2.5 | Statistical analysis
We conducted all of the statistical analyses using complex sample procedures of the Statistical Package for the Social Sciences (SPSS) software program version 21.0 (IBM Corp., Armonk, NY, USA). Because the KYRBS data were collected through a representative, stratified, and clustered sampling method (as a statistical representative of the general population), data from the survey were weighed based on the sample design. Descriptive statistics were used to depict the basic characteristics of the study population. The chi-square test for categorical variables and independent t-test for continuous variables were used appropriately to compare the general characteristics between subjects with and without asthma. Following the selection of significant covariates using univariable logistic regression analysis, multivariate logistic regression analysis was carried out to determine which sleep-related factors (e.g., sleep satisfaction, sleep duration, and WCUS) were independently contributing to the risk of suicidal ideation in adolescent asthmatics: Model 1 adjusted for sex and grade; Model 2 adjusted for Model 1 variables + socioeconomic variables (residential type, SES, and academic achievement) and health-related behavioral variables (breakfast skipping, smoking, alcohol drinking, and vigorous exercise); and Model 3 adjusted for Model 2 variables + psychological variables (perceived status of health, perceived level of happiness, perceived frequency of stress, and experience of depressive symptoms). The results were expressed using adjusted odds ratios (OR) and 95% confidence intervals (CI). Statistical significance was indicated byp- values < 0.05 in all tests.