الفهرس 
Imputation of Missing Values using Cluster wise Regression : A Mathematical Programming Approach
AbstractOnly 14 pages are availabe for public view
 |  | from | 83 |  |  |
| | | from | 83 | | |
Abstract
The presence of missing values in heterogeneous datasets – that is, datasets partitioned into homogenous clusters with respect to the relationship between the explanatory variables and the response variable – necessitates the use of two or more regression models subjected to a single objective function that best summarizes the structure of the dataset, for imputing the missing values. This can be done using the clusterwise regression model. Three imputation methods based on the clusterwise linear regression, namely: the largest cluster, the simple weighting, and the inverse distance weighting imputation methods are proposed in this thesis. The idea is to estimate the clusterwise linear regression through the mathematical programming approach of Ismail (2019)on the basis of the complete set of observations, and then integrate the estimated clusterwise regression linear model in the proposed imputation methods, to impute the missing values in the response variable. The performance of the proposed imputation methods are evaluated through a simulation study under the missing at random (MAR) mechanism with different percentages of missing values.