« Experts clinging on to their predictions | Main | Count data are less useful than you think »

Comments

Feed You can follow this conversation by subscribing to the comment feed for this post.

Andy

What is OCCAM data? I did Google it, didn't turn up anything in the first couple of pages. And a scan of the NYT article didn't help either.

junkcharts

Andy: see this link.

zbicyclist

Kaiser, I think OCCAM is a great framework for thinking about big data issues, but I would recommend you provide that link every time you mention OCCAM. Not all of us are regular readers.

Ken

Many of the problems seem to be missing data problems, and that is something that statisticians should be expert in.

junkcharts

zbicyclist: Point taken. I was in a bit of a hurry when I wrote that post.

Ken: yes, many issues like biased samples and censoring are nicely modeled as missing data problems. Another big issue I'm concerned about is having nuisance predictors while also missing relevant predictors. Because of observational data, we frequently don't have the right set of predictors. A third issue would be a network of direct and indirect effects. The general point is that the complexity of the analysis is increased, not decreased, by having "big data".

Ken

To add, the problem with the clotting agent is similar to one that occurs in diagnostic testing. Only those that have a positive result on a screening test actually have a better test. This effectively results in lots of missing data as most subjects don't have the better test, which results in severe biases if the data is not treated correctly.

When looking at big data for medicine we are going to have a mess of different tests and possibly treatments that will obscure any possible diagnosis, as you will never know if the disease just went away or was fixed if you don't know if there was a disease in the first place. I expect there will be some very nice Bayesian analyses that will demonstrate that standard data-mining techniques just aren't enough.

The comments to this entry are closed.

NEW BOOTCAMP



Link to Principal Analytics Prep

See our curriculum, instructors. Apply.
Kaiser Fung. Business analytics and data visualization expert. Author and Speaker.
Visit my website. Follow my Twitter. See my articles at Daily Beast, 538, HBR.

See my Youtube and Flickr.

Next Events

Jun: 5 NYPL Public Lecture on Analytics Careers, New York, NY

Past Events

Apr: 2 Data Visualization Seminar, Pasadena, CA

Mar: 30 ASA DataFest, New York, NY

See more here

Courses

Numbersense: Statistical Reasoning in Practice, Principal Analytics Prep

Applied Analytics Frameworks & Methods, Columbia

The Art of Data Visualization, NYU

Junk Charts Blog



Link to junkcharts

Graphics design by Amanda Lee

Search3

  • only in Big Data

Community