Here is the latest bag of tweets^*, which covers April 2013.

(*) These are interesting news that I found on Twitter and that I archive periodically.

• StackStats: Great answer: What is the meaning of “All models are wrong, but some are useful” http://t.co/COQuDKyRMo #modeling (28 Apr)
• peter_c_william: Reading the R mailing lists, I find they have mastered RTFM to a level unequaled in my knowledge of human history. http://t.co/kldS0bWAeD (28 Apr)
• lucaborger: Speeding up #Rstats – awesome post by ‏@noamross http://t.co/YWH8SUw2d3 HT @larysar (28 Apr)
• Statistics2013: Glossary of statistical terms: http://t.co/3s2tgHD9Iw #STATS2013 (27 Apr)
• denisparra: a bit old, but very useful R resource : “Don’t R alone! A guide to tools for collaboration with R” http://t.co/iAzQb2QFDa #rstats (27 Apr)
• cndreisbach: Using Clojure reader literals to create a transactional database: http://t.co/pncUrrMWhg. Insanely baller. (27 Apr)
• mbostock: New, in-depth explanation, with less magic. How Selections Work: http://t.co/XBdJZjXdm9 #d3js (27 Apr)
• zentree: ‘Learning to code in #Rstats’ in Quantum Forest. http://t.co/rTjRwVpAo3 (26 Apr)
• whit537: Oh, and http://t.co/UB8pUjGedQ is pretty sweet. Instant ephemeral (30-minute) Postgres dbs. Great for testing. (26 Apr)
• peter_c_william: Stephen Wolfram does a polished analysis of Facebook users. http://t.co/YmWpMt2Bk6 (25 Apr)
• lmichelbacher: @emacs_knight I’m sure the knight knew that about this valuable time saver: org-sort (C-c ^) sorts tables according to the current column. (25 Apr)
• ShirleySWangWSJ: Two interesting takes on DSM-5: http://t.co/F0ipBI6Fkq via @Health_Affairs and http://t.co/TpyKXD558x via @NatureNews (h/t @noahWG) (25 Apr)
• tomstafford: That last link is the very enjoyable Meehl (1978) http://t.co/A59O6S6Nud via @johnmyleswhite (25 Apr)
• techmilind: Excellent tutorial on large scale machine learning, by @markusweimer : http://t.co/aBCHki6RO6 (25 Apr)
• golovashkin: In numerical optimization, folks rely on Hans Mittelmann benchmarks to compare solvers’ performances; http://t.co/nJvzKy4qLA for stat / ML? (25 Apr)
• tek_news: HNews: Emacs setup for Python development http://t.co/Jed960h2aL #python (25 Apr)
• hadleywickham: @seanjtaylor see also http://t.co/xw64PoIbxG (25 Apr)
• ds_ldn: Probabilistic programming is a newer way of posing machine learning problems by @zaxtax http://t.co/XsSjXZkQeJ (25 Apr)
• recology_: “Sublime Text 2/3 plugin which allows to diff and merge files in ST…” http://t.co/pHKPXTQ5uv via @prismatic (25 Apr)
• wesmckinn: pandas 0.11.0 is out! 3 solid months of development, > 900 commits, 50 contributors http://t.co/RN4nGJOQYl #pydata (24 Apr)
• quartzmo: Awesome to read about Jekyll used at healthcare .gov in @dhcole’s article. But wouldn’t caching html be even better? http://t.co/2cYmhT53IQ (24 Apr)
• PLOSMedicine: #BigData mining and new hypotheses in mental health research http://t.co/UxXqFROkTK via @sanjayb493 #globalmentalhealth (24 Apr)
• SublimeTxtTips: RT @codecarson Awesome visual tweaks for Sublime Text. http://t.co/4WGnfDVVD7 #sublimetext (24 Apr)
• ISTC_BigData: ScalaR: How to improve interactive #visualization of very large data sets http://t.co/C8Ko7vmaKN (24 Apr)
• rtroncy: Linked CSV: Enabling CSV to be linked together and to be interpreted as RDF. http://t.co/ksb0ZoNRAq #odw13 via @JeniT (24 Apr)
• worldbankdata: You can now access the data tables from the World Development Indicators online: http://t.co/CSVVLVfOBL #opendata #WDI2013 (24 Apr)
• peterpaulrubens: Immensely helpful! → dataset: databases for lazy people http://t.co/OkjvFnSAYI thx @driven_by_data & @pudo! (24 Apr)
• Atabey_Kaygun: SADDLE: Scala Data Library http://t.co/h0RBkrlX93 via @prismatic (23 Apr)
• jorgetavares: http://t.co/GnSwl8IZw6 #books #free (23 Apr)
• beaucronin: (Advanced) machine learning glossary http://t.co/1ozhBcZWZO (23 Apr)
• statalgo: @gappy3000 I use Gabor’s list[] solution: https://t.co/1TjCklDn2o (23 Apr)
• tdhopper: Another great scikit-learn tool that @ogrisel is just teaching me about: Pipelines http://t.co/4HBIDNekZ6 (23 Apr)
• siah: Free ebook “Unix Text Processing” http://t.co/CI0UJlLlnh (via @DataJunkie) (22 Apr)
• ThembeK: Top 5 most critical skills for a statistician… http://t.co/UQHMhnVuEG (22 Apr)
• lucaborger: RT ‏@siah The ebook for “Learning Statistics with R” is available for free http://t.co/9aEYOfl2ZR #rstats | HT @NickGolding (22 Apr)
• ronert_obst: Bayesian Computational Methods http://t.co/kLBVJYl8lu (22 Apr)
• bbatsov: Can’t stop blogging today :-) Custom configuration for shells in #Emacs http://t.co/wJfFIv0a3u At this point I’m going back to writing code. (22 Apr)
• robjhyndman: My new forecasting book is finally finished http://t.co/1vvMdjmLHO (21 Apr)
• zachgemignani: The Ultimate Collection Data Storytelling Resources, to catch up on the current thinking on this hot #dataviz topic http://t.co/iqmkh52oHs (20 Apr)
• grossbart: I made a quick map/reduce/zip example for those interested: http://t.co/svCrgA6aBf (19 Apr)
• robjhyndman: Reliability, Reproducibility and the Reinhart-Rogoff error – http://t.co/1M4k9wlfOp (19 Apr)
• biocs: How many scientists run web services and have no idea about crypto? This would be useful to do http://t.co/Y3TymMTbJF (19 Apr)
• gappy3000: oldie but goldie: “What’s there to like about R?”, for those who call #rstats “wonky”… http://t.co/VNtG4Nol1i (19 Apr)
• GregRahn: My new favorite app for OS X: #Hadoop JobTracker Mac Menu Bar App http://t.co/NyMqBikmsi (19 Apr)
• freakonometrics: [free ebook] Bruce Hansen’s Econometrics textbook http://t.co/iAcNz5RqWP via @DEAGiles (19 Apr)
• orgmode_bot: Let’s check the changes at orgmode 8.0, see http://t.co/LrxLlngjzh (19 Apr)
• ogrisel: @jakevdp pelican: http://t.co/6yEtVunNZ3 although more like a blog generator. There is notebook plugin: http://t.co/IhCUI20Cbg (18 Apr)
• inningPalmer: NumPy Beginner’s Guide (2nd Edition) | Packt Publishing http://t.co/ay5BezBAOE (18 Apr)
• RDataMining: Graphical Models with R – a PDF document http://t.co/sasNXaSc4z (18 Apr)
• kwbroman: @xieyihui In general, look for “copy editor symbols” e.g. http://t.co/slPyUgB5hN (18 Apr)
• Atabey_Kaygun: PLOS “Text Mining Collection” Journal: http://t.co/sLp8GwgEuV (18 Apr)
• siah: 6 Free E-Books on Learning to Program with Python http://t.co/Mrfr2jdvkk (17 Apr)
• wesmckinn: And a totally awesome package name RT @mharrison: Plotting to d3/vega from Python/pandas < https://t.co/Bi8QizcOpV (17 Apr)
• neilfws: “Although this has been done many times in many languages, we really wanted to do it in MATLAB” - http://t.co/ppQ0uyBqN4 (17 Apr)
• siah: Applied Parallel Computing (PyCon 2013 Tutorial) slides and code http://t.co/u2rUkDv90x (17 Apr)
• EGouillart: Cours de #Python scientifique hier+aujourd’hui à l’#ENS Paris à 70 profs de classe prépa ! Les docs de cours sont sur http://t.co/JcwaJOHrlW (17 Apr)
