andrew_gelman_stats andrew_gelman_stats-2012 andrew_gelman_stats-2012-1468 knowledge-graph by maker-knowledge-mining
Source: html
Introduction: Terence Teo writes: I was wondering if multilevel models can be used as an alternative to 2SLS or IV models to deal with (i) endogeneity and (ii) selection problems. More concretely, I am trying to assess the impact of investment treaties on foreign investment. Aside from the fact that foreign investment is correlated over time, it may be the case that countries that already receive sufficient amounts of foreign investment need not sign treaties, and countries that sign treaties are those that need foreign investment in the first place. Countries thus “select” into treatment; treaty signing is non-random. As such, I argue that to properly estimate the impact of treaties on investment, we must model the determinants of treaty signing. I [Teo] am currently modeling this as two separate models: (1) regress predictors on likelihood of treaty signing, (2) regress treaty (with interactions, etc) on investment (I’ve thought of using propensity score matching for this part of the model)
sentIndex sentText sentNum sentScore
1 Terence Teo writes: I was wondering if multilevel models can be used as an alternative to 2SLS or IV models to deal with (i) endogeneity and (ii) selection problems. [sent-1, score-0.463]
2 More concretely, I am trying to assess the impact of investment treaties on foreign investment. [sent-2, score-1.264]
3 Aside from the fact that foreign investment is correlated over time, it may be the case that countries that already receive sufficient amounts of foreign investment need not sign treaties, and countries that sign treaties are those that need foreign investment in the first place. [sent-3, score-3.144]
4 Countries thus “select” into treatment; treaty signing is non-random. [sent-4, score-0.702]
5 As such, I argue that to properly estimate the impact of treaties on investment, we must model the determinants of treaty signing. [sent-5, score-1.207]
6 I [Teo] am currently modeling this as two separate models: (1) regress predictors on likelihood of treaty signing, (2) regress treaty (with interactions, etc) on investment (I’ve thought of using propensity score matching for this part of the model). [sent-6, score-1.832]
7 Here is the (non-nested) multilevel model I have in mind: investment_{i,t} = investment_{i,t-1} + treaty_{j,i,t-1} + X_{i,t-1} + error_{i,t-1} treaty_{j,t} = political institutions_{j, t-1} + X_{j,t-1} + error_{j,t-1} Can I do this? [sent-8, score-0.224]
8 Would a Bayesian framework along the lines of chapter 16 in your book work? [sent-9, score-0.094]
9 My reply: first off, Jennifer’s the causal expert, not me, so my response will be kinda vague. [sent-10, score-0.067]
10 Second, don’t you need some sort of instrument for the treaty signing? [sent-11, score-0.597]
11 Beyond this, if you are working in a more traditional instrumental variables framework, I suspect that multilevel models will be useful for all the usual reasons. [sent-13, score-0.314]
wordName wordTfidf (topN-words)
[('treaty', 0.461), ('treaties', 0.405), ('investment', 0.401), ('signing', 0.241), ('foreign', 0.235), ('teo', 0.202), ('regress', 0.145), ('countries', 0.137), ('multilevel', 0.115), ('latent', 0.111), ('model', 0.109), ('sign', 0.097), ('framework', 0.094), ('models', 0.092), ('impact', 0.088), ('selection', 0.084), ('endogeneity', 0.08), ('determinants', 0.08), ('trying', 0.08), ('unobserved', 0.073), ('need', 0.07), ('simulating', 0.07), ('propensity', 0.068), ('iv', 0.068), ('kinda', 0.067), ('instrument', 0.066), ('amounts', 0.066), ('properly', 0.064), ('instrumental', 0.06), ('ii', 0.059), ('including', 0.058), ('matching', 0.058), ('fake', 0.058), ('select', 0.056), ('sufficient', 0.055), ('assess', 0.055), ('receive', 0.055), ('assumed', 0.053), ('measured', 0.052), ('stuck', 0.05), ('reality', 0.05), ('score', 0.049), ('jennifer', 0.049), ('interactions', 0.048), ('plausible', 0.047), ('correlated', 0.047), ('define', 0.047), ('traditional', 0.047), ('separate', 0.044), ('expert', 0.044)]
simIndex simValue blogId blogTitle
same-blog 1 1.0 1468 andrew gelman stats-2012-08-24-Multilevel modeling and instrumental variables
Introduction: Terence Teo writes: I was wondering if multilevel models can be used as an alternative to 2SLS or IV models to deal with (i) endogeneity and (ii) selection problems. More concretely, I am trying to assess the impact of investment treaties on foreign investment. Aside from the fact that foreign investment is correlated over time, it may be the case that countries that already receive sufficient amounts of foreign investment need not sign treaties, and countries that sign treaties are those that need foreign investment in the first place. Countries thus “select” into treatment; treaty signing is non-random. As such, I argue that to properly estimate the impact of treaties on investment, we must model the determinants of treaty signing. I [Teo] am currently modeling this as two separate models: (1) regress predictors on likelihood of treaty signing, (2) regress treaty (with interactions, etc) on investment (I’ve thought of using propensity score matching for this part of the model)
2 0.10321765 1248 andrew gelman stats-2012-04-06-17 groups, 6 group-level predictors: What to do?
Introduction: Yi-Chun Ou writes: I am using a multilevel model with three levels. I read that you wrote a book about multilevel models, and wonder if you can solve the following question. The data structure is like this: Level one: customer (8444 customers) Level two: companys (90 companies) Level three: industry (17 industries) I use 6 level-three variables (i.e. industry characteristics) to explain the variance of the level-one effect across industries. The question here is whether there is an over-fitting problem since there are only 17 industries. I understand that this must be a problem for non-multilevel models, but is it also a problem for multilevel models? My reply: Yes, this could be a problem. I’d suggest combining some of your variables into a common score, or using only some of the variables, or using strong priors to control the inferences. This is an interesting and important area of statistics research, to do this sort of thing systematically. There’s lots o
Introduction: Elias Bareinboim asked what I thought about his comment on selection bias in which he referred to a paper by himself and Judea Pearl, “Controlling Selection Bias in Causal Inference.” I replied that I have no problem with what he wrote, but that from my perspective I find it easier to conceptualize such problems in terms of multilevel models. I elaborated on that point in a recent post , “Hierarchical modeling as a framework for extrapolation,” which I think was read by only a few people (I say this because it received only two comments). I don’t think Bareinboim objected to anything I wrote, but like me he is comfortable working within his own framework. He wrote the following to me: In some sense, “not ad hoc” could mean logically consistent. In other words, if one agrees with the assumptions encoded in the model, one must also agree with the conclusions entailed by these assumptions. I am not aware of any other way of doing mathematics. As it turns out, to get causa
4 0.094760329 352 andrew gelman stats-2010-10-19-Analysis of survey data: Design based models vs. hierarchical modeling?
Introduction: Alban Zeber writes: Suppose I have survey data from say 10 countries where by each country collected the data based on different sampling routines – the results of this being that each country has its own weights for the data that can be used in the analyses. If I analyse the data of each country separately then I can incorporate the survey design in the analyses e.g in Stata once can use svyset ….. But what happens when I want to do a pooled analysis of the all the data from the 10 countries: Presumably either 1. I analyse the data from each country separately (using multiple or logistic regression, …) accounting for the survey design and then combine the estimates using a meta analysis (fixed or random) OR 2. Assume that the data from each country is a simple random sample from the population, combine the data from the 10 countries and then use multilevel or hierarchical models My question is which of the methods is likely to give better estimates? Or is the
5 0.093392059 439 andrew gelman stats-2010-11-30-Of psychology research and investment tips
Introduction: A few days after “ Dramatic study shows participants are affected by psychological phenomena from the future ,” (see here ) the British Psychological Society follows up with “ Can psychology help combat pseudoscience? .” Somehow I’m reminded of that bit of financial advice which says, if you want to save some money, your best investment is to pay off your credit card bills.
6 0.090193108 25 andrew gelman stats-2010-05-10-Two great tastes that taste great together
7 0.090136513 1737 andrew gelman stats-2013-02-25-Correlation of 1 . . . too good to be true?
8 0.089583017 375 andrew gelman stats-2010-10-28-Matching for preprocessing data for causal inference
10 0.088207789 392 andrew gelman stats-2010-11-03-Taleb + 3.5 years
11 0.084337056 2294 andrew gelman stats-2014-04-17-If you get to the point of asking, just do it. But some difficulties do arise . . .
12 0.082436405 1900 andrew gelman stats-2013-06-15-Exploratory multilevel analysis when group-level variables are of importance
13 0.082176872 383 andrew gelman stats-2010-10-31-Analyzing the entire population rather than a sample
14 0.080552585 704 andrew gelman stats-2011-05-10-Multiple imputation and multilevel analysis
15 0.078958876 1392 andrew gelman stats-2012-06-26-Occam
16 0.077161022 754 andrew gelman stats-2011-06-09-Difficulties with Bayesian model averaging
17 0.076587334 295 andrew gelman stats-2010-09-25-Clusters with very small numbers of observations
18 0.075396374 251 andrew gelman stats-2010-09-02-Interactions of predictors in a causal model
19 0.075304747 368 andrew gelman stats-2010-10-25-Is instrumental variables analysis particularly susceptible to Type M errors?
20 0.072397195 653 andrew gelman stats-2011-04-08-Multilevel regression with shrinkage for “fixed” effects
topicId topicWeight
[(0, 0.13), (1, 0.095), (2, 0.036), (3, 0.006), (4, 0.042), (5, 0.043), (6, -0.019), (7, -0.033), (8, 0.097), (9, 0.083), (10, 0.016), (11, 0.007), (12, -0.017), (13, 0.013), (14, 0.001), (15, -0.001), (16, 0.006), (17, -0.009), (18, -0.017), (19, 0.022), (20, -0.01), (21, -0.004), (22, 0.01), (23, -0.004), (24, -0.014), (25, -0.016), (26, 0.005), (27, -0.019), (28, -0.034), (29, 0.004), (30, -0.042), (31, -0.022), (32, -0.004), (33, -0.009), (34, -0.013), (35, -0.018), (36, -0.002), (37, -0.0), (38, 0.009), (39, 0.02), (40, -0.006), (41, -0.002), (42, -0.003), (43, -0.022), (44, 0.016), (45, 0.006), (46, 0.025), (47, 0.034), (48, -0.022), (49, -0.013)]
simIndex simValue blogId blogTitle
same-blog 1 0.95915622 1468 andrew gelman stats-2012-08-24-Multilevel modeling and instrumental variables
Introduction: Terence Teo writes: I was wondering if multilevel models can be used as an alternative to 2SLS or IV models to deal with (i) endogeneity and (ii) selection problems. More concretely, I am trying to assess the impact of investment treaties on foreign investment. Aside from the fact that foreign investment is correlated over time, it may be the case that countries that already receive sufficient amounts of foreign investment need not sign treaties, and countries that sign treaties are those that need foreign investment in the first place. Countries thus “select” into treatment; treaty signing is non-random. As such, I argue that to properly estimate the impact of treaties on investment, we must model the determinants of treaty signing. I [Teo] am currently modeling this as two separate models: (1) regress predictors on likelihood of treaty signing, (2) regress treaty (with interactions, etc) on investment (I’ve thought of using propensity score matching for this part of the model)
2 0.83392847 772 andrew gelman stats-2011-06-17-Graphical tools for understanding multilevel models
Introduction: There are a few things I want to do: 1. Understand a fitted model using tools such as average predictive comparisons , R-squared, and partial pooling factors . In defining these concepts, Iain and I came up with some clever tricks, including (but not limited to): - Separating the inputs and averaging over all possible values of the input not being altered (for average predictive comparisons); - Defining partial pooling without referring to a raw-data or maximum-likelihood or no-pooling estimate (these don’t necessarily exist when you’re fitting logistic regression with sparse data); - Defining an R-squared for each level of a multilevel model. The methods get pretty complicated, though, and they have some loose ends–in particular, for average predictive comparisons with continuous input variables. So now we want to implement these in R and put them into arm along with bglmer etc. 2. Setting up coefplot so it works more generally (that is, so the graphics look nice
3 0.82666963 1248 andrew gelman stats-2012-04-06-17 groups, 6 group-level predictors: What to do?
