Analysis of missing values in simultaneous linear functional relationship model for circular variables

Missing values arise in many research fields and is a common problem in analysis. Unlike linear data, the methods proposed to handle missing values for circular variables have not been developed. This could be contributed to the closed form of circular variables. An imputation methods based on circular mean by column and sample circular mean are proposed for the simultaneous linear functional relationship model for circular variables. Simulation studies are conducted to assess the performance of the proposed methods. The results suggest that the proposed method provide an adequate approach in handling the presence of missing values for circular variables.