by Caleb Scharf · 8 Sep 2014 · 321pp · 95,858 words
my measurements to look like if my hypothesis is correct. In addition to the complications posed by random sampling, there is the issue of more systematic bias to my survey. Maybe Cheshire cats are typically overweight and slow, so it’s easier for me to catch them and count more of them
by Sarah Boslaugh · 10 Nov 2012
expect random error to affect an individual’s score consistently in one direction or the other. Random error makes measurement less precise but does not systematically bias results because it can be expected to have a positive effect on one occasion and a negative effect on another, thus canceling itself out over
…
diameter one µm (micrometer), any bacteria smaller than this will not be part of the population that you are observing. This sampling limitation will introduce systematic bias into the study; however, as long as you are clear that the population about which you can make inferences is bacteria of diameter greater than
by Daniel Kahneman · 24 Oct 2011 · 654pp · 191,864 words
common basis. On the other hand, the errors that individuals make are independent of the errors made by others, and (in the absence of a systematic bias) they tend to average to zero. However, the magic of error reduction works well only when the observations are independent and their errors uncorrelated. If
by Ben Goldacre · 1 Jan 2012 · 402pp · 129,876 words
you’d expect to see, over time, in any trial. Such rules are useful because they restrict the intrusion of human judgement, which can introduce systematic bias. But whatever we do about early stopping in medicine, it will probably pollute the data. A review from 2010 took around a hundred truncated trials
by Cass R. Sunstein · 23 Aug 2006
point that bears on the foundations of democracy itself. But accuracy is likely only under identifiable conditions, in which people do not suffer from a systematic bias that makes their answers worse than random. If we asked everyone in the world to estimate the population of Egypt, or to say how many
…
can identify two situations in which the judgment of a statistical group will be wrong. The first are those in which group members show a systematic bias. The second, a generalization of the first, are those in which their answers are worse than random. The failures of statistical judgments in these circumstances
…
by private and public institutions. Often statistical groups will be wrong. Sometimes they will be disastrously wrong. The (Occasional) Power of Numbers / 33 Bias / A systematic bias in one or another direction will create serious problems for the group’s answers. Suppose that a large number of Nazis were asked to answer
…
depends on whether the relevant experts were in a position to offer good answers on the questions at hand. If the experts suffer from a systematic bias, or if their answers are worse than random, any effort to aggregate expert judgments will produce blunders. Maybe we shouldn’t trust the people who
…
it might be too thin simply because most institutions will have few investors;53 another is that members of the organization might suffer from a systematic bias. Aware of these risks, an institution might create a public market, available to all, believing that through this route it will obtain more accurate results
…
, by 2100, to global warming. Why should we trust the average answer? Where people’s answers are worse than random, and where there is a systematic bias, the average answer is not going to be accurate. As I have emphasized, markets have many advantages over surveys because they create incentives for people
…
Sun Microsystems, 171 Supreme Court, U.S., 134–35, 136, 184 Surowiecki, James, 21 surveys, 8, 198–200 synergy, deliberating groups and, 54–55, 220 systematic bias, 33–36, 41, 132, 199, 219 tennis, 140 terrorism, 29 individual rights and, 214 predictions market and, 107–9, 142–43 group polarization and, 93
by David Spiegelhalter · 14 Oct 2019 · 442pp · 94,734 words
evidence is actually worth. For example, intensive analysis of data sets derived from routine data can increase the possibility of false discoveries, both due to systematic bias inherent in the data sources and from carrying out many analyses and only reporting whatever looks most interesting, a practice sometimes known as ‘data-dredging
…
occasion, and so being a precise or repeatable number. Valid, in the sense of measuring what you really want to measure, and not having a systematic bias. Figure 3.1 Process of inductive inference: each arrow can be interpreted as ‘tells us something about’1 For example, the adequacy of the sex
…
we hadn’t done X?’). We are a long way from AI having this ability. This book emphasizes the classic statistical problems of small samples, systematic bias (in the statistical sense) and lack of generalizability to new situations. The list of challenges for algorithms shows that although having masses of data may
…
is conditional not only on the truth of the null hypothesis, but also on all other assumptions underlying the statistical model, such as lack of systematic bias, independent observations, and so on. This whole process has become known as Null Hypothesis Significance Testing (NHST) and, as we shall see below, it has
…
with a control group. What is the statistical uncertainty / confidence in the findings? Check margins of error, confidence intervals, statistical significance, sample size, multiple comparisons, systematic bias. Is the summary appropriate? Check appropriate use of averages, variability, relative and absolute risks. HOW TRUSTWORTHY IS THE SOURCE? How reliable is the source of
