EPM5005 - Data management and statistical computing

Leader: Dr D Sibbritt

Offered

Alfred Hospital First semester 2008 (Off-campus)

Synopsis

This unit will describe and demonstrate the complexity of data management and statistical computing methods. It will enable students to communicate effectively about the issues in storing and retrieving information, and in assessing the quality and limitations of data repositories. It uses examples from real data sets to give students practical skills in design, data management, assessment of data quality and handling of large volumes of data.

Objectives

On completion of this unit students should be able to demonstrate:

1. Understanding of different sources and methods of data storage such as unit records, matrix files, longitudinal data, relational databases;
2. Understanding of relational database concepts and design, and other data structures;
3. Proficiency in the handling and analysis of large data sets;
4. Skills in data manipulation and management using the major statistical software packages;
5. Skills in linking files through unique and non-unique identifiers;
6. Understanding of data quality control and data entry methods, and experience in applying validation checks to data;
7. Skills in data cleaning, identification of outliers and data trimming using appropriate statistical methods;
8. Understanding of processes leading to finalisation of data sets prior to analysis;
9. Ability to communicate with researchers in data-related issues of design, conduct and analysis of studies.

Assessment

Written assignments
final examination

Co-requisites

MPH1040