andrew_gelman_stats andrew_gelman_stats-2012 andrew_gelman_stats-2012-1209 knowledge-graph by maker-knowledge-mining
Source: html
Introduction: Philipp Doebler writes: I was quite happy that recently you shared some thoughts of yours and others on meta-analysis. I especially liked the slides by Chris Schmid that you linked from your blog. A large portion of my work deals with meta-analysis and I am also fond of using Bayesian methods (actually two of the projects I am working on are very Bayesian), though I can not say I have opinions with respect to the underlying philosophy. I would say though, that I do share your view that there are good reasons to use informative priors. The reason I am writing to you is that this leads to the following dilemma, which is puzzling me. Say a number of scientists conduct similar studies over the years and all of them did this in a Bayesian fashion. If each of the groups used informative priors based on the research of existing groups the priors could become more and more informative over the years, since more and more is known over the subject. At least in smallish studies these p
sentIndex sentText sentNum sentScore
1 Philipp Doebler writes: I was quite happy that recently you shared some thoughts of yours and others on meta-analysis. [sent-1, score-0.079]
2 I especially liked the slides by Chris Schmid that you linked from your blog. [sent-2, score-0.219]
3 A large portion of my work deals with meta-analysis and I am also fond of using Bayesian methods (actually two of the projects I am working on are very Bayesian), though I can not say I have opinions with respect to the underlying philosophy. [sent-3, score-0.716]
4 I would say though, that I do share your view that there are good reasons to use informative priors. [sent-4, score-0.425]
5 The reason I am writing to you is that this leads to the following dilemma, which is puzzling me. [sent-5, score-0.232]
6 Say a number of scientists conduct similar studies over the years and all of them did this in a Bayesian fashion. [sent-6, score-0.586]
7 If each of the groups used informative priors based on the research of existing groups the priors could become more and more informative over the years, since more and more is known over the subject. [sent-7, score-1.382]
8 At least in smallish studies these priors will have an impact on the conclusion, and the impact will increase with time. [sent-8, score-1.011]
9 The worst case might be, that a) there is a form of regression to the mean of outcomes the individual studies and b) the variance of the effect sizes are smaller due to the highly informative priors. [sent-9, score-1.159]
10 In some sense each of the primary studies is boosting its sample size by using informative priors. [sent-10, score-1.239]
11 While this all makes perfect sense on the level of the primary studies, on the meta-analytic level the studies look as if they had achieved more precise estimates then they actually have and also there might be less heterogeneity observed than there really is. [sent-11, score-1.553]
12 One could even say, that the newer studies are forstalling the meta-analysis. [sent-12, score-0.507]
13 I am not sure if the above leads to the advice to use non-informative priors on the primary study level, so that primary study level outcomes are not influenced by other studies, or if the above only underlines the need to report outcomes in primary studies for more than one prior. [sent-13, score-2.724]
14 It is difficult to combine posterior distributions as there is the risk of counting some information multiple times. [sent-16, score-0.168]
15 Sometimes I say, As a Bayesian I want scientists to report their data non-Bayesianly. [sent-17, score-0.191]
wordName wordTfidf (topN-words)
[('studies', 0.402), ('primary', 0.357), ('informative', 0.3), ('priors', 0.245), ('outcomes', 0.187), ('level', 0.171), ('bayesian', 0.136), ('leads', 0.132), ('say', 0.125), ('impact', 0.125), ('boosting', 0.118), ('fond', 0.118), ('schmid', 0.118), ('dilemma', 0.118), ('smallish', 0.114), ('groups', 0.113), ('newer', 0.105), ('deals', 0.101), ('puzzling', 0.1), ('scientists', 0.099), ('heterogeneity', 0.098), ('portion', 0.096), ('achieved', 0.093), ('report', 0.092), ('influenced', 0.091), ('combine', 0.086), ('conduct', 0.085), ('welcome', 0.085), ('counting', 0.082), ('shared', 0.079), ('slides', 0.078), ('worst', 0.075), ('projects', 0.075), ('precise', 0.073), ('study', 0.073), ('liked', 0.073), ('opinions', 0.07), ('linked', 0.068), ('though', 0.068), ('sizes', 0.067), ('smaller', 0.067), ('existing', 0.066), ('views', 0.066), ('conclusion', 0.066), ('perfect', 0.065), ('chris', 0.065), ('respect', 0.063), ('sense', 0.062), ('observed', 0.061), ('due', 0.061)]
simIndex simValue blogId blogTitle
same-blog 1 1.0 1209 andrew gelman stats-2012-03-12-As a Bayesian I want scientists to report their data non-Bayesianly
