Look: I am eager to learn stuff I don't know--which requires actively courting and posting smart disagreement.

But as you will understand, I don't like to post things that mischaracterize and are aimed to mislead.

-- Brad Delong

Copyright Notice

Everything that appears on this blog is the copyrighted property of somebody. Often, but not always, that somebody is me. For things that are not mine, I either have obtained permission, or claim fair use. Feel free to quote me, but attribute, please. My photos and poetry are dear to my heart, and may not be used without permission. Ditto, my other intellectual property, such as charts and graphs. I'm probably willing to share. Let's talk. Violators will be damned for all eternity to the circle of hell populated by Rosanne Barr, Mrs Miller [look her up], and trombonists who are unable play in tune. You cannot possibly imagine the agony. If you have a question, email me: jazzbumpa@gmail.com. I'll answer when I feel like it. Cheers!

Friday, April 1, 2011

Graph Fights!

It all starts with this post in January by John Taylor, where he talks about the (pretty reasonable sounding) correlation between business investment and unemployment.   Other than agreeing with this statement by Krugman  .  .  .

But when Taylor leaps from that correlation to saying that what we need for economic recovery is to “lighten up on the anti-business sentiment coming out of Washington,” I wonder what is going on in his head.

.  .  .   I have no dog in the fight, and can sit back and watch with growing amusement.

Mark Thoma supplies links, so I don't have to.  But it takes a few click-throughs to get to this one by Noah Smith, which, because of its insights, really should not be missed.

Another insight worth noting is this one from a much younger John Taylor, quoted by Justin Wolfers.

Behind the use of time-series estimation is the assumption that the structure and coefficients to be estimated remain stable over the sample period…  If this assumption is in fact not correct, the estimated function would have little use either as an explanation of the causes of murder or of the policy implications of changing the value of an exogenous variable in the structure.

I think about and use time series data a lot - in fact as recently as yesterday.  So this is something worth keeping in mind when any of us look at those kinds of data series.  Though I'm usually looking for what changed, rather than some underlying determinant.

There are other lessons here about cherry picking, data analysis, and data mining that should make you cautious of any graphic presentation - no matter how convincing it seems to be.

One of my father's catch phrases was, "Figures might not lie, but liars sure know how to figure."  He was born in April, but was certainly no fool.

Update:  Just to be clear, I'm not calling Taylor or anyone else a liar.  The quote above from my dad, in red,  is a general caution, not an indictment.

Update 2:  Karl Smith weighs in, and finds: "In short, in either of these basic comparisons I just don’t see a lot of there there.

No comments: