A New Approach to Inference in Multi-Survey Studies with Unknown\n Population Size

2014/01/27 by Kyle Vincent, Vincent, Kyle, Saman Muthukumarana +1
Mathematics · Social Sciences · #Census and Population Estimation #FOS: Computer and information sciences #Methodology (stat.ME) #Other Statistics (stat.OT) #Statistical Methods and Bayesian Inference #Survey Methodology and Nonresponse #Survey Sampling and Estimation Techniques

paper · pdf · doi:10.48550/arxiv.1401.6849

openalex publication_date 2014/01/27 · openalex created_date 2022/10/01 · openalex updated_date 2026/07/28

Abstract

We investigate a Poisson sampling design in the presence of unknown selection\nprobabilities when applied to a population of unknown size for multiple\nsampling occasions. The fixed-population model is adopted and extended upon for\ninference. The complete minimal sufficient statistic is derived for the\nsampling model parameters and fixed-population parameter vector. The\nRao-Blackwell version of population quantity estimators is detailed. An\napplication is applied to an emprical population. The extended inferential\nframework is found to have much potential and utility for empirical studies.\n

Citations

• Estimating the Population Size for Capture-Recapture Data with Unequal Catchability
• Equation of State Calculations by Fast Computing Machines
• Monte Carlo sampling methods using Markov chains and their applications
• Respondent-Driven Sampling II: Deriving Valid Population Estimates from Chain-Referral Samples of Hidden Populations
• Respondent-Driven Sampling: A New Approach to the Study of Hidden Populations

Related

• A Broadened Approach for Improved Estimation in Survey Sampling
• Bayesian Predictive Inference For Finite Population Quantities Under Informative Sampling
• Estimating Population Size with Link-Tracing Sampling
• Bootstrap inference for the finite population total under complex sampling designs
• Bayesian Approach to Handling Informative Sampling