MOMENT-BASED INFERENCE WITH STRATIFIED DATA

Many data sets used by economists and other social scientists are collected by stratified sampling. The sampling scheme used to collect the data induces a probability distribution on the observed sample that differs from the target or underlying distribution for which inference is to be made. If this effect is not taken into account, subsequent statistical inference can be seriously biased. This paper shows how to do efficient semiparametric inference in moment restriction models when data from the target population are collected by three widely used sampling schemes: variable probability sampling, multinomial sampling, and standard stratified sampling.

Estimation of seed orchard efficiencies by means of multistage variable probability sampling

This paper describes two frameworks for developing effective multistage variable probability sampling methods to estimate seed orchard efficiencies. In both cases a standard multistage approach is implemented initially in multiple orchards and years. The effectiveness of this approach is then evaluated against several alternative methods, using the initial efficiency data collected, and subsequent survey procedures are prescribed on the basis of this analysis. An example illustrating the application of this methodology in coastal Douglas-fir (Pseudotsugamenziesii (Mirb.) Franco) seed orchards in British Columbia is presented.