by Tim Harford · 2 Feb 2021 · 428pp · 103,544 words
, 149, 151, 154 and Google Flu Trends, 153–57 vs. human judgment, 167–71 pattern-recognizing, 183 and proliferation of big data, 157–59 and systematic bias, 166 and teacher evaluations, 163–64 trustworthiness of, 179–82 See also big data Allegory of Faith, The (Vermeer), 29–30 Allied Art Commission, 21
…
criminal justice, 176–79 in sampling, 135–38, 142–45, 147–51 selection bias, 2, 245–46 survivorship bias, 109–10, 112–13, 122–26 systematic bias in algorithms, 166 and value of statistical knowledge, 17 big data and certification of researchers, 182 and criminal justice, 176–79 and excessive credulity in
by Sebastien Page · 4 Nov 2020 · 367pp · 97,136 words
bps—a fraction of our 300 bps of precost alpha. We left it to the reader to interpret whether this slight excess beta constitutes a systematic bias, but if so, the impact remains small relative to the magnitude of the net alphas. Regarding liquidity, our outsiders have a similar liquidity profile, on
by David Spiegelhalter · 2 Sep 2019 · 404pp · 92,713 words
evidence is actually worth. For example, intensive analysis of data sets derived from routine data can increase the possibility of false discoveries, both due to systematic bias inherent in the data sources and from carrying out many analyses and only reporting whatever looks most interesting, a practice sometimes known as ‘data-dredging
…
occasion, and so being a precise or repeatable number. • Valid, in the sense of measuring what you really want to measure, and not having a systematic bias. Figure 3.1 Process of inductive inference: each arrow can be interpreted as ‘tells us something about’1 For example, the adequacy of the sex
…
we hadn’t done X?’). We are a long way from AI having this ability. This book emphasizes the classic statistical problems of small samples, systematic bias (in the statistical sense) and lack of generalizability to new situations. The list of challenges for algorithms shows that although having masses of data may
…
is conditional not only on the truth of the null hypothesis, but also on all other assumptions underlying the statistical model, such as lack of systematic bias, independent observations, and so on. This whole process has become known as Null Hypothesis Significance Testing (NHST) and, as we shall see below, it has
…
a control group. 2. What is the statistical uncertainty / confidence in the findings? Check margins of error, confidence intervals, statistical significance, sample size, multiple comparisons, systematic bias. 3. Is the summary appropriate? Check appropriate use of averages, variability, relative and absolute risks. HOW TRUSTWORTHY IS THE SOURCE? 4. How reliable is the
by Ben Goldacre · 1 Jan 2008 · 322pp · 107,576 words
fourth the placebo, and so on. This sounds fair enough, but in fact it’s a glaring hole that opens your trial up to possible systematic bias. Let’s imagine there is a patient who the homeopath believes to be a no-hoper, a heart-sink patient who’ll never really get
by Trisha Greenhalgh · 18 Nov 2010 · 321pp · 97,661 words
by Andrew W. Lo · 3 Apr 2017 · 733pp · 179,391 words
by Igor Tulchinsky · 30 Sep 2019 · 321pp
by Victor A. Canto · 2 Jan 2005 · 337pp · 89,075 words
by Noam Chomsky · 24 Oct 2014
by Norman Finkelstein · 9 Jan 2018 · 578pp · 170,758 words
by Michael Lewis · 6 Dec 2016 · 336pp · 113,519 words
by Tom Chivers · 12 Jun 2019 · 289pp · 92,714 words
by Daniel Simons and Christopher Chabris · 10 Jul 2023 · 338pp · 104,815 words
by Ronald Bailey · 20 Jul 2015 · 417pp · 109,367 words
by Philippe van Parijs and Yannick Vanderborght · 20 Mar 2017
by Seth Stephens-Davidowitz · 9 May 2022 · 287pp · 69,655 words
by Samuel Arbesman · 31 Aug 2012 · 284pp · 79,265 words
by Richard A. Brealey, Stewart C. Myers and Franklin Allen · 15 Feb 2014
by Martin Kleppmann · 16 Mar 2017 · 1,237pp · 227,370 words
by Lawrence Lessig · 14 Jul 2001 · 494pp · 142,285 words
by Jevin D. West and Carl T. Bergstrom · 3 Aug 2020
by Tom Chivers and David Chivers · 18 Mar 2021 · 172pp · 51,837 words
by Richard H. Thaler · 10 May 2015 · 500pp · 145,005 words
by Michael Huemer · 29 Oct 2012 · 577pp · 149,554 words
by Toby Segaran and Jeff Hammerbacher · 1 Jul 2009
by Martin Kleppmann · 17 Apr 2017
by Abhijit V. Banerjee and Esther Duflo · 12 Nov 2019 · 470pp · 148,730 words
by Richard Seymour
by Ray Moynihan and Barbara Mintzes · 1 Oct 2010 · 269pp · 77,042 words
by Annie Duke · 6 Feb 2018 · 288pp · 81,253 words
by Tom Rosenstiel · 17 Aug 2026 · 400pp · 107,776 words
by Nassim Nicholas Taleb · 20 Feb 2018 · 306pp · 82,765 words
by Eric von Hippel · 1 Apr 2005 · 220pp · 73,451 words
by Michael Strevens · 12 Oct 2020
by Rick Perlstein · 1 Jan 2008 · 1,351pp · 404,177 words
by Jeanne Lenzer · 12 Dec 2017 · 328pp · 98,127 words
by Erica Thompson · 6 Dec 2022 · 250pp · 79,360 words
by Hannah Fry · 17 Sep 2018 · 296pp · 78,631 words
by Milton Friedman · 1 Jan 1992 · 275pp · 82,640 words
by Bruce Frey · 9 May 2006 · 755pp · 121,290 words
by Carol Alexander · 2 Jan 2007 · 320pp · 33,385 words
by Sabine Hossenfelder · 11 Jun 2018 · 340pp · 91,416 words
by Juliet B. Schor · 12 May 2010 · 309pp · 78,361 words
by Geoffrey West · 15 May 2017 · 578pp · 168,350 words
by Maneet Ahuja, Myron Scholes and Mohamed El-Erian · 29 May 2012 · 302pp · 86,614 words
by Andrew Yang · 15 Nov 2021
by Lawrence Freedman · 9 Oct 2017 · 592pp · 161,798 words
by Viktor Mayer-Schonberger and Kenneth Cukier · 5 Mar 2013 · 304pp · 82,395 words
by David Callahan · 9 Aug 2010
by Viktor Mayer-Schönberger · 1 Jan 2009 · 263pp · 75,610 words
by Philip Augar · 20 Apr 2005 · 290pp · 83,248 words