Sas enterprise guide software

Continuous variables were presented as means ± standard deviation (SD), and categorical variables as percentages (%). To compare the baseline characteristics of the study participants based on their metabolic health and obesity status, analysis of variance (ANOVA) and Scheffe’s test for post-hoc analysis or chi-square test was employed. Multiple imputation procedure was performed to impute the missing variables. The hazard ratio (HR) and 95% confidence interval (CI) for incident HF during the follow-up period for each group were determined by performing Cox proportional hazards analyses. Model 1 was adjusted for age, sex, and income; model 2 was further adjusted for smoking, alcohol drinking, and physical activities; model 3 was adjusted for TC, eGFR (eGFR <60 ml/min/1.73 m² or ≥60 ml/min/1.73 m²), AF, IHD, and COPD as well as for the variables included in model 2.
Initially, the risk of incident HF was assessed in terms of the baseline metabolic health and obesity status, with the MHNO group being considered as the reference group. Next, the transition of metabolic health and obesity status over 2 years, with the stable MHNO group as the reference group, was further analyzed. Statistical analyses were performed using the SAS Enterprise Guide software (version 7.1, SAS Institute, Inc., Cary, NC).

Descriptive statistics was used to describe the behaviour of the sows during the stays in the transfer vehicles. In addition, possible correlations between behavioural variables, the duration of the stay and the temperature in the vehicles were calculated using Spearman correlations. All statistical analyses were performed with SAS Enterprise Guide software (version 5.1, SAS Institute Inc., Cary, NC, USA). Results are presented per load and as medians across loads, except for temperature in the transfer vehicles, which is presented as mean ± STD per load. A probability level of p < 0.05 was considered statistically significant, whereas 0.05 < p < 0.10 was considered a tendency.

The primary outcome, resolution of the treated area of the AK lesion, was predetermined as either partial (resolution of the area covered by the microwave probe, but with a rim of persistent AK) or full resolution (complete resolution of the entire AK) over all time periods. Response was assessed at visits 3 (day 8), 4 (day 15), 6 (day 28), 8 (day 42), 10 (day 60) and 11 (day 120). Mixed‐effects logistic regression models analysed the effect of microwave therapy with random effects for participant and visit (≤ 6 per participant). Each visit was analysed as a categorical variable as they were spaced unequally in time. Variables representing sex, age, skin site (hand/scalp) and AK subtype (thick/thin) are included as covariates.
The secondary outcome of long‐term response was assessed using data from visits 10 and 11 (days 60 and 120) only. Again, nonlinear models were utilized with random effects for participant and visit (≤ 2 per participant) and covariates for sex, age, skin site (hand/scalp) and AK subtype (thick/thin).
Pain during and following treatment were secondary outcomes. SAS Enterprise Guide software (version 6·1, SAS Institute Inc., Cary, NC, USA) was used for all statistical analyses.