Statistical Analyses
Data analyses were performed using the Statistical Package for Social
Sciences program version 24.0 (IBM SPSS Statistics for Windows; IBM
Corp, Armonk, NY). Descriptive statistics in the form of frequencies and
percentages were reported for categorical variables and mean ± standard
deviation (SD) for continuous variables. The chi-square test was used to
compare categorical variables between the two groups (atorvastatin 80mg
users vs. atorvastatin 40mg users), and Student’s t-test was used to
compare continuous variables between the two groups.
Cox proportional hazard regression analysis was used to assess the
association between atorvastatin doses and time-to-primary composite
outcome and secondary effectiveness outcomes at 1 month and 12 months
following discharge. The 1-month and 12-month Cox proportional hazard
models were adjusted for clinically relevant variables. The results were
presented as unadjusted hazard ratio and adjusted hazard ratio (aHR)
with 95% confidence intervals (CIs). A P-value of <0.05 was
used to indicate statistical significance. Furthermore, multivariate
logistic regression was used to determine the predictors of prescribing
atorvastatin 80mg among ACS patients. Sixteen clinically relevant
variables were included in the logistic regression model, using the
backward stepwise likelihood ratio with the probability of entry of 0.05
and removal of 0.10 at each step. The results are presented as adjusted
odds ratio (aOR) with corresponding 95% CI. A P-value of
<0.05 was used for statistical significance.