William M. Briggs

Statistician to the Stars!

Page 144 of 427

The Downside Of Technology: Being On Call 24/7—Guest Post by The Blonde Bombshell (with pic!)

Blonde Bombshell at the beach

Let me first say that I am a modest person with a modest existence. I have a job, which is nothing special, but I do it well. I have a husband and children (now grown, but still of interest to me) and a few ordinary hobbies.

I’ve made great efforts to keep my work and home life separate. I go to the office when others relish “working from home.” I like to go to the office because it is a physical space designed for work. I like my work to be conducted within defined hours. I like to be able to leave work (and with my unassuming job, this is still mostly possible) and hypothetically not be bothered with it until I return.

One reason for my insistence on keeping the office space separate from home is that my experience working for pay at home was dismal. The work was part-time, but I invariably put in more than my share of hours. Tremendous guilt would descend if time were spent in the kitchen wiping down counters or preparing lunch. The worst part was there was no change of venue to clearly indicate when it was time to move from work mode to leisure. It was always work mode, as files and other reminders of work were piled around the house.

There is increasing pressure for people to merge their private and public identities, and I am mystified why this would be a good idea for the Average Joe or Jane. For those people whose work life is not tied to the clock—some CEOs and public figures, and possibly some academics and bloggers, it makes sense. Personally, I don’t want to check work email before going to bed or first thing in the morning. In fact, my work email is just that. It is separate, and not filtered through my private account, and I generally don’t check work email on weekends.

Social media applications are compelling users to merge their public and private identities, and I don’t think this is a good thing. This last week Skype announced that one can now log in with Facebook. Well, I don’t want to log in with Facebook.

Facebook itself is the nexus of the public/private problem. I was a late adopter, and most of by FB friends are high school classmates, many whom I have not clamped eyes on for more than a quarter-century. I am grateful to FB for kindling these connections, but then when I am asked to connect with someone that I know professionally, the button goes unclicked. And it is not because that I don’t like or respect this person, it is that I just don’t want her to be mixed into my bucket of friends. FB has since made an effort to let users divide friends, but I am not confident that this will always be the case. FB is continually making tweaks that upset the masses. Because of the quasi-public nature of FB, I also hide my innately shallow and frivolous nature by not liking new nail polish colors or novel recipes using snack foods. This is certainly not information I would like shared with my boss (or the head of HR).

As for Skype, my user name is on the cute side. Just the other day a colleague overseas asked me about Skype on my work computer, and I said that I had it once, but IT scrubbed it as a security risk, but I could ask for it to be reinstalled (admin password needed). If I ever get Skype at the office, I will have to reveal what I regard to be my personal nickname. Then this opens up the possibility that I can be Skyped by this person at any time to hash over a new idea.

My cellphone, which I pay for as a private person, is used for work from time to time. It is not enough to quibble about, but enough to be noted, as my cellphone is a means of production not owned by management.

Work email is a problem. While I have been with my current employer for a substantial period of time, I regard my work identity as temporary and open to change. My login email with LinkedIn is my work email, mostly because I was using LinkedIn for work. However, trouble could ensure if I ever thought about looking for a new job using LinkedIn as a resource.

When I’m at the office, and working, and using internet applications, I want this to be completely separate from when I am browsing at home. It isn’t Amazon’s fault that it makes book suggestions based on the books that I purchase for my boss.

With the mixing and mingling of my working identity with my private self, I feel I’m losing is that little space between the “office me” and the “home me.” Technology is wonderful, and I can barely remember the dark days before there was a computer on every lap. But I don’t want technology to force me into working more hours than I’m legally obligated to—no matter how well it is cloaked as a convenience.

Academic Philosopher Finds New Way To Dehumanize People; Calls For Beetroot Liberation

We ignore them at our peril

Update Now with new and improved title! (Title writing is a talent which your humble author possesses not.)

In the classic 1978 documentary Attack of the Killer Tomatoes! we watch as a bushel of plump Roma and muscular beefsteak tomatoes become self-aware and then take their revenge on hapless representatives of a pasta-sauce-making species. The carnage is indescribable, the horror unspeakable, the irony indisputable.

Yes, irony, for that red-soaked massacre, or something like it, must have been in the mind of Michael Marder, an academic philosopher, and author of Plant-Thinking: A Philosophy of Vegetal Life. In this, his masterpiece, Marder wrote that we had better make a move for “plant liberation” before brigades of rutabagas flanked by Swiss chard take up arms and wreak havoc.

I’m kidding about the rutabagas, though the future of pasties is unclear if Marder, who also wrote “Vegetal Democracy: The Plant that is Not One”, is correct and plants have “rights.” And Marder did invent the slogan “plant liberation.”

Now, when you boil or fry a spud, it kills it. But it also makes it into a traditional accompaniment to Thanksgiving dinner or a tasty snack to have with beer. Problem is, making beer slaughters acres upon acres of barley. And Thanksgiving, well, this still politically allowed holiday (in most jurisdictions) sees its share of turkeys with their throats cut.

But if we human beings don’t partake in these murderous repasts—that is, if we don’t take the lives of living things—then we whither and cease. As Yours Truly has pointed out before, you must to kill to live. This is an inescapable logical conclusion. How does Marder fit this into his philosophy?

