OPTIMAL-DESIGN OF SYNDICATED PANELS - A MATHEMATICAL-PROGRAMMING APPROACH

A new design concept for syndicated panels is proposed which explicitl y handles tradeoffs between the economics of the panel (i.e., costs an d revenues) and its econometrics (risk of sampling errors). Economic a nd statistical criteria are directly incorporated, leading to new math ematical programming formulations for deciding panel composition and s ize. These models provide insights into the complexities of panel desi gn that are not available from traditional statistical methods. Much o f the published literature does not address syndication or panel sampl ing and attendant complications such as demographic shifts and turnove r standards. The present paper provides new methods, with worked examp les, for optimizing the design when such conditions are present and th ereby extends the range of situations for which optimal designs can be obtained, The traditional 'cost of a sample unit' is disaggregated to separate costs of sample recruitment, retention and maintenance, thus linking the sampling considerations to the optimization of the operat ion of the panel.