Introduction: Philipp Doebler writes: I was quite happy that recently you shared some thoughts of yours and others on meta-analysis. I especially liked the slides by Chris Schmid that you linked from your blog. A large portion of my work deals with meta-analysis and I am also fond of using Bayesian methods (actually two of the projects I am working on are very Bayesian), though I can not say I have opinions with respect to the underlying philosophy. I would say though, that I do share your view that there are good reasons to use informative priors. The reason I am writing to you is that this leads to the following dilemma, which is puzzling me. Say a number of scientists conduct similar studies over the years and all of them did this in a Bayesian fashion. If each of the groups used informative priors based on the research of existing groups the priors could become more and more informative over the years, since more and more is known over the subject. At least in smallish studies these p
2 0.26875666 1926 andrew gelman stats-2013-07-05-More plain old everyday Bayesianism
Introduction: Following up on this story , Bob Goodman writes: A most recent issue of the New England Journal of Medicine published a study entitled “Biventricular Pacing for Atrioventricular Block and Systolic Dysfunction,” (N Engl J Med 2013; 368:1585-1593), whereby “A hierarchical Bayesian proportional-hazards model was used for analysis of the primary outcome.” It is the first study I can recall in this journal that has reported on Table 2 (primary outcomes) “The Posterior Probability of Hazard Ratio < 1" (which in this case was .9978). This is ok, but to be really picky I will say that there’s typically not so much reason to care about the posterior probability that the effect is greater than 1; I’d rather have an estimate of the effect. Also we should be using informative priors.
3 0.2216128 1092 andrew gelman stats-2011-12-29-More by Berger and me on weakly informative priors
Introduction: A couple days ago we discussed some remarks by Tony O’Hagan and Jim Berger on weakly informative priors. Jim followed up on Deborah Mayo’s blog with this: Objective Bayesian priors are often improper (i.e., have infinite total mass), but this is not a problem when they are developed correctly. But not every improper prior is satisfactory. For instance, the constant prior is known to be unsatisfactory in many situations. The ‘solution’ pseudo-Bayesians often use is to choose a constant prior over a large but bounded set (a ‘weakly informative’ prior), saying it is now proper and so all is well. This is not true; if the constant prior on the whole parameter space is bad, so will be the constant prior over the bounded set. The problem is, in part, that some people confuse proper priors with subjective priors and, having learned that true subjective priors are fine, incorrectly presume that weakly informative proper priors are fine. I have a few reactions to this: 1. I agree
Introduction: Deborah Mayo sent me this quote from Jim Berger: Too often I see people pretending to be subjectivists, and then using “weakly informative” priors that the objective Bayesian community knows are terrible and will give ridiculous answers; subjectivism is then being used as a shield to hide ignorance. . . . In my own more provocative moments, I claim that the only true subjectivists are the objective Bayesians, because they refuse to use subjectivism as a shield against criticism of sloppy pseudo-Bayesian practice. This caught my attention because I’ve become more and more convinced that weakly informative priors are the right way to go in many different situations. I don’t think Berger was talking about me , though, as the above quote came from a publication in 2006, at which time I’d only started writing about weakly informative priors. Going back to Berger’s article , I see that his “weakly informative priors” remark was aimed at this article by Anthony O’Hagan, who w
5 0.20022213 850 andrew gelman stats-2011-08-11-Understanding how estimates change when you move to a multilevel model
Introduction: Ramu Sudhagoni writes: I am working on combining three longitudinal studies using Bayesian hierarchical technique. In each study, I have at least 70 subjects follow up on 5 different visit months. My model consists of 10 different covariates including longitudinal and cross-sectional effects. Mixed models are used to fit the three studies individually using Bayesian approach and I noticed that few covariates were significant. When I combined using three level hierarchical approach, all the covariates became non-significant at the population level, and large estimates were found for variance parameters at the population level. I am struggling to understand why I am getting large variances at population level and wider credible intervals. I assumed non-informative normal priors for all my cross sectional and longitudinal effects, and non-informative inverse-gamma priors for variance parameters. I followed the approach explained by Inoue et al. (Title: Combining Longitudinal Studie
6 0.16792339 846 andrew gelman stats-2011-08-09-Default priors update?
7 0.16754998 1955 andrew gelman stats-2013-07-25-Bayes-respecting experimental design and other things
8 0.16682845 2368 andrew gelman stats-2014-06-11-Bayes in the research conversation
9 0.15763602 2268 andrew gelman stats-2014-03-26-New research journal on observational studies
10 0.14714783 1946 andrew gelman stats-2013-07-19-Prior distributions on derived quantities rather than on parameters themselves
11 0.13842729 1858 andrew gelman stats-2013-05-15-Reputations changeable, situations tolerable
12 0.13689649 1465 andrew gelman stats-2012-08-21-D. Buggin
13 0.13679364 2109 andrew gelman stats-2013-11-21-Hidden dangers of noninformative priors
14 0.13664505 2227 andrew gelman stats-2014-02-27-“What Can we Learn from the Many Labs Replication Project?”
15 0.13657875 1877 andrew gelman stats-2013-05-30-Infill asymptotics and sprawl asymptotics
16 0.1347907 1454 andrew gelman stats-2012-08-11-Weakly informative priors for Bayesian nonparametric models?
17 0.13326757 1046 andrew gelman stats-2011-12-07-Neutral noninformative and informative conjugate beta and gamma prior distributions
18 0.13156863 1695 andrew gelman stats-2013-01-28-Economists argue about Bayes
20 0.12629497 468 andrew gelman stats-2010-12-15-Weakly informative priors and imprecise probabilities
topicId topicWeight
[(0, 0.217), (1, 0.112), (2, 0.028), (3, -0.054), (4, -0.052), (5, -0.033), (6, 0.044), (7, 0.026), (8, -0.119), (9, 0.048), (10, 0.018), (11, -0.006), (12, 0.095), (13, 0.025), (14, 0.078), (15, 0.022), (16, 0.023), (17, 0.031), (18, -0.01), (19, 0.062), (20, -0.088), (21, 0.038), (22, -0.029), (23, 0.051), (24, -0.033), (25, -0.01), (26, 0.03), (27, -0.005), (28, -0.009), (29, 0.047), (30, -0.041), (31, -0.062), (32, 0.014), (33, -0.009), (34, 0.041), (35, 0.059), (36, -0.017), (37, 0.006), (38, 0.08), (39, 0.007), (40, -0.008), (41, -0.009), (42, 0.097), (43, -0.002), (44, 0.044), (45, -0.057), (46, -0.048), (47, 0.056), (48, 0.013), (49, 0.006)]
simIndex simValue blogId blogTitle
same-blog 1 0.97339052 1209 andrew gelman stats-2012-03-12-As a Bayesian I want scientists to report their data non-Bayesianly
Introduction: Philipp Doebler writes: I was quite happy that recently you shared some thoughts of yours and others on meta-analysis. I especially liked the slides by Chris Schmid that you linked from your blog. A large portion of my work deals with meta-analysis and I am also fond of using Bayesian methods (actually two of the projects I am working on are very Bayesian), though I can not say I have opinions with respect to the underlying philosophy. I would say though, that I do share your view that there are good reasons to use informative priors. The reason I am writing to you is that this leads to the following dilemma, which is puzzling me. Say a number of scientists conduct similar studies over the years and all of them did this in a Bayesian fashion. If each of the groups used informative priors based on the research of existing groups the priors could become more and more informative over the years, since more and more is known over the subject. At least in smallish studies these p
2 0.77137166 468 andrew gelman stats-2010-12-15-Weakly informative priors and imprecise probabilities
Introduction: Giorgio Corani writes: Your work on weakly informative priors is close to some research I [Corani] did (together with Prof. Zaffalon) in the last years using the so-called imprecise probabilities. The idea is to work with a set of priors (containing even very different priors); to update them via Bayes’ rule and then compute a set of posteriors. The set of priors is convex and the priors are Dirichlet (thus, conjugate to the likelihood); this allows to compute the set of posteriors exactly and efficiently. I [Corani] have used this approach for classification, extending naive Bayes and TAN to imprecise probabilities. Classifiers based on imprecise probabilities return more classes when they find that the most probable class is prior-dependent, i.e., if picking different priors in the convex set leads to identify different classes as the most probable one. Instead of returning a single (unreliable) prior-dependent class, credal classifiers in this case preserve reliability by
