to:nb   4356

« earlier    

The Phoenix Mosque and the Persians of Medieval Hangzhou, Lane, Chen, Morton
"In the early 1250s, Möngke Khan, grandson and successor of the mighty Mongol emperor, Genghis Khan, sent out his younger brothers Qubilai and Hulegu to consolidate his power. Hulegu was welcomed into Iran while his older brother, Qubilai, continued to erode the power of the Song emperors of southern China. In 1276, he finally forced their submission and peacefully occupied the Song capital, Hangzhou. The city enjoyed a revival as the cultural capital of a united China and was soon filled with traders, adventurers, artists, entrepreneurs, and artisans from throughout the great Mongol Empire—including a prosperous, influential, and seemingly welcome community of Persians. In 1281, one of the Persian settlers, Ala al-Din, built the Phoenix Mosque in the heart of the city where it still stands today. This study of the mosque and the Ju-jing Yuan cemetery, which today is a lake-side public park, casts light on an important and transformative period in Chinese history, and perhaps the most important period in Chinese-Islamic history."
to:NB  books:noted  islamic_civilization  china  yuan  mongol_empire  medieval_eurasian_history 
3 days ago by cshalizi
Difficulty of Reaching Respondents and Nonresponse Bias: Evidence from Large Government Surveys | The Review of Economics and Statistics | MIT Press Journals
"How high is unemployment? How low is labor force participation? Is obesity more prevalent among men? How large are household expenditures? We study the sources of the relevant official statistics—the Current Population Survey, the Behavioral Risk Factor Surveillance System, and the Consumer Expenditure Survey—and find that the answers depend on whether we look at easy- or at difficult-to-reach respondents, measured by the number of call and visit attempts made by interviewers. A challenge to the (conditionally-)random-nonresponse assumption, these findings empirically substantiate the theoretical warning against making population-wide estimates from surveys with low response rates."
to:NB  statistics  social_measurement  missing_data 
7 days ago by cshalizi
Moment-Based Tests under Parameter Uncertainty | The Review of Economics and Statistics | MIT Press Journals
"This paper considers moment-based tests applied to estimated quantities. We propose a general class of transforms of moments to handle the parameter uncertainty problem. The construction requires only a linear correction that can be implemented in sample and remains valid for some extended families of nonsmooth moments. We reemphasize the attractiveness of working with robust moments, which lead to testing procedures that do not depend on the estimator. Furthermore, no correction is needed when considering the implied test statistic in the out-of-sample case. We apply our methodology to various examples with an emphasis on the backtesting of value-at-risk forecasts."
to:NB  statistics  hypothesis_testing 
7 days ago by cshalizi
Moderate Environmental Variation Across Generations Promotes the Evolution of Robust Solutions | Artificial Life | MIT Press Journals
"Previous evolutionary studies demonstrated how robust solutions can be obtained by evaluating agents multiple times in variable environmental conditions. Here we demonstrate how agents evolved in environments that vary across generations outperform agents evolved in environments that remain fixed. Moreover, we demonstrate that best performance is obtained when the environment varies at a moderate rate across generations, that is, when the environment does not vary every generation but every N generations. The advantage of exposing evolving agents to environments that vary across generations at a moderate rate is due, at least in part, to the fact that this condition maximizes the retention of changes that alter the behavior of the agents, which in turn facilitates the discovery of better solutions. Finally, we demonstrate that moderate environmental variations are advantageous also from an evolutionary computation perspective, that is, from the perspective of maximizing the performance that can be achieved within a limited computational budget."
