Statistical analysis

Descriptive statistics were used to characterize the study sample and summarize their responses. In order to assess the precision of our survey results, 95% confidence intervals (95% CIs) were calculated for the descriptive results of some key outcomes, using bootstrapping with 1000 iterations of the sample [32, 33]. Multivariable logistic regression analysis was performed to determine if the response to the main outcome about the location of the scar (Q12) depended on various other demographic predictor variables. The number of predictor variables tested in the model depended on the descriptive results to the outcome variable, according to the generally accepted guideline of 10 events per variable [34–39]. Also as per best practices, the predictor variables were selected for testing in the regression model based on our expectations of their relevancy, not on prior statistical testing [37–40].