econometrics   2224

« earlier    

How to Use Economic Theory to Improve Estimators: Shrinking Toward Theoretical Restrictions | The Review of Economics and Statistics | MIT Press Journals
"We propose to use economic theories to construct shrinkage estimators that perform well when the theories' empirical implications are approximately correct but perform no worse than unrestricted estimators when the theories' implications do not hold. We implement this construction in various settings, including labor demand and wage inequality, and estimation of consumer demand. We provide asymptotic and finite sample characterizations of the behavior of the proposed estimators. Our approach is an alternative to the use of theory as something to be tested or to be imposed on estimates. Our approach complements uses of theory for identification and extrapolation."
to:NB  economics  econometrics  statistics  estimation  shrinkage 
25 days ago by cshalizi
Legacy and Athlete Preferences at Harvard
The lawsuit Students For Fair Admissions v. Harvard University provided an un-precedented look at how an elite school makes admissions decisions. Using publicly released reports, we examine the preferences Harvard gives for recruited athletes, lega-cies, those on the dean’s interest list, and children of faculty and staff (ALDCs). Among white admits, over 43% are ALDC. Among admits who are African American, Asian American, and Hispanic, the share is less than 16% each. Our model of admissions shows that roughly three quarters of white ALDC admits would have been rejected if they had been treated as white non-ALDCs. Removing preferences for athletes and legacies would significantly alter the racial distribution of admitted students, with the share of white admits falling and all other groups rising or remaining unchanged

-- Do we have additional insights on the selection criteria?
education  inequality  university  united_states_of_america  econometrics 
8 weeks ago by rvenkat
Generalizable and Robust TV Advertising Effects by Bradley Shapiro, Günter J. Hitsch, Anna Tuchman :: SSRN
We provide generalizable and robust results on the causal sales effect of TV advertising for a large number of products in many categories. Such generalizable results provide a prior distribution that can improve the advertising decisions made by firms and the analysis and recommendations of policy makers. A single case study cannot provide generalizable results, and hence the literature provides several meta-analyses based on published case studies of advertising effects. However, publication bias results if the research or review process systematically rejects estimates of small, statistically insignificant, or “unexpected” advertising elasticities. Consequently, if there is publication bias, the results of a meta-analysis will not reflect the true population distribution of advertising effects. To provide generalizable results, we base our analysis on a large number of products and clearly lay out the research protocol used to select the products. We characterize the distribution of all estimates, irrespective of sign, size, or statistical significance. To ensure generalizability, we document the robustness of the estimates. First, we examine the sensitivity of the results to the assumptions made when constructing the data used in estimation. Second, we document whether the estimated effects are sensitive to the identification strategies that we use to claim causality based on observational data. Our results reveal substantially smaller advertising elasticities compared to the results documented in the extant literature, as well as a sizable percentage of statistically insignificant or negative estimates. If we only select products with statistically significant and positive estimates, the mean and median of the advertising effect distribution increase by a factor of about five. The results are robust to various identifying assumptions, and are consistent with both publication bias and bias due to non-robust identification strategies to obtain causal estimates in the literature.
causal_inference  econometrics  via:nyhan 
8 weeks ago by rvenkat
Thomas Piketty's New Book Brings Political Economy Back to Its Sources -
-- I look forward to what the book has to say about India's economic history.

"This part of the book looks empirically at the reasons that left-wing, or social democratic parties have gradually transformed themselves from being the parties of the less-educated and poorer classes to become the parties of the educated and affluent middle and upper-middle classes. To a large extent, traditionally left parties have changed because their original social-democratic agenda was so successful in opening up education and high-income possibilities to the people who in the 1950s and 1960s came from modest backgrounds. These people, the “winners” of social democracy, continued voting for left-wing parties but their interests and worldview were no longer the same as that of their (less-educated) parents. The parties’ internal social structure thus changed—the product of their own political and social success. In Piketty’s terms, they became the parties of the “Brahmin left” (La gauche Brahmane), as opposed to the conservative right-wing parties, which remained the parties of the “merchant right” (La droite marchande)."

-- Even in India "Brahmin left" and "Merchant right" dichotomy is at best, only partially correct. While in erstwhile communist Bengal and Kerala, this held true, in other parts of the country, especially Tamil Nadu, there was no Brahmin left, progressive forces were driven by enlightened lower castes and other non-Brahmin castes. (Unless he is using the terms metaphorically, but in that case, I would object to its use in the first place). Also, the pathways to populism discussed in the [book] seem to be a very different from the way it happened in India.

-- Wonder if Pikettey's sweeping discussions would be as poorly received as Pinker's recent books.
book_review  political_economy  economic_history  world_history  world_trends  econometrics 
9 weeks ago by rvenkat
Econometrics –
In economics and the social sciences, we typically cannot rely on experiments to answer questions about the way the world works. In these circumstances, causality is often harder to establish than in the physical or biological sciences. We can, however, often make use of "natural'' experiments where inadvertently the conditions of randomisation - the lynchpin of scientific…
statistics  economics  econometrics 
11 weeks ago by id1
[1906.10258] Policy Targeting under Network Interference
"This paper discusses the problem of estimating individualized treatment allocation rules under network interference. We propose a method with several appealing features for applications: we let treatment and spillover effects be heterogeneous in the population, and we construct targeting rules that exploit such heterogeneity; we accommodate for arbitrary, possibly non-linear, regression models, and we propose estimators that are robust to model misspecification; treatment allocation rules depend on an arbitrary set of individual, neighbors' and network characteristics, and we allow for general constraints on the policy function and capacity constraints on the number of treated units; the proposed methodology is valid also when only local information of the network is observed. From a theoretical perspective, we establish the first set of guarantees on the utilitarian regret under interference, and we show that it achieves the min-max optimal rate in scenarios of practical and theoretical interest. We provide a mixed-integer linear program formulation of the optimization problem, that can be solved using standard optimization routines. We discuss the empirical performance in simulations, and we illustrate our method by investigating the role of social networks in micro-finance decisions."
to:NB  social_influence  causal_inference  network_data_analysis  statistics  econometrics 
11 weeks ago by cshalizi

« earlier    

related tags

2sls  _classroom_  ab-testing  abtesting  alex-chinco  artificialintelligence  backup  bayesian  best-practices  blog  blogs  book  book_review  books  books:noted  business  byronsharp  carr  causal_inference  causality  causation  class_struggles_in_america  code  conceptual-vocab  continuity  control  course  courses  coveted  d-in-d  dag  data-analysis  data-science  datascience  dataset  demand-estimation  density  discussion  dissertation  drugs  econometrics-in-r  economic_history  economics  econotariat  education  effects  employment  endogenous-exogenous  estimation  estimators  evolution  example  examples  excel  exercises  fairness  finance  financial-economics  financial-markets  fixed  for_friends  forecasting  free  gametheory  garch  garett-jones  gdp  geoda  gis  globalization  globalwarming  gotchas  gretl  growth  hansl  have_read  howto  ideas  in_nb  income  income_distribution  increase-decrease  india  inequality  instrumental_variables  intervention  intricacy  inverse_problems  italian  jdaykin  jerry  julia  labor  latex  learning  lecture  lectures  links  machinelearning  macroeconomics  math  mathematics  media  metabuch  methodology  microeconomics  minwage  ml  mlb  mooc  natural_experiment  network_data_analysis  nonparametric  nonparametrics  notes  online  panel  papers  people  perception  persuasion  poedata  poisson  political_economy  portable  poverty  predictive-analytics  probability  programming  propensity-score-matching  public_policy  python  quant  quantecon  quantitative  r-project  r.stats  r  racine.jeffrey  raj.chetty  re:adafaepov  read:2019  regresion  regression  reinforcement_learning  research  research_design  resource  rmii  roi  rstats  shrinkage  signum  social  social_influence  social_measurement  software  spatial-econometrics  spatial-statistics  spatial  spatial_statistics  sports  stata  statistics  strategy  teaching  technology  text_mining  textbooks  time-series-econometrics  time-series  tips  to:nb  to_read  to_teach:data_over_space_and_time  to_teach:linear_models  to_teach:undergrad-ada  travel  tutorial  twitter  ubi  unemployment  united_states_of_america  university  video-lectures  volatility  wealth  whats_gone_wrong_with_america  world_history  world_trends 

Copy this bookmark: