andrew_gelman_stats andrew_gelman_stats-2012 andrew_gelman_stats-2012-1520 knowledge-graph by maker-knowledge-mining
Source: html
Introduction: When we suggest a new method, we are duty-bound to not just demonstrate that it works better than existing approaches (or is superior in some other way such as simplicity or cost). We also need to explain why, if this new method is so great, people aren’t already using it. Various answers are possible, for example: - The new idea is technically advanced, requiring a level of mathematical or engineering complexity such that it could not easily have been discovered by accident. Hence its novelty can be explained as a product of some particular historical process. - The new idea is clever and unexpected, as with the mechanical device underlying Rubik’s Cube. - The new idea could only exist given recent technological developments (perhaps hardware developments such as a new composite material or an ultralight battery, or software developments such as a new MCMC algorithm). - The new idea usually isn’t so impressive but it shows its virtues in some previously hidden domain (fo
sentIndex sentText sentNum sentScore
1 When we suggest a new method, we are duty-bound to not just demonstrate that it works better than existing approaches (or is superior in some other way such as simplicity or cost). [sent-1, score-0.236]
2 We also need to explain why, if this new method is so great, people aren’t already using it. [sent-2, score-0.427]
3 Various answers are possible, for example: - The new idea is technically advanced, requiring a level of mathematical or engineering complexity such that it could not easily have been discovered by accident. [sent-3, score-0.416]
4 - The new idea is clever and unexpected, as with the mechanical device underlying Rubik’s Cube. [sent-5, score-0.301]
5 - The new idea could only exist given recent technological developments (perhaps hardware developments such as a new composite material or an ultralight battery, or software developments such as a new MCMC algorithm). [sent-6, score-1.319]
6 - The new idea usually isn’t so impressive but it shows its virtues in some previously hidden domain (for example, you wouldn’t have much need for relativity theory if you’re modeling sub-relativistic velocities). [sent-7, score-0.472]
7 My point is that when we promote a new idea, we must—explicitly or implicitly—explain why our brilliant predecessors did not already discover and use it. [sent-11, score-0.248]
8 I thought about the above after reading this from John Cook: According a recent biography of Henri Poincaré, Poincaré … worked regularly from 10 to 12 in the morning and from 5 till 7 in the late afternoon. [sent-12, score-0.187]
9 He found that working longer seldom achieved anything … Poincaré made tremendous contributions to math and physics. [sent-13, score-0.15]
10 His two-hour work sessions must have been sprints, working with an intensity that could not be sustained much longer. [sent-14, score-0.146]
11 I [Cook] expect most of us would accomplish more if we worked harder when we worked, rested more, and cut out half-work. [sent-15, score-0.176]
12 I’ve thought this for a long time, as I’m sure has almost anybody who works at a flexible job. [sent-19, score-0.146]
13 It’s long been my goal to work intensely for whatever number of hours a week is possible and then relax the rest of the time, rather than spending hours and hours each week rearranging my files, responding to email, etc. [sent-20, score-1.018]
14 Yet this doesn’t always happen (hence it’s long been my goal etc. [sent-21, score-0.177]
15 I think one reason is that it’s hard to work intensely, and once you’re at work it’s easier to spend your time quasi-goofing-off. [sent-26, score-0.074]
16 I was once at a workshop where the person next to me was checking email on the laptop, literally more than once per minute. [sent-27, score-0.105]
17 I’m reminded of the advice in the classic book, How to Talk So Your Kids Will Listen and Listen So Your Kids Will Talk. [sent-29, score-0.218]
18 One of the comments on Cook’s post led me to this website by computer scientist Cal Newport which is full of advice for students, along the lines of: “‘follow your passion’ is bad advice if your goal is to end up loving what you do. [sent-33, score-0.613]
19 Unlike the usual in-your-face internet self-help gurus , he doesn’t seem to feel the need to be obnoxious or to supply having-it-all parables. [sent-35, score-0.086]
20 Gladwellian, one might say, and I mean that in the best possible sense of the word. [sent-39, score-0.078]
wordName wordTfidf (topN-words)
