Sas survey procedure

Statistical analyses were performed using the SAS survey procedure (version 9.4; SAS Institute, Cary, NC, USA) to reflect the complex sampling design. Values are presented as mean values ± standard deviation (SD) for continuous variables, and as numbers and percentages (%) for categorical variables. The distribution of TG levels was considerably skewed and was log-transformed before the statistical analysis. The t-test and chi-square test were used to discuss differences of clinical measurements. Pearson’s correlation coefficient was used to evaluate the relationship between sUA levels and variables (BMI, WC, BP, total cholesterol (TC), low-density lipoprotein cholesterol (LDL-C), HDL-C, TG, and FPG). Multivariate logistic regression analysis was performed to estimate the association of hyperuricemia with MetS, its various components, and general obesity. We calculated the adjusted odds ratio (OR) with its 95% confidence interval (95% CI). Subgroup analyses were conducted after categorizing the subjects according to age, sex, and presence of MetS with or without general obesity. The statistical tests were two-sided, and a p value <0.05 was considered statistically significant.

Statistical analyses were performed using the SAS survey procedure (ver. 9.3; SAS Institute, Cary, NC, USA) to reflect the complex sampling design and sampling weights of KNHANES and to provide nationally representative prevalence estimates. The procedures included unequal probabilities of selection, oversampling, and nonresponse so that inferences could be made about the Korean adolescent participants.
The prevalence and 95% confidence intervals (CIs) for CL were calculated. In the univariate analysis, the Rao-Scott chi-square test (using PROC SURVEYFREQ in SAS) was used to test the association between CL and risk factors in a complex sampling design. Participants’ characteristics were described using means and standard errors for continuous variables and numbers and percentages for categorical variables. Multiple logistic regression analyses were used to examine the association between CL and PM₁₀. First, we adjusted for age and gender (Model 1). Then, we adjusted for age, gender, and other confounders that showed borderline significant differences f (P < 0.150) (Model 2). P-values were two-tailed and a P < 0.05 was considered significant.

All data are presented as means and SE or as proportions. Descriptive analysis was used to assess the characteristics of subjects.
To examine the differences in BMI, WC, total body fat, and trunk fat with the prevalence of UI, χ² analysis was employed. Multivariate logistic regression analyses were used to estimate the odds ratios (ORs) and 95% confidence intervals (CIs) to examine the associations between the prevalence of UI and obesity. Statistical analyses were performed using the SAS survey procedure (version 9.2; SAS Institute, Inc., Cary, NC, USA) to reflect the complex sampling design. Statistical significance was considered for P values was <.05.

The nationwide data were analyzed statistically using the SAS survey procedure (version 9.3; SAS Institute, Cary, NC) to examine the association between CL, tinnitus, and risk factors in a complex sampling design. To reflect nationwide prevalence estimates, sample weights from the KNHANES were applied in all analyses as described previously [14 (link)]. All P-values were two-sided, and P < 0.05 was considered statistically significant.
Participants’ characteristics were described using the mean and standard error (SE) for continuous variables, and number and percentage (SE) for categorical variables. Multiple logistic regression analyses were used to test the association between CL and tinnitus. We first adjusted for age and sex (model 1); then, we adjusted for the variables in model 1 plus BMI (model 2); and, finally, for the variables in model 2 plus smoking status, alcohol consumption, regular exercise, MetS, ELhsg and depressed mood (model 3). In addition, the interaction of sex and the association between CL and tinnitus was investigated.

The data in Table 1 are presented as mean±SE for continuous variables or as % (SE) for categorical variables, and t-tests or χ² tests were done, respectively. The association between ASM and PTAs of 0.5, 1, 2, 4 kHz was presented as Pearson’s correlation, and age-adjusted linear regression was used to verify the relationship between body composition variables and PTAs. Multiple logistic regression analyses were also performed to estimate the association between ASM and hearing loss. And we presented as OR (95% CI) after adjusting for certain factors in each model using hierarchical analysis (model 1: adjusted for age; model 2: adjusted for age, current smoking, alcohol use, regular exercise, and body fat percentage; model 3: adjusted for age, current smoking, alcohol use, regular exercise, body fat percentage, education level, income level, and tinnitus; model 4: adjusted for all variables in model 3 plus hypertension, diabetes mellitus, and chronic kidney disease; model 5: adjusted for all variables in model 4 plus noise at work, noise outside work, and noise at any given moment). All statistical analyses were stratified by gender and performed using the SAS survey procedure (version 9.3; SAS Institute, Cary, NC, USA) to reflect the sampling weights and complex sampling design analyses of KNHANES. All data of P < 0.05 were accepted as statistically significant results.