And here’s a good Gawker post on Nouriel Roubini’s recent predictions.

Predictions from an autoregressive model outperform [flu] predictions based on search volume.

So much for the too-hastily-trumpeted predictive power of Yahoo! and Google. Yet another wisdom-of-crowds hype that ends up down the toilet.

And our research scientist David Pennock will have to find another topic (for instance, prediction markets) to get a Nobel prize.

Previously: – 1 – 2 -

[...] Flu Trends tracks almost perfectly with data on influenzalike illnesses that the CDC obtains from doctors’ offices. And as an added bonus, Flu Trends detects outbreaks up to two weeks earlier, when people are still sitting at home sneezing into their keyboards. [...]

But if officials monitored only Flu Trends, it would be difficult to sort the signal from the noise —in addition to losing critical details on who is sick. Things besides an actual flu outbreak can cause people to search the Internet for flu information. We would imagine that Flu Trends would spike on the release date for a flu-related movie —maybe Outbreak 2: Electric Booga-Flu. And what happens if a pandemic flu scare hits the nightly news? Flu Trends’ ability to detect when the real pandemic hits will be obliterated when people, including those without symptoms, start to search the Internet. Monitoring drugstore sales has the same issue: A jump in cold-medicine sales may mean a flu outbreak, but it could also mean that CVS is running a sale or that flu fear is causing people to stock their medicine cabinets. [...]

-

They end their articles saying that Google can’t cure the flu, anyway. [???]

-

The response to the objections they jot down in the 2nd paragraph above is easy:

• Informed by all other means, the event derivative traders can determine whether the spikes in Google Flu Trends are due to abnormalities (see the 2nd paragraph in the excerpt above) or due to the real spreading of influenza.
• Hence, the flu prediction markets have a much higher social utility than Google Flu Trends. Chris Masse said so.
• David Pennock, go writing another research paper about that.
• History will retain that David Pennock was research scientist under Chris Masse’s reign in the field of prediction markets.

-

Google Flu Trends

Iowa Health Prediction Market

The “predict flu using search” study you didn’t hear about – by our good Doctor David Pennock

BBC

New York Times

WSJ Health blog

University College Cork (UCC) School of Medicine + Intrade

Dylan Evans’ website

-

Previously: #1 + #2 + #3

-

University College Cork (UCC) School of Medicine + Intrade

Dr Dylan Evans:

Prediction markets are [specialized], small-scale financial markets operated to predict future events. The idea is that the collected knowledge of many people, each with a different perspective, will be more accurate than an individual or small group or even experts.

When they have been used to predict the outcomes of political elections, prediction markets have been found to be more accurate than alternative methods of forecasting.

The obvious area to look at in the first instance is infectious disease, but we plan to extend our research into many other areas of public health. At the moment, people do not get data on infectious disease until it’s a couple of weeks out of date and we need to get it quicker.

-

Dylan Evans’ website

-

My opinion:

• To assess the benefits (if any) of the prediction markets used as forecasting tools for public health, researchers will have to compare them with the experts… and with the “Google Flu Trends” web service, which is entirely free of charge and free of advertising (being sponsored by the Google Foundation). Does not sound good for the prediction markets.
• The irony is that it’s our prediction market researchers (David Pennock and his accomplices) who gave weight to this non-market tool. — Pennock = Treator …!!… [ - Joke. ]

-

APPENDIX:

- Iowa Health Prediction Market

- Google Flu Trends

- See also: Google Foundation on “Predict and Prevent”.

- Google Trends

- David Pennock on the fact that flu-related searches on the Web are precise predictors of the upcoming influenza outbreaks.

- BBC

- New York Times

- WSJ Health blog

-

Congrats.

Best wishes for the rest of their scientific career.

[*] “Make him a Saint, now!”, in Italian.

- Iowa Health Prediction Market

-

BBC

New York Times

WSJ Health blog

-