TAMS revisions
On 2 July 2012, TAMS (Television and Audience Measurement Survey) implemented the new 2011 population updates from IHS Global Insight. These updates, which see the total adult 15+ population growing by 2.7%, had a significant impact on the TAMS results, because there are some differences in the model that the research house uses to determine the population profile, compared to the model used by the previous demographers.
When applied to the TAMS meter universe, a growth of 6% in the household universe and 1.5% in the 4+ universe occurs. In addition, the universe update brought significant changes within the data with respect to changes in the TAMS profiles in terms of age, population group and LSM. Significant movements were also seen in areas such as Gauteng, Reef etc.
The industry should carefully examine these population changes, bearing them in mind when dealing with changed audience results, as there can be some trend-line breaks. These are particularly marked when using audience numbers (thousands) as opposed to share percentages.
However, the universe update was not the only change to TAMS in the last months. On 6 August 2012, several RIMS were also 'unbundled' (LSM, gender and language), which led to a substantial change in the weighting of the data.
In the past, SAARF stabilised certain audiences by grouping LSMs together, for weighting purposes. For household weighting, one of the most important ones was the grouping of LSM 1-5 together. In the new scheme, LSM 1-4 is now grouped together and LSM 5 is weighted on its own.
People using LSM 5 as a target market will find that due to this change, significant changes in thousands can be seen and therefore should be careful of trending back. Going forward, the LSM individual weights will be stable, especially if using source periods after 6 August 2012.
Users must bear both these changes in mind, as these have had implications on planning target markets and performances, particularly in forecasting vs post campaigning, as the source period may have been on the old universe or pre-unbundling of RIMS and the projected period might have occurred after either one or both of these changes.
Where possible, it is recommended that users select source periods after 6 August 2012, to ensure that comparisons are equable.
SAARF and Nielsen are busy conducting further analyses on some major target markets and will provide further information, as soon as possible, to assist users of the data to understand the implications of the latest changes.
In general, one can say that users can compare audiences across these breaks, as the audiences were legitimately and correctly measured at each given point, with the best possible measure at that time. Users must keep the indicated changes in mind and the significant audience shifts that have occurred due to the two changes.
One can compare TAMS data from the January 2012 update to 2 July 2012, when there was the big universe change, due to the use of a new demographic contractor.
From the 2 July 2012 (universe update), the data is rebased to the new population. However, a completely new phase then started on the 6 August 2012 (unbundling of RIMS).
It is clear that all involved, including the members of the TAMS Council, underestimated the extent of the changes resulting from these two actions. SAARF will therefore be embarking on a communication campaign, and in-depth articles are being prepared to assist users to understand the two changes discussed above.
As there is a concern amongst certain stakeholders that the DStv audience share may be overstated, the SAARF board has decided that the TAMS audit process mentioned above will review this matter as well. Once the results are in, it will be communicated to stakeholders.
The board has also decided that in independent audit will be done of the TAMS survey by an international TAMS expert and a committee of the board has been appointed to draw up a brief for the intended audit.