Introduction: Deborah Mayo sent me this quote from Jim Berger: Too often I see people pretending to be subjectivists, and then using “weakly informative” priors that the objective Bayesian community knows are terrible and will give ridiculous answers; subjectivism is then being used as a shield to hide ignorance. . . . In my own more provocative moments, I claim that the only true subjectivists are the objective Bayesians, because they refuse to use subjectivism as a shield against criticism of sloppy pseudo-Bayesian practice. This caught my attention because I’ve become more and more convinced that weakly informative priors are the right way to go in many different situations. I don’t think Berger was talking about me , though, as the above quote came from a publication in 2006, at which time I’d only started writing about weakly informative priors. Going back to Berger’s article , I see that his “weakly informative priors” remark was aimed at this article by Anthony O’Hagan, who w
4 0.72200465 850 andrew gelman stats-2011-08-11-Understanding how estimates change when you move to a multilevel model
Introduction: Ramu Sudhagoni writes: I am working on combining three longitudinal studies using Bayesian hierarchical technique. In each study, I have at least 70 subjects follow up on 5 different visit months. My model consists of 10 different covariates including longitudinal and cross-sectional effects. Mixed models are used to fit the three studies individually using Bayesian approach and I noticed that few covariates were significant. When I combined using three level hierarchical approach, all the covariates became non-significant at the population level, and large estimates were found for variance parameters at the population level. I am struggling to understand why I am getting large variances at population level and wider credible intervals. I assumed non-informative normal priors for all my cross sectional and longitudinal effects, and non-informative inverse-gamma priors for variance parameters. I followed the approach explained by Inoue et al. (Title: Combining Longitudinal Studie
5 0.70757961 1092 andrew gelman stats-2011-12-29-More by Berger and me on weakly informative priors
Introduction: A couple days ago we discussed some remarks by Tony O’Hagan and Jim Berger on weakly informative priors. Jim followed up on Deborah Mayo’s blog with this: Objective Bayesian priors are often improper (i.e., have infinite total mass), but this is not a problem when they are developed correctly. But not every improper prior is satisfactory. For instance, the constant prior is known to be unsatisfactory in many situations. The ‘solution’ pseudo-Bayesians often use is to choose a constant prior over a large but bounded set (a ‘weakly informative’ prior), saying it is now proper and so all is well. This is not true; if the constant prior on the whole parameter space is bad, so will be the constant prior over the bounded set. The problem is, in part, that some people confuse proper priors with subjective priors and, having learned that true subjective priors are fine, incorrectly presume that weakly informative proper priors are fine. I have a few reactions to this: 1. I agree
6 0.70524192 846 andrew gelman stats-2011-08-09-Default priors update?