[('poincar', 0.28), ('advice', 0.218), ('developments', 0.174), ('newport', 0.17), ('new', 0.167), ('cook', 0.163), ('intensely', 0.144), ('idea', 0.134), ('listen', 0.129), ('hours', 0.129), ('requiring', 0.115), ('email', 0.105), ('worked', 0.104), ('goal', 0.1), ('method', 0.093), ('kids', 0.087), ('need', 0.086), ('battery', 0.085), ('relativity', 0.085), ('noninformativity', 0.085), ('cal', 0.085), ('henri', 0.085), ('sprints', 0.085), ('ultralight', 0.085), ('example', 0.085), ('strategy', 0.084), ('reading', 0.083), ('hence', 0.082), ('already', 0.081), ('gladwellian', 0.08), ('assertions', 0.08), ('laptop', 0.08), ('transcript', 0.08), ('rearranging', 0.08), ('possible', 0.078), ('long', 0.077), ('loving', 0.077), ('hardware', 0.077), ('desktop', 0.077), ('working', 0.076), ('week', 0.076), ('cost', 0.076), ('seldom', 0.074), ('passion', 0.074), ('spend', 0.074), ('billions', 0.072), ('accomplish', 0.072), ('aren', 0.071), ('sessions', 0.07), ('works', 0.069)]
simIndex simValue blogId blogTitle
same-blog 1 1.0000004 1520 andrew gelman stats-2012-10-03-Advice that’s so eminently sensible but so difficult to follow
Introduction: When we suggest a new method, we are duty-bound to not just demonstrate that it works better than existing approaches (or is superior in some other way such as simplicity or cost). We also need to explain why, if this new method is so great, people aren’t already using it. Various answers are possible, for example: - The new idea is technically advanced, requiring a level of mathematical or engineering complexity such that it could not easily have been discovered by accident. Hence its novelty can be explained as a product of some particular historical process. - The new idea is clever and unexpected, as with the mechanical device underlying Rubik’s Cube. - The new idea could only exist given recent technological developments (perhaps hardware developments such as a new composite material or an ultralight battery, or software developments such as a new MCMC algorithm). - The new idea usually isn’t so impressive but it shows its virtues in some previously hidden domain (fo
2 0.16213402 2287 andrew gelman stats-2014-04-09-Advice: positive-sum, zero-sum, or negative-sum
Introduction: There’s a lot of free advice out there. I offer some of it myself! As I’ve written before (see this post from 2008 reacting to this advice from Dan Goldstein for business school students, and this post from 2010 reacting to some general advice from Nassim Taleb), what we see is typically presented as advice to individuals, but it’s also interesting to consider the possible total effects if the advice is taken. It’s time to play the game again. This time it’s advice from sociologist Fabio Rojas for Ph.D. students. I’ll copy his eight points of advice, then, for each, evaluate whether I think it is positive or negative sum: 1. Show up. Even if you feel horrible, show up. No matter what. Period. Unless someone died in your family, show up. 2. Do your job. Grade the papers. Do the lab work. Unless the work is extreme, take it in stride. 3. Be completely realistic about how you will be evaluated from day #1 – acquire a teaching record and a record of publication. Don’t h
3 0.14952095 1502 andrew gelman stats-2012-09-19-Scalability in education
Introduction: This blog is an exercise in scalability. Instead of sending a long email to one person, I put the email in a blog where thousands can read it. Instead of devoting three hours to a referee report that will only be read by two people (the author and the journal editor), I do the equivalent here on the blog. When the American Statistical Association asked me to participate in a workshop to give writing advice for a select group of young researchers, I agreed to participate in this program, as long as the authors were willing to have their articles and my comments posted on the blog. I think my advice on writing research articles had much more effect being posted on the web than it would’ve had, if I’d kept it in that meeting. (On the other hand, my advice benefited from having those two student papers to push against. If I’d just tried to give general advice without the context, I don’t think it would’ve been so useful to anyone.) I’ve tried to be scalable for many years before
4 0.13647407 278 andrew gelman stats-2010-09-15-Advice that might make sense for individuals but is negative-sum overall
Introduction: There’s a lot of free advice out there. As I wrote a couple years ago, it’s usually presented as advice to individuals, but it’s also interesting to consider the possible total effects if the advice is taken. For example, Nassim Taleb has a webpage that includes a bunch of one-line bits of advice (scroll to item 132 on the linked page). Here’s his final piece of advice: If you dislike someone, leave him alone or eliminate him; don’t attack him verbally. I’m a big Taleb fan (search this blog to see), but this seems like classic negative-sum advice. I can see how it can be a good individual strategy to keep your mouth shut, bide your time, and then sandbag your enemies. But it can’t be good if lots of people are doing this. Verbal attacks are great, as long as there’s a chance to respond. I’ve been in environments where people follow Taleb’s advice, saying nothing and occasionally trying to “eliminate” people, and it’s not pretty. I much prefer for people to be open
5 0.13355076 1428 andrew gelman stats-2012-07-25-The problem with realistic advice?
