Sandbox: Difference between revisions

From ChanceWiki
Jump to navigation Jump to search
(39 intermediate revisions by the same user not shown)
Line 2: Line 2:


==Forsooth==
==Forsooth==
COLONEL [Buzz] ALDRIN:  Infinity and beyond.  (Laughter.)
THE PRESIDENT:  This is infinity here.  It could be infinity.  We don’t really don’t know.  But it could be.  It has to be something -- but it could be infinity, right?
Okay.  (Applause.) 
<div align=right>in: [https://www.whitehouse.gov/the-press-office/2017/06/30/remarks-president-signing-executive-order-national-space-council Remarks by the President signing an Executive Order on the National Space Council] <br>
Office of the White House Press Secretary, 30 June 2017. </div>
Suggested by Mike Olinick


==Quotations==
==Quotations==
Line 20: Line 10:
<div align=right>-- Donald Kennedy (former president of Stanford University), ''Academic Duty'', Harvard University Press, 1997, p.17</div>
<div align=right>-- Donald Kennedy (former president of Stanford University), ''Academic Duty'', Harvard University Press, 1997, p.17</div>


==Rats, again!==
==Redefining statistical significance==
[http://www.slate.com/articles/health_and_science/science/2017/07/de_blasio_s_team_consistently_misreads_the_stats_when_broadcasting_victories.html De Blasio wants to dramatically reduce NYC’s rat population. Don’t hold your breath.]<br>
[https://news.uchicago.edu/article/2017/09/01/scholars-take-aim-false-positives-research Scholars take aim at false positives in research]<br>
by Jonathan Auerbach, ''Slate'', 21 July 2017
by Thomas Gaulkin, ''UChicagoNews'', 1 September 2017


New York City mayor Bill DiBlasio has announced a $32 million [http://www1.nyc.gov/office-of-the-mayor/news/472-17/de-blasio-administration-32-million-neighborhood-rat-reduction-plan#/0 plan to reduce the city's rat population].  In
University Chicago economist John List is one of 72 collaborators whose commentary,
Chance News 102, we described a [https://www.causeweb.org/wiki/chance/index.php/Chance_News_102#Rats.21_NYC_capture-recapture_experiment rats! capture-recapture experiment] to estimate the size of that population, which disputed the folk wisdom that the city had more rates than peopleBut in any case, reducing the number sounds like a good idea.
[https://www.nature.com/articles/s41562-017-0189-z.epdf?author_access_token=Eb6x88zTNQ7PuVxPt1CpXdRgN0jAjWel9jnR3ZoTv0PlqY8PQKtlL9OP0czNSVZ5rodrqWv-lxLd4whdDH-qvHpF5PQtT1U4AblMVaKnbDH0ctY2yThyrB_ccetKNmK4sasDTgzcxT5_u2wTJ8C6sg%3D%3D Redfine statistical significance], was just published in ''Nature Human Behavior''The subtitle reads,  
"We propose to change the default P-value threshold for statistical significance from 0.05 to 0.005 for claims of
new discoveries."


In his ''Slate'' article, Auerbach questions the mayor's enthusiastic claims of a 70% reduction in select areas, which he likens to other impressive-sounding claims about improvements in homicides, violent crime and pedestrian fatalities.  He worries that by responding to extreme events, the apparent improvements may be due to the regression effect.  We read:
[http://rsos.royalsocietypublishing.org/content/3/9/160384 The natural selection of bad science]
<blockquote>
Regression here refers to the statistical phenomenon that exceptional events are usually just that: exceptions, not the norm. For example, the genes inherited from tall parents generally produce shorter children. The student with the highest score on one test is unlikely to do as well on the next. And locations with the highest crime tend to exhibit lower crime the following year.
</blockquote>
The first example refers to Galton's famous example of heritability of height, but the language is bit loose.  Galton found that children of taller parents tended to be above average in height, but not by quite as much as their parents. (The ''BMJ'' has a good tutorial on [http://www.bmj.com/content/308/6942/1499 regression to the mean] that gives more detail on Galton's findings;  a [http://www.bmj.com/content/309/6957/780 followup piece] gives further examples.)


The ''Slate'' article provides a number of data graphics to illustrate the problem.
[http://www.sciencemag.org/news/2017/07/it-will-be-much-harder-call-new-findings-significant-if-team-gets-its-way It will be much harder to call new findings ‘significant’ if this team gets its way]
 
<center>
[[File:NYC crime Slate.png ‎| 500px]]
</center>


==In progress==
[https://www.nytimes.com/2017/11/07/world/americas/mass-shootings-us-international.html What explains U.S. mass shootings? International comparisons suggest an answer]<br>
by Max Fisher and Josh Keller , ''New York Times'', 7 November 2017
---
[https://www.theguardian.com/us-news/2017/sep/22/college-free-speech-violence-survey-junk-science 'Junk science': experts cast doubt on widely cited college free speech survey]<br>
by Lois Beckett, The Guardian, 22 September 2017


[https://www.washingtonpost.com/opinions/a-chilling-study-shows-how-hostile-college-students-are-toward-free-speech/2017/09/18/cbb1a234-9ca8-11e7-9083-fbfddf6804c2_story.html A chilling study shows how hostile college students are toward free speech]<br>
''Washington Post''
----
----
[https://www.nytimes.com/2017/10/03/us/politics/las-vegas-shooting-gun-claims-fact-check.html Spurious chart, data on N.R.A. spending mislead in gun debate]<br>
by Linda Qiu, ''New York Times'', 3 October 2017


==In progress==
http://www.aei.org/publication/chart-of-the-day-more-guns-less-gun-violence-between-1993-and-2013/
[https://www.forbes.com/sites/kalevleetaru/2017/02/02/lies-damned-lies-and-statistics-how-bad-statistics-are-feeding-fake-news/#1159c15150ca Lies, Damned Lies And Statistics: How Bad Statistics Are Feeding Fake News]<br>
by Kalev Leetaru, ''Forbes'', "Big Data" blog, 2 February 2017
----
----
[http://www.chronicle.com/blogs/letters/statistical-errors-are-often-not-due-to-mathematical-errors/ Statistical errors are often not due to mathematical errors]<br>
[https://www.vox.com/science-and-health/2017/8/28/16211392/100-500-year-flood-meaning The “500-year” flood, explained: why Houston was so underprepared for Hurricane Harvey]<br>
by Brian Zaharatos, letter to the editor, ''Chronicle of Higher Education'', 11 July 2017
by Dara Lind, ''Vox'', 28 August 2017


Zaharatos writes in response to a June 28 article from the Chronicle, entitled [http://www.chronicle.com/article/A-New-Theory-on-How/240470 A new theory on how researchers can solve the reproducibility crisis: Do the math].  While acknowledging some good points raised in the article, he notes that the arguments were undercut by some misinterpretations of statistical concepts, such as this faulty description of significance:
The subtitle notes that Hurricane Harvey has produced Houston's  third “500-year” flood in the past three years.
<blockquote>
[F]or a p-value of 0.05…a study’s finding will be deemed significant if researchers identify a 95-percent chance that it is genuine.
</blockquote>
Regarding the headline, he notes that people's difficulties interpreting statistical studies are not purely mathematical: "Mathematical skills are necessary for success in statistics, but they are far from sufficient. Statisticians — and researchers using statistics — ought to have a nuanced understanding of the concepts that mathematics helps them quantify."
----


[https://www.wsj.com/articles/harveys-test-businesses-struggle-with-flawed-insurance-as-floods-multiply-1504022632 Harvey’s test: Businesses struggle with flawed insurance as floods multiply]<br>
by Ruth Simon and Cameron McWhirter, ''Wall Street Journal'', 29 August 2017


[https://www.washingtonpost.com/news/monkey-cage/wp/2017/07/14/jeff-sessions-used-our-research-to-claim-that-sanctuary-cities-have-more-crime-hes-wrong Jeff Sessions used our research to claim that sanctuary cities have more crime. He’s wrong.]<br>
"Twenty storms causing a billion dollars or more in damage have taken place since 2010, not including Hurricane Harvey, compared with nine billion-dollar floods in the full decade of the 1980s, according to inflation-adjusted estimates from the National Oceanic and Atmospheric Administration."  
by Loren Collingwood and Benjamin Gonzalez-O'Brien, ''Washington Post'', "Monkey Cage" blog,  14 July 2017


[http://www.politifact.com/texas/statements/2017/may/10/sally-hernandez/sally-hernandez-says-cities-labeled-sanctuaries-ha/ Sally Hernandez says cities labeled as sanctuaries have less crime, according to FBI statistics]<br>
Brigitte Baldi StatEd [https://fivethirtyeight.com/features/its-time-to-ditch-the-concept-of-100-year-floods/ It’s time To ditch the concept of ‘100-year floods’]
by W. Gardner Selby, ''Politifact'', 10 May 2017


Half-True
[http://floodsafety.com/national/property/risk/]
Hernandez
"FBI crime statistics have found that labeled ‘sanctuary’ cities experience lower rates of all crime types, including homicides."


