Skip to main content

Table 2 Multiple Linear Regression Model for Predictors of Sleep Quality using an Adaptive LASSO-penalized variable selection method

From: Sleep quality and nocturnal pain in patients with femoroacetabular impingement and acetabular dysplasia

Bootstrapped Adaptive LASSO Parameter Estimates
Model Outcome and Predictor Variablesa Mean Estimate SD 95% CI Standardized Estimate Adjusted R2 VIF
PSQI Total      0.4041  
 Intercept 20.2082 1.6311 17.0903 to 23.4622 0   0
 HOOS Pain −0.0794 0.0194 −0.1150 to −0.0430 −0.3609   1.1553
 SF12 Role Emotional −0.0817 0.0292 − 0.1405 to − 0.0320 −0.2635   1.3337
 SF12 Mental Health −0.0653 0.0293 −0.1263 to − 0.0199 −0.1678   1.3234
  1. Note. The adaptive LASSO estimates were based on 10,000 bootstrap samples of the model; Mean Estimate = bootstrap parameter estimate (regression coefficient); SD Standard deviation of the mean parameter estimate; 95% CI for the mean parameter estimate; For the 95% CI that does not contain zero (0), the respective mean parameter estimate is statistically significant at alpha = 0.05 (two-tailed); Standardized Estimate = bootstrap standardized regression coefficient; Adjusted R-squared is the model R-squared based on the adaptive LASSO-penalized variable selection; VIF Variance Inflation Factor. Observed sample, N = 115. aPredictor variables were selected from a pool of 39 potential predictor variables via the adaptive LASSO-penalized variable selection method (which performs simultaneous variable selection and parameter estimation) in the context of a linear regression model that was based on 10,000 bootstrap samples. PSQI Total Pittsburgh Sleep Quality Index Total Score, HOOS Pain Hip disability and Osteoarthritis Outcome Score (Pain subscale), SF12 Short Form Health Survey (subscales for Role Emotional and Mental Health)