Quasi-least squares regression method with dentistry data

In dentistry, single-jaw surgery or double-jaw surgery is performed depending on the patient's need to correct severe skeletal malocclusions. The effect of these surgical methods used in treatment is to be investigated with quasi-least squares regression (QLS), which is a new data analysis method for correlated data obtained by extending generalized estimating equations (GEE).

The aim of this study is to investigate whether jaw surgery methods (single jaw and double jaw) and time are effective on some outcome variables (C point menton distance, cervical plane angle, distance from point C to pogonion perpendicular, angle between cervical plane and facial plane) using QLS method.

In application, 114 measurements were performed on the lateral cephalometric radiographs of 34 patients aged 18 years and older who received orthodontic treatment and underwent surgery in the period of 2000-2018. The effects of time and group variables on four dependent variables were investigated and evaluated using QLS and GEE methods.

Single-jaw surgery and double-jaw surgery as a group variable on all outcome variables were not significant. Among the working correlation structures used in QLS, the highest correlation value was obtained by "Markov" working correlation structure.

Single-jaw surgery and double-jaw surgery were found to be statistically insignificant for outcome variables examined. QLS is superior to GEE in cases where repeated measurements are performed at unequal time intervals and there are missing observations.