Summary Report of the AAPOR Task Force on Non-probability Sampling

@article{Baker2013SummaryRO,
  title={Summary Report of the AAPOR Task Force on Non-probability Sampling},
  author={Reg Baker and J. Michael Brick and Nancy Bates and Michael P. Battaglia and Mick P. Couper and Jill A Dever and Krista Gile and Roger Tourangeau},
  journal={Journal of Survey Statistics and Methodology},
  year={2013},
  volume={1},
  pages={90-143}
}
Survey researchers routinely conduct studies that use different methods of data collection and inference. But for at least the past 60 years, the probabilitysampling framework has been used in most surveys. More recently, concerns about coverage and nonresponse coupled with rising costs have led some to wonder whether non-probability sampling methods might be an acceptable alternative, at least under some conditions (Groves 2006; Savage and Burrows 2007). A wide range of non-probability designs… 
Beyond Probability Sampling: Population Inference in a World without Benchmarks
TLDR
It is argued that research results can be trusted when reliable results emerge across data sources affected by very different types of survey errors, and conditions necessary for reliable conclusions are proposed.
Explorations in Non-Probability Sampling Using the Web
TLDR
A review of non-probability sampling strategies and some of the key issues are summarized and conditions under which non- Probability Sampling may be a reasonable approach are proposed.
On valid descriptive inference from non-probability sample
ABSTRACT 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
Adaptive Design Strategies for Nonresponse Follow-Up in Economic Surveys
Abstract The U.S. Census Bureau is investigating nonrespondent subsampling strategies for use in the 2017 Economic Census. In previous research, we developed an optimized allocation procedure for
Integrating Probability and Nonprobability Samples for Survey Inference
TLDR
This work proposes a method of combining both probability and nonprobability samples in a way that exploits their strengths to overcome their weaknesses within a Bayesian inferential framework, and demonstrates that informative priors based on nonProbability data can lead to reductions in variances and mean squared errors for linear model coefficients.
Measures of Selection Bias in Regression Coefficients Estimated from Non-Probability Samples
Selection bias is a serious potential problem for inference about relationships of scientific interest based on samples without well-defined probability sampling mechanisms. Motivated by the
Selection Bias in Nonprobability Surveys: A Causal Inference Approach
TLDR
This dissertation proposes an alternative classification for sources of selection bias for nonprobability surveys based on principles borrowed from the field of causal inference, and shows how net selection bias can be decomposed into separate additive components associated with exchangeability, positivity, and composition respectively.
Nonprobability and Probability-Based Sampling Strategies in Sexual Science
TLDR
An overview of Internet sampling as a useful, cost-efficient, nonprobability sampling method of value to sex researchers conducting modeling work or clinical trials is provided and it is argued that probability-based sampling methods may be more readily applied in sex research with hard-to-reach populations than is typically thought.
Measures of the Degree of Departure from Ignorable Sample Selection.
TLDR
A simple index of degree of departure from ignorable sample selection that corrects this deficiency is proposed, which is called the standardized measure of unadjusted bias (SMUB), and is grounded in the model-based framework of nonignorable selection.
Blending of Probability and Non-Probability Samples: Applications to a Survey of Military Caregivers
TLDR
A survey of military caregivers focused on unpaid caregivers of wounded, ill, or injured servicemembers and veterans who served in the US armed forces following September 11, 2001 shows that the subpopulation of interest endures greater hardships than caregivers of veterans with earlier dates of service.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 245 REFERENCES
Reduction of Nonresponse Bias in Surveys through Case Prioritization
How response rates are increased can determine the remaining nonresponse bias in estimates. Studies often target sample members that are most likely to be interviewed to maximize response rates.
Reduction of Nonresponse Bias through Case Prioritization
TLDR
The two components of this approach to reducing nonresponse bias, assignment of case priority based on response propensity models, and empirical results from the use of a different protocol for prioritized cases are described.
Inference for Non‐random Samples
Observational data are often analysed as if they had resulted from a controlled study, and yet the tacit assumption of randomness can be crucial for the validity of inference. We take some simple
Variance Estimation, Design Effects, and Sample Size Calculations for Respondent-Driven Sampling
TLDR
A bootstrap method is presented for constructing confidence intervals around respondent-driven sampling estimates and it is demonstrated in simulations that it outperforms the naive method currently in use.
Ignorable and informative designs in survey sampling inference
SUMMARY The role of the sample selection mechanism in a model-based approach to finite population inference is examined. When the data analyst has only partial information on the sample design then a
An Evaluation of Nonresponse and Coverage Errors in a Prerecruited Probability Web Panel Survey
TLDR
Nonresponse error measured by the differences between the estimates from the respondents and the known full sample values was not found to be large, implying that nonresponse error in this Web survey data may not be critical, but coverage properties of the full survey sample show some problems.
Missing-Data Adjustments in Large Surveys
TLDR
Useful properties of a general-purpose imputation method for numerical data are suggested and discussed in the context of several large government surveys and weighting-based analogs to predictive mean matching are outlined.
Using Probability vs. Nonprobability Sampling to Identify Hard-to-Access Participants for Health-Related Research
TLDR
The recruitment costs and participant characteristics associated with the use of probability and nonprobability sampling strategies in a longitudinal study of older hemodialysis patients and their spouses are compared.
An Evaluation of Model-Dependent and Probability-Sampling Inferences in Sample Surveys
Abstract In this paper we are concerned with inferences from a sample survey to a finite population. We contrast inferences that are dependent on an assumed model with inferences based on the
For objective causal inference, design trumps analysis
For obtaining causal inferences that are objective, and therefore have the best chance of revealing scientific truths, carefully designed and executed randomized experiments are generally considered
...
1
2
3
4
5
...