According to a quotation lifted from NPR, which treats ideas like “The Right Of Plants To Evolve” sympathetically (on your dime):

“[T]he commendable desire to ameliorate the condition of animals, currently treated as though they were meat-generating machines, does not justify strategic argumentation in favor of the indiscriminate consumption of plants. The same logic ultimately submits to total instrumentalization the bodies of plants, animals and humans by setting them over and against an abstract and rational mind.”

Therefore, he concludes, “the struggles for the emancipation of all instrumentalized living beings should be fought on a common front.”

Notice his incorporation of militaristic lingo (strategic, struggle, front): I told you he had those tomatoes in mind. Marder forgets, or is unaware, that farming is precisely breeding meat-generating machines. I have no idea what “instrumentalized living beings” are. Do they include e. coli, malaria-carrying mosquitoes, weeds? Probably. But these niceties we can ignore. Let’s get to the good stuff.

What Marder is really against is the “indiscriminate consumption of plants.” Presumably this means if you already downed one side salad you should not have another, or should at least skip the croutons on the second.

And there it is: Marder thinks people are eating too much. Progressives don’t like fat people and are determined to do something about it, including going to extremes like “discovering” “rights” in plants. Of course, he just can’t say straight out that blubber bothers him. He has to mask it in academese or it will never be published in peer-reviewed journals.

In a New York Times piece, he says this:

[B]oth Western and non-Western philosophers have been aware of what we may now call “plant subjectivity” for millennia. Most famously, Aristotle postulated the existence of a vegetal soul with its capacities for reproduction growth, and nourishment, as the most basic stratum of life. To Aristotle, all living beings, including animals and humans, are alive by virtue of sharing this rudimentary vitality with plants. Other levels of the psyche — the sensory and the rational — then presuppose the presence of vegetal soul for their proper functioning and actualization.

Aristotle did no such thing. Or rather, he did, but he didn’t mean by soul what Marder says. Quoting from Stanford’s Plato:

As Aristotle says “by form I mean the essence of each thing, and its primary substance” (1032b1), and “when I speak of substance without matter I mean the essence” (1032b14). It is the form of a substance that makes it the kind of thing that it is, and hence it is form that satisfies the condition initially required for being the substance of something. The substance of a thing is its form.

Join essence to matter and you create the form of asparagus. Aristotle never implied plants have ghostly souls that strum harps on clouds after they have been heartlessly julienned by some chef. So there is, if you do or don’t pardon the pun, no meat in this argument.

His next attempt is to say “researchers” have witnessed “deliberate behavior” in plants, which is patent nonsense. to deliberate means to reason. Sure, leaves turn toward the sun, but the plant’s soul is not informing the plant which way is east. The process is dumb chemical reaction, nothing more. Marder knows this and must admit “plants are not capable of deliberation or of making decisions in the human sense of the term.” But that’s only to soften up weak minds, because directly after he writes, “But they do engage with their environments and with one another in ways that are incredibly sophisticated, plastic and responsive — in a word, intelligent, though not perhaps conscious.”

It’s a word, all right, but it isn’t intelligent. A more apt choice is the one that’s been coming out of our heartbeat-away Joe Biden: malarkey. Intelligent implies intellect, and plants haven’t got one, period. Plants are unthinking machines. But Marder says this “plant-as-machine” bias, in his own inadvertent use of a pun, is so “entrenched that it is difficult to digest evidence to the contrary.”

As evidence of “intelligence” he cites “a report on the enhanced ability of common pea plants, recipients of biochemical communication, to withstand drought, even though they did not directly experience this abiotic stress-inducer.” But this is like saying a rock teetering on the edge of a cliff “decides” to fall, or that it “experiences” gravity and “chooses” to leap.

Still, Marder will have “respect” for “vegetal life”, a respect which includes eating plants. Not in great quantities, but respectfully and in awe. We must not “reduce plants to storehouses of carbohydrates and vitamins or to that other source of energy so widely applauded today, biofuel.” And we weep when we realize it “is especially pernicious to grow plants from sterile seeds, already robbed of their reproductive potential, patented and appropriated by profit-driven enterprises.” We must eat only free-range plants. His philosophy thus resembles a bad James Cameron movie.

The Thing from another planet; or, a thinking carrot

And here is another progressive boogey man: profit. Such a disquieting word. Farmers, claims Marden, are “forced to buy seeds from multinational corporations.” Forced? One imagines he wrote this piece, which is displayed on a multinational-corporation-owned website, on a multinational-corporation produced Mac. But we do not expect consistency from the Left.

We recall the killer tomatoes again when Marder writes “Violence against plants backfires, as it leads to violence against humans and against the environment as a whole.” He never defines what he means by “violence against plants”, but perhaps it is when dull knifes are used to dice celery. Unsharpened blades, you see, slip easier and commit violence against their human wielders.

No progressive philosophy is complete without a movement, which naturally leads to a government program and thus to employment of progressives. Marder’s cause is “the project of plant liberation” This, says he, “would allow plants to be what they are and to realize their potentialities.” He allows that we “cannot subsist on inorganic matter alone, as plants do, but we can critically question our dietary choices without prescribing a perfectly violence-free and universally applicable eating pattern.”

Will the citizenry march to the banner “All plants to be what they are!”? Will a