Eugene Antipov
@analyticalcrm
Data Analytics Professor, Marketing data scientist, R | SPSS | Stata, Upwork's expert-vetted/top-rated data specialist
Parsimonious and elegant probabilistic models for retention curve projection — especially the Beta‑Discrete‑Weibull Model developed for customer analytics by @faderp and Bruce Hardie — can be quite successfully applied in HR analytics, too. Our paper: rdcu.be/eaAsl
📚🚨 I posted 11 new chapters of my upcoming book! Model to Meaning: How to Interpret Statistical Results with #marginaleffects for #RStats and Python. These are early drafts and I really need your feedback! Errors, content requests, improvements, etc. marginaleffects.com
Where's the demand in Data Science? 3 letters: MMM. Here's how to learn it for free (business case included). Let's go! 💡Next Wednesday, I have a free workshop (Special Guests: @pymc_labs, @twiecki and @alex_andorra ) on Bayesian MMM! Here's a taste of what we are covering: 1.…
An excellent addition to a collection of probability paradoxes everyone should be aware of (along with Simpson's paradox, base rate fallacy and others).
A "cognitive bias" is a systematic error in thinking that ruins decision-making. The 12 most powerful cognitive biases I've found:
📢 Delighted to share the cover of my book Spatial Statistics for Data Science: Theory and Practice with R 😍😍😍 🔗 paulamoraga.com/book-spatial/ Thanks so much to my editor @lara_crc & all the team at @CRC_MathStats! The book will be available soon! #rstats #stats #datascience
Google can now generate high-quality AI images. And it's completely FREE to use! Here's a step-by-step guide on how to use it:
GPT-4 is a phenomenal AI tool in 2023. But it costs $20/month to use it. Here are 7 ways to access it for free:
⚡️ New chapters on #geostatistics in my Spatial Statistics book ⚡️ Covering simulation of #Gaussian random fields, #Variogram & #Kriging predictions 💻📊📈🗺️ 👉 paulamoraga.com/book-spatial/k… #rstats #rspatial #gischat #datascience
“Are there clear examples of the opposite idea, where four visually similar visualizations can have vastly different numerical stats?” statmodeling.stat.columbia.edu/2023/09/17/are…
Anyone can make ggplots now. Just try this package. Article: buff.ly/43yIEhU #rstats #datascience
We finally have a public version of our "Micro PyBLP" paper. TLDR: use micro data if you can! Highlights: a. How to select and form micro-moments (including "optimal" variety) b. How to avoid "incompatible" micro moments c. How to calculate correct weighting matrices + inference
A framework for incorporating many types of micro data, from summary statistics to full surveys of selected consumers, into Berry, Levinsohn, and Pakes (1995)-style estimates of differentiated products demand systems, from @conlon_chris and @jeff_gortmaker nber.org/papers/w31605
New tutorial: "MrP with {marginaleffects}." A super easy way to adjust non-representative data using Multilevel Regression and Poststratification in #RStats. Let me know what you think! marginaleffects.com/articles/mrp.h…
#webR will be a good substitute for the Rshiny server. Using webR, we can execute #Shiny applications entirely on the client side (e.g., the browser), harnessing the client's resources and presenting prospects for scalability. Resource for beginners: lnkd.in/eGJ--33H
Didn't post the code for this yesterday. Try it out for yourselves here: gist.github.com/walkerke/c139d…
Saw this article yesterday about migration from California to Texas: usatoday.com/story/money/20… They used PUMS data, so I wanted to run the numbers myself to see other top flows Try it out for yourselves in #rstats:
I use #rstats to do #GIS every day because it is such a powerful connector of different tools and resources. Read this 🧵 for a step-by-step workflow of how to do GIS operations with this made-up table of customer locations in R:
1/n It is ready! In this post, I walk through how to use renv, Docker, and GitHub Actions to automate a workflow that makes your R projects reproducible across time and space 🤖🤓. The goal is to help you avoid the age-old problem of *dependency hell*: haines-lab.com/post/2022-01-2…
ooo I have discovered how to use renv + docker + github actions to automate docker images for projects. This means I can develop locally with R, and then automatically make an image with the right R version + R libraries/versions for anyone to use on their own machine 🥳