November 2012 Information Session Line-up • IHS Demography & UE changes 2 July 2012 • Unbundling of Living Standards Measure (LSM) 6 August 2012 • Expansion Panel Plans • Metering • 2013 Universe Update schedule • TV Events Data Release 2 Copyright © 2011 The Nielsen Company. Confidential and proprietary. IHS Demography & UE changes 2 July 2012 IHS Global Insight estimates applies to AMPS 2011B TAMS Universe Update 2 July 2012: Move from 2011A to 2011B (6 month AMPS data) Adults 15+ TV Population 2011A 2011B #Difference % Difference Total TV Population 29 209 654 30 039 437 829 783 2.8 Nguni 11 027 342 11 979 797 952 455 Sotho English/ Other Afrikaans/ Both 9 997 586 3 433 374 4 751 351 10 236 856 3 194 837 4 627 947 239 270 -238 537 -123 404 8.6 2.4 -6.9 -2.6 LSM 1 – 4 LSM 5 LSM 6 LSM 7 LSM 8 LSM 9 LSM 10 4 727 909 5 609 036 7 031 159 3 862 070 2 784 117 3 007 468 2 187 894 4 889 073 5 630 683 7 518 738 3 876 841 2 889 648 3 129 350 2 105 104 161 164 21 647 487 579 14 771 105 531 121 882 -82 790 3.4 0.4 6.9 0.4 3.8 4.1 -3.8 Metropolitan 11 008 610 12 175 340 1 166 730 City/ Large Town Small Town/ Village Settlement/ Rural 4 320 409 3 795 804 10 084 831 4 452 069 3 812 746 9 599 280 131 660 16 942 -485 551 10.6 3.0 0.4 Significant increase Copyright © 2011 The Nielsen Company. Confidential and proprietary. Significant decrease -4.8 4 Universe Update 2011B Individuals by Province Current Pre July 5 SAARF TAM Information day Unbundling of Living Standards Measure (LSM) 6 August 2012 What do we mean by weighting? • The process by which the data of each individual in the sample is expanded to the universe so that the data released is representative of the South African population. • While the universe remains constant, an individuals ‘weight’ may differ slightly day to day as the sample is different every day • An individual has one daily weight which satisfies all weighting characteristics eg sex, age, LSM, region, etc. 7 Copyright © 2012 The Nielsen Company. Confidential and proprietary. Random Iterative Method (RIM) Weighting A method of weighting that puts selected non-interlocking and grouped interlocking variables in isolation through an iterative sequence of weighting adjustments. The sequence adjusts for each rim in turn and then repeats itself as many times as is required in order to obtain a convergence, in which the sum of the weighted rims matches the target population estimates, or is as close as is possible to achieve. Source: Nielsen Audience Measurement Glossary 8 Copyright © 2012 The Nielsen Company. Confidential and proprietary. SAARF TAM Information day RIM Weighting example 9 Copyright © 2012 The Nielsen Company. Confidential and proprietary. SAARF TAM Information day Recent updates to TAMS data •2nd July: Universe Update (with new IHS population figures). •6th August: RIM weight unbundling. Changes to LSM RIM weight structure 10 Copyright © 2011 The Nielsen Company. Confidential and proprietary. Universe trend Aug-2010 to Sept-2012 •The overall TV Universe has grown. •The non-satellite Universe has decreased slightly, while the satellite universe has shown significant growth. Universe Update Jan 2012 Universe Update July 2012 RIM Weight changes Aug 2012 PVR Panel introduced into TAMS sample – Dec 2011 11 Copyright © 2011 The Nielsen Company. Confidential and proprietary. Live, Monday to Sunday, 2h00 to 25h59 TVR 000s trend Aug-2010 to Sept-2012 •TVR 00s for Tot Individuals has not shown the same degree of growth as the Universe, indicating declining viewing levels. •Non-satellite TVR 000s have declined, as has the non-satellite Universe. •Satellite TVR 000s have grown, in line with the rapidly increasing Universe. Universe Update Jan 2012 Universe Update July 2012 RIM Weight changes Aug 2012 PVR Panel introduced into TAMS sample – Dec 2011 12 Copyright © 2011 The Nielsen Company. Confidential and proprietary. Live, Monday to Sunday, 2h00 to 25h59 TVR % trend Aug-2010 to Sept-2012 •Overall, viewing levels have shown a slow, but steady decline. •This is true of both non-satellite and satellite target markets. Universe Update Jan 2012 Universe Update July 2012 RIM Weight changes Aug 2012 PVR Panel introduced into TAMS sample – Dec 2011 13 Copyright © 2011 The Nielsen Company. Confidential and proprietary. Live, Monday to Sunday, 2h00 to 25h59 ATV trend Aug-2010 to Sept-2012 •Average time spent, in minutes, reflects the general decline in audiences, as seen in the TVR percentages. Universe Update Jan 2012 Universe Update July 2012 RIM Weight changes Aug 2012 PVR Panel introduced into TAMS sample – Dec 2011 14 Copyright © 2011 The Nielsen Company. Confidential and proprietary. Live, Monday to Sunday, 2h00 to 25h59 The effects of the LSM changes to LSM 1 – 5 target markets •Prior to 6th August LSM 1 – 5 was grouped. •The separation of LSM 5 from LSM 1 – 4 resulted in a re-distribution of audiences as shown in the test data . The Universes for LSM 1 – 5, for both sets of data, add up to 10.7 Million, but LSM 1 – 4 Universe increases from 2.9 Million to almost 5 Million. Conversely, the LSM 5 Universe decreases from 7. 8 Million To 5.7 Million. Although on the surface it appears that Universe numbers have been lost in LSM 5, they have in fact been re-distributed to LSM 1 – 4, hence the increase in this group. Week 11, 12/03/2012 – 18/03/2012 Copyright © 2011 The Nielsen Company. Confidential and proprietary. 15 The effects of the LSM changes to LSM 1 – 5 target markets LSM 5 Universe decreases LSM 1-4 Universe increases 16 Copyright © 2011 The Nielsen Company. Confidential and proprietary. LSM 5 – 7: various target markets After the Universe update in Week 27, there was a slight increase in LSM 5 – 7 TVR 000 sizes. However, due to the redistribution of audiences into LSM 1 – 4, following the LSM RIM weight change, TVR 000s decrease after Week 32. Viewing levels for LSM 5 – 7 target markets increase (some slightly and others substantially), despite the re-distribution of audiences. Live + VOSDAL , Monday to Sunday, 2h00 to 25h59 Copyright © 2011 The Nielsen Company. Confidential and proprietary. 17 The effects of the LSM changes to LSM 8 – 10 target markets •Prior to 6th August LSM 7 – 8 was grouped. •The ungrouping of LSM 7 and 8 also resulted in a re-distribution of audiences as shown in the test data. The effect is less dramatic than seen in the LSM 1 – 5 re-distribution. The Universes for LSM 7 – 8 add up to 6.6 Million, but differ in the way they are distributed within this grouping. The LSM 8 Universe increases from 2.6 Million to 2.7 Million. Conversely, the LSM 7 Universe decreases from 4 Million to 3.7 Million. Although on the surface it appears that Universe numbers have been lost in LSM 7, they have in fact been re-distributed to LSM 8, hence the slight increase in this group. Week 11, 12/03/2012 – 18/03/2012 Copyright © 2011 The Nielsen Company. Confidential and proprietary. 18 The effects of the LSM changes to LSM 8 – 10 target markets LSM 7 Universe decreases LSM 8 Universe increases 19 Copyright © 2011 The Nielsen Company. Confidential and proprietary. The effects of the LSM changes to LSM 8 – 10 target markets •After the Week 27 Universe Update, Universe for LSM 8 – 10 target markets generally remained the same. •After the Week 32 RIM weight change, LSM 8 – 10 target markets generally had slight increases in their Universe sizes. 20 Copyright © 2011 The Nielsen Company. Confidential and proprietary. The effects of the LSM changes to LSM 8 – 10 target markets No substantial changes in TVR 000s are noted in general for LSM 8 – 10 target markets after the Universe update in Week 27. After the LSM RIM weight changes in Week 32, there are increases in the LSM 8 – 10 TVR 000s. For LSM 8 – 10 Individuals, a slight decrease in viewing levels occurs after the Universe update. Viewing levels remain the same or increase generally after the LSM RIM structure change. Live + VOSDAL , Monday to Sunday, 2h00 to 25h59 Copyright © 2011 The Nielsen Company. Confidential and proprietary. 21 A word of caution to media planners Other aspects that users should bear in mind when comparing TAMS data before and after a universe update are the following: • Make sure you have not eroded your sample size with too many filters. Data on small sample sizes is unstable. • Look at the whole picture i.e. even if you are only interested in LSM 8-10, do a run that has LSM 1-4, LSM 5-7 and LSM 8-10 in it. This way you can look at your “target market” in relation to the rest. In fact you might find out that your “true” target market is actually LSM 5-7 and not LSM 8-10. • Make sure there were no unusual events like the “World Cup Soccer” in either you source or projected period. • Don’t just look at your channels, also look at competing media and other activities • Look at extraneous factors like programme schedule changes, special sporting events, weather conditions… • Remember Margin of Error. 22 Copyright © 2011 The Nielsen Company. Confidential and proprietary. References To assist users in using and understanding the TAMS data after both the new IHS universe estimates were applied to the TAMS data and some of the TAMS RIMS were unbundled, three articles were written. Please follow the links below to the SAARF web site • Article on Implications when SAARF changed Demographers • Article on TAMS LSM and other RIM Unbundling • Some Case Studies, which looks at the effect of both changes 23 Copyright © 2011 The Nielsen Company. Confidential and proprietary. 2013 Universe Update schedule Next Universe update scheduled for Jan 2013 25 Copyright © 2011 The Nielsen Company. Confidential and proprietary. Expansion Panel Plans / Metering TAM Expansion 1707 3000+ 27 Copyright © 2011 The Nielsen Company. Confidential and proprietary. TV Events Data Release Data release over holiday season… 29 Copyright © 2011 The Nielsen Company. Confidential and proprietary. Q&A 30 Copyright © 2011 The Nielsen Company. Confidential and proprietary.