Statistical paradises and paradoxes in big data. I: Law of large populations, big data paradox, and the 2016 US presidential election

DOI10.1214/18-AOAS1161SFzbMath1405.62241OpenAlexW2883811944MaRDI QIDQ1624804

Xiao-Li Meng

Publication date: 16 November 2018

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Full work available at URL: https://projecteuclid.org/euclid.aoas/1532743473

zbMATH Keywords

bias-variance tradeoffEuler identitydata confidentiality and privacydata defect correlationdata defect index (d.d.i.)data quality-quantity tradeoffMonte Carlo and quasi Monte Carlo (MCQMC)non-response biasparadoxes in big data

Mathematics Subject Classification ID

Applications of statistics to social sciences (62P25) Sampling theory, sample surveys (62D05) Foundations and philosophical topics in statistics (62A01)

Related Items

On valid descriptive inference from non-probability sample, Robust Bayesian inference for big data: combining sensor-based records with traditional survey data, Data Integration by Combining Big Data and Survey Sample Data for Finite Population Inference, Developments in Survey Research over the Past 60 Years: A Personal Perspective, Sampling Techniques for Big Data Analysis, Is there a role for statistics in artificial intelligence?, Sampling: Design and Analysis, 3rd ed., Statistical theory powering data science, Addressing selection bias and measurement error in COVID-19 case count data using auxiliary information, Rejoinder: ``Let's be imprecise in order to be precise (about what we don't know), On making valid inferences by integrating data from surveys and other sources, Comments on ``Data science, big data and statistics, Variable selection in propensity score adjustment to mitigate selection bias in online surveys

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Rejection odds and rejection ratios: a proposal for statistical practice in testing hypotheses
• Struggles with survey weighting and regression modeling
• Statistics can lie but can also correct for lies: reducing response bias in NLAAS via Bayesian imputation
• On the absolute bias ratio of ratio estimators
• Nonresponse weighting adjustment using estimated response probability
• Inference and missing data
• Assessing the accuracy of the maximum likelihood estimator: Observed versus expected Fisher information
• Robust Models in Probability Sampling
• A Theory of Statistical Models for Monte Carlo Integration
• A Generalization of Sampling Without Replacement From a Finite Universe