Comments on: The Future is Yesterday

By: bandar euro 2016

bandar euro 2016 — Mon, 20 Jun 2016 15:19:50 +0000

bandar euro 2016 The Future is Yesterday | Messy Matters

By: daftar taruhan judi euro

daftar taruhan judi euro — Sun, 05 Jun 2016 19:17:59 +0000

daftar taruhan judi euro The Future is Yesterday | Messy Matters

By: http://agen.bolaeuro2016.net/agen-bola-euro/

http://agen.bolaeuro2016.net/agen-bola-euro/ — Fri, 03 Jun 2016 15:23:35 +0000

http://agen.bolaeuro2016.net/agen-bola-euro/

The Future is Yesterday | Messy Matters

By: naruto shippuden manga

naruto shippuden manga — Sat, 12 Mar 2016 09:14:10 +0000

naruto shippuden manga The Future is Yesterday | Messy Matters

By: waterproofing outdoor wood

waterproofing outdoor wood — Tue, 21 Oct 2014 04:45:15 +0000

waterproofing outdoor wood The Future is Yesterday | Messy Matters

By: celine bag replica

celine bag replica — Fri, 06 Jun 2014 09:37:17 +0000

celine bag replica The Future is Yesterday | Messy Matters

By: Abhishek Tiwari

Abhishek Tiwari — Thu, 02 Apr 2009 07:13:31 +0000

Nice article and I am really enjoying this blog. I was curious if similar kind of predictions are possible for the next emerging pandemics like what Nathan Wolfe is trying to do through Global Viral Forecasting Initiative (http://www.gvfi.org/)

By: Rajan

Rajan — Thu, 02 Apr 2009 07:02:40 +0000

Thanks for the response Sharad.

By: Sharad Goel

Sharad Goel — Wed, 01 Apr 2009 13:17:23 +0000

Rajan, this is a great comment. Implicitly I’m assuming (as did the Yahoo! and Google studies) that squared error is the pertinent loss function, and by this metric, the AR and search models perform comparably. As you say, however, you may in fact only care about predicting turning points.

The autoregressive model uses the last two reported flu levels. It essentially predicts that this week’s flu level is the same as last week’s level adjusted by either an upward or downward trend as inferred from the earlier week.

By: Rajan

Rajan — Tue, 31 Mar 2009 20:39:22 +0000

I like this example too, because it shows how simple models can do really well.

However, in my experience, sometimes you have to watch out with AR models, because sometimes they just say that the best least squares estimator (given an AR model) is to forecast that the next value is basically the same as the last. The error of such a model can be very good in numerical terms, but as a forecast it might not be so good, because it can “miss” (i.e. the forecast lags) every turning point in the time series. So, the forecast curve can look like the actuals shifted to the right by some time period. It’s hard to tell if that’s what is happening in the figure.