• teoliphant: #IPython #pydata Wakari Pro Tip. Open any online .ipynb notebook in Wakari by replacing http:// with https://t.co/4lRFI6FInC in the URL. (16 Apr)
• freakonometrics: Acknowledgment from an anonymous doctoral dissertation http://t.co/NwOdTuSHdI see also http://t.co/KasyWGX7Py (16 Apr)
• reid_jf: Statistical Models in Julia (Doug Bates) http://t.co/tn4wEJEYZh (15 Apr)
• tristanzajonc: Couldn’t agree more: “the current state of the art of measurement of predictive model fit is unsatisfying” http://t.co/gEr842w2xz (15 Apr)
• climagic: for f in *; do b=$(echo “$f” | tr ‘[A-Z]’ ‘[a-z]’); mv “$f” “$b”; done # Lower case all files in a folder. Thx @argyris (15 Apr)
• CeADARIreland: Python data tools just keep getting better http://t.co/iJWC1joCtO (15 Apr)
• lucaborger: Very useful paper: “Nine simple ways to make it easier to (re)use your data” https://t.co/smiJbFJQIk by @ethanwhite et al. MT @tomjwebb (15 Apr)
• Atabey_Kaygun: Testing cut-points in a simple undirected graph (an algorithm and its implementation in lisp) http://t.co/LTN1BrALRa (15 Apr)
• neilfws: Good article on p-values but no need to rebrand medical statistics as “data science”. Increasingly sick of the term. http://t.co/YXZVlPtHr6 (15 Apr)
• zentree: ‘Teaching introductory statistics from a Bayesian perspective’ a 10 yo conference paper (PDF). #TeachingStats http://t.co/4059UWNDIy (15 Apr)
• getpy: “Python’s Magical Self” by @mind_blight at @ConcentricSky: http://t.co/MDjrpkV3n3 (15 Apr)
• zentree: William Briggs on some reasons why confidence intervals don’t make much sense. http://t.co/Tb5oTkVM6H (15 Apr)
• abmathewks: mages’ blog: Transforming subsets of data in R with by, ddply a… http://t.co/WEl63IEJQ2 (15 Apr)
• paulblaser: Using R — Working with Geospatial Data - http://t.co/ft18opI6P5 (15 Apr)
• SelectStats: Really useful list of R tricks - http://t.co/2BuxTOZMIj If you’re not using R already you should definitely try it. #rstats #statistics (15 Apr)
• M_T_Patterson: ’effects’ library in R is excellent for visualizing marginal effects.. see http://t.co/QO0EGRcKLq for an example #RStats, #glm, #packages (14 Apr)
• albertocairo: New, quick post: “Making your message visible: Trend lines in scatter plots” http://t.co/zAQp3uaPl8 #dataviz #infographics #ddj (14 Apr)
• moorejh: #programming #bioinformatics RT @hnycombinator: What I Wish I Knew When Learning Haskell [39 slides,S. Diehl] http://t.co/XyIbw6ENwe (14 Apr)
• KevlinHenney: “Where the Unix philosophy breaks down” by @JohnDCook: http://t.co/eXRdPI4EO6 #accu2013 (14 Apr)
• smdiehl: @gappy3000 http://t.co/xsFwJDb7FU (13 Apr)
• cpsievert: How to become an ’expert’ data scientist in 6 months http://t.co/3T1NgRfMYB #YouveGotToBeKiddingMe (13 Apr)
• cndreisbach: Really enjoyed this article about Clojure design: http://t.co/hXABzucEkY. It makes me want to try the author’s “dire” library, as well. (13 Apr)
• chengweiwei: A concise online course on WEKA machine learning tool (given by its developers) - http://t.co/VpksTAAd6J (13 Apr)
• vsbuffalo: @fonnesbeck This too looks cool: http://t.co/cqYT97NI0B (12 Apr)
• fonnesbeck: @vsbuffalo I haven’t been either, but I’ve been watching the Numba project with interest: http://t.co/3Clfpw1HO4 (12 Apr)
• sgsfak: #clojure all grown up http://t.co/EaMdqYJR3O (11 Apr)
• moorejh: #bioinformatics #genomics #complexity #datamining RT @cistronic: Graph Constrained Discriminant Analysis http://t.co/kGekNxtJq9 (11 Apr)