to:NB  evolution  re:democratic_cognition 
7 days ago by cshalizi
Emergence of analogy from relation learning | PNAS
"By middle childhood, humans are able to learn abstract semantic relations (e.g., antonym, synonym, category membership) and use them to reason by analogy. A deep theoretical challenge is to show how such abstract relations can arise from nonrelational inputs, thereby providing key elements of a protosymbolic representation system. We have developed a computational model that exploits the potential synergy between deep learning from “big data” (to create semantic features for individual words) and supervised learning from “small data” (to create representations of semantic relations between words). Given as inputs labeled pairs of lexical representations extracted by deep learning, the model creates augmented representations by remapping features according to the rank of differences between values for the two words in each pair. These augmented representations aid in coping with the feature alignment problem (e.g., matching those features that make “love-hate” an antonym with the different features that make “rich-poor” an antonym). The model extracts weight distributions that are used to estimate the probabilities that new word pairs instantiate each relation, capturing the pattern of human typicality judgments for a broad range of abstract semantic relations. A measure of relational similarity can be derived and used to solve simple verbal analogies with human-level accuracy. Because each acquired relation has a modular representation, basic symbolic operations are enabled (notably, the converse of any learned relation can be formed without additional training). Abstract semantic relations can be induced by bootstrapping from nonrelational inputs, thereby enabling relational generalization and analogical reasoning."
to:NB  machine_learning  analogy  artificial_intelligence 
7 days ago by cshalizi
Single-neuron perturbations reveal feature-specific competition in V1 | Nature
"The computations performed by local neural populations, such as a cortical layer, are typically inferred from anatomical connectivity and observations of neural activity. Here we describe a method—influence mapping—that uses single-neuron perturbations to directly measure how cortical neurons reshape sensory representations. In layer 2/3 of the primary visual cortex (V1), we use two-photon optogenetics to trigger action potentials in a targeted neuron and calcium imaging to measure the effect on spiking in neighbouring neurons in awake mice viewing visual stimuli. Excitatory neurons on average suppressed other neurons and had a centre–surround influence profile over anatomical space. A neuron’s influence on its neighbour depended on their similarity in activity. Notably, neurons suppressed activity in similarly tuned neurons more than in dissimilarly tuned neurons. In addition, photostimulation reduced the population response, specifically to the targeted neuron’s preferred stimulus, by around 2%. Therefore, V1 layer 2/3 performed feature competition, in which a like-suppresses-like motif reduces redundancy in population activity and may assist with inference of the features that underlie sensory input. We anticipate that influence mapping can be extended to investigate computations in other neural populations."
to:NB  neuroscience  neural_coding_and_decoding  neural_data_analysis 
7 days ago by cshalizi
[1609.08816] Identifying Causal Effects With Proxy Variables of an Unmeasured Confounder
"We consider a causal effect that is confounded by an unobserved variable, but with observed proxy variables of the confounder. We show that, with at least two independent proxy variables satisfying a certain rank condition, the causal effect is nonparametrically identified, even if the measurement error mechanism, i.e., the conditional distribution of the proxies given the con- founder, may not be identified. Our result generalizes the identification strategy of Kuroki & Pearl (2014) that rests on identification of the measurement error mechanism. When only one proxy for the confounder is available, or the required rank condition is not met, we develop a strategy to test the null hypothesis of no causal effect."
to:NB  to_read  causal_inference  statistics 
7 days ago by cshalizi
[1902.10286] On Multi-Cause Causal Inference with Unobserved Confounding: Counterexamples, Impossibility, and Alternatives
"Unobserved confounding is a central barrier to drawing causal inferences from observational data. Several authors have recently proposed that this barrier can be overcome in the case where one attempts to infer the effects of several variables simultaneously. In this paper, we present two simple, analytical counterexamples that challenge the general claims that are central to these approaches. In addition, we show that nonparametric identification is impossible in this setting. We discuss practical implications, and suggest alternatives to the methods that have been proposed so far in this line of work: using proxy variables and shifting focus to sensitivity analysis."
to:NB  causal_inference  statistics  to_read 
7 days ago by cshalizi
The Class Ceiling: Why it Pays to be Privileged, Friedman, Laurison
"Politicians continually tell us that anyone can get ahead. But is that really true? This important book takes readers behind the closed doors of elite employers to reveal how class affects who gets to the top. Friedman and Laurison show that a powerful ‘class pay gap’ exists in Britain’s elite occupations. Even when those from working-class backgrounds make it into prestigious jobs, they earn, on average, 16% less than colleagues from privileged backgrounds. But why is this the case? . Drawing on 175 interviews across four case studies - television, accountancy, architecture, and acting – they explore the complex barriers facing the upwardly mobile. This is a rich, ambitious book that demands we take seriously not just the glass but also the class ceiling."
to:NB  inequality  sociology  economics  books:noted 
10 days ago by cshalizi
Neurath Reconsidered | SpringerLink
"This highly readable book is a collection of critical papers on Otto Neurath (1882-1945). It comprehensively re-examines Neurath’s scientific, philosophical and educational contributions from a range of standpoints including historical, sociological and problem-oriented perspectives. Leading Neurath scholars disentangle and connect Neurath’s works, ideas and ideals and evaluate them both in their original socio-historical context and in contemporary philosophical debates. Readers will discover a new critical understanding.
"Drawing on archive materials, essays discuss not only Neurath’s better-known works from lesser-known perspectives, but also his lesser-known works from the better-known perspective of their place in his overall philosophical oeuvre. Reflecting the full range of Neurath's work, this volume has a broad appeal. Besides scholars and researchers interested in Neurath, Carnap, the Vienna Circle, work on logical empiricism and the history and philosophy of science, this book will also appeal to graduate students in philosophy, sociology, history and education. Readers will find Neurath’s thoughts described and evaluated in an accessible manner, making it a good read for those beyond the academic world such as social leaders and activists."

--- There is something charming about the idea of "social leaders and activists" reading a compilation like this...
to:NB  books:noted  logical_positivism  socialism  history_of_ideas  neurath.otto  vienna_circle  philosophy 
15 days ago by cshalizi
The Social Stratification of Environmental and Genetic Influences on Education: New Evidence Using a Register-Based Twin Sample | Sociological Science
"The relative importance of genes and shared environmental influences on stratification outcomes has recently received much attention in the literature. We focus on education and the gene-environmental interplay. Specifically, we investigate whether—as proposed by the Scarr-Rowe hypothesis—genetic influences are more important in advantaged families. We argue that the social stratification of family environments affects children’s chances to actualize their genetic potential. We hypothesize that advantaged families provide more child-specific inputs, which enhance genetic expression, whereas the rearing environments of children in disadvantaged families are less adapted to children’s individual abilities, leading to a suppression of genetic potential. We test this relationship in Germany, which represents an interesting case due to its highly selective schooling system characterized by early tracking and the broad coverage of part-time schools. We use novel data from the TwinLife panel, a population-register–based sample of twins and their families. Results of ACE-variance decompositions support the Scarr-Rowe hypothesis: Shared environmental influences on education matter only in disadvantaged families, whereas genetic influences are more important in advantaged families. Our findings support the growing literature on the importance of the gene-environmental interplay and emphasize the role of the family environment as a trigger of differential genetic expression."

--- It will be interesting to see whether/how they argue for the ACE decomposition...
to:NB  human_genetics  inequality  heritability  re:g_paper 
24 days ago by cshalizi
Modern statistics modern biology | Statistics for life sciences, medicine and health | Cambridge University Press
"If you are a biologist and want to get the best out of the powerful methods of modern computational statistics, this is your book. You can visualize and analyze your own data, apply unsupervised and supervised learning, integrate datasets, apply hypothesis testing, and make publication-quality figures using the power of R/Bioconductor and ggplot2. This book will teach you 'cooking from scratch', from raw data to beautiful illuminating output, as you learn to write your own scripts in the R language and to use advanced statistics packages from CRAN and Bioconductor. It covers a broad range of basic and advanced topics important in the analysis of high-throughput biological data, including principal component analysis and multidimensional scaling, clustering, multiple testing, unsupervised and supervised learning, resampling, the pitfalls of experimental design, and power simulations using Monte Carlo, and it even reaches networks, trees, spatial statistics, image data, and microbial ecology. Using a minimum of mathematical notation, it builds understanding from well-chosen examples, simulation, visualization, and above all hands-on interaction with data and code."
