Binging on Gelman again while I was traveling. Here is a gem (link).
If you ever dreamed of having "all the data", be sure to give this a read and give it a few moments' thought. Skim through the main post quickly. The good stuff is in the comments.
« Trifacta, an attempt to simplify the analyst's life | Main | My dataviz workshop starts in October »
You don't have all the data
|
|
Comments
You can follow this conversation by subscribing to the comment feed for this post.
The comments to this entry are closed.
Search3
Recent Posts
- Know your data 34: coming for your most private data
- Book review: Don't Trust Your Gut
- The role of prior infection in the vaccine trials
- Why you must know how analytical results were obtained
- The difference between prediction and estimation
- Know your data 33: oops the dog did it
- Are 81 percent of Elon Musk's twitter followers fake?
- The Musk sampling plan, thought through
- Reading Statistical Analytics Illustrated
- More case-counting puzzles
Recent Comments
- Dan on Know your data 34: coming for your most private data
- Kaiser on The difference between prediction and estimation
- Thomas Dietterich on The difference between prediction and estimation
- Paul on The role of prior infection in the vaccine trials
- Dan Vargo on Why you must know how analytical results were obtained
- Anonny on More case-counting puzzles
- John on The fun and frustration of seeking context
- Anonny on Do better
- Michael Droy on All else is never equal
- Ron Kenett on Unnecessary complications
Next Events
Jan: 10 NYPL Data Science Careers Talk, New York, NYPast Events
Aug: 15 NYPL Analytics Resume Review Workshop, New York, NYApr: 2 Data Visualization Seminar, Pasadena, CA
Mar: 30 ASA DataFest, New York, NY
See more here
Principal Analytics Prep
Copyright
This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 United States License
Community
- Andrew Gelman
Statistical Modeling, Causal Inference and Social Science (Columbia) - Ben Goldacre
Bad Science, debunking bad medicine - Cathy O'Neil
mathbabe: Exploring and venting about quantitative issues - Chance News
Statistics in the news - Christian Robert
Xi'an's Og: statistics, theory (Paris Dauphine) - David Spiegelhalter
Understanding Uncertainty (Cambridge) - Dean Baker
Beat the Press: economics - Felix Salmon
Economics - Franz Dill
The Eponymous Pickle - JMP
Statistics, dataviz, experimental design, etc. - John D. Cook
The Endeavour: Statistics, applied math, computing - Larry Cahoon
Good Stats, Bad Stats - Larry Wasserman
Normal Deviate: statistics, theory - Michael Trick
Operations research (Carnegie Mellon) - Nate Silver
FiveThirtyEight: Polls, politics, sports - John Johnson
Biostats, clinical trials - Significance Magazine
From RSS and ASA - Simply Statistics
Jeff Leek, Robert Peng, Rafa Irizarry (Johns Hopkins) - Social Science Statistics
Harvard - STATS
Numbers Behind the News (GMU)
Categories
- Aggregation (125)
- Algorithms (105)
- Analytics-business interaction (197)
- Artificial intelligence (38)
- Assumptions (57)
- Bayesian (10)
- Behavior (129)
- Bias (258)
- Big Data (268)
- Blogs (125)
- Books (32)
- Business (391)
- Business tip (20)
- Career advice (1)
- Causation creep (24)
- Cause-effect (227)
- Chapter 1 (27)
- Chapter 2 (49)
- Chapter 3 (23)
- Chapter 4 (49)
- Chapter 5 (19)
- Controls (89)
- Covid-19 (191)
- Crime (43)
- Current Affairs (350)
- Data (424)
- Data Science The Missing Pieces (8)
- Dataviz (41)
- Decision-making (147)
- Dilemma of being together (6)
- Economy (67)
- Education (96)
- Environment (8)
- Errors (267)
- Ethics (164)
- Fairness (19)
- False confession (2)
- False negative (77)
- False positive (113)
- Film (11)
- Food (61)
- Games (3)
- Health (293)
- Hiring (14)
- How to act like a data scientist (4)
- Inside the Black Box (2)
- Interview (10)
- Junk Charts (21)
- Know your data (49)
- Machine learning (87)
- Mass media (102)
- Medicine (224)
- Models (243)
- Music (5)
- Neat reads (7)
- Numbersense (13)
- Numbersense Pros (9)
- NumbersRuleYourWorld (9)
- Politics (105)
- Press (55)
- Principal Analytics Prep (12)
- Professional foul (1)
- Proxy unmasking (5)
- Rules (11)
- Science (502)
- Significance (157)
- Sports (62)
- Statbusters (12)
- StatImproWords (6)
- Statisticians (360)
- Story time (41)
- Story-first (4)
- Suggested reading (2)
- Surveys (32)
- Sway of being asymmetric (1)
- Television (7)
- Tests (185)
- Travel (46)
- Variability (251)
- Web/Tech (186)
- XYopia (3)
Can we please kill hypothesis testing already?
http://wmbriggs.com/blog/?p=11261
"Hypothesis tests confuse making a decision about the truth of some proposition with the probability the proposition is true. HTs cannot give the probability any hypothesis is true. HTs conflate probabilities and decisions, which is always suboptimal."
Posted by: Nate | 09/09/2014 at 10:49 AM
Nate: I take a slightly less incendiary position on this topic. Firstly, the concept of statistical significance is central to statistics, regardless of methodology--the idea that the observed sample is but one realization of many alternatives is very important.
Secondly, it is wrong to say "hypothesis tests confuse making a decision about the truth of some proposition with ..." -- the theory of hypothesis testing is fine; its common misinterpretation is the point of contention. I do agree that it is a hopeless enterprise to explain to nontechnical people how to use it.
Posted by: junkcharts | 09/19/2014 at 03:53 AM