• moorejh: #datascience #bioinformatics RT @dataJujitsu beginner’s tutorial on subsetting / cleaning data in #Rstats http://t.co/jSaVME5AHn (11 Apr)
• Atabey_Kaygun: Working with Wordnet and Lisp: http://t.co/G7mETJLmdf (11 Apr)
• ConcejeroPedro: #RStats Beautiful R-caret vignette for 10-fold cross-validation and ROC AUC computing with prevalence and PPV http://t.co/tSKCCDUdjb (11 Apr)
• timgluz: Free preliminary version for “33 miniatures Mathematical and Algorithmic Applications of Linear Algebra” http://t.co/kBBKb65ab4 (11 Apr)
• recology_: looks promising -> @OKFN Progress on the Data Explorer http://t.co/ulj6SMmCyk via @prismatic (11 Apr)
• recology_: presentation generator with Jekyll underneath http://t.co/n74sQrSYHa via @prismatic (11 Apr)
• gappy3000: Hadley Wickham: Tidy Data http://t.co/iWTwpqZdgr (11 Apr)
• mblondel_ml: @johnmyleswhite This workshop might be of interest to Julia people http://t.co/HZKZMHQd8B (11 Apr)
• neilfws: “in R how to get error messages in english” not the problem that you might think at first :) http://t.co/OFfJYVRfSW (11 Apr)
• Rbloggers: A quick introduction to ggplot2: (This article was first published on Inundata » R, and kindly co… http://t.co/SDaV06KgRA #rstats (11 Apr)
• xieyihui: If you cannot remember how to write math expressions (cf demo(plotmath)) in #rstats, bookmark this page: http://t.co/PgDMaNfSuV (11 Apr)
• GenomeBrowser: The UCSC Cancer Browser has a new look! View & analyze cancer genomics data and associated clinical info: http://t.co/B8tebc8SBM (11 Apr)
• QuestAnswers: Psychiatric Genetics: Are We There Yet? http://t.co/BzKth32LRP #oa (11 Apr)
• lisaczhang: 4 Studies which Show that Using a Second Monitor Can Boost Productivity http://t.co/0MlvJv8eHS (10 Apr)
• BrendanNyhan: Terrifying: “average statistical power of studies in the field of neuroscience is probably no more than ~8-31%” http://t.co/HiqvjrEZVq (10 Apr)
• JohnMHancock: The NIH Toolbox - Setting a standard for biomedical research http://t.co/atP8kQh55Q #Standards #OA (10 Apr)
• Atabey_Kaygun: Category Theory & Programming (Haskell) http://t.co/CiH8NB4JAl (10 Apr)
• StackTeX: Blog: TeXtalk: an interview with Leo Liu http://t.co/9huNiheJHA (10 Apr)
• tomstafford: Also: “Understanding Git Conceptually” http://t.co/Bik1rLA9SP (10 Apr)
• jjgibaja: MOOC Interrupted: Top 10 Reasons Our Readers Didn’t Finish a Massive Open Online Course | Open Culture http://t.co/xJS6T7RDny (10 Apr)
• msgbi: Bash productivity Keep TODOs in git https://t.co/5n7A66yPXV (10 Apr)
• poeschko: A cool interactive way to learn Git: http://t.co/bFBWm72Ez3 (10 Apr)
• planetclojure: Neural Network Visualisation http://t.co/4C4prTbqeu (10 Apr)
• trvrb: Tutorial on inferring spatiotemporal dynamics from viral sequence data hosted on GitHub https://t.co/zEx236mnyJ (9 Apr)
• kdnuggets: Statistical Analysis and Data Mining journal, April 2013: Psychotropic drug stats, Biclustering, Associations http://t.co/mwzTfpBzKB (9 Apr)
• Cmrn_DP: Post on a Bayesian (“alright we get it!”) solution to the Multi Armed Bandit problem http://t.co/7XZrB87Xaw (7 Apr)
• YvesMulkers: Data Mining Book Review: Thinking Statistically A short review for a short book. Thinking Statistically, by Uri … http://t.co/QGB7SwHHx4 (7 Apr)
• kdnuggets: FDA Triples Down on Data Mining , data/text mining for adverse events, finding safety signals, & illegal drug use http://t.co/FVvelPW3A4 (7 Apr)