Introduction: Yi-Chun Ou writes: I am using a multilevel model with three levels. I read that you wrote a book about multilevel models, and wonder if you can solve the following question. The data structure is like this: Level one: customer (8444 customers) Level two: companys (90 companies) Level three: industry (17 industries) I use 6 level-three variables (i.e. industry characteristics) to explain the variance of the level-one effect across industries. The question here is whether there is an over-fitting problem since there are only 17 industries. I understand that this must be a problem for non-multilevel models, but is it also a problem for multilevel models? My reply: Yes, this could be a problem. I’d suggest combining some of your variables into a common score, or using only some of the variables, or using strong priors to control the inferences. This is an interesting and important area of statistics research, to do this sort of thing systematically. There’s lots o
4 0.80289692 823 andrew gelman stats-2011-07-26-Including interactions or not
Introduction: Liz Sanders writes: I viewed your 2005 presentation “Interactions in multilevel models” and was hoping you or one of your students/colleagues could point me to some readings about the issue of using all possible vs. only particular interaction terms in regression models with continuous covariates (I think “functional form validity” is the term I have encountered in the past). In particular, I am trying to understand whether I would be mis-specifying a model if I deleted two of its interaction terms (in favor of using only 2-way treatment interaction terms). The general full model, for example, is: Y = intercept + txt + pre1 + pre2 + txt*pre1 + txt*pre2 + pre1*pre2 + txt*pre1*pre2, where txt is effect coded (1=treatment, -1=control) and pre1 and pre2 are two different pretests that are assumed normally distributed. (The model is actually a multilevel model; the error terms are not listed for brevity.) The truncated model, on the other hand, would only test 2-way treatment inte
5 0.80154014 1395 andrew gelman stats-2012-06-27-Cross-validation (What is it good for?)
Introduction: I think cross-validation is a good way to estimate a model’s forecasting error but I don’t think it’s always such a great tool for comparing models. I mean, sure, if the differences are dramatic, ok. But you can easily have a few candidate models, and one model makes a lot more sense than the others (even from a purely predictive sense, I’m not talking about causality here). The difference between the model doesn’t show up in a xval measure of total error but in the patterns of the predictions. For a simple example, imagine using a linear model with positive slope to model a function that is constrained to be increasing. If the constraint isn’t in the model, the predicted/imputed series will sometimes be nonmonotonic. The effect on the prediction error can be so tiny as to be undetectable (or it might even increase avg prediction error to include the constraint); nonetheless, the predictions will be clearly nonsensical. That’s an extreme example but I think the general point h
6 0.79653889 948 andrew gelman stats-2011-10-10-Combining data from many sources
7 0.79539454 2033 andrew gelman stats-2013-09-23-More on Bayesian methods and multilevel modeling
9 0.78462446 1294 andrew gelman stats-2012-05-01-Modeling y = a + b + c
11 0.77609712 77 andrew gelman stats-2010-06-09-Sof[t]
12 0.77140683 397 andrew gelman stats-2010-11-06-Multilevel quantile regression
13 0.76957351 1425 andrew gelman stats-2012-07-23-Examples of the use of hierarchical modeling to generalize to new settings
14 0.76484823 1392 andrew gelman stats-2012-06-26-Occam
15 0.75779611 1196 andrew gelman stats-2012-03-04-Piss-poor monocausal social science
16 0.75552726 1900 andrew gelman stats-2013-06-15-Exploratory multilevel analysis when group-level variables are of importance
17 0.75426745 417 andrew gelman stats-2010-11-17-Clutering and variance components
18 0.75383848 753 andrew gelman stats-2011-06-09-Allowing interaction terms to vary
19 0.75382107 704 andrew gelman stats-2011-05-10-Multiple imputation and multilevel analysis
20 0.75274897 936 andrew gelman stats-2011-10-02-Covariate Adjustment in RCT - Model Overfitting in Multilevel Regression
topicId topicWeight
[(2, 0.011), (9, 0.032), (16, 0.075), (24, 0.098), (53, 0.32), (72, 0.031), (76, 0.028), (95, 0.043), (99, 0.234)]
simIndex simValue blogId blogTitle
1 0.953677 413 andrew gelman stats-2010-11-14-Statistics of food consumption
Introduction: Visual Economics shows statistics on average food consumption in America: My brief feedback is that water is confounded with these results. They should have subtracted water content from the weight of all dietary items, as it inflates the proportion of milk, vegetable and fruit items that contain more water. They did that for soda (which is represented as sugar/corn syrup), amplifying the inconsistency. Time Magazine had a beautiful gallery that visualizes diets around the world in a more appealing way.
