Stata software 16

Descriptive statistics were expressed as frequencies or as medians with interquartile ranges for categorical and continuous variables, respectively. A logistic regression model was used to assess for variables associated with a cephalosporin allergy label. These variables were selected a priori based on clinical knowledge and previous research in children with other antibiotic allergies and included: sex, race/ethnicity, presence of a chronic condition, private or public insurance, and number of health care visits in the first two years of life.^{5 (link)}
Presence of penicillin allergy label was not incorporated into the regression model because in children, eventually labeled as both cephalosporin and penicillin allergic, the penicillin allergy does not always precede the cephalosporin allergy label. A chi square test was used to determine differences in the frequency of antibiotic prescribing based on allergy label status. A two-sided 5% significance level (P < 0.05) was used for all statistical inferences, and all analyses were conducted using Stata software 16 (StataCorp).

All the statistical analyses were performed using STATA software 16.1 (StataCorp LP, College Station, TX, USA). Study data were sample weighted against the total national registered population of Thailand in 2009, and methods for complex survey design analysis were applied (14 (link)). The baseline characteristics of study subjects were compared between groups using descriptive statistics. Parametric and non-parametric tests were applied depending on the distribution of data. Kruskal-Wallis test and chi-square test were used for continuous and categorical variables, respectively. A p < 0.05 was considered statistically significant for all tests. The association between groups and all-cause mortality was explored using univariate and multivariate Cox proportional hazards models. The proportional hazards assumption was checked on the basis of Schoenfeld residuals. There was no evidence that the proportional-hazards assumption was violated. Multivariate models were adjusted for potentially confounding factors, including age, residential area, diabetes, chronic kidney disease, cardiovascular disease, cerebrovascular disease, and history of smoking. The results of multivariate analysis are shown as hazard ratio (HR) and 95% confidence interval (CI) for univariate analysis, and as adjusted hazard ratio (aHR) and 95% CI for multivariate analysis.

All answers were reported as frequency and percentage for categorical variables and as median and interquartile range (p25–p75) for non-normally distributed continuous variables. Statistical differences between groups (age, experience and unit volume) were evaluated using Fisher’s exact test for categorical variables and non-parametric Kruskal–Wallis test for quantitative variables.
Statistical analysis was performed using Stata^® software 16.1 (StataCorp LP, College Station, Texas, USA) and a p-value < 0.05 was considered statistically significant.

Based on the JD-R Theory, we developed a conceptual model, as shown in Figure 1. The figure posits JD and JR directly and indirectly affect task performance because of their effects on burnout and work engagement. In addition, burnout and work engagement also have their own, separate direct effects on task performance.
We conducted analytical analyses using STATA software 16.0. Initially we sought to examine the participants' demographics to determine if there were correlations amongst all the variables. Second, we generated a structural equation modeling (SEM) analysis, to understand the direct and indirect effects of JD-R (the independent variable) on task performance through the hypothesized mediators, burnout, and work engagement using a maximum likelihood method of estimation. We also conducted regression analyses with extensive covariates, including personal characteristics. The results from the regression analyses are similar to those reported here. Results of regression analyses are not provided within this study but can be provided upon request. The common method variance analysis was performed, and the results showed that only 27% of the variance shared by JD-R, work engagement, burnout, and task performance items, suggesting common method variance was not an issue in the data.

Descriptive and Pearson’s correlation analyses were first undertaken to observe the sample characteristics and the correlations among all variables. Then, we conducted Structural Equation Modeling (SEM) analysis, with a bootstrapping approach of 1000 iterations, to examine the relation between ACEs, mindfulness, and PWB. SEM, differing from regression techniques, allows simultaneous examination of direct and indirect effects through mediating variables [62 (link)]. STATA software 16.0 was used for all analyses. In results not shown, we conducted regression analyses with extensive covariates, including personal and family characteristics, the results of which indicated that the relations among ACE, mindfulness, and PWB were similar with those reported here.