Imputing missing values using cumulative linear regression. Issue 3 (30th August 2019)

• Record Type: Journal Article
• Authors: Mostafa, Samih M.
• Is Part Of: CAAI transactions on intelligence technology. Volume 4:Issue 3(2019)
• Page Start: 182
• Page End: 200
• Publication Date: 2019-08-30
• Subjects: regression analysis -- mean square error methods -- estimation theory -- data handling; cumulative linear regression -- statistical methods -- imputation algorithm -- linear regression technique -- imputed variables -- linear regression equation -- imputation time -- missing data handling -- missing values -- root‐mean‐square error -- mean absolute error -- coefficient of determination; C1140Z Other topics in statistics -- C4130 Interpolation and function approximation (numerical analysis) -- C6130 Data handling techniques; Artificial intelligence -- Periodicals; Computer science -- Periodicals; Artificial intelligence; Computer science; Electronic journals; Periodicals; 006.305
• DOI: 10.1049/trit.2019.0032
• Languages: English
• ISSNs: 2468-6557

Abstract

Abstract : The concept of missing data is important to apply statistical methods on the dataset. Statisticians and researchers may end up to an inaccurate illation about the data if the missing data are not handled properly. Of late, Python and R provide diverse packages for handling missing data. In this study, an imputation algorithm, cumulative linear regression, is proposed. The proposed algorithm depends on the linear regression technique. It differs from the existing methods, in that it cumulates the imputed variables; those variables will be incorporated in the linear regression equation to filling in the missing values in the next incomplete variable. The author performed a comparative study of the proposed method and those packages. The performance was measured in terms of imputation time, root‐mean‐square error, mean absolute error, and coefficient of determination ( R 2 ) . On analysing on five datasets with different missing values generated from different mechanisms, it was observed that the performances vary depending on the size, missing percentage, and the missingness mechanism. The results showed that the performance of the proposed method is slightly better.