link to AFSC home page

link to AFSC home page link to NMFS home page link to NOAA home page

Resource Ecology & Fisheries Management (REFM) Division

AFSC Quarterly
Research Reports
Oct-Nov-Dec 2006
Contents
Feature
ABL Reports
FMA Reports
NMML Reports
RACE Reports
REFM Reports
Items
Quarterly Index
Quarterly Home

Economics & Social Sciences Research Program

Southwest and Gulf Coast Data Collection Projects: Optimal Sample Sizes Computed for Vessel Classes

In order to conduct two ongoing regional economic data collection projects in the Southwest and Gulf Coast Regions of Alaska, we needed to develop an appropriate sampling methodology. Since the majority of gross revenue within each vessel class comes from a few number of boats, a simple random sampling (SRS) of vessels would only include a small portion of the total exvessel values, and therefore, would be misleading. Thus, for the two projects, an unequal probability sampling (UPS) method without replacement was implemented. Specifically, two tasks need to be accomplished to estimate the population parameters using the UPS. First, the optimal sample size needs to be determined. Second, once the optimal sample size is determined, the population parameters and confidence intervals need to be estimated.

Using the sampling procedures already developed, we conducted the first task which computed the optimal sample sizes for three vessel classes in each of the two data collection projects. In this process we used 2005 Commercial Fisheries Entry Commission (CFEC) exvessel revenue data, and assumed an allowed error of 10% in population estimates and a 95% confidence level. The resulting sample sizes were found out to be smaller than those derived from SRS sampling. The next step is to conduct the second task in which we will identify the specific vessels that will be included in the “mail-out” sample of the three vessel classes, using Pareto sampling.

By Chang Seung


Paper Reduction Act (PRA) Packet Prepared for Southwest Data Collection Project

The Paper Reduction Act (PRA) packet for the Southwest region data collection project has been prepared (see Quarterly Report, April-May-June 2006). One of the most important documents that needed to be included in the packet is the supporting statement (SS), which describes the methodologies that we will use to obtain the data. In the SS, we provided justifications for collecting the data, explained how the data will be collected, provided burden hours and annualized costs, and provided other necessary information. In particular, we described what efforts we exercised, or will exercise, to maximize the response rates. These efforts include focus group meetings, simplification of questions, and use of a modified Dillman method in which four contacts will be made to increase response rates.

The four contacts that we will use are advance letter, initial mailing letter, postcard reminder, and follow-up phone call for the mail survey of vessel owners. We prepared these letters, postcard reminder, and phone scripts. For telephone interviews with local businesses and fish processors, we developed phone scripts. With these efforts to maximize the response rate, it is expected that the response rates for the mail survey of vessel owners and phone interviews with local businesses (including fish processors) will be around 55% and 65%, respectively.

By Chang Seung
 

<<< previous

next >>>


            Home | FOIA | Privacy | USA.gov | Accessibility      doc logo