2 0.94146919 1589 andrew gelman stats-2012-11-25-Life as a blogger: the emails just get weirder and weirder
Introduction: In the email the other day, subject line “Casting blogger, writer, journalist to host cable series”: Hi there Andrew, I’m casting a male journalist, writer, blogger, documentary filmmaker or comedian with a certain type personality for a television pilot along with production company, Pipeline39. See below: A certain type of character – no cockiness, no ego, a person who is smart, savvy, dry humor, but someone who isn’t imposing, who can infiltrate these organizations. This person will be hosting his own show and covering alternative lifestyles and secret societies around the world. If you’re interested in hearing more or would like to be considered for this project, please email me a photo and a bio of yourself, along with contact information. I’ll respond to you ASAP. I’m looking forward to hearing from you. *** Casting Producer (646) ***.**** ***@gmail.com I was with them until I got to the “no ego” part. . . . Also, I don’t think I could infiltrate any org
Introduction: Tapen Sinha writes: Living in Mexico, I have been witness to many strange (and beautiful) things. Perhaps the strangest happened during the first outbreak of A(H1N1) in Mexico City. We had our university closed, football (soccer) was played in empty stadiums (or should it be stadia) because the government feared a spread of the virus. The Metro was operating and so were the private/public buses and taxis. Since the university was closed, we took the opportunity to collect data on facemask use in the public transport systems. It was a simple (but potentially deadly!) exercise in first hand statistical data collection that we teach our students (Although I must admit that I did not dare sending my research assistant to collect data – what if she contracted the virus?). I believe it was a unique experiment never to be repeated. The paper appeared in the journal Health Policy. From the abstract: At the height of the influenza epidemic in Mexico City in the spring of 2009, the f
4 0.91597879 1677 andrew gelman stats-2013-01-16-Greenland is one tough town
Introduction: Americans (including me) don’t know much about other countries. Jeff Lax sent me to this blog post by Myrddin pointing out that Belgium has a higher murder rate than the rest of Western Europe. I have no particular take on this, but it’s a good reminder that other countries differ from each other. Here in the U.S., we tend to think all western European countries are the same, all eastern European countries are the same, etc. In reality, Sweden is not Finland . P.S. According to the Wiki , Greenland is one tough town. I guess there’s nothing much to do out there but watch satellite TV, chew the blubber, and kill people.
5 0.90617967 1856 andrew gelman stats-2013-05-14-GPstuff: Bayesian Modeling with Gaussian Processes
Introduction: I think it’s part of my duty as a blogger to intersperse, along with the steady flow of jokes, rants, and literary criticism, some material that will actually be useful to you. So here goes. Jarno Vanhatalo, Jaakko Riihimäki, Jouni Hartikainen, Pasi Jylänki, Ville Tolvanen, and Aki Vehtari write : The GPstuff toolbox is a versatile collection of Gaussian process models and computational tools required for Bayesian inference. The tools include, among others, various inference methods, sparse approximations and model assessment methods. We can actually now fit Gaussian processes in Stan . But for big problems (or even moderately-sized problems), full Bayes can be slow. GPstuff uses EP, which is faster. At some point we’d like to implement EP in Stan. (Right now we’re working with Dave Blei to implement VB.) GPstuff really works. I saw Aki use it to fit a nonparametric version of the Bangladesh well-switching example in ARM. He was sitting in his office and just whip
same-blog 6 0.89322269 1468 andrew gelman stats-2012-08-24-Multilevel modeling and instrumental variables
7 0.87328583 46 andrew gelman stats-2010-05-21-Careers, one-hit wonders, and an offer of a free book
8 0.87293065 1802 andrew gelman stats-2013-04-14-Detecting predictability in complex ecosystems
9 0.86358345 1905 andrew gelman stats-2013-06-18-There are no fat sprinters
10 0.84792525 991 andrew gelman stats-2011-11-04-Insecure researchers aren’t sharing their data
11 0.84688807 1902 andrew gelman stats-2013-06-17-Job opening at new “big data” consulting firm!
12 0.84430039 733 andrew gelman stats-2011-05-27-Another silly graph
13 0.83180559 2022 andrew gelman stats-2013-09-13-You heard it here first: Intense exercise can suppress appetite
15 0.8176195 1047 andrew gelman stats-2011-12-08-I Am Too Absolutely Heteroskedastic for This Probit Model
16 0.8132714 495 andrew gelman stats-2010-12-31-“Threshold earners” and economic inequality
17 0.79925907 2067 andrew gelman stats-2013-10-18-EP and ABC
18 0.79904985 880 andrew gelman stats-2011-08-30-Annals of spam
19 0.78765857 354 andrew gelman stats-2010-10-19-There’s only one Amtrak
20 0.78370881 237 andrew gelman stats-2010-08-27-Bafumi-Erikson-Wlezien predict a 50-seat loss for Democrats in November