the median hypothesis
november 2011 by chl
"[...] there is a need for an algorithm to construct a hypothesis (either a single hypothesis or some combination), given the posterior belief. several methods have been proposed for this problem: for example, gibbs sampling, ensemble methods, and choosing the maximum posterior. we propose [...] choosing the median hypothesis. this method is close to the average gibbs classifier and bayes optimal classifier in terms of accuracy while having the same run-time efficiency, during the generalization phase, as the maximum posterior method."
video
watchlist
median-hypothesis
tukey's-median
via:shivak
stat
from delicious
november 2011 by chl
understanding the new statistics: effect sizes, confidence intervals, and meta-analysis
september 2011 by chl
'the fact that these are "new statistics" for many psychologists, in this day and age, tells us much about the state of the discipline.' -- cshalizi
stat
book
shopping?
from delicious
september 2011 by chl
introduction to statistical computing
september 2011 by chl
lectures, homeworks & labs from cosma shalizi's recent statistical computing course @ cmu: from screen scraping to mcmc
stat
comp
data-proc
course
by:cshalizi
has:by
from delicious
september 2011 by chl
sta 414/2104: statistical methods for machine learning and data mining
may 2011 by chl
Great lectures notes by Radford Neal on #machinelearning with #rstats,
ml
dm
stat
course
by:radford-neal
r
rstats
machinelearning
from delicious
may 2011 by chl
technocalifornia: recommender systems: we're doing it (all) wrong
april 2011 by chl
ratings: ordinal, interval, nonsensical?
rec-sys
stat
likert-scale
big-deal?
from delicious
april 2011 by chl
jstat : a javascript statistical library
march 2011 by chl
this is really nice: RT @JanWillemTulp #jStat, a statistical library in #Javascript (partial port of #R)
javascript
stat
lib
jStat
from delicious
march 2011 by chl
[1006.3868] philosophy and the practice of bayesian statistics
june 2010 by chl
"a substantial school in the philosophy of science identifies bayesian inference with inductive inference and even rationality as such, and seems to be strengthened by the rise and practical success of bayesian statistics. we argue that the most successful forms of bayesian statistics do not actually support that particular philosophy but rather accord much better with sophisticated forms of hypothetico-deductivism."
hypothetico-deductivism
paper
by:andrew-gelman
by:cshalizi
stat
bayes
from delicious
june 2010 by chl
fivethirtyeight: politics done right: consensus olympic medal count projections: day 3
february 2010 by chl
method: "[...] a simple mean of the number of medals that each country was expected to win in each discipline, as averaged across the nine sources."
olympics-2010
medals
stat
from delicious
february 2010 by chl
morris l. eaton, multivariate statistics: a vector space approach (beachwood, ohio, usa: institute of mathematical statistics, 2007)
february 2010 by chl
"the purpose of this book is to present a version of multivariate statistical theory in which vector space and invariance methods replace, to a large extent, more traditional multivariate methods."
lin-alg
stat
math
book
via:cshalizi
from delicious
february 2010 by chl
incredibly simple approximation — the endeavour
june 2009 by chl
"said another way, the estimate based on all the data is only twice as good as the estimate based on just the first and last points."
stat
approximation
bancroft's-rule
june 2009 by chl
bayesian statistics is misnamed — the endeavour
april 2009 by chl
'it’s certainly easier to say “bayesian statistics” than to say “that school of statistics that represents uncertainty in unknown parameters by probabilities,” even though the latter is accurate.'
bayes
stat
april 2009 by chl
unbiased estimators can be terrible — the endeavour
april 2009 by chl
"exact in the limit, useless on the way there."
unbiased-estimators
stat
april 2009 by chl
four pillars of bayesian statistics — the endeavour
april 2009 by chl
"teaching frequentist statistics has increased my appreciation for bayesian statistics."
stat
adhockery
april 2009 by chl
electronic books
march 2009 by chl
by wolfgang härdle (xplore) et al.; applied multivariate statistical analysis, applied nonparametric regression, applied quantitative finance &c.
math
stat
fin
free
books
xplore
via:cshalizi
march 2009 by chl
modeling with data
march 2009 by chl
"let me tell you why I'm setting up another blog: because statistics is amazing. seriously enthralling." / to go with ben klemens' book, modeling with data.
