Not So Standard Deviations

Hilary and Roger discuss the paradigm-shifting Echo Show, whether we need explainable AI or not, and how lessons from DevOps could be useful in analysis development. Show notes: Peter Norvig on explainable AI: https://www.computerworld.com.au/article/621059/google-research-chief-questions-value-explainable-ai/ Wired article about Google's Site Reliability Engineering: https://www.wired.com/2016/04/google-ensures-services-almost-never-go/?mbid=nl_4616 Support us through our Patreon page: https://www.patreon.com/NSSDeviations Roger on Twitter: https://twitter.com/rdpeng Hilary on Twitter: https://twitter.com/hspter Get the Not So Standard Deviations book: https://leanpub.com/conversationsondatascience/ Subscribe to the podcast on Apple Podcasts: https://itunes.apple.com/us/podcast/not-so-standard-deviations/id1040614570 Subscribe to the podcast on Google Play: https://play.google.com/music/listen?u=0#/ps/Izfnbx6tlruojkfrvhjfdj3nmna Find past episodes: https://soundcloud.com/nssd-podcast Contact us at nssdeviations@gmail.com

This episode heralds the return of CEO Hilary. Also, Hilary and Roger discuss cybersecurity in the cloud, Theranos, residual variation in data analyses, and Airbnb’s Data University. Show notes: P-hacking or not? https://twitter.com/NASAGISS/status/875368384971649025 Theranos equipment sold on startup liquidators: https://twitter.com/startuplqdtr/status/873385484860313600 Trump signs cybersecurity executive order: https://www.geekwire.com/2017/trump-cybersecurity-cloud/ Airbnb is running its own internal university: https://techcrunch.com/2017/05/24/airbnb-is-running-its-own-internal-university-to-teach-data-science/ Support us through our Patreon page: https://www.patreon.com/NSSDeviations Roger on Twitter: https://twitter.com/rdpeng Hilary on Twitter: https://twitter.com/hspter Get the Not So Standard Deviations book: https://leanpub.com/conversationsondatascience/ Subscribe to the podcast on Apple Podcasts: https://itunes.apple.com/us/podcast/not-so-standard-deviations/id1040614570 Subscribe to the podcast on Google Play: https://play.google.com/music/listen?u=0#/ps/Izfnbx6tlruojkfrvhjfdj3nmna Find past episodes: https://soundcloud.com/nssd-podcast Contact us at nssdeviations@gmail.com

Hilary and Roger talk about the EARL conference, a data science tri-lemma, data science ethics, and Hilary’s CD collection. Show notes: P-hacking conversation: https://twitter.com/jakevdp/status/868564701239627776 Wrangle Conf: http://wrangleconf.com/ Gabe Becker’s EARL talk: https://twitter.com/groundwalkergmb/status/872918368319266816 Thomas Vaugh Shiny UI: https://twitter.com/hspter/status/872596718876975104 Business Science: http://www.business-science.io/ tidyquant: https://business-science.github.io/tidyquant/ timekit: https://business-science.github.io/timekit/ Karl Broman analysis of data file formats: http://kbroman.org/blog/2017/04/30/sqlite-feather-and-fst/ Support us through our Patreon page: https://www.patreon.com/NSSDeviations Roger on Twitter: https://twitter.com/rdpeng Hilary on Twitter: https://twitter.com/hspter Get the Not So Standard Deviations book: https://leanpub.com/conversationsondatascience/ Subscribe to the podcast on Apple Podcasts: https://itunes.apple.com/us/podcast/not-so-standard-deviations/id1040614570 Subscribe to the podcast on Google Play: https://play.google.com/music/listen?u=0#/ps/Izfnbx6tlruojkfrvhjfdj3nmna Find past episodes: https://soundcloud.com/nssd-podcast Contact us at nssdeviations@gmail.com

Roger and Hilary discuss the meaning of “data driven”, the value of Cloud Computing (again), and algorithmic transparency. Show notes: Artificial Intelligence Owes You an Explanation: http://www.slate.com/articles/technology/future_tense/2017/05/why_artificial_intelligences_should_have_to_explain_their_actions.html When artificial intelligence botches your medical diagnosis, who’s to blame? https://qz.com/989137/when-a-robot-ai-doctor-misdiagnoses-you-whos-to-blame/ Weapons of Math Destruction: https://weaponsofmathdestructionbook.com Analyst Mindset - Episode 1: https://youtu.be/pOA2wggeQkQ Teen Vogue: http://www.teenvogue.com Support us through our Patreon page: https://www.patreon.com/NSSDeviations Roger on Twitter: https://twitter.com/rdpeng Hilary on Twitter: https://twitter.com/hspter Get the Not So Standard Deviations book: https://leanpub.com/conversationsondatascience/ Subscribe to the podcast on Apple Podcasts: https://itunes.apple.com/us/podcast/not-so-standard-deviations/id1040614570 Subscribe to the podcast on Google Play: https://play.google.com/music/listen?u=0#/ps/Izfnbx6tlruojkfrvhjfdj3nmna Find past episodes: https://soundcloud.com/nssd-podcast Contact us at nssdeviations@gmail.com