— Sally Hernandez on Tuesday, April 18th, 2017 in an oped commentary co-authored by four other Texas sheriffs
[https://pubs.usgs.gov/fs/FS-229-96/ USGS Fact Sheet]
Sally Hernandez says cities labeled as sanctuaries have less crime, according to FBI statistics
----
[https://www.sciencealert.com/watch-here-s-the-best-guide-we-ve-seen-to-how-correlation-and-causation-work Here's Why Sometimes Correlation Does Actually Imply Causation]
----
[https://www.nytimes.com/2017/08/29/magazine/the-new-front-in-the-gerrymandering-wars-democracy-vs-math.html?_r=0 The new front in the gerrymandering wars: Democracy vs. math]


[https://arxiv.org/pdf/1709.01596.pdf Evaluating Partisan Gerrymandering in Wisconsin]


[https://www.nytimes.com/2017/10/06/opinion/sunday/computers-gerrymandering-wisconsin.html How computers turned gerrymandering into a science]<br>
by Jordan Ellenberg, ''Sunday Review'', ''New York Times'', 6 October 2017
----
----


[https://www.nytimes.com/2017/08/02/upshot/its-time-to-end-the-old-debate-over-gerrymandering.html Debate is over: Gerrymandering is crucial to G.O.P.’s hold on House]<br>
[https://www.nytimes.com/2017/08/22/opinion/exxon-climate-change-.html What Exxon Mobil didn’t say about climate change]<br>
by Nate Cohn, ''New York Times'', "TheUpshot" blog, 2 August 2017
by Geoffrey Supran and Naomi Oreskes, ''New York Times'', 22 August 2017
 
----
[https://www.reuters.com/article/us-facebook-advertising-research/facebook-digital-ads-figures-differ-from-census-data-analyst-idUSKCN1BH0H3 Facebook digital ads figures differ from census data: analyst]


==Chance of gun death==
----
http://www.nytimes.com/2015/12/05/upshot/in-other-countries-youre-as-likely-to-be-killed-by-a-falling-object-as-a-gun.html?rref=upshot&module=Ribbon&version=context&region=Header&action=click&contentCollection=The%20Upshot&pgtype=Multimedia
[https://qz.com/1059862/dont-base-your-amazon-purchases-on-the-number-of-reviews-a-product-has/ Don’t base all your Amazon purchases on the number of reviews a product has]<br>
by Corinne Purtill, Quartz, 23 August 2017


[http://journals.sagepub.com/doi/full/10.1177/0956797617711291 The Love of Large Numbers: A Popularity Bias in Consumer Choice]


==Some math doodles==
==Some math doodles==

Revision as of 01:00, 8 November 2017


Forsooth

Quotations

“We know that people tend to overestimate the frequency of well-publicized, spectacular events compared with more commonplace ones; this is a well-understood phenomenon in the literature of risk assessment and leads to the truism that when statistics plays folklore, folklore always wins in a rout.”

-- Donald Kennedy (former president of Stanford University), Academic Duty, Harvard University Press, 1997, p.17

Redefining statistical significance

Scholars take aim at false positives in research
by Thomas Gaulkin, UChicagoNews, 1 September 2017

University Chicago economist John List is one of 72 collaborators whose commentary, Redfine statistical significance, was just published in Nature Human Behavior. The subtitle reads, "We propose to change the default P-value threshold for statistical significance from 0.05 to 0.005 for claims of new discoveries."

The natural selection of bad science

It will be much harder to call new findings ‘significant’ if this team gets its way

In progress

What explains U.S. mass shootings? International comparisons suggest an answer
by Max Fisher and Josh Keller , New York Times, 7 November 2017 --- 'Junk science': experts cast doubt on widely cited college free speech survey
by Lois Beckett, The Guardian, 22 September 2017

A chilling study shows how hostile college students are toward free speech
Washington Post


Spurious chart, data on N.R.A. spending mislead in gun debate
by Linda Qiu, New York Times, 3 October 2017

http://www.aei.org/publication/chart-of-the-day-more-guns-less-gun-violence-between-1993-and-2013/


The “500-year” flood, explained: why Houston was so underprepared for Hurricane Harvey
by Dara Lind, Vox, 28 August 2017

The subtitle notes that Hurricane Harvey has produced Houston's third “500-year” flood in the past three years.

