. Age of the children, which was non-normally distributed (Kolmogorov-Smirnov test for normality p = 0.003), was compared using a Mann-Whitney test. Nonsmoking and smoking caregivers were compared on questions of the effects of smoking on the child’s kidneys, cholesterol, and blood pressure withχ²-tests. Fisher’s exact tests were used to determine whether the number of missing responses differed between the non-smoking and smoking caregivers on these questions. To account for missing data, best/worst case scenario analysis was performed by assigning “no” responses to non-smoking caregivers with missing data, and “yes” responses to smoking caregivers with missing data. For descriptive statistics, frequencies were expressed as the percent of non-missing responses. Age was reported as the median and interquartile range (IQR). Data were analyzed with SAS version 9.2 for Windows^® (SAS Institute, Cary, NC, USA). A p-value less than 0.05 was considered statistically significant.

All data are presented as mean ± standard error or as a percentage (standard error). Logarithmic transformation was performed to achieve normal distribution when necessary. A student’s t-test or chi-square test was used to investigate the differences in the presence of periodontal treatment needs according to the variables. Multiple logistic regression analyses were used to assess the associations of periodontal treatment needs and consumption of carbonated beverages. The model was adjusted for age, sex, body mass index, smoking, drinking, exercise, metabolic syndrome, frequency of tooth brushing per day, use of secondary oral products, dental examination within a year, and consumption of beer and coffee. A survey procedure of a statistical software package (SAS version 9.2 for Windows, SAS Institute, Cary, NC, USA) was used for statistical analysis to account for the complex sampling design. Two-sided P values of < 0.05 were considered statistically significant.

Statistical analysis was performed using SAS version 9.2 for Windows (SAS Institute, Cary, North Carolina). Baseline participant characteristics were expressed as means ± standard deviations (SD) for continuous data, or as frequency and percentage for categorical data. Continuous data was assessed for normality (Shapiro-Wilk). For each small fibre test, results were dichotomized into normal and abnormal based on reference values, and differences in characteristics between normal and abnormal participants were assessed using the student’s t-test, the Wilcoxon rank-sum test, or the χ²-test (depending on the type and distribution of the variable). Cohen’s kappa coefficient was used to determine agreement among the dichotomized small fiber tests. Pearson correlation coefficients between LDI_Flare area values and clinical and electrophysiological characteristics were calculated. The Benjamini-Hochberg procedure was used to adjust for multiple comparisons between the three different dichotomizations of normal and abnormal small fiber test results in the following categories of variables: abnormal examination findings, nerve conduction studies, and small fiber tests and VPT. Due to the exploratory nature of this study, the false discovery rate for this procedure was set at 0.10, otherwise, significance was set at α-level of 0.05.

All data are presented as the mean ± standard error or as % (standard error). The Chi-square test for categorical variables or the independent t test for continuous variables was performed to assess the differences in characteristics according to the number of teeth. Multiple logistic regression analyses were performed to assess the associations between the number of teeth and diabetic retinopathy. For multivariate analysis, the participants were divided into 3 groups based on the numbers of remaining teeth:  < 20, 20 to 27, and ≥28. Model 1 was age- and sex-adjusted, whereas Model 2 was adjusted for the variables in Model 1 and BMI, smoking, drinking, exercise, and hypertension. Model 3 was adjusted for the variables in Model 2 and glycated hemoglobin (HbA1c) level, duration of diabetes mellitus, frequency of brushing, and frequency of using extra dental care. The survey procedure of SAS version 9.2 for Windows (SAS Institute, Cary, NC) was used for statistical analyses to account for the complex sampling design. Two-sided P values of < .05 were considered statistically significant.