Hilary and Roger revisit the desktop vs. cloud discussion, Hilary recaps csvconf, and Roger discusses the aesthetics of data analysis. Show Notes: Verena Haunschmid’s desktop: https://twitter.com/expectapatronum/status/857608745333006337 Roger’s desktop vs. cloud poll: https://twitter.com/rdpeng/status/857964527702376449 Remake package: https://github.com/richfitz/remake Episode 29 interview with Chief Data Officer of the Department of Transportation: https://soundcloud.com/nssd-podcast/episode-29-standards-are-like-toothbrushes Roger's Dean's Lecture on the Past and Future of Data Analysis: https://www.youtube.com/watch?v=qFtJaq4TlqE Angel D’az post on music and data analysis: https://www.linkedin.com/pulse/data-analysts-have-lot-learn-from-musicians-angel-d-az?published=t Designing Your Life: http://designingyour.life/the-book/ Roger on Twitter: https://twitter.com/rdpeng Hilary on Twitter: https://twitter.com/hspter Support us through our Patreon page: https://www.patreon.com/NSSDeviations Get the Not So Standard Deviations book: https://leanpub.com/conversationsondatascience/ Subscribe to the podcast on Apple Podcasts: https://itunes.apple.com/us/podcast/not-so-standard-deviations/id1040614570 Subscribe to the podcast on Google Play: https://play.google.com/music/listen?u=0#/ps/Izfnbx6tlruojkfrvhjfdj3nmna Find past episodes: https://soundcloud.com/nssd-podcast Contact us at nssdeviations@gmail.com

Hilary and Roger talk about the EPA taking down data (or not?), whether statisticians are paternalistic, and how to evaluate machine learning consumer products. Show Notes: Mosh: the mobile shell - https://mosh.org Statisticians are paternalistic Twitter thread: https://twitter.com/deronaucoin/status/854802719030116352 David Robinson post on story arcs: http://varianceexplained.org/r/tidytext-plots/ fst package by Mark Klik: http://www.fstpackage.org YouTube channel Amy Codes: https://www.youtube.com/channel/UCms28DbROfiYP2kBRpKTyyw Chase the toy poodle: https://www.instagram.com/littlechasebigworld/ Marnie the dog: https://www.instagram.com/marniethedog/ Popeye the Foodie Dog: https://www.instagram.com/popeyethefoodie/ Portland Catmapper: https://www.instagram.com/catmapper/ Roger on Twitter: https://twitter.com/rdpeng Hilary on Twitter: https://twitter.com/hspter Support us through our Patreon page: https://www.patreon.com/NSSDeviations Get the Not So Standard Deviations book: https://leanpub.com/conversationsondatascience/ Subscribe to the podcast on iTunes: https://itunes.apple.com/us/podcast/not-so-standard-deviations/id1040614570 Subscribe to the podcast on Google Play: https://play.google.com/music/listen?u=0#/ps/Izfnbx6tlruojkfrvhjfdj3nmna Find past episodes: https://soundcloud.com/nssd-podcast Contact us at nssdeviations@gmail.com

Hilary and Roger discuss Trump using an iPhone and implications for analyzing his tweets, computing setups for data science, and building simple versus complex tool chains to rely on. And the return of free advertising! Show notes: Trump is using an iPhone now: http://www.theverge.com/2017/3/29/15103504/donald-trump-iphone-using-switched-android Snap S-1 Registration Statement: https://www.sec.gov/Archives/edgar/data/1564408/000119312517029199/d270216ds1.htm NSSD Episode 35 with Sean Taylor: https://soundcloud.com/nssd-podcast/episode-35-special-guest-sean-taylor Writing an R Package from Scratch: https://hilaryparker.com/2014/04/29/writing-an-r-package-from-scratch/ Sticky Notes Podcast: https://itunes.apple.com/us/podcast/sticky-notes-the-classical-music-podcast/id1215386938?mt=2 fundManageR: https://github.com/abresler/fundManageR Big Little Lies: http://www.hbo.com/big-little-lies Roger on Twitter: https://twitter.com/rdpeng Hilary on Twitter: https://twitter.com/hspter Support us through our Patreon page: https://www.patreon.com/NSSDeviations Get the Not So Standard Deviations book: https://leanpub.com/conversationsondatascience/ Subscribe to the podcast on iTunes: https://itunes.apple.com/us/podcast/not-so-standard-deviations/id1040614570 Subscribe to the podcast on Google Play: https://play.google.com/music/listen?u=0#/ps/Izfnbx6tlruojkfrvhjfdj3nmna Find past episodes: https://soundcloud.com/nssd-podcast Contact us at nssdeviations@gmail.com