Harvey’s test: Businesses struggle with flawed insurance as floods multiply
by Ruth Simon and Cameron McWhirter, Wall Street Journal, 29 August 2017

"Twenty storms causing a billion dollars or more in damage have taken place since 2010, not including Hurricane Harvey, compared with nine billion-dollar floods in the full decade of the 1980s, according to inflation-adjusted estimates from the National Oceanic and Atmospheric Administration."

Brigitte Baldi StatEd It’s time To ditch the concept of ‘100-year floods’

[1]

USGS Fact Sheet


Here's Why Sometimes Correlation Does Actually Imply Causation


The new front in the gerrymandering wars: Democracy vs. math

Evaluating Partisan Gerrymandering in Wisconsin

How computers turned gerrymandering into a science
by Jordan Ellenberg, Sunday Review, New York Times, 6 October 2017


What Exxon Mobil didn’t say about climate change
by Geoffrey Supran and Naomi Oreskes, New York Times, 22 August 2017


Facebook digital ads figures differ from census data: analyst


Don’t base all your Amazon purchases on the number of reviews a product has
by Corinne Purtill, Quartz, 23 August 2017

The Love of Large Numbers: A Popularity Bias in Consumer Choice

Some math doodles

<math>P \left({A_1 \cup A_2}\right) = P\left({A_1}\right) + P\left({A_2}\right) -P \left({A_1 \cap A_2}\right)</math>

<math>P(E) = {n \choose k} p^k (1-p)^{ n-k}</math>

<math>\hat{p}(H|H)</math>

<math>\hat{p}(H|HH)</math>

Accidental insights

My collective understanding of Power Laws would fit beneath the shallow end of the long tail. Curiosity, however, easily fills the fat end. I long have been intrigued by the concept and the surprisingly common appearance of power laws in varied natural, social and organizational dynamics. But, am I just seeing a statistical novelty or is there meaning and utility in Power Law relationships? Here’s a case in point.

While carrying a pair of 10 lb. hand weights one, by chance, slipped from my grasp and fell onto a piece of ceramic tile I had left on the carpeted floor. The fractured tile was inconsequential, meant for the trash.

BrokenTile.jpg

As I stared, slightly annoyed, at the mess, a favorite maxim of the Greek philosopher, Epictetus, came to mind: “On the occasion of every accident that befalls you, turn to yourself and ask what power you have to put it to use.” Could this array of large and small polygons form a Power Law? With curiosity piqued, I collected all the fragments and measured the area of each piece.

Piece Sq. Inches % of Total
1 43.25 31.9%
2 35.25 26.0%
3 23.25 17.2%
4 14.10 10.4%
5 7.10 5.2%
6 4.70 3.5%
7 3.60 2.7%
8 3.03 2.2%
9 0.66 0.5%
10 0.61 0.5%
Montante plot1.png

The data and plot look like a Power Law distribution. The first plot is an exponential fit of percent total area. The second plot is same data on a log normal format. Clue: Ok, data fits a straight line. I found myself again in the shallow end of the knowledge curve. Does the data reflect a Power Law or something else, and if it does what does it reflect? What insights can I gain from this accident? Favorite maxims of Epictetus and Pasteur echoed in my head: “On the occasion of every accident that befalls you, remember to turn to yourself and inquire what power you have to turn it to use” and “Chance favors only the prepared mind.”

Montante plot2.png

My “prepared” mind searched for answers, leading me down varied learning paths. Tapping the power of networks, I dropped a note to Chance News editor Bill Peterson. His quick web search surfaced a story from Nature News on research by Hans Herrmann, et. al. Shattered eggs reveal secrets of explosions. As described there, researchers have found power-law relationships for the fragments produced by shattering a pane of glass or breaking a solid object, such as a stone. Seems there is a science underpinning how things break and explode; potentially useful in Forensic reconstructions. Bill also provided a link to a vignette from CRAN describing a maximum likelihood procedure for fitting a Power Law relationship. I am now learning my way through that.

Submitted by William Montante