to:NB  books:noted  statistics  computational_statistics  biology  genomics  R 
24 days ago by cshalizi
What Is Real? | Giorgio Agamben
"Eighty years ago, Ettore Majorana, a brilliant student of Enrico Fermi, disappeared under mysterious circumstances while going by ship from Palermo to Naples. How is it possible that the most talented physicist of his generation vanished without leaving a trace? It has long been speculated that Majorana decided to abandon physics, disappearing because he had precociously realized that nuclear fission would inevitably lead to the atomic bomb. This book advances a different hypothesis. Through a careful analysis of Majorana's article "The Value of Statistical Laws in Physics and Social Sciences," which shows how in quantum physics reality is dissolved into probability, and in dialogue with Simone Weil's considerations on the topic, Giorgio Agamben suggests that, by disappearing into thin air, Majorana turned his very person into an exemplary cipher of the status of the real in our probabilistic universe. In so doing, the physicist posed a question to science that is still awaiting an answer: What is Real?"
to:NB  books:noted  majorana.ettore  barely-comprehensible_metaphysics  to_be_shot_after_a_fair_trial  foundations_of_statistics  statistical_mechanics 
24 days ago by cshalizi
[1902.04114] Using Embeddings to Correct for Unobserved Confounding
"We consider causal inference in the presence of unobserved confounding. In particular, we study the case where a proxy is available for the confounder but the proxy has non-iid structure. As one example, the link structure of a social network carries information about its members. As another, the text of a document collection carries information about their meanings. In both these settings, we show how to effectively use the proxy to do causal inference. The main idea is to reduce the causal estimation problem to a semi-supervised prediction of both the treatments and outcomes. Networks and text both admit high-quality embedding models that can be used for this semi-supervised prediction. Our method yields valid inferences under suitable (weak) conditions on the quality of the predictive model. We validate the method with experiments on a semi-synthetic social network dataset. We demonstrate the method by estimating the causal effect of properties of computer science submissions on whether they are accepted at a conference."
to:NB  causal_inference  statistics  blei.david  re:homophily_and_confounding  to_read 
28 days ago by cshalizi
[1902.06281] Approximate leave-future-out cross-validation for time series models
"One of the common goals of time series analysis is to use the observed series to inform predictions for future observations. In the absence of any actual new data to predict, cross-validation can be used to estimate a model's future predictive accuracy, for instance, for the purpose of model comparison or selection. As exact cross-validation for Bayesian models is often computationally expensive, approximate cross-validation methods have been developed; most notably methods for leave-one-out cross-validation (LOO-CV). If the actual prediction task is to predict the future given the past, LOO-CV provides an overly optimistic estimate as the information from future observations is available to influence predictions of the past. To tackle the prediction task properly and account for the time series structure, we can use leave-future-out cross-validation (LFO-CV). Like exact LOO-CV, exact LFO-CV requires refitting the model many times to different subsets of the data. Using Pareto smoothed importance sampling, we propose a method for approximating exact LFO-CV that drastically reduces the computational costs while also providing informative diagnostics about the quality of the approximation."
to:NB  time_series  cross-validation  statistics 
28 days ago by cshalizi
Penalized estimation of directed acyclic graphs from discrete data | SpringerLink
"Bayesian networks, with structure given by a directed acyclic graph (DAG), are a popular class of graphical models. However, learning Bayesian networks from discrete or categorical data is particularly challenging, due to the large parameter space and the difficulty in searching for a sparse structure. In this article, we develop a maximum penalized likelihood method to tackle this problem. Instead of the commonly used multinomial distribution, we model the conditional distribution of a node given its parents by multi-logit regression, in which an edge is parameterized by a set of coefficient vectors with dummy variables encoding the levels of a node. To obtain a sparse DAG, a group norm penalty is employed, and a blockwise coordinate descent algorithm is developed to maximize the penalized likelihood subject to the acyclicity constraint of a DAG. When interventional data are available, our method constructs a causal network, in which a directed edge represents a causal relation. We apply our method to various simulated and real data sets. The results show that our method is very competitive, compared to many existing methods, in DAG estimation from both interventional and high-dimensional observational data."
