Data Quality for Analytics Using SAS

Chapter 18: Influence of Data Completeness on Model Quality in Predictive Modeling

18.1 Introduction

General

Random and systematic missing values

Missing values in the scoring data partition

18.2 Simulation Methodology and Data Preparation

Inserting random missing values

Inserting systematic missing values

Replacing missing values

Process flow

Simulation scenarios

18.3 Results for Random Missing Values

Random missing values only in the training data

Random missing values in the training and scoring data

Business case

18.4 Results for Systematic Missing Values

Systematic missing values only in the training data

Systematic missing values in the training and scoring data

18.5 Comparison of Results between Different Scenarios

Introduction

Graphical ...