home: News to Me: Data

Do Numbers Lie?

"How to Call B.S. on Big Data: A Practical Guide
by Michelle Nijhuis
"The New Yorker," June 3, 2017
Kristin Fontichiaro Summarizes It All in Her Blog: "More ways to avoid getting tripped up by bad data in the news"
In brief:
1. BS & lies are not the same thing. Pay attention.
2. Consider the source - what is their motive & agenda? Where did they get their info?
3. If it sounds too good to be true, it probably is.
4. Check the plausibility of data driven claims.
5. Correlation doesn't necessarily imply causation.
6. Machines can be racist, sexist, wrong-headed. Their programming may be biased.
7. "Big Data Hubris" - are predictors reliable?
8. "BS Asymmetry Principle" coined by Alberto Brandolini : "the amount of energy needed to refute bullshit is an order of magnitude bigger than that needed to produce it."

Lies, Damn Lies & Statistics

HILARIOUS send-up of stat nonsense. I am thinking about causation and correlation, and never the twain shall meet.

Speaking of twain, Mark Twain is often credited with the clever quip "lies, damned lies, and statistics." He actually popularized the phrase in the United States, attributing it to British Prime Minister Benjamin Disraeli: "There are three kinds of lies: lies, damned lies, and statistics." This too has proven false as several essays on phrase origins point out - sample. Arthur James Balfour is the most likely culprit:)

U.S. Data

American Fact Finder
find popular facts (population, income, etc.) and frequently requested data about your community
Bureau of Justice Statistics
Bureau of Labor Statistics Data Tools
Bureau of Transportation Statistics
Census Bureau
leading source of quality data about the nation's people and economy
Census Bureau Statistical Abstracts Infographics & Visualizations
Data.gov
covers a variety of topics, including agriculture, climate, education, energy, and science & research
Enigma Public Data
curated collection of open data - a gateway
Environmental Protection Agency
Environmental Dataset Gateway - EPA's official open data catalog
Federal Researve Economic Data
FiveThirtyEight
Election data
Health Data
making high value health data more accessible to entrepreneurs, researchers, and policy makers in the hopes of better health outcomes
National Bureau of Economic Research
National Center for Education Statistics
National Center for Health Statistics
gathered by the Center for Disease Control
Pew Research Center Datasets
also check out the Fact Tank blog for News in the Numbers as well as the subject sub-sections
President's Council on Sports, Fitness & Nutrition
facts and statistics gathered by the Department of Health and Human Services
Rand State Statistics
social science data for the U.S. at the national, state, and local levels.

International Data

Gapminder
Geob.ase Gazeteer
find statistics, population, weather, webcams, travel information for millions of worldwide locations
Google Public Data Explorer
provides a directory of official public statistics from the web
Human Rights Data Analysis Group
International Monetary Fund Data
UN Data
"a world of information" - a statistical database of all United Nations data
UNICEF Research and Reports
driving change for children through data - grounded in empirical data, rigorous research and thoughtful analysis
World Bank Data Banks
World Bank Data Indicators
World Health Organization - Global Health Observatory Data
find resources on water sanitation, childhood weight levels, disease and infection, etc.
World Mapper
a collection of world maps called cartograms, where territories are re-sized on each map according to the subject of interest

Public Opinion Polling Resources

Gallup
Harris Poll
Pew Research Center
Roper Center for Public Opinion Research (Cornell University)
Dataverse
produced by the Odum Institute for Research in Social Science, UNC
World Values Survey
Survey Research Center
Institute for Social Research, University of Michigan