Scottish Health and Care Experience Survey 2013/14 - Technical Report
Scottish Health and Care Experience Survey 2013/14. This is a postal survey which was sent to a random sample of patients who were registered with a GP in Scotland in October 2013. This report contains details of the survey design and development.
Annex E Significance Testing
a. Comparison of results at National, NHS Board and CHP over the two survey periods (2011/12 and 2013/14)
For each question (where comparison is possible), the test statistic can be calculated as follows:
![Formula Formula](/binaries/content/gallery/publications/statistics-publication/2015/03/scottish-health-care-experience-survey-2013-14-technical-report/00473125.gif)
For a result in 2013/14 to be not statistically significantly different from 2011/12, then
![Formula Formula](/binaries/content/gallery/publications/statistics-publication/2015/03/scottish-health-care-experience-survey-2013-14-technical-report/00473126.gif)
To illustrate this, let the:
- percentage positive score in 20011/12 and 2013/14 for Scotland, an NHS Board or CHP be denoted by p1 and p2 respectively.
- number of valid responses in 2011/12 and 2013/14 be denoted by n1 and n2 respectively.
- design effect in years 2011/12 and 2013/14 be denoted as deff1 and deff2 respectively.
Then the standard error can be calculated as:
![Formula Formula](/binaries/content/gallery/publications/statistics-publication/2015/03/scottish-health-care-experience-survey-2013-14-technical-report/00473127.gif)
b. Comparison of results for NHS Board and CHP with Scotland
For each question (where comparison is applicable), the test statistic can be calculated as follows:
![Formula Formula](/binaries/content/gallery/publications/statistics-publication/2015/03/scottish-health-care-experience-survey-2013-14-technical-report/00473128.gif)
For the NHS Board or CHP to be not statistically significantly different from Scotland results, then
![Formula Formula](/binaries/content/gallery/publications/statistics-publication/2015/03/scottish-health-care-experience-survey-2013-14-technical-report/00473129.gif)
To illustrate this, let the:
- percentage positive score for NHS Board or CHP be denoted by pgeog.
- percentage positive score for Scotland be denoted by pScotland.
- number of valid responses for NHS Board or CHP (geography) be denoted by ngeog.
- number of valid responses for Scotland be denoted by nScotland.
- design effect for NHS Board or CHP and Scotland be denoted by deffgeog and deffScotland respectively.
Then the standard error can be calculated as
![Formula Formula](/binaries/content/gallery/publications/statistics-publication/2015/03/scottish-health-care-experience-survey-2013-14-technical-report/00473130.gif)
Contact
Email: Andrew Paterson
There is a problem
Thanks for your feedback