to:NB  causal_discovery  graphical_models  statistics 
29 days ago by cshalizi
Generalized additive models with flexible response functions | SpringerLink
"Common generalized linear models depend on several assumptions: (i) the specified linear predictor, (ii) the chosen response distribution that determines the likelihood and (iii) the response function that "maps the linear predictor to the conditional expectation of the response. Generalized additive models (GAM) provide a convenient way to overcome the restriction to purely linear predictors. Therefore, the covariates may be included as flexible nonlinear or spatial functions to avoid potential bias arising from misspecification. Single index models, on the other hand, utilize flexible specifications of the response function and therefore avoid the deteriorating impact of a misspecified response function. However, such single index models are usually restricted to a linear predictor and aim to compensate for potential nonlinear structures only via the estimated response function. We will show that this is insufficient in many cases and present a solution by combining a flexible approach for response function estimation using monotonic P-splines with additive predictors as in GAMs. Our approach is based on maximum likelihood estimation and also allows us to provide confidence intervals of the estimated effects. To compare our approach with existing ones, we conduct extensive simulation studies and apply our approach on two empirical examples, namely the mortality rate in São Paulo due to respiratory diseases based on the Poisson distribution and credit scoring of a German bank with binary responses."
to:NB  additive_models  regression  statistics 
29 days ago by cshalizi
Book Review: Mapping Society: The Spatial Dimensions of Social Cartography by Laura Vaughan | LSE Review of Books
"In Mapping Society: The Spatial Dimensions of Social Cartography – available to download here for free – Laura Vaughan offers an analysis of how maps have both described and shaped social phenomena. This is a scholarly and thoroughly researched book that unpicks the context behind many of the foremost examples of social cartography, finds Inderbir Bhullar, and reveals how the layout of cities can exacerbate or ameliorate social ills."
to:NB  books:noted  book_reviews  maps  visual_display_of_quantitative_information  statistics  to_teach:data_over_space_and_time  track_down_references 
29 days ago by cshalizi
Political Hobbyism: A Theory of Mass Behavior
"For many citizens, participation in politics is not motivated by civic duty or selfinterest, but by hobbyism: the objective is self-gratification. I offer a theory of political hobbyism, situate the theory in existing literature, and define and distinguish the hobbyist motivation from its alternatives. I argue that the prevalence of political hobbyism depends on historical conditions related to the nature of leisure time, the openness of the political process to mass participation, and the level of perceived threat. I articulate an empirical research agenda, highlighting how poli-hobbyism can help explain characteristics of participants, forms of participation, rates of participation, and the nature of partisanship. Political hobbyism presents serious problems for a functioning democracy, including participants confusing high stakes for low stakes, participation too focused on the gratifying aspects of politics, and unnecessarily potent partisan rivalries."
to:NB  political_science  us_politics  our_decrepit_institutions  re:democratic_cognition 
29 days ago by cshalizi
The Bias Is Built In: How Administrative Records Mask Racially Biased Policing by Dean Knox, Will Lowe, Jonathan Mummolo :: SSRN
"Researchers often lack the necessary data to credibly estimate racial bias in policing. In particular, police administrative records lack information on civilians that police observe but do not investigate. In this paper, we show that if police racially discriminate when choosing whom to investigate, using administrative records to estimate racial bias in police behavior amounts to post-treatment conditioning, and renders many quantities of interest unidentified---even among investigated individuals---absent strong and untestable assumptions. In most cases, no set of controls can eliminate this statistical bias, the exact form of which we derive through principal stratification in a causal mediation framework. We develop a bias-correction procedure and nonparametric sharp bounds for race effects, replicate published findings, and show traditional estimation techniques can severely underestimate levels of racially biased policing or even mask discrimination entirely. We conclude by outlining a general and feasible design for future studies that is robust to this inferential snare."
to:NB  to_read  causal_inference  police  discrimination  statistics  to_teach:undergrad-ADA  via:henry_farrell 
29 days ago by cshalizi

« earlier    

related tags

academia  academic_freedom  additive_models  agent-based_models  algebra  america  american_history  analogy  anthropology  aral_sea  archaeology  aronow.peter  artificial_intelligence  automata_theory  aztecs  barely-comprehensible_metaphysics  biology  blei.david  book_reviews  books:coveted  books:noted  bootstrap  bounded_rationality  branching_processes  causal_discovery  causal_inference  cellular_automata  central_asia  china  cities  classifiers  climatology  cognitive_science  collective_cognition  comparative_sociology  computational_complexity  computational_statistics  conspiracy_theories  corruption  cross-validation  data_sets  democracy  demography  density_estimation  discrimination  downloaded  dynamical_systems  early_modern_world_history  ecology  econometrics  economic_geography  economic_history  economics  environmental_management  epidemic_models  epidemiology_of_representations  ergodic_theory  evolution  experimental_design  experimental_sociology  expertise  explanation  explanation_by_mechanisms  extreme_values  feynman_diagrams  foundations_of_statistics  france  fraud  game_theory  genetics  genomics  geography  globalization  graph_theory  graphical_models  have_read  heritability  high-dimensional_statistics  history  history_of_ideas  history_of_science  history_of_technology  holmes.susan  huber.peter  human_genetics  hypothesis_testing  identity_group_formation  imperialism  india  inequality  information_theory  initiation  initiation_as_hazing  institutions  intellectuals  interacting_particle_systems  internet  iq  islamic_civilization  kauffman.stuart  kernel_estimators  learning_in_games  learning_theory  literary_criticism  literary_history  logical_positivism  lupia.arthur  machine_learning  macro_from_micro  majorana.ettore  maps  market_failures_in_everything  mathematics  medieval_eurasian_history  missing_data  misspecification  model_checking  modeling  mongol_empire  nationalism  native_american_history  natural_history_of_truthiness  network_data_analysis  networked_life  networks  neural_coding_and_decoding  neural_data_analysis  neural_networks  neurath.otto  neuroscience  nk_networks  nonparametrics  optimization  our_decrepit_institutions  philosophy  philosophy_of_mind  philosophy_of_science  point_processes  police  political_parties  political_science  post-apocalyptic  prediction  printing_press_as_an_agent_of_change  probability  public_opinion  r  race  racine.jeffrey  racism  rakhlin.sasha  random_fields  re:actually-dr-internet-is-the-name-of-the-monsters-creator  re:computational_complexity_of_communism  re:democratic_cognition  re:do-institutions-evolve  re:g_paper  re:homophily_and_confounding  re:network_differences  rectification_of_names  recurrence_times  regression  religion  renormalization  rhetorical_self-fashioning  ripley.brian_d.  ritual  san_francisco  science_as_a_social_process  science_fiction  science_in_society  scientific_revolution  sensitivity_analysis  simulation  smoothing  social_identity  social_influence  social_life_of_the_mind  social_measurement  social_media  social_networks  social_science_methodology  socialism  sociology  something_about_america  spatial_statistics  spatio-temporal_statistics  spectral_methods  splines  statistical_inference_for_stochastic_processes  statistical_mechanics  statistics  stochastic_differential_equations  stochastic_processes  text_mining  theoretical_computer_science  time_series  to_be_shot_after_a_fair_trial  to_read  to_teach:baby-nets  to_teach:data-mining  to_teach:data_over_space_and_time  to_teach:undergrad-ada  track_down_references  us_politics  ussr  vienna_circle  visual_display_of_quantitative_information  voter_model  yuan 

Copy this bookmark: