Abstract
A graphic procedure for determining whether a statistically significant change in television ratings has occurred is proposed. The method takes into account the fact that the ratings are generated from the same sample of viewers rather than from two independent samples. In addition it incorporates the effect of sample size. The method is applicable for the analysis of all market research data collected by such panel methods.
Highlights
Television ratings are due to appear on the South African scene shortly
These ratings will be based on information collected from television monitors installed in 500 South African homes, which have been carefully chosen so as to be representative of South African television viewership
If k is the rating for programme 1, this means that a significant difference in viewership can be claimed in such a situation only when the rating difference exceeds the level: 3,841 + v'3,841 2 + 30,728Nk
Summary
Television ratings are due to appear on the South African scene shortly. These ratings will be based on information collected from television monitors installed in 500 South African homes, which have been carefully chosen so as to be representative of South African television viewership. These ratings will be of considerable interest to advertisers, and, in particular, advertisers will want to test whether changes in ratings for particular programmes reflect a real change in popularity or whether the change is the result of sampling error. The important parameters are found to be sample size, the (lower) rating, and the proportion of viewership common to both ratings
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
