Open Access Open Access  Restricted Access Subscription Access

Research Frame work of Missing Data Analysis using Mathematical Models

A. Finny Belwin, A. Linda Sherin

Abstract


Abstract

This article deals with providing an overall framework of missing data analysis using mathematical models. Mathematical models serves at large for missing data imputation. Several algorithms in machine learning techniques like Mean, Median, Standard Deviation, Regression and Naïve Bayesian classifier use Mathematical models for analysis. The performance of above mathematical models has been compared by using correlation statistics analysis gives the imputed values are positively related or negatively related or not related with each other. To evaluate the performance of missing values can be measured by using nonparametric approach to inference on multivariate categorical data, which set the bounds to the data imputation. Based upon the performance of nonparametric approach to inference on multivariate categorical data, the imputed missing values are increasing or decreasing or a bounded monotonic sequence of finite limit and also analyzing that every bounded sequence of missing values has a convergent subsequence. Recognizing the above as a specific Poisson process probability gives an easy and exact way of constructing a practical decision indicator. This comes at the cost of requiring the appropriate boundedness conditions. To evaluate the performance, the standard machine learning repository dataset can be used. This article focuses primarily on how to implement Mathematical models to perform imputation of missing values.

 

Keywords: Imputation, Knowledge Transfer, missing data, Mathematical Models, Boundedness conditions, data patterns, multivariate data, multiple imputation.


Keywords


Imputation, Knowledge Transfer, missing data, Mathematical Models, Boundedness conditions, data patterns, multivariate data, multiple imputation.

Full Text:

PDF

Refbacks

  • There are currently no refbacks.