stat
analytics
modeling
modeling-with-data
blog
by:ben-klemens
march 2009 by chl
machine learning (theory) » prediction science
march 2009 by chl
"the lack of unification is fertile territory for new research [...]"
learning-theory
ml
prediction
stat
march 2009 by chl
social science statistics blog: follow-up on robins' talk ("a bold vision of artificial intelligence and philosophy")
march 2009 by chl
"the algorithm involves looking for conditional independencies in the data [...]. for some data generating processes, [...] the causal model will be revealed -- the ordering and all of the effect sizes. / the key assumption is "faithfulness," which states that when two variables are found to be conditionally independent in the data, we can conclude that there is no causal arrow between them [...]. without that assumption we can't infer the causal model from a joint density, but with it we can -- and the point of jamie's talk was that [...] even more information can be gleaned from the joint density than has been recognized."
faithfulness
causality
stat
via:arthegall
march 2009 by chl
related tags
! ⊕ adaptive-systems ⊕ adhockery ⊕ alg ⊕ amazing ⊕ analytics ⊕ anova ⊕ apl ⊕ apophenia ⊕ approximation ⊕ archive ⊕ association-measures ⊕ astronomy ⊕ astrostatistics ⊕ averages ⊕ awesome ⊕ bancroft's-rule ⊕ bart ⊕ bayes ⊕ bfgs ⊕ bias-variance-trade-off ⊕ big-deal? ⊕ binomial-distribution ⊕ bio ⊕ bio-inf ⊕ blog ⊕ blogs ⊕ bolasso ⊕ book ⊕ book-review ⊕ books ⊕ bootstrapping ⊕ by:andrew-gelman ⊕ by:arthegall ⊕ by:ben-klemens ⊕ by:cosma-shalizi ⊕ by:cshalizi ⊕ by:dataspora ⊕ by:dennis-shasha ⊕ by:geoff-hinton ⊕ by:harald-baayen ⊕ by:kevin-knight ⊕ by:longhai-li ⊕ by:manda-wilson ⊕ by:michael-jordan ⊕ by:nassim-nicholas-taleb ⊕ by:persi-diaconis ⊕ by:radford-neal ⊕ c ⊕ cartography ⊕ causality ⊕ central-limit-theorem ⊕ chi-square ⊕ classification ⊕ classifier ⊕ clojure ⊕ cnx ⊕ co-occurrence ⊕ cog-psy ⊕ collocations ⊕ comment ⊕ commentary ⊕ comp ⊕ comp-bio ⊕ comp-ling ⊕ complexity ⊕ course ⊕ courses ⊕ courseware? ⊕ cumulants ⊕ data-analysis ⊕ data-proc ⊕ data-science ⊕ deborah-mayo ⊕ deep-nets ⊕ density-estimation ⊕ dm ⊕ draft ⊕ econometrics ⊕ edu ⊕ emwa ⊕ esl-2 ⊕ etymology ⊕ evolution ⊕ examples ⊕ expectation ⊕ expected-improvement ⊕ experimental-design ⊕ faithfulness ⊕ filetype:pdf ⊕ fin ⊕ food-for-thought ⊕ free ⊕ free:cc ⊕ freq ⊕ from:gavin ⊕ gary-king ⊕ genomics ⊕ geo ⊕ gliding ⊕ gold's-theorem ⊕ google ⊕ gsl ⊕ gui ⊕ guidelines ⊕ has:by ⊕ heavy-tails ⊕ heh ⊕ histograms ⊕ history ⊕ hypothesis-testing ⊕ hypothetico-deductivism ⊕ in:vector ⊕ incanter ⊕ inequalities ⊕ interaction-effects ⊕ interesting ⊕ interpretability ⊕ intro ⊕ ip ⊕ ir ⊕ iran-election-2009 ⊕ j ⊕ jackknife ⊕ java ⊕ javascript ⊕ jmp ⊕ john-tukey ⊕ josh-tenenbaum ⊕ jStat ⊕ kendall's-τ ⊕ kernel-density-estimates ⊕ language ⊕ lasso ⊕ later ⊕ learning ⊕ learning-theory ⊕ least-squares ⊕ lecture-notes ⊕ lectures ⊕ lib ⊕ likert-scale ⊕ lin-alg ⊕ lin-reg ⊕ linear-regression ⊕ linf ⊕ ling ⊕ linked ⊕ links ⊕ lisp ⊕ list ⊕ loess ⊕ long ⊕ lt ⊕ machinelearning ⊕ manga ⊕ materials ⊕ math ⊕ matlab ⊕ medals ⊕ media:document ⊕ media:html ⊕ media:pdf ⊕ media:ps ⊕ median ⊕ median-hypothesis ⊕ mental-models ⊕ misc ⊕ mixture-models ⊕ ml ⊕ mle ⊕ modeling ⊕ modeling-with-data ⊕ mondrian ⊕ moving-average ⊕ multi-level-bayesian-models ⊕ multivariate-stat ⊕ n-gram ⊕ na ⊕ nd ⊕ networks ⊕ nflxprize ⊕ nlp ⊕ nn ⊕ node-harvest ⊕ non-parametric ⊕ normal-distribution ⊕ olympics-2010 ⊕ opt ⊕ orange ⊕ outliers ⊕ p:m3p2r ⊕ paper ⊕ pattern-recognition ⊕ pca ⊕ perl ⊕ person ⊕ physics ⊕ poisson-intensity-reconstruction ⊕ poker ⊕ power-laws ⊕ prediction ⊕ primer ⊕ principal-cumulant-components ⊕ prob ⊕ probability ⊕ processing ⊕ prog-lang ⊕ psychology ⊕ pubtrack ⊕ python ⊕ quote ⊕ r ⊕ r-a-fisher ⊕ random-forests ⊕ random-projections ⊕ rank-correlation ⊕ reading-list ⊕ readings ⊕ rec-sys ⊕ refresh:1 ⊕ refs ⊕ regression ⊕ regression-trees ⊕ regularization ⊕ resampling ⊕ research-paper ⊕ reservoir-sampling ⊕ review ⊕ revisit ⊕ rmse ⊕ robust-stat ⊕ rstats ⊕ sampling ⊕ sas ⊕ screencast ⊕ search ⊕ search-evaluation ⊕ search-quality ⊕ seminars ⊕ seq-sim ⊕ series:synthesis-lectures ⊕ sgd ⊕ shopping ⊕ shopping? ⊕ significance-tests ⊕ simpson's-paradox ⊕ simulation ⊕ sna ⊕ soc-sci ⊕ sochastic-approximation ⊕ spiral-tap ⊕ spss ⊕ sqlite ⊕ stat ⊖ stat-arb ⊕ stat-efficiency ⊕ stat-nlp ⊕ stat-robustness ⊕ stat-significance ⊕ stata ⊕ statnet ⊕ syllabus ⊕ t-test ⊕ tail-weight-index ⊕ teaching ⊕ text-analysis ⊕ thesis ⊕ thesis/phd ⊕ time-series ⊕ track-down:pdf ⊕ trees ⊕ tukey's-median ⊕ tutorial ⊕ tutorials ⊕ twitter ⊕ unbiased-estimators ⊕ variable-selection ⊕ variance ⊕ via:? ⊕ via:aaronsw ⊕ via:agray0 ⊕ via:alstrup ⊕ via:andreas.s ⊕ via:arsyed ⊕ via:arthegall ⊕ via:bos ⊕ via:csantos ⊕ via:cshalizi ⊕ via:dabd ⊕ via:hublicious ⊕ via:innersmile0790 ⊕ via:jhammerb ⊕ via:jolby ⊕ via:m78 ⊕ via:mreid ⊕ via:nikete ⊕ via:paks ⊕ via:pskomoroch ⊕ via:shivak ⊕ via:ted-dunning ⊕ via:trunov ⊕ via:walterra ⊕ via:wnpxrz ⊕ via:xyll ⊕ video ⊕ video-lectures ⊕ viz ⊕ watchlist ⊕ wishlist ⊕ wrt:mackay ⊕ xlispstat ⊕ xplore ⊕ ☆ ⊕Copy this bookmark: