Sample Design for the Terrorism Risk Insurance Program Survey

• Activity Number: 412
• Type: Contributed
• Date/Time: Thursday, August 12, 2004 : 8:30 AM to 10:20 AM
• Sponsor: Section on Survey Research Methods
• Author(s): G. Hussain Choudhry*+ and Mats G. Nyfjall and Marianne Winglee
• Companies: Westat and Westat and Westat
• Keywords: statified sample design ; systematic sampling ; optimum sample allocation ; nonlinear programming ; composite selection probabilities

Abstract

We describe the sample design for the Terrorism Risk Insurance Program (TRIP) survey that was conducted for the U.S. department of Treasury to estimate at the national level and for a number of domains the uptake rate and the average premium paid for the terrorism risk insurance. The domains of interest were the industry groups, geographic domains, and size categories. The sampling frame for the private sector was constructed from the Dun and Bradstreet listings of businesses and that for the state and local governments and special districts was compiled from the 2002 Census of Governments conducted by the U.S. Bureau of the Census. The sample design was a stratified design with systematic sampling of business entities from within strata. We used a nonlinear programming technique to determine the optimum sample allocation to minimize the total sample while achieving the required precision levels for the survey estimates. We determined the composite selection probabilities for the systematic sampling procedure that at least one member (headquarters or a subsidiary) of the business was selected, and constructed the sampling weights based on the composite selection probabilities.