Health care systems are constantly evolving under the flow of enormous amounts of data. Almost every examination and treatment under the health care system is now digitally recorded, along with every outpatient and A&E attendance – the list goes on. The volume of data being generated is leading to information overload and the skills to make sense of all this data are becoming vital for those involved in the planning, commissioning or organisation of health services.
The full potential of data is often not realised and this is in part due to how its recorded, stored and managed. While data often provides valuable insight into what is going on in an organisation and how various processes could be improved, understanding the uncertainty associated with data due to improper coding, rounding errors, inaccuracies and missing records is key for developing reliable decision making tools. The aim of this course is to explore various properties of the data sets, understand their limitations, select and retrieve data and finally make sense of it. The completion of this course will act as a stepping stone towards more advanced modelling and analytical methods.
This course will also provide an intuitive introduction to applied statistical tools, fundamental statistical skills for data preparation, handling raw data as well as introducing participants to the causes of data uncertainty and it can be dealt with.
At the end of this module participants should be able to:
- Evaluate the importance of data and when and how to collect data for modelling purposes.
- Locate key sources of health and social care data
- Store and analyse data
- Distinguish between sources of variability: underlying statistical uncertainty (e.g. death, illness, travel time), uncertainty in the quality of data, about the future and variability that can be understood and managed (e.g. variation by time of day, season of year)
- Determine what techniques are appropriate for various types of data analysis
- Prepare data efficiently and effectively
- Undertake basic exploratory data analysis, interpret and effectively display the results of the analyses using tables and charts
- Use SPSS to carry out data analysis and produce reports.
- What is data?
- Importance of data
- Types and sources of data
- Primary and secondary data
- IT systems and databases
Data preparation and preliminary analysis
- Data preparation steps
- Data input, edit and modification
- Creating Pivot Tables/Charts
- Using a data dictionary
- Data cleaning: outliers and missing values
- Data Uncertainty
Hands-on Session using SPSS
- Data manipulation and preparation using SPSS
Exploratory data analysis (EDA)
- Rationale for EDA
- Different tools and methods for EDA
Hands-on session using SPSS
- EDA using SPSS
The course consists of one day’s face-to-face training at our central London campus.
For face-to-face delivery, a mixed structure is generally adopted. There is a blend of theoretical sessions introducing the topics and techniques of interest using examples to illustrate key themes. In the afternoon, interactive and hands-on experience of the tools commonly used to prepare and analyse data is provided via a computer lab session.
In order to take part in this module, potential participants will not need to have an specific skills or qualifications but a basic understanding of databases, elementary statistics and Microsoft Excel will certainly help those attending to get the most from the course.
The software tools used in this module include SPSS and Microsoft Excel.
Prof. Thierry Chaussalet: HSCMG@westminster.ac.uk
Tel: +44 (0)20 3506 4575