7 0.69717634 1926 andrew gelman stats-2013-07-05-More plain old everyday Bayesianism
9 0.69127858 801 andrew gelman stats-2011-07-13-On the half-Cauchy prior for a global scale parameter
10 0.6893301 1946 andrew gelman stats-2013-07-19-Prior distributions on derived quantities rather than on parameters themselves
11 0.67727566 63 andrew gelman stats-2010-06-02-The problem of overestimation of group-level variance parameters
12 0.67477447 446 andrew gelman stats-2010-12-03-Is 0.05 too strict as a p-value threshold?
13 0.67315668 1877 andrew gelman stats-2013-05-30-Infill asymptotics and sprawl asymptotics
14 0.67046058 1149 andrew gelman stats-2012-02-01-Philosophy of Bayesian statistics: my reactions to Cox and Mayo
15 0.66705132 1157 andrew gelman stats-2012-02-07-Philosophy of Bayesian statistics: my reactions to Hendry
16 0.65489113 1858 andrew gelman stats-2013-05-15-Reputations changeable, situations tolerable
17 0.65301132 1454 andrew gelman stats-2012-08-11-Weakly informative priors for Bayesian nonparametric models?
18 0.65223926 1989 andrew gelman stats-2013-08-20-Correcting for multiple comparisons in a Bayesian regression model
19 0.65006268 1674 andrew gelman stats-2013-01-15-Prior Selection for Vector Autoregressions
20 0.64840263 2252 andrew gelman stats-2014-03-17-Ma conférence demain (mardi) à l’École Polytechnique
topicId topicWeight
[(10, 0.057), (15, 0.014), (16, 0.052), (21, 0.023), (23, 0.013), (24, 0.237), (42, 0.014), (45, 0.011), (55, 0.023), (63, 0.012), (69, 0.012), (95, 0.028), (98, 0.012), (99, 0.393)]
simIndex simValue blogId blogTitle
1 0.99216586 1363 andrew gelman stats-2012-06-03-Question about predictive checks
Introduction: Klaas Metselaar writes: I [Metselaar] am currently involved in a discussion about the use of the notion “predictive” as used in “posterior predictive check”. I would argue that the notion “predictive” should be reserved for posterior checks using information not used in the determination of the posterior. I quote from the discussion: “However, the predictive uncertainty in a Bayesian calculation requires sampling from all the random variables, and this includes both the model parameters and the residual error”. My [Metselaar's] comment: This may be exactly the point I am worried about: shouldn’t the predictive uncertainty be defined as sampling from the posterior parameter distribution + residual error + sampling from the prediction error distribution? Residual error reduces to measurement error in the case of a model which is perfect for the sample of experiments. Measurement error could be reduced to almost zero by ideal and perfect measurement instruments. I would h
2 0.98833776 1974 andrew gelman stats-2013-08-08-Statistical significance and the dangerous lure of certainty
Introduction: In a discussion of some of the recent controversy over promiscuously statistically-significant science, Jeff Leek Rafael Irizarry points out there is a tradeoff between stringency and discovery and suggests that raising the bar of statistical significance (for example, to the .01 or .001 level instead of the conventional .05) will reduce the noise level but will also reduce the rate of identification of actual discoveries. I agree. But I should clarify that when I criticize a claim of statistical significance, arguing that the claimed “p less than .05″ could easily occur under the null hypothesis, given that the hypothesis test that is chosen is contingent on the data (see examples here of clothing and menstrual cycle, arm circumference and political attitudes, and ESP), I am not recommending a switch to a more stringent p-value threshold. Rather, I would prefer p-values not to be used as a threshold for publication at all. Here’s my point: The question is not whether
3 0.98823488 37 andrew gelman stats-2010-05-17-Is chartjunk really “more useful” than plain graphs? I don’t think so.
Introduction: Helen DeWitt links to this blog that reports on a study by Scott Bateman, Carl Gutwin, David McDine, Regan Mandryk, Aaron Genest, and Christopher Brooks that claims the following: Guidelines for designing information charts often state that the presentation should reduce ‘chart junk’–visual embellishments that are not essential to understanding the data. . . . we conducted an experiment that compared embellished charts with plain ones, and measured both interpretation accuracy and long-term recall. We found that people’s accuracy in describing the embellished charts was no worse than for plain charts, and that their recall after a two-to-three-week gap was significantly better. As the above-linked blogger puts it, “chartjunk is more useful than plain graphs. . . . Tufte is not going to like this.” I can’t speak for Ed Tufte, but I’m not gonna take this claim about chartjunk lying down. I have two points to make which I hope can stop the above-linked study from being sla
4 0.98740971 970 andrew gelman stats-2011-10-24-Bell Labs
Introduction: Sining Chen told me they’re hiring in the statistics group at Bell Labs . I’ll do my bit for economic stimulus by announcing this job (see below). I love Bell Labs. I worked there for three summers, in a physics lab in 1985-86 under the supervision of Loren Pfeiffer, and by myself in the statistics group in 1990. I learned a lot working for Loren. He was a really smart and driven guy. His lab was a small set of rooms—in Bell Labs, everything’s in a small room, as they value the positive externality of close physical proximity of different labs, which you get by making each lab compact—and it was Loren, his assistant (a guy named Ken West who kept everything running in the lab), and three summer students: me, Gowton Achaibar, and a girl whose name I’ve forgotten. Gowtan and I had a lot of fun chatting in the lab. One day I made a silly comment about Gowton’s accent—he was from Guyana and pronounced “three” as “tree”—and then I apologized and said: Hey, here I am making fun o
5 0.98690295 1744 andrew gelman stats-2013-03-01-Why big effects are more important than small effects
Introduction: The title of this post is silly but I have an important point to make, regarding an implicit model which I think many people assume even though it does not really make sense. Following a link from Sanjay Srivastava, I came across a post from David Funder saying that it’s useful to talk about the sizes of effects (I actually prefer the term “comparisons” so as to avoid the causal baggage) rather than just their signs. I agree , and I wanted to elaborate a bit on a point that comes up in Funder’s discussion. He quotes an (unnamed) prominent social psychologist as writing: The key to our research . . . [is not] to accurately estimate effect size. If I were testing an advertisement for a marketing research firm and wanted to be sure that the cost of the ad would produce enough sales to make it worthwhile, effect size would be crucial. But when I am testing a theory about whether, say, positive mood reduces information processing in comparison with negative mood, I am worried abou
7 0.98595285 1402 andrew gelman stats-2012-07-01-Ice cream! and temperature
same-blog 8 0.98514259 1209 andrew gelman stats-2012-03-12-As a Bayesian I want scientists to report their data non-Bayesianly
9 0.98438799 1941 andrew gelman stats-2013-07-16-Priors
10 0.98434818 2129 andrew gelman stats-2013-12-10-Cross-validation and Bayesian estimation of tuning parameters
11 0.98429632 2200 andrew gelman stats-2014-02-05-Prior distribution for a predicted probability
13 0.98413289 247 andrew gelman stats-2010-09-01-How does Bayes do it?
14 0.98394048 2109 andrew gelman stats-2013-11-21-Hidden dangers of noninformative priors
15 0.98371577 2266 andrew gelman stats-2014-03-25-A statistical graphics course and statistical graphics advice
16 0.98361367 1644 andrew gelman stats-2012-12-30-Fixed effects, followed by Bayes shrinkage?
17 0.98255759 1150 andrew gelman stats-2012-02-02-The inevitable problems with statistical significance and 95% intervals
19 0.98178303 963 andrew gelman stats-2011-10-18-Question on Type M errors
20 0.98164892 1946 andrew gelman stats-2013-07-19-Prior distributions on derived quantities rather than on parameters themselves