Response Letter to OMB

Response to OMB, February 16, 2011

1. The focus group facilitator and Savage and Waldman wrote took detailed notes during the sessions, which are still being written up. A summary of these findings will be discussed in the final report to the FCC.

2. Measures developed by Zwerina et. al. (1996) were used to generate an efficient non-linear optimal design for the levels of the features that comprise the media environment options. A fractional factorial design created 72 paired descriptions of the media environment, A and B, that are grouped into 9 versions (1, 2, 3, 4, 5, 6, 7, 8, and 9), of eight choice scenarios (or sets), with a single version to be randomly distributed to each respondent. See the Appendix to the survey for the table that details the values for the experimental design. The descriptions of the variables in this table are:

Alt: - hypothetical media environment alternative (A, B);

Vers. – version (1, 2, 3, 4, 5, 6, 7, 8, or 9);

Set – set of eight choice questions within each version;

Advertising – level of advertising (low, medium or high);

Diversity of opinion - level of diversity (low, medium or high);

Community news - level of community news and events (low , medium or high);

Multiculturalism – level of multiculturalism (low, medium or high); and

Cost – cost of median environment ($).

Note that cost varies by five classifications, I, II, III , IV and V. Each individual respondent within a version will receive a cost classification based on the cost of their actual own media environment. For example, if the respondent has version 1, and has indicated that the cost of their actual media environment is $25 (“dov_amt”), the design will assign them to “Cost I.” We do this to ensure that the costs in the choice scenarios provide more realistic experimental values that better reflect the actual costs the respondent pays in the market. Continuing our example, the first row of the “experimental design” table shows that Alternative A will have low advertising, medium diversity, high community news, medium multiculturalism and a cost of $10.

The criteria for cost allocation are provided on page 8 of the survey, Table 2. last row:

Table 2. Features of Overall Media Environment
Feature	Levels
Diversity of opinion	Only one viewpoint (Low) A few different viewpoints (Medium) Many different viewpoints (High)
Community news	Very little or no information on community news and events (Low) Some information on community news and events (Medium) A lot of information on community news and events (High)
Multiculturalism	Very little or no information reflecting the interests of women and minorities (Low) Some information reflecting the interests of women and minorities (Medium) A lot of information reflecting the interests of women and minorities (High)
Advertising	Barely noticeable (Low) Noticeable but not annoying (Medium) Annoying (High)
Cost	[KN insert appropriate cost range; $0 to $50 per month if $0 ≤ [DOV_AMT] ≤ $30 $5 to $100 per month if $30 < [DOV_AMT] ≤ $70 $5 to $150 per month if $70 < [DOV_AMT] ≤ $120 $10 to $200 per month if $120 < [DOV_AMT] ≤ $180 $10 to $250 per month if $[DOV_AMT] > $180

References

Zwerina, K., Huber, J., and Kuhfeld, W. 1996. “A General Method for Constructing Efficient Choice Designs. in Marketing Research Methods in the SAS System,” 2002, Version 8 edition, SAS Institute, Cary, North Carolina.

3