STATS 250 Lecture Notes - Lecture 5: Provisional Ballot, Bias Of An Estimator
49
STATS 250 Full Course Notes
Verified Note
49 documents
Document Summary
Use mathematical properties to show that the expected value of statistics are unbiased. Given an arbitrary sampling design, let s be a sample of size n that is feasible given the sampling design. When pi i >0 is the probability of inclusion for observation, tau-hat is an unbiased estimator for tau. The survey consists of 2 samples from cuyahoga county, some voters casted provisional ballots, some did not. Provisionals are sampled from a list that contains all people who casted a provisional ballot. The voters are sampled from voters in the same local areas as the provisionals included in that sample. Nonprovisional voter matches were found in 12 zip-9 areas, 135 zip-8 areas, 224 zip-7 areas, 8 zip-6 areas, 7 zip-5 areas and 2 zip-4 areas. The goal is to estimate the conditional distribution of casting a provisional ballot with respect to various variables that were measured in the survey instruments used.
