Homepage
Close
Menu

Site Navigation

  • Home
  • Archive(TODO)
    • By Day
    • By Month
  • About(TODO)
  • Stats
Close
by jeremyphoward on 2020-03-12 (UTC).

Survival analysis is used to handle "censored data". That means: data where we sometimes don't know the label yet.

Most data scientists aren't familiar with this technique. That's understandable, because there's lots of fields where it doesn't really come up. But we need it now! pic.twitter.com/mHjIz1lLw7

— Jeremy Howard (@jeremyphoward) March 12, 2020
learning
by jeremyphoward on 2020-03-12 (UTC).

There are *lots* of ways to model censored data. Here's a great little summary of a few, which shows (for 2 datasets) that random forests (with some tweaks) works best.https://t.co/VhQYiaT79Q

— Jeremy Howard (@jeremyphoward) March 12, 2020
learning
by jeremyphoward on 2020-03-12 (UTC).

Most decision tree ensemble libs can do survival analysis. Here's a nice intro for the wonderful xgboost lib: https://t.co/LfFEPjmcpt

— Jeremy Howard (@jeremyphoward) March 12, 2020
learning
by jeremyphoward on 2020-03-12 (UTC).

What's even more awesome is that @AllenDowney has made the chapters available as runnable colab notebooks, which is just about the best way to learn I know of!https://t.co/vjM9x0AU24

— Jeremy Howard (@jeremyphoward) March 12, 2020
learningtutorialbayesian
by jeremyphoward on 2020-03-12 (UTC).

If you want to go really deep on this, check out Stan, which is a whole language for probabilistic programming. Here's some survival models for Stan:https://t.co/DPFLm2bbzO

— Jeremy Howard (@jeremyphoward) March 12, 2020
learningtoolbayesian

Tags

learning tutorial misc nlp rstats gan ethics research dataviz survey python tool security kaggle video thought bayesian humour tensorflow w_code bias dataset pytorch cv tip application javascript forecast swift golang rl jax julia gnn causal surey diffusion
© Copyright Philosophy 2018 Site Template by Colorlib