statistics – Page 8 – Andrew Fairless, Ph.D.

What I Read: null hypothesis significance testing falls apart when considering replications

By Andrew Fairless on July 8, 2021June 22, 2021

https://statmodeling.stat.columbia.edu/2021/06/17/guttman-points-out-another-problem-with-null-hypothesis-significance-testing-it-falls-apart-when-considering-replications/ Guttman points out another problem with null hypothesis significance testing: It falls apart when considering replications.by Andrew Gelman17 June 2021, 9:22 am “… another problem with null hypothesis significanceContinue readingWhat I Read: null hypothesis significance testing falls apart when considering replications

What I Read: 3 Statistical Paradoxes

By Andrew Fairless on May 13, 2021April 17, 2021

https://towardsdatascience.com/top-3-statistical-paradoxes-in-data-science-e2dc37535d99 Top 3 Statistical Paradoxes in Data ScienceObservation bias and sub-group differences generate statistical paradoxes.Francesco Casalegno “Observation bias and sub-group differences can easily produce statistical paradoxes in any data scienceContinue readingWhat I Read: 3 Statistical Paradoxes

What I Read: Scaling vs. Normalizing Data

By Andrew Fairless on April 19, 2021April 2, 2021

https://towardsai.net/p/data-science/scaling-vs-normalizing-data-5c3514887a84 Data ScienceScaling vs. Normalizing DataJanuary 10, 2021Author(s): Lawrence Alaso Krukrubo “Scaling and normalization are so similar that they’re often applied interchangeably, but as we’ve seen from the definitions, theyContinue readingWhat I Read: Scaling vs. Normalizing Data

What I Read: Rip van Winkle’s Razor, Adaptive Data Analysis

By Andrew Fairless on April 17, 2021April 10, 2021

http://www.offconvex.org/2021/04/07/ripvanwinkle/ Rip van Winkle’s Razor, a Simple New Estimate for Adaptive Data AnalysisSanjeev Arora, Yi ZhangApr 7, 2021 “Can you trust a model whose designer had access to the test/holdoutContinue readingWhat I Read: Rip van Winkle’s Razor, Adaptive Data Analysis

What I Read: Statistics, Geometry Problem

By Andrew Fairless on April 6, 2021March 22, 2021

https://www.quantamagazine.org/statistics-postdoc-tames-decades-old-geometry-problem-20210301/ Statistics Postdoc Tames Decades-Old Geometry ProblemTo the surprise of experts in the field, a postdoctoral statistician has solved one of the most important problems in high-dimensional convex geometry.Erica KlarreichMarchContinue readingWhat I Read: Statistics, Geometry Problem

What I Read: Causal design patterns

By Andrew Fairless on April 1, 2021March 15, 2021

https://emilyriederer.netlify.app/post/causal-design-patterns/ Causal design patterns for data analystsJan 30, 2021 “…it’s easy to do causal inference wrong. For example, attempting to control for the wrong variables can sometimes induce correlations andContinue readingWhat I Read: Causal design patterns

What I Read: Isolation Forest

By Andrew Fairless on February 16, 2021January 18, 2021

https://towardsdatascience.com/isolation-forest-is-the-best-anomaly-detection-algorithm-for-big-data-right-now-e1a18ec0f94f Isolation Forest is the best Anomaly Detection Algorithm for Big Data Right NowAndrew YoungNov 13 “Isolation forest or “iForest” is an astoundingly beautiful and elegantly simple algorithm that identifiesContinue readingWhat I Read: Isolation Forest

What I Read: Dynamic Data Testing

By Andrew Fairless on February 16, 2021January 18, 2021

https://medium.com/anomalo-hq/dynamic-data-testing-f831435dba90 Dynamic Data TestingJeremy StanleyNov 18 “Can’t we write down a clear set of rules that govern exactly how our data should behave, just like we do when testing software?Continue readingWhat I Read: Dynamic Data Testing

What I Read: Structural Time Series

By Andrew Fairless on February 11, 2021January 13, 2021

https://structural-time-series.fastforwardlabs.com/Structural Time SeriesFF16 · October 2020 “We will describe a family of models—Generalized Additive Models, or GAMs—which have the advantage of being scalable and easy to interpret, and tend toContinue readingWhat I Read: Structural Time Series

What I Read: Think Like an Epidemiologist

By Andrew Fairless on January 16, 2021December 24, 2020

https://www.nytimes.com/2020/08/04/science/coronavirus-bayes-statistics-math.html How to Think Like an EpidemiologistDon’t worry, a little Bayesian analysis won’t hurt you.By Siobhan RobertsAug. 4, 2020Updated 4:57 p.m. ET “Observing early research in March about how theContinue readingWhat I Read: Think Like an Epidemiologist

Tag: statistics