Introduction: In an article entitled 16 Weeks, Thomas Basbøll ruthlessly lays out the time constraints that limit what a student will be able to write during a semester and recommends that students follow a plan: Try to be realistic. If you need time for “free writing” or “thought writing” (writing to find out what you think) book that into your calendar as well, but the important part of the challenge is to find time to write down what you already know needs to be written. If you don’t yet know what you’re going to say this semester, then your challenge is, in part, to figure that out. But you should still find at least 30 minutes a day to write down something you know you want to say. Keep in mind that we are only talking about sixteen weeks in the very near future. . . . Assuming that you do have something say, then, here’s the challenge: write always and only when (and what) your calendar tells you to. Don’t write when “inspired” to do so (unless this happens to coincide with your writing s
6 0.13059679 738 andrew gelman stats-2011-05-30-Works well versus well understood
7 0.12778991 390 andrew gelman stats-2010-11-02-Fragment of statistical autobiography
8 0.11518969 1506 andrew gelman stats-2012-09-21-Building a regression model . . . with only 27 data points
9 0.11242689 2116 andrew gelman stats-2013-11-28-“Statistics is what people think math is”
10 0.10634144 1140 andrew gelman stats-2012-01-27-Educational monoculture
11 0.10473911 1611 andrew gelman stats-2012-12-07-Feedback on my Bayesian Data Analysis class at Columbia
12 0.10403249 2245 andrew gelman stats-2014-03-12-More on publishing in journals
13 0.10193289 2172 andrew gelman stats-2014-01-14-Advice on writing research articles
14 0.099482223 1848 andrew gelman stats-2013-05-09-A tale of two discussion papers
15 0.099478938 2232 andrew gelman stats-2014-03-03-What is the appropriate time scale for blogging—the day or the week?
17 0.09788619 1832 andrew gelman stats-2013-04-29-The blogroll
18 0.096067324 878 andrew gelman stats-2011-08-29-Infovis, infographics, and data visualization: Where I’m coming from, and where I’d like to go
19 0.09559866 937 andrew gelman stats-2011-10-02-That advice not to work so hard
20 0.095319435 1695 andrew gelman stats-2013-01-28-Economists argue about Bayes
topicId topicWeight
[(0, 0.245), (1, -0.035), (2, -0.07), (3, 0.056), (4, 0.032), (5, 0.024), (6, 0.065), (7, -0.002), (8, -0.003), (9, 0.001), (10, 0.02), (11, -0.024), (12, 0.032), (13, -0.011), (14, -0.009), (15, 0.011), (16, 0.023), (17, -0.03), (18, -0.007), (19, 0.031), (20, 0.029), (21, -0.021), (22, 0.014), (23, 0.054), (24, -0.017), (25, 0.014), (26, 0.044), (27, -0.016), (28, 0.024), (29, 0.025), (30, -0.015), (31, -0.016), (32, 0.003), (33, -0.014), (34, 0.029), (35, -0.046), (36, -0.027), (37, 0.039), (38, -0.034), (39, -0.032), (40, -0.005), (41, 0.003), (42, -0.017), (43, -0.005), (44, 0.066), (45, 0.001), (46, -0.038), (47, 0.024), (48, -0.004), (49, 0.001)]
simIndex simValue blogId blogTitle
same-blog 1 0.9845385 1520 andrew gelman stats-2012-10-03-Advice that’s so eminently sensible but so difficult to follow
Introduction: When we suggest a new method, we are duty-bound to not just demonstrate that it works better than existing approaches (or is superior in some other way such as simplicity or cost). We also need to explain why, if this new method is so great, people aren’t already using it. Various answers are possible, for example: - The new idea is technically advanced, requiring a level of mathematical or engineering complexity such that it could not easily have been discovered by accident. Hence its novelty can be explained as a product of some particular historical process. - The new idea is clever and unexpected, as with the mechanical device underlying Rubik’s Cube. - The new idea could only exist given recent technological developments (perhaps hardware developments such as a new composite material or an ultralight battery, or software developments such as a new MCMC algorithm). - The new idea usually isn’t so impressive but it shows its virtues in some previously hidden domain (fo
2 0.84921038 1225 andrew gelman stats-2012-03-22-Procrastination as a positive productivity strategy
