The way in which a survey is conducted affects the estimates it produces. The way in which the sample is obtained is arguably the most important factor, particularly for media measurement surveys.
The NRS is based on a random sample of adults aged 15+ in Great Britain.
Only specifically selected individuals can be interviewed to ensure that the sample is as representative as possible – there are no quotas and no substitutions.
People with identical demographic characteristics will have different reading habits according to their lifestyle and availability. NRS uses a random sample to reduce the bias towards people who are more likely to be available for interview than others.
It is difficult to correct for the ‘availability’ bias by weighting. It matters more for certain sorts of publication than others. Hence the importance of ensuring the most representative sample possible.
In order to ensure that the sample is random there are strict rules governing each stage of the decision of whom to interview:
- The areas – based on Output Areas, as defined by the Census
- The specific addresses to approach – drawn from the Postal Address File
- Who should be interviewed at each address – a random selection procedure based on the ages of household members
If you would like to know more about the sampling procedures, please refer to the Technical Information.
Sometimes we are asked why NRS doesn’t use an Internet Panel for the sample, as this would be less expensive and more convenient.
It is not possible to obtain an Internet Panel sample which is representative enough to provide a media currency. Online panels tend to be skewed towards particular sorts of respondent, especially heavy Internet users, and cannot represent non-Internet users. While weighting can help correct some of these differences, it is not enough for NRS purposes. Indeed, some Internet panels, such as YouGov, use NRS readership data to weight their own findings.
The following chart shows the proportion of the population likely to be represented by different sorts of sample: The NRS sample with a response rate of over 50%; a high quality quota sample; and an online panel.
INSERT CHART HERE
