Prevalence estimation

Following Dunn and Everitt,(5) we ask the following questions of a survey report.

• Do the authors clearly define the sampled population?

• Do the authors discuss similarities and possible differences between their sampled population and the stated target population?

• Do the authors report what sampling mechanism has been used?

• Is the sampling mechanism random? If not, why not?

• Exactly what sort of random sampling mechanism has been used?

• Do the methods of data analysis make allowances for the sampling mechanism used?

Of course, it is vital that what counts as a case should be explained in absolute detail, including the method of eliciting symptoms (e.g. structured interview schedule), screening items, additional impairment criteria, and so on, as well as operational criteria or algorithms used in making a diagnosis. In the following we concentrate on the statistical issues. First, we consider survey design (and the associated sampling mechanisms), and then we move on to discuss the implications of design for the subsequent analysis of the results.

Booze Basher

Booze Basher

Get All The Support And Guidance You Need To Permanently STOP The Battle With Alcohol Once And For All. This Book Is One Of The Most Valuable Resources In The World When It Comes To Transformational Tools For Battling Booze Binges And Staying Alcohol-Free.

Get My Free Ebook


Post a comment