Response to OMB Review Questions 6.6.14

1. It is not clear to me if the estimates are intended to produce State level estimates, as well as regional and national estimates. I saw some language in SSA indicating that every State would be included in the study; if that is done with certainty, is that because the aim is to produce state level estimates? In SSB, it does not seem that State level estimates are proposed (and maybe the effective sample size would not permit it?)

The survey is not intended to produce State-level estimates.  We will only produce regional-level estimates.  The wording in the SSA that every state would be included was only for sampling purposes.  Typically, we limit the number of states to be included for cost reasons, since most studies are administered via an on-farm visit.  Since the Cervid study will be administered only via CATI, there is no reason to exclude any states.

2. I am very glad to see that NASS will be employing its list frame from the 2012 Census of Agriculture and will assist NAMHS in the collection of data. In addition to improving NASS’ list frame for future Census’, I wonder if NASS would benefit from the Cervid Study in terms of content. Have NASS Cervid experts been consulted, or have you mainly been working with sampling statisticians/Census of Ag operations staff?

For the sampling aspect of the study, we work with the sampling statisticians, via our liaison in the Survey Administration Branch (Kevin Harding).  For the questionnaire design, we work with NASS questionnaire experts.  We don’t know if the NASS questionnaire experts consult with NASS Cervid experts. 

We always submit any reports that result from our NASS-collaborative surveys to NASS for review prior to publication.  We’d be happy to collaborate further if that would be helpful.

3. Thank you for presenting the power estimation method and results. It seems that the sample size is powered to produce point estimates with precision, but it is not clear to me if the sample size is powered for comparison of estimates (for example, differences in deer farming between the Northeast and West). Please clarify.

The sample size is not powered for comparison of estimates.  One of our goals is to develop descriptive statistics with a coefficient of variation (CV) less than 20 percent.  This applies to any sub-population estimates (regional, operation-type, size category) as well as national estimates.  However, the primary goal of NAHMS studies is to develop accurate national estimates.  In setting the sample size, we try to achieve a balance of precision, cost, and producer burden.