Hilary and Roger talk with Sean Taylor of Facebook about his new software package prophet, how to make tools usable and re-usable, and of course, Excel. Show notes: Sean Taylor http://seanjtaylor.com The Statistics Software Signal: http://seanjtaylor.com/post/39573264781/the-statistics-software-signal Automatic statistician https://www.automaticstatistician.com/about/ Roger on Twitter: https://twitter.com/rdpeng Hilary on Twitter: https://twitter.com/hspter Support us through our Patreon page: https://www.patreon.com/NSSDeviations Get the Not So Standard Deviations book: https://leanpub.com/conversationsondatascience/ Subscribe to the podcast on iTunes: https://itunes.apple.com/us/podcast/not-so-standard-deviations/id1040614570 Subscribe to the podcast on Google Play: https://play.google.com/music/listen?u=0#/ps/Izfnbx6tlruojkfrvhjfdj3nmna Find past episodes: https://soundcloud.com/nssd-podcast Contact us at nssdeviations@gmail.com

Hilary and Roger discuss Stitch Fix’s massive Algorithms Tour, reproducibility from a physical scientist perspective, and interpretability in machine learning. Show notes F this: http://sgsa.stat.ucla.edu/f-this/ Interpretability is the new reproducibility: http://simplystatistics.org/2017/03/08/when-do-we-need-interpretability/ NSF Workshop on Systematic Approach to Robustness, Reliability, and Reproducibility in Scientific Research: http://www.mrsec.harvard.edu/2017NSFReliability/index.html Roger on Twitter: https://twitter.com/rdpeng Hilary on Twitter: https://twitter.com/hspter Support us through our Patreon page: https://www.patreon.com/NSSDeviations Get the Not So Standard Deviations book: https://leanpub.com/conversationsondatascience/ Subscribe to the podcast on iTunes: https://itunes.apple.com/us/podcast/not-so-standard-deviations/id1040614570 Subscribe to the podcast on Google Play: https://play.google.com/music/listen?u=0#/ps/Izfnbx6tlruojkfrvhjfdj3nmna Find past episodes: https://soundcloud.com/nssd-podcast Contact us at nssdeviations@gmail.com

Hilary and Roger talk about the interview process for data science and data analyst jobs, opinionated analysis development, and what job interviews were like back in 1999. Show notes: Roger’s podcasting setup: http://simplystatistics.org/2017/02/20/podcasting-setup/ Opinionated Analysis Development: https://www.rstudio.com/resources/videos/opinionated-analysis-development/ Susan Fowler’s Medium post: https://www.susanjfowler.com/blog/2017/2/19/reflecting-on-one-very-strange-year-at-uber 10% Happier: http://www.10percenthappier.com Henrik Bengtsson’s Future package: https://cran.r-project.org/web/packages/future/index.html Roger on Twitter: https://twitter.com/rdpeng Hilary on Twitter: https://twitter.com/hspter Support us through our Patreon page: https://www.patreon.com/NSSDeviations Get the Not So Standard Deviations book: https://leanpub.com/conversationsondatascience/ Subscribe to the podcast on iTunes: https://itunes.apple.com/us/podcast/not-so-standard-deviations/id1040614570 Subscribe to the podcast on Google Play: https://play.google.com/music/listen?u=0#/ps/Izfnbx6tlruojkfrvhjfdj3nmna Find past episodes: https://soundcloud.com/nssd-podcast

Hilary and Roger discuss training in PhD programs, estimating the variance vs. the standard deviation, the bias variance tradeoff, and explainable machine learning. Show notes: Support us through our Patreon page: https://www.patreon.com/NSSDeviations Explainable AI: http://www.darpa.mil/program/explainable-artificial-intelligence Stitch Fix Blog NBA Rankings: http://multithreaded.stitchfix.com/blog/2016/11/22/nba-rankings/ David Robinson’s Empirical Bayes book: http://varianceexplained.org/r/empirical-bayes-book/ War on the Rocks podcast: https://warontherocks.com/2017/01/introducing-bombshell-the-explosive-first-episode/ Roger on Twitter: https://twitter.com/rdpeng Hilary on Twitter: https://twitter.com/hspter Get the Not So Standard Deviations book: https://leanpub.com/conversationsondatascience/ Subscribe to the podcast on iTunes: https://itunes.apple.com/us/podcast/not-so-standard-deviations/id1040614570 Subscribe to the podcast on Google Play: https://play.google.com/music/listen?u=0#/ps/Izfnbx6tlruojkfrvhjfdj3nmna Find past episodes: https://soundcloud.com/nssd-podcast

Hilary and Roger go on a podcast bender and discuss how they record the podcast, missing data methods, rstudio::conf, Uber Movement, diagnosis with prediction models, and Alexa/Siri. Whew! Show notes: Zencastr: https://zencastr.com Ecamm: http://www.ecamm.com Libsyn: https://www.libsyn.com Hilary’s slides on Opinionated Analysis Development: http://www.slideshare.net/hilaryparker/opinionated-analysis-development Tidytext book: http://tidytextmining.com Uber Movement: https://movement.uber.com/cities Data Science Bowl 2017: https://www.kaggle.com/c/data-science-bowl-2017 Pitch Deck Kickstarter: https://www.kickstarter.com/projects/fred/pitch-deck/ Out of the Blocks podcast: http://www.npr.org/podcasts/451202110/out-of-the-blocks-on-w-y-p-r Roger on Twitter: https://twitter.com/rdpeng Hilary on Twitter: https://twitter.com/hspter Support us through our Patreon page: https://www.patreon.com/NSSDeviations Get the Not So Standard Deviations book: https://leanpub.com/conversationsondatascience/ Subscribe to the podcast on iTunes: https://itunes.apple.com/us/podcast/not-so-standard-deviations/id1040614570 Subscribe to the podcast on Google Play: https://play.google.com/music/listen?u=0#/ps/Izfnbx6tlruojkfrvhjfdj3nmna Find past episodes: https://soundcloud.com/nssd-podcast

Hilary and Roger follow up on open data and data sharing in government. They also discuss artificial intelligence, self-driving cars, and doing your taxes in R. Show notes: Lucy D’Agostino McGowan (@LucyStats) made a great translation of Hill’s criteria using XKCD comics: http://www.lucymcgowan.com/hill-for-data-scientists.html Lucy’s web page: http://www.lucymcgowan.com Preparing for the Future of Artificial Intelligence: https://www.whitehouse.gov/sites/default/files/whitehouse_files/microsites/ostp/NSTC/preparing_for_the_future_of_ai.pdf Partially Derivative White House Special – with DJ Patil, US Chief Data Scientist: http://12%20Dec%202016%20White%20House%20Special%20with%20DJ%20Patil,%20US%20Chief%20Data%20Scientist Not So Standard Deviations – Standards are Like Toothbrushes – with with Daniel Morgan, Chief Data Officer for the U.S. Department of Transportation and Terah Lyons, Policy Advisor to the Chief Technology Officer of the U.S.: https://soundcloud.com/nssd-podcast/episode-29-standards-are-like-toothbrushes Henry Gitner Philatelists: http://www.hgitner.com Some Pioneers of Modern Statistical Theory: A Personal Reflection by Sir David R. Cox: https://drive.google.com/file/d/0B678uTpUfn80a2RkOUc5LW51cVU/view?usp=sharing

Roger travels to Washington, DC to talk with Daniel Morgan, Chief Data Officer for the U.S. Department of Transportation and Terah Lyons, Policy Advisor to the Chief Technology Officer of the U.S. The discussion covered open data, the process of making data available, standards for data formats (and their relation to toothbrushes), and of course—automated vehicles. Show Notes: Data about Pavement: https://infopave.fhwa.dot.gov National Highway Traffic Safety Administration (NHTSA) Federal Automated Vehicles Policy: https://one.nhtsa.gov/nhtsa/av/av-policy.html Office of Science and Technology Policy (OSTP): https://www.whitehouse.gov/administration/eop/ostp U.S. Digital Service: https://www.whitehouse.gov/participate/united-states-digital-service

Hilary and Roger talk about building data science products that provide a good user experience while adhering to some kind of ground truth, whether it’s in medicine, education, news, or elsewhere. Also Gilmore Girls. Show notes: HIll’s criteria for causation: https://en.wikipedia.org/wiki/Bradford_Hill_criteria O’Reilly Bots Podcast: https://www.oreilly.com/topics/oreilly-bots-podcast NHTSA’s Federal Automated Vehicles Policy: http://www.nhtsa.gov/nhtsa/av/index.html