• kdnuggets: You need to know both sides: an introduction to SAS for R Programmers #rstats http://t.co/7rOcJ1ofap (7 Apr)
• tdhopper: A second edition of Sutton and Barton’s Reinforcement Learning is coming! http://t.co/W4tPQCCDlV (7 Apr)
• RLangTip: Free e-book on multilevel modeling with #rstats using nlme and multilevel packages: http://t.co/BCcgjkcsrg (05 Apr)
• HarlanH: RT @JackieKazil: why? why? why! – a lesson for #datascience teams http://t.co/Ek6yIyo50M (5 Apr)
• lmrei: http://t.co/QC6fLm23Dz - http://t.co/qiSw3wICHd 4 million financial and economic time-series datasets ready to use from Python :) (5 Apr)
• timgluz: Complete n00bs guide to enhancing Solr/Lucene search with Mahout’s Machine Learning http://t.co/QApaoTrytt via @prismatic (5 Apr)
• RickWicklin: Many #JuliaLang tutorials from #mit conference http://t.co/HVzRLKq2mQ #statistics MT @jacopoanselmi: (5 Apr)
• reid_jf: Bioconductor 2.12 is released following R 3.0.0 “Masked Marvel” #rstats http://t.co/Tn6u0znztB (5 Apr)
• rob_aldridge: Just came across this helpful way to find (and then delete) large files in Gmail in order to free up space. http://t.co/KwMTQADEDe (5 Apr)
• zoltanvarju: Resources that Helped Me Learn Haskell http://t.co/TQBnUNeVgL | Atomic Spin (5 Apr)
• DataWL: R, D3.js and SNA Course: I took the SNA course by Lada Adamic in coursera. It’s a super interes… http://t.co/ToElTXYxMS #bigdata #data (5 Apr)
• stuartsierra: My Strange Loop 2012 talk ‘Functional Design Patterns’ is on InfoQ http://t.co/T4tWHCQAbb #clojure (4 Apr)
• ScientificData: Scientific Data’s website is now live: http://t.co/nKPzUbRR0D (4 Apr)
• DataWL: R 3.0.0 is released! (what’s new, and how to upgrade): A few hours ago Peter Dalgaard (of R Cor… http://t.co/N8THmNNneP #bigdata #data (3 Apr)
• zoltanvarju: Yet Another Lambda Blog » Haskell as fast as C: A case study http://t.co/8Qn10VqfyC (3 Apr)
• zoltanvarju: Think Big » Programming Trends to Watch: Logic and Probabilistic Programming http://t.co/QNuNpG1XtC (3 Apr)
• moorejh: RT @gauravjain49: Cool paper by @moorejh discusses #GWAS challenges that require computational method http://t.co/e4nqFW5EdM #Bioinformatics (3 Apr)
• kwbroman: Blog: Thoughts on statistical consulting http://t.co/TgTOaUlprZ (3 Apr)
• jsross119: Great Ioannidis Ed: limits of using admin data for clinical research, value of RCTs - must read for research fellows http://t.co/kCFunvTlmE (3 Apr)
• timelyportfolio: great week for #d3js and #rstats have http://t.co/xcirbjTkwI, @rhealthvis, @patrickm145 library, and @nachocab #clickme (3 Apr)
• wesmckinn: Congrats to pandas dev @atomklein on releasing a new #scala data toolkit Saddle today http://t.co/h9BF4F3yLI (2 Apr)
• kwbroman: @d3visualization RT @StrictlyStat Introducing the healthvis R package - one line D3 graphics with R #rstats http://t.co/0PqBDYRN9Y (2 Apr)
• patrickm145: DexCharts progress… http://t.co/PNfbqjHZfB #d3js reusable charts. New: Chord Diagram and Dendrograms (2 Apr)
• siah: My friend, Sebastien Bubeck, is writing an interesting blog “Topics on optimization, probability, & statistics” http://t.co/Ruan6Cy5FU (1 Apr)
• Viral_B_Shah: Videos from the #julialang tutorial at MIT Independent Activities Period in Jan 2013: http://t.co/yu8eCMvYaq (1 Apr)
• recology_: ahhhh, very useful -> print commands in .sh file as they execute set -x verbose (1 Apr)
• QuidLabs: Topological data analysis – here’s a primer http://t.co/V1DRXQuJP2 #dataintelligence (1 Apr)