Introduction: Reading this amusing book review on willpower by Will Self ( link from Jenny Davidson) reminds me that recently [actually, several months ago; recall that most of this blog is published on a delay], I felt frustrated that I wasn’t getting anything done. I think that when I write this sort of thing it annoys people, because I’m lucky enough to be in a position to get a lot done—projects ranging from the ethics column to Stan—but I get frustrated when I spend a week trying to work, and then when the week’s over, I realize that all I did was respond to emails, review a bunch of journal submissions and grant proposals, and spend a lot of time staring into space while putting off whatever it was that I really thought I should be doing. I thought and thought, and I decided that my best strategy is what I call positive procrastination . Procrastination is of course typically considered a bad thing (or, as ironic-style writers would write, a Bad Thing). But you can actually use it, ju
3 0.83719194 166 andrew gelman stats-2010-07-27-The Three Golden Rules for Successful Scientific Research
Introduction: A famous computer scientist, Edsger W. Dijkstra, was writing short memos on a daily basis for most of his life. His memo archives contains a little over 1300 memos. I guess today he would be writing a blog, although his memos do tend to be slightly more profound than what I post. Here are the rules (follow link for commentary), which I tried to summarize: Pursue quality and challenge, avoid routine. (“Raise your quality standards as high as you can live with, avoid wasting your time on routine problems, and always try to work as closely as possible at the boundary of your abilities. Do this, because it is the only way of discovering how that boundary should be moved forward.”) When pursuing social relevance, never compromise on scientific soundness. (“We all like our work to be socially relevant and scientifically sound. If we can find a topic satisfying both desires, we are lucky; if the two targets are in conflict with each other, let the requirement of scientific sou
4 0.83410907 592 andrew gelman stats-2011-02-26-“Do you need ideal conditions to do great work?”
Introduction: John Cook links to a blog by Ben Deaton arguing that people often waste time trying to set up ideal working conditions, even though (a) your working conditions will never be ideal, and (b) the sorts of constraints and distractions that one tries to avoid, can often stimulate new ideas. Deaton seems like my kind of guy–for one thing, he works on nonlinear finite element analysis, which is one of my longstanding interests–and in many ways his points are reasonable and commonsensical (I have little doubt, for example, that Feynman made a good choice in staying clear of the Institute for Advanced Study!), but I have a couple of points of disagreement. 1. In my experience, working conditions can make a difference. And once you accept this, it could very well make sense to put some effort into improving your work environment. I like to say that I spent twenty years reconstructing what it felt like to be in grad school. My ideal working environment has lots of people coming in
5 0.82960081 49 andrew gelman stats-2010-05-24-Blogging
Introduction: Rajiv Sethi quotes Bentley University economics professor Scott Sumner writing on the first anniversary of his blog: Be careful what you wish for. Last February 2nd I [Sumner] started this blog with very low expectations… I knew I wasn’t a good writer . . . And I was also pretty sure that the content was not of much interest to anyone. Now my biggest problem is time–I spend 6 to 10 hours a day on the blog, seven days a week. Several hours are spent responding to reader comments and the rest is spent writing long-winded posts and checking other economics blogs. . . . I [Sumner] don’t think much of the official methodology in macroeconomics. Many of my fellow economists seem to have a Popperian view of the social sciences. You develop a model. You go out and get some data. And then you try to refute the model with some sort of regression analysis. . . . My problem with this view is that it doesn’t reflect the way macro and finance actually work. Instead the models are
6 0.82430059 2172 andrew gelman stats-2014-01-14-Advice on writing research articles
7 0.82175207 597 andrew gelman stats-2011-03-02-RStudio – new cross-platform IDE for R
8 0.81486148 1428 andrew gelman stats-2012-07-25-The problem with realistic advice?
9 0.81284434 1769 andrew gelman stats-2013-03-18-Tibshirani announces new research result: A significance test for the lasso
10 0.80959105 2287 andrew gelman stats-2014-04-09-Advice: positive-sum, zero-sum, or negative-sum
11 0.80887848 937 andrew gelman stats-2011-10-02-That advice not to work so hard
12 0.80838954 272 andrew gelman stats-2010-09-13-Ross Ihaka to R: Drop Dead
13 0.80506772 1245 andrew gelman stats-2012-04-03-Redundancy and efficiency: In praise of Penn Station
14 0.80433458 2053 andrew gelman stats-2013-10-06-Ideas that spread fast and slow
15 0.80355173 278 andrew gelman stats-2010-09-15-Advice that might make sense for individuals but is negative-sum overall
16 0.80160111 727 andrew gelman stats-2011-05-23-My new writing strategy
17 0.79965436 1134 andrew gelman stats-2012-01-21-Lessons learned from a recent R package submission
18 0.79649794 395 andrew gelman stats-2010-11-05-Consulting: how do you figure out what to charge?
19 0.79513091 865 andrew gelman stats-2011-08-22-Blogging is “destroying the business model for quality”?
20 0.79116744 2216 andrew gelman stats-2014-02-18-Florida backlash
topicId topicWeight
[(9, 0.015), (15, 0.032), (16, 0.081), (21, 0.024), (24, 0.168), (29, 0.025), (32, 0.01), (55, 0.162), (58, 0.01), (63, 0.013), (86, 0.015), (90, 0.011), (99, 0.281)]
simIndex simValue blogId blogTitle
1 0.98123896 1896 andrew gelman stats-2013-06-13-Against the myth of the heroic visualization
Introduction: Alberto Cairo tells a fascinating story about John Snow, H. W. Acland, and the Mythmaking Problem: Every human community—nations, ethnic and cultural groups, professional guilds—inevitably raises a few of its members to the status of heroes and weaves myths around them. . . . The visual display of information is no stranger to heroes and myth. In fact, being a set of disciplines with a relatively small amount of practitioners and researchers, it has generated a staggering number of heroes, perhaps as a morale-enhancing mechanism. Most of us have heard of the wonders of William Playfair’s Commercial and Political Atlas, Florence Nightingale’s coxcomb charts, Charles Joseph Minard’s Napoleon’s march diagram, and Henry Beck’s 1933 redesign of the London Underground map. . . . Cairo’s goal, I think, is not to disparage these great pioneers of graphics but rather to put their work in perspective, recognizing the work of their excellent contemporaries. I would like to echo Cairo’
2 0.97929919 1299 andrew gelman stats-2012-05-04-Models, assumptions, and data summaries
Introduction: I saw an analysis recently that I didn’t like. I won’t go into the details, but basically it was a dose-response inference, where a continuous exposure was binned into three broad categories (terciles of the data) and the probability of an adverse event was computed for each tercile. The effect and the sample size was large enough that the terciles were statistically-significantly different from each other in probability of adverse event, with the probabilities increasing from low to mid to high exposure, as one would predict. I didn’t like this analysis because it is equivalent to fitting a step function. There is a tendency for people to interpret the (arbitrary) tercile boundaries as being meaningful thresholds even though the underlying dose-response relation has to be continuous. I’d prefer to start with a linear model and then add nonlinearity from there with a spline or whatever. At this point I stepped back and thought: Hey, the divide-into-three analysis does not lite
3 0.97335231 168 andrew gelman stats-2010-07-28-Colorless green, and clueless
Introduction: Faithful readers will know that my ideal alternative career is to be an editor in the Max Perkins mold. If not that, I think I’d enjoy being a literary essayist, someone like Alfred Kazin or Edmund Wilson or Louis Menand, who could write about my favorite authors and books in a forum where others would read and discuss what I wrote. I could occasionally collect my articles into books, and so on. On the other hand, if I actually had such a career, I wouldn’t have much of an option to do statistical research in my spare time, so I think for my own broader goals, I’ve gotten hold of the right side of the stick. As it is, I enjoy writing about literary matters but it never quite seems worth spending the time to do it right. (And, stepping outside myself, I realize that I have a lot more to offer the world as a statistician than literary critic. Criticism is like musicianship–it can be hard to do, and it’s impressive when done well, but a lot of people can do it. Literary criticism
4 0.96453154 2019 andrew gelman stats-2013-09-12-Recently in the sister blog
Introduction: Don’t be so quick to place politicians’ views of “national interests” above the mood of the public More on those pollsters who apparently throw away completed survey responses A theory of the importance of Very Serious People in the Democratic Party Mother–child conversations about pictures and objects: Referring to categories and individuals
5 0.9630996 269 andrew gelman stats-2010-09-10-R vs. Stata, or, Different ways to estimate multilevel models
Introduction: Cyrus writes: I [Cyrus] was teaching a class on multilevel modeling, and we were playing around with different method to fit a random effects logit model with 2 random intercepts—one corresponding to “family” and another corresponding to “community” (labeled “mom” and “cluster” in the data, respectively). There are also a few regressors at the individual, family, and community level. We were replicating in part some of the results from the following paper : Improved estimation procedures for multilevel models with binary response: a case-study, by G Rodriguez, N Goldman. (I say “replicating in part” because we didn’t include all the regressors that they use, only a subset.) We were looking at the performance of estimation via glmer in R’s lme4 package, glmmPQL in R’s MASS package, and Stata’s xtmelogit. We wanted to study the performance of various estimation methods, including adaptive quadrature methods and penalized quasi-likelihood. I was shocked to discover that glmer
6 0.95222408 50 andrew gelman stats-2010-05-25-Looking for Sister Right
7 0.95207584 333 andrew gelman stats-2010-10-10-Psychiatric drugs and the reduction in crime
8 0.95126957 688 andrew gelman stats-2011-04-30-Why it’s so relaxing to think about social issues
9 0.94789255 874 andrew gelman stats-2011-08-27-What’s “the definition of a professional career”?
10 0.94654226 1406 andrew gelman stats-2012-07-05-Xiao-Li Meng and Xianchao Xie rethink asymptotics
same-blog 11 0.94168413 1520 andrew gelman stats-2012-10-03-Advice that’s so eminently sensible but so difficult to follow
12 0.93955076 620 andrew gelman stats-2011-03-19-Online James?
13 0.93685567 1617 andrew gelman stats-2012-12-11-Math Talks :: Action Movies
14 0.93679255 1463 andrew gelman stats-2012-08-19-It is difficult to convey intonation in typed speech
15 0.93514699 706 andrew gelman stats-2011-05-11-The happiness gene: My bottom line (for now)
16 0.92937267 13 andrew gelman stats-2010-04-30-Things I learned from the Mickey Kaus for Senate campaign
17 0.92451108 201 andrew gelman stats-2010-08-12-Are all rich people now liberals?
18 0.92389411 997 andrew gelman stats-2011-11-07-My contribution to the discussion on “Should voting be mandatory?”
19 0.9203254 2186 andrew gelman stats-2014-01-26-Infoviz on top of stat graphic on top of spreadsheet
20 0.91992855 252 andrew gelman stats-2010-09-02-R needs a good function to make line plots