Multiple regression analysis predictor models in exotropia surgery.

We developed a statistical model based on multiple regression analysis from a sample population of 30 patients with intermittent exotropia who underwent bilateral recession of the lateral recti muscles. We also identified predictor variables, which accounted for most of the change in deviation per millimeter of surgery performed. The application of multiple regression analysis to the problem of exotropia may be limited by variation in predictor variables according to sample population, multicollinearity, measurement unreliability, and the unproven assumption that the preoperative calculation of effect per millimeter correlates well with postoperative clinical success. Controlled clinical trials are needed to determine the value of multiple regression analysis in exotropia surgery. Discriminant analysis may represent an alternative statistical technique with application to this particular problem.