On valid descriptive inference from non-probability sample

10/01/2018
by   Li-Chun Zhang, et al.
0

We examine the conditions under which descriptive inference can be based directly on the observed distribution in a non-probability sample, under both the super-population and quasi-randomisation modelling approaches. Review of existing estimation methods reveals that the traditional formulation of these conditions may be inadequate due to potential issues of under-coverage or heterogeneous mean beyond the assumed model. We formulate unifying conditions that are applicable to both type of modelling approaches. The difficulties of empirically validating the required conditions are discussed, as well as valid inference approaches using supplementary probability sampling. The key message is that probability sampling may still be necessary in some situations, in order to ensure the validity of descriptive inference, but it can be much less resource-demanding provided the presence of a big non-probability sample.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/26/2020

Data Integration by combining big data and survey sample data for finite population inference

The statistical challenges in using big data for making valid statistica...
research
01/29/2018

Sampling techniques for big data analysis in finite population inference

In analyzing big data for finite population inference, it is critical to...
research
05/15/2023

Bayesian predictive inference when integrating a non-probability sample and a probability sample

We consider the problem of integrating a small probability sample (ps) a...
research
10/23/2022

Testing model specification in approximate Bayesian computation

We present a procedure to diagnose model misspecification in situations ...
research
01/09/2020

Statistical Data Integration in Survey Sampling: A Review

Finite population inference is a central goal in survey sampling. Probab...
research
05/28/2023

Pretest estimation in combining probability and non-probability samples

Multiple heterogeneous data sources are becoming increasingly available ...

Please sign up or login with your details

Forgot password? Click here to reset