Handling missing data in medical questionnaires : a comparative study

• Main Author: Woon, Eric Sing Yong.
• Other Authors: School of Electrical and Electronic Engineering
• Format: Final Year Project
• Language: English
• Published: 2012
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Control engineering
• Online Access: http://hdl.handle.net/10356/49602
• Institution: Nanyang Technological University

Missing Data plagues almost all researchers’ surveys or designed experiments. No matter how carefully they try to design their surveys to have their questions to be fully responded, , Missing data can still occur due to questions being unanswered or technical fault in the system. The problem lies with dealing with missing data, once it has been deemed impossible to recover the actual missing values. Traditional approaches used by researchers to handle missing data include case deletion and mean imputation. These methods are fast and easy to be implement however they do not preserve the relationships among the different variables, thus inflating the correlation. This report will look and compare different methods to overcome the problem of missing data.