Skip to main content

Posts

Showing posts from March, 2016

Causal Impact and Statistics I

How can we use statistics to get at causal impact? Of course, correlation does not imply causation. Remember my lesson from a Dilbert's comic last week. But still, there are inferences to be drawn somehow. It may be a fact that MacDonald's just spent a lot of money on an ad campaign involving firecrackers and tapdancing penguins. It may be, also, that they sold a million hamburgers worldwide yesterday. It does not follow that they sold the million hamburgers because of that ad campaign. What MacDonald's clearly wants is some idea of how many hamburgers they would have sold if they had had some other ad campaign in place, possibly some less expensive campaign. Something involving their familiar clown and his sidekicks. Here's a social sciency thing about "Bayesian structural time-series models" that aims at getting at the problem. It's actually based on the experiences of Google, paid clicks versus free clicks, etc. -- I just prefer the MacDonald

A Thought for Easter

Trying to imagine the scene over in Clinton headquarters when they first saw certain footage of a Sanders rally on March 26th. "Really? Cute birds hopping onto his podium now? so he can sermonize about world peace? We're supposed to run against Francis of Assisi?" Given their penchant for co-opting Bernie, they'll be hiring a bird trainer any minute now. Happy Easter everyone. I had nothing prepared for a proper Easter post, but the St. Francis style moment at least gives us a good religious/historical analogy for the day. Thanks for that Bernie. I hope you had a good Purim.

A Lesson About Correlation

One of the Dilbert cartoons that came up on my day-to-day desk calendar recently offers a valuable lesson. Correlation does not imply causation. Usually, the pointy-haired boss plays the stooge in his exchanges with Dilbert, but in this case its the boss who brings the point home. Dilbert tells him, "Studies show that companies with a high level of trust in employees also perform the best." Dilbert is presumably hoping that the boss will infer from this correlation of performance and trust that there is a causative link, and that the boss ought to trust Dilbert more, thereby allowing their common employer to reap the rewards. Instead, the boss acutely responds, "If you ever start performing well, I'll trust you, too." Ah, yes, one of the problems with that sort of causal argument (but only one of them) is that the causal arrow is easily reversed. Good one, boss.

Water Flows in Brooklyn

The March issue of Harper's includes an article by Elizabeth Royte called "The Hidden Rivers of Brooklyn," which begins with a discussion of the view from a parapet on the tower of Litchfield Villa, on the western edge of Prospect Park. "I was barely able to make out -- over treetops and tall buildings -- a glint of Gowanus Bay, roughly two miles away. Edwin Litchfield ... would have had no trouble seeing the bay and much of his land holdings out of a second-floor window." Thus, she has set up her themes, of development, Brooklyn's history, and water. Two paragraphs later she introduces us to Eymund Diegel, a sort of hydrological Adrian Monk, and she follows him, carrying the reader along, as he tries to reconstruct the one-time flow of water over the area, as it would have run back before the water was corralled into pipes. A few grafs further on, we're treated to this description, which is worth the price of the issue at a newsstand: Wanderi

Deflation: Not a Bad Thing

Every once in awhile we hear econo pundits telling us how evil deflation would be. Why? Well ... deflation is often a symptom of bad times. If a lot of people are out of work and have no purchasing power, demand for a wide range of products will drop and so will the general level of prices, i.e. there will be deflation. This is one way of getting to deflation, and the causes of that symptom are, to those directly affected, bad things indeed. BUT ... deflation there is only a symptom, not a cause of the trouble, and this doesn't rule out the possibility that deflation in other contexts may be harmless, or better-than-harmless. One often encounters a suspicion of deflation that goes beyond any real justification, and this is the background of an expectation that a central bank should program into an economy a mild level of price inflation, say 2 to 3%. Just to keep those deflationary demons away? These thoughts are motivated by Apple's product launching event on March 2

John Berger on Art

John Berger was the writer behind WAYS OF SEEING, a 1972 television series (and accompanying book) in art and politics that has been very influential in academic discussions of that crossroads. He has a new book out, PORTRAITS, and I've been looking at a review of it in the February 2016 issue of HARPER's.  The review, written by Mark Kingwell, calls this a "monumental late-life collection of some six dozen appreciations of individual artists." One of these appreciations, of Vincent van Gogh, says this: "All modern artists have thought of their innovations as offering a closer approach to reality, as a way of making reality more evident. It is here, and only here, that the modern artist and revolutionary have sometimes found themselves side by side, both inspired by the idea of pulling down the screen of clichés." Kingwell, the reviewer, finds this idea touching, but naïve. "What force in such dreams, then, down here on planet Earth?" he a

AIDS timeline: the 1980s

Hillary Clinton's recent misstatement about the early days of the AIDS epidemic and her effort to give the Reagans'  some credit for a sensible reaction, in order to make nice at Nancy Reagan's funeral, inspired  me to go back over the period. Here is a timeline of some pertinent events, without unnecessary editorializing. June 1981: Reports of clusters of Kaposi's sarcoma and pneumocystis carini pneumonia in New York and California. Clusters involved gay men, later in the year clusters cases involving users of IV drugs appeared. In the following years, the presence of haemophiliac-patients among the victims will become clear. April 13, 1982: Rep. Henry Waxman convenes the first Congressional hearings on these deaths. July 1982: Somebody coins the term "AIDS" for what is going on. March 1983: CDC mentions a clustering of cases of AIDS among Haitians. May 1983: Scientists in France gave a name to a virus there, LAV. July 1983: San Francisco Gener

Writers and Confrontations

"Students like to say that they stage no confrontations because people avoid confrontations in modern life. “Modern life is so lonely,” they say. This is laziness. It’s the writer’s job to stage confrontations, so the characters will say surprising and revealing things, and educate and entertain us all. If a writer can’t or won’t do that, he should withdraw from the trade." - Kurt Vonnegut One of my Facebook friends posted this quote recently. I like it, and that will have to be my complete excuse for including it here. 

Trump: Three Unsayable Things

A few words about Donald Trump. Yes, I despise him, and I think his advance toward the nomination has been a thoroughly depressing spectacle. But that's not what I'm going to say today. Instead, it is this: Trump has spoken thoughts that have long been unspeakable in Republican circles. For example, he has offered some kind words for the work of Planned Parenthood. How shocking! He very heavily qualifies those words as soon as they come out of his mouth, but he says them.  Also, Trump has said that we as a nation were bamboozled into a war with Iraq by lies (or falsehoods when he's being polite) about weapons of mass destruction. Nobody else is saying that, in either party really. Yes, Sanders criticizes Mrs Clinton's hawkish votes as Senator, but he has left the WMD thing in the memory hole. I'm glad somebody has pulled it out of there.  One more: Trump suggests that the US can and should play a mediator's/deal-makers role in the Israel/Palest

The Joy of Alphabetization

In the February issue of Harper's , in the "Easy Chair" column near the front, John Crowley has a column about the Encyclopedia Britannica, and in general about the fun of old-fashioned alphabetized reference books, the sort of thing we used for reference before we had cyberspace and wikipedia. Given the alphabetized structure, Crowley writes, "any search for anything passes through things that have nothing in common with it but an initial letter. It's impossible not to abstract something from some of them. Look up 'Dog' ( Damascu to Educ ) to study the attractive plates ... and you may notice the nearby entry for 'Dogger Bank' ('an extensive shoal in the North Sea') and the sea battle fought there on January 24, 1915, which you had not previously heard of." Indeed. That was and still is the fun of browsing through such works. Soon Crumb is on to the sales tactics of the old-fashioned door-to-door encyclopedia salesmen. But t