YWT Data Datasets, Analytics & Research for Professionals

YWT Data

Datasets, Analytics & Research for Professionals

Latest Articles

Shifting Ground: How Federal Agencies Quietly Redraw Their Statistical Baselines — and Why Your Longitudinal Analysis May Already Be Broken
Statistical Methods

Shifting Ground: How Federal Agencies Quietly Redraw Their Statistical Baselines — and Why Your Longitudinal Analysis May Already Be Broken

When the Census Bureau redefines a survey population, the Bureau of Labor Statistics revises its reference period, or the CDC quietly updates its weighting methodology, the time-series data that researchers depend on develops invisible fractures. Most published studies never account for these structural discontinuities, yet the downstream consequences for longitudinal analysis and policy modeling can be severe. This article examines documented instances of baseline volatility across major federa
State Lines, Blurred Findings: The Hidden Cost of Geographic Aggregation in US Data Research
Statistical Methods

State Lines, Blurred Findings: The Hidden Cost of Geographic Aggregation in US Data Research

Aggregating data to the state level is one of the most common — and most consequential — shortcuts in American research. When county- and tract-level variation disappears into a single state average, the resulting analysis can mislead policymakers, misallocate resources, and produce findings that are statistically coherent but empirically hollow. This article examines the mechanics of that distortion and offers a practical framework for choosing the appropriate unit of analysis before aggregatio
Discipline by Discipline: A Data-Driven Audit of American Science's Reproducibility Record
Data Literacy

Discipline by Discipline: A Data-Driven Audit of American Science's Reproducibility Record

Replication failure is not evenly distributed across American science. Drawing on publicly available datasets from major reproducibility initiatives, this analysis quantifies which disciplines are genuinely reforming and which continue to resist the most basic demands of scientific verification.
Precision Theater: How the Systematic Omission of Margin of Error Is Misleading America's Decision-Makers
Data Literacy

Precision Theater: How the Systematic Omission of Margin of Error Is Misleading America's Decision-Makers

When data consumers encounter a statistic without its accompanying margin of error, they are not receiving incomplete information — they are receiving a distorted picture engineered, however unintentionally, to project false certainty. This article examines how the routine suppression of uncertainty disclosures in high-profile data reporting constitutes a form of statistical misinformation, and what data professionals can do to push back.
Hidden in Plain Sight: How Denominator Choices Are Distorting America's Most Cited Statistics
Data Literacy

Hidden in Plain Sight: How Denominator Choices Are Distorting America's Most Cited Statistics

Per capita figures appear in nearly every policy brief, news headline, and research summary produced in the United States — yet the population base used to construct them is almost never disclosed or defended. The choice of denominator is not a technical footnote; it is a substantive analytical decision that can invert conclusions, obscure disparities, and quietly steer billions of dollars in resource allocation. Data professionals who fail to interrogate that choice are inheriting someone else'
Shrinking Samples, Expanding Claims: The Quiet Crisis of Attrition in America's Longitudinal Surveys
Data Literacy

Shrinking Samples, Expanding Claims: The Quiet Crisis of Attrition in America's Longitudinal Surveys

Participation rates in the United States' most influential longitudinal surveys have been declining for decades, and the people who remain in these studies are increasingly unlike those who dropped out. The result is a compounding distortion that widens with every successive wave — yet the research claims built on this eroding foundation rarely acknowledge how much the ground has shifted beneath them.
The Invisible Overhead: Unpacking the True Cost of Reproducing Published Research
Data Literacy

The Invisible Overhead: Unpacking the True Cost of Reproducing Published Research

Reproducing a published study is rarely as straightforward as its methods section implies. Across economics, public health, and social science, data professionals are absorbing enormous hidden costs in time, labor, and institutional goodwill—costs that rarely appear in any budget line but accumulate into a systemic crisis for the research enterprise. This article examines where those costs originate, who bears them, and what a genuinely replication-ready research standard would require.
Joined at the Seam, Broken at the Core: The Hidden Costs of Linking Federal Datasets
Data Literacy

Joined at the Seam, Broken at the Core: The Hidden Costs of Linking Federal Datasets

Merging datasets across federal agencies can appear straightforward in a script but catastrophic in its consequences. Incompatible geographies, misaligned time windows, and conflicting unit definitions routinely corrupt merged results before a single statistical test is run. This article examines the structural fault lines that make cross-agency data linkage one of the most underappreciated sources of research error in the United States.
Temporal Validity and the Quiet Obsolescence of Data: A Framework for Assessing When Your Dataset Has Outlived Its Usefulness
Data Literacy

Temporal Validity and the Quiet Obsolescence of Data: A Framework for Assessing When Your Dataset Has Outlived Its Usefulness

Researchers routinely treat historical datasets as perpetually reliable evidence, yet the real-world conditions those datasets once captured may have shifted beyond recognition. Economic disruptions, demographic realignments, and policy overhauls can render even widely cited datasets scientifically misleading long before anyone thinks to question them. This article examines the mechanisms of data decay and introduces a structured approach for evaluating freshness risk before a dataset is committ
Postal Logic, Research Failure: The Systematic Distortions Built Into Every ZIP Code Study
Statistical Methods

Postal Logic, Research Failure: The Systematic Distortions Built Into Every ZIP Code Study

ZIP codes were engineered to move mail efficiently, not to capture how populations cluster, commute, or experience inequality. When researchers treat these postal boundaries as meaningful demographic units, they introduce errors that can persist undetected through peer review and into policy. This article examines the structural mismatch between ZIP codes and human geography — and maps a path toward spatial frameworks that actually reflect American life.
The Provenance Problem: How Synthetic Training Data Is Quietly Corrupting the Scientific Record
Data Literacy

The Provenance Problem: How Synthetic Training Data Is Quietly Corrupting the Scientific Record

Synthetic datasets — generated by AI models rather than collected from observed phenomena — are entering research pipelines at an accelerating rate, often without adequate documentation of their origins or limitations. When these records are treated as equivalent to empirically gathered data, the resulting findings carry a form of hidden uncertainty that standard peer review processes are not designed to detect. The implications for reproducibility, policy, and scientific credibility deserve urg
Statistical Work on Trial: What Data Professionals Must Understand When Their Analysis Enters the Courtroom
Statistical Methods

Statistical Work on Trial: What Data Professionals Must Understand When Their Analysis Enters the Courtroom

A rising volume of civil rights, antitrust, and employment discrimination cases in the United States is placing data scientists in an unfamiliar role: expert witness. The evidentiary standards that govern a courtroom differ substantially from those of academic peer review or industry practice, and analytical work that would pass scrutiny in a research context can be dismantled under cross-examination. This article examines what makes statistical analysis legally defensible and what practicing da
Borrowed Assumptions: What Pre-Packaged Datasets Are Doing to Your Research Before You Run a Single Query
Data Literacy

Borrowed Assumptions: What Pre-Packaged Datasets Are Doing to Your Research Before You Run a Single Query

When researchers reach for a curated, ready-to-use dataset, they are not simply saving time — they are inheriting every undocumented decision made by whoever cleaned it first. This article examines how preprocessing choices baked into widely used datasets in economics, public health, and housing can silently distort findings. We offer a structured provenance auditing framework any data professional can apply before trusting a packaged source.
Beyond the Headline Numbers: Unlocking the ACS Tables Most Data Professionals Have Never Opened
Data Literacy

Beyond the Headline Numbers: Unlocking the ACS Tables Most Data Professionals Have Never Opened

The American Community Survey publishes thousands of detailed cross-tabulated tables that go far beyond the population and income figures most researchers cite. From commute duration by occupation to housing cost burden by citizenship status, these overlooked tables offer analytical depth that headline ACS figures simply cannot provide. This guide walks through eight high-value table series and shows exactly how to retrieve them.
When the Ground Shifts Beneath Your Model: A Practitioner's Guide to Distribution Shift in Production ML Systems
Statistical Methods

When the Ground Shifts Beneath Your Model: A Practitioner's Guide to Distribution Shift in Production ML Systems

A model that scores impressively on held-out test data can degrade silently once it encounters the real world — not because of a coding error, but because the statistical properties of the environment it operates in have changed. Distribution shift is among the most consequential and least-monitored failure modes in applied machine learning. This guide breaks down its principal forms, illustrates each with concrete US-context examples, and provides a structured monitoring checklist for productio
What Isn't There: How Systematically Absent Health Data Distorts US Research and Policy
Data Literacy

What Isn't There: How Systematically Absent Health Data Distorts US Research and Policy

Missing data in major US health datasets is rarely random—and that distinction carries enormous consequences for researchers, policymakers, and the populations those policies serve. This article examines the structural patterns behind absent records in CDC and CMS data, illustrates how those absences have skewed published findings, and provides practical detection frameworks for data professionals working with incomplete health records.
Ten High-Value Public Datasets US Data Scientists Should Be Using Right Now
Statistical Methods

Ten High-Value Public Datasets US Data Scientists Should Be Using Right Now

Government data repositories contain some of the richest, most underutilized research assets available to US data professionals—if you know where to look and how to work around their limitations. This curated guide profiles ten publicly available datasets across federal agencies, detailing their contents, update cadences, documented pitfalls, and real-world research applications for both experienced researchers and those newer to government data sources.
Seven Measures That Tell a Richer Story Than the P-Value Ever Could
Statistical Methods

Seven Measures That Tell a Richer Story Than the P-Value Ever Could

The American Statistical Association has issued repeated guidance urging researchers to move beyond mechanical reliance on p-values, yet the 0.05 threshold continues to dominate published research across healthcare, economics, and the social sciences. This guide introduces seven alternative metrics — explained through real published US research — that together provide the kind of statistical storytelling modern data science demands. Adopting them does not require abandoning rigor; it requires ex
Garbage In, Policy Out: Auditing the Structural Flaws in America's Most Trusted Federal Datasets
Data Literacy

Garbage In, Policy Out: Auditing the Structural Flaws in America's Most Trusted Federal Datasets

Federal datasets like the American Community Survey and the Behavioral Risk Factor Surveillance System are foundational to US research pipelines — but embedded collection inconsistencies and demographic blind spots can silently corrupt downstream analysis. Before your next download, here is what critical data professionals need to examine. Understanding these structural limitations is no longer optional; it is a prerequisite for responsible research.