FCC Record, Volume 26, No. 19, Pages 14991 to 15893, October 24 - November 10, 2011 Page: 15,039
The following text was automatically extracted from the image on this page using optical character recognition software:
weekly periods (or two separate four-week sweeps periods) to obtain an "average" for each of two years,
has been both a necessary and rational procedure.89 To abandon such a long-standing precedent, given
the difficulties in obtaining any survey diaries from "over-the-air" households in communities such as
those in the Palm Springs DMA, is unmerited in light of today's market realities."
15. In 1972, the Commission established procedures for determining significantly viewed
status based on the methodology used to create the original list of significantly viewed signals. The
procedures were similar to those used by Arbitron, the entity under contract to the Commission at that
time to create the original significantly viewed list, which allowed new stations and stations not meeting
the standards for significantly viewed status in 1972 to have an opportunity to be granted significantly
viewed status in a similar manner. As a result of the decision in KCST-TV, the Commission added
procedures to grant waivers of significantly viewed status, again based on the statistical methodology
used for the Arbitron study.
16. While Time Warner's statistical consultant makes valid points in his assessment of the
appropriate theoretical statistical model and the required sample size for a rigorous statistical analysis,
the procedures for determining significantly viewed status are only intended to estimate over-the-air
viewing levels. We recognize that they do not require a sophisticated statistical analysis, but rather
constitute a practical methodology, within reasonable statistical bounds, to permit the carriage of
available stations or grant waivers when viewing levels no longer demonstrate that a station is
"significantly viewed" over the air. It would be unfair to the Petitioners, in this instance, to impose a
different and more difficult test than has been sufficient in the past even though employing the statistical
techniques discussed by Time Warner's consultant could theoretically produce more precise results. The
methodology used for significant viewing showings is unique to the particular purpose and without
further study should not, and cannot, be changed in the context of this petition, even if we think we
should consider modifying these requirements.92
17. Time Warner also argues that, based on this same analysis, we do not know how Nielsen
determines whether a household is a non-cable/non-ADS household or what constitutes a usable in-tab
household. It maintains that these sampling errors cast doubt on the statistical analysis. Pursuant to
Section 76.54(c) of the Commission's rules, Petitioners provided Time Warner with notification that they
intended to purchase Nielsen data and included an explanation of Nielsen's procedures for re-tabulation
"9Id. at 6. Petitioners state that, unlike WISN, they submitted for the record all of the Nielsen data for each
of the five communities, from each of the four Nielsen sweep periods for each of two years.
90Id. at 6-7. Petitioners point out that in this case the number of over-the-air households is only five percent.
See id. at Appendix A.
"See Reconsideration of the Cable Television Report and Order, 36 FCC Rcd 2d 326 (1972).
92For example, Time Warner's consultant argues that we should use a 95 percent confidence interval (i.e., 2
standard errors) to determine the sample size that will produce statistically reliable results. While it is true that
statisticians most frequently use a 95 percent confidence level to detennrmine the appropriate sample size for a study
and to assess the reliability of a reported statistic, Section 76.54 of the Commission's rules sets forth a lower level of
confidence - approximately 68 percent, based on a confidence level of one standard error. The Commission
previously determined that one standard error provides reasonable confidence about the reported audience estimates,
even with small samples, both in adopting the rule and in subsequent significant viewing cases. See supra n.91 We
therefore should not use a different standard here beyond the requirements of the existing rule.
Federal Communications Commission
Here’s what’s next.
This book can be searched. Note: Results may vary based on the legibility of text within the document.
Tools / Downloads
Get a copy of this page or view the extracted text.
Citing and Sharing
Basic information for referencing this web page. We also provide extended guidance on usage rights, references, copying or embedding.
Reference the current page of this Book.
United States. Federal Communications Commission. FCC Record, Volume 26, No. 19, Pages 14991 to 15893, October 24 - November 10, 2011, book, November 2011; Washington D.C.. (digital.library.unt.edu/ark:/67531/metadc133013/m1/63/: accessed October 23, 2017), University of North Texas Libraries, Digital Library, digital.library.unt.edu; crediting UNT Libraries Government Documents Department.