Open Access

Publication Rules

NRS Rules for the Release of Readership Estimates 6, 12 and 24-Month Databases

These rules determine, for any given publication, the minimum database period for which NRS publishes estimates, and the minimum recommended database period for conducting special analyses - 6 months (denoted on the database by the letter H in the published tables), 12 months (denoted by the letter Y) or 24 months (denoted by the letter T). Notwithstanding anything in the following rules, estimates for newspaper supplements will be released on the same database period as estimates for their parent newspapers.

A. Release of Estimates

The normal minimum database period on which estimates are released by the survey is 6 months. However in the case of titles newly added to the survey, the intention is to release estimates for such titles after as short a period of measurement as possible, subject to the title first achieving a specified level of unweighted readership. The rules are as follows:

1. No estimates for any title newly added to the survey will be released on less than one month’s fieldwork. Where a title is newly launched, no estimates for that title will be released until at least four consecutive issues have been published.
2. Subject to 1 above, estimates for a title newly added to the survey will first be released when the title achieves a minimum of 175 unweighted AIR respondents. If such an estimate is released on less than a 6-month sample, subsequent estimates will be based on the cumulative monthly sample achieved by the title until a 6-month database has been accumulated.
3. Thereafter estimates for such a title will be released on a rolling 6-month database, and rolling 12-month estimates will also be released as soon as a 12-month database has been accumulated.
4. If this minimum of 175 unweighted AIR respondents is not reached after 6 months, but is reached after 7 to 12 months of measurement, the first estimate released will relate to the period in which the sample threshold is reached (e.g. 7 months January-July, 8 months January-August, etc). Once such an estimate is released, further estimates for the title will be released based on the cumulative monthly sample achieved by the title until a 12-month database has been achieved. Subsequent estimates will then be based on a rolling 12-month database.
5. If this minimum of 175 unweighted AIR respondents is not reached after 12 months, a title may have estimates released if it achieves at least 225 unweighted AIR respondents over 24 months. However, if it reaches this threshold after 12 but before 24 months of measurement, no estimate will be released for the title until a full 24 months’ measurement has been completed (because of the procedure under which the 24-month estimates are produced. - further details of that procedure are available from either NRS Ltd or Ipsos-MORI).
6. If a title does not achieve at least 225 unweighted AIR respondents after 24 months no estimates will be released.

B. Changing Database Periods

Once a title has estimates released on a 6, 12 or 24-month database period as described above, the database period on which subsequent estimates are based may change, as determined by the following rules. Estimates for newspaper supplements will be published on the same minimum database period as their respective parent newspaper.

1. From 24 months to 12 months

   Estimates for a title on a 24-month database will be transferred to a 12-month database if the title achieves an unweighted AIR sample of at least 175 respondents in any 12-month period ending in June. The media list will be reviewed each year once data to June are available, and any qualifying titles will have 12-month estimates released for the following February-January and subsequent periods. Once estimates are released on a 12-month database, release of estimates on a 24-month database will cease.

2. From 12 months to 6 months

   Estimates for a title on a 12-month database will also be released on a 6-month database if the title achieves an unweighted AIR sample of at least 175 respondents in each of two consecutive 6-month periods, such a total 12-month period ending in June. As in B 1) above, the media list will be reviewed each year once data to June are available, and any qualifying titles will have 6-month estimates released for the following August-January and subsequent periods. 12-month estimates for such titles will continue to be released.

Transferring to a Longer Database Period
3. From 6 months to 12 months

   Estimates for a title released on a 6-month database will cease to be released if the title’s 6-month unweighted AIR sample falls below 175 respondents for two consecutive 6-month periods, this total 12-month period ending in June. The media list will be reviewed each year once data to June are available, and any qualifying title will cease to have 6-month estimates released from the following January. 12-month estimates for such titles will continue to be released, subject to C 2) below.

4. From 12 months to 24 months

   Estimates for a title released on a 12-month database will cease to be released, and be replaced by estimates based on a 24-month database, if the title’s 12-month unweighted AIR sample falls below 175 respondents for two consecutive 12-month periods, this total 24-month period ending in June. The media list will be reviewed each year once data to June are available, and any qualifying title will cease to have 12-month estimates released for periods beginning the following January. Estimates based on 24 months will then be released, subject to rule D below.

C. Cessation of Released Estimates

Estimates for a title released on a 24-month database will cease to be released if the weighted all-adult estimates for the title are such that, for two consecutive 24-month periods ending in June, the title’s all-adult estimate for each period falls below the lower limit of the 95% confidence interval of a theoretical all-adult estimate of 0.3%. The media list will be reviewed each year once data to June are available, and the last estimates released for such a title will be for the period ending that December. The intention of this rule is to avoid any title being removed from the survey if the shortfall against the required minimum could be the result only of sample variation, rather than a real diminution of readership below 0.3% of all adults.

D. All Titles Measured by the Survey

Whilst being subject to the above rules, the addition of a title new to the survey sometimes raises unexpected issues. Each addition will therefore be reviewed by Ipsos MORI and NRS Ltd, and should any such issues be judged to arise, they will be brought to the attention of the NRS Development Advisory Group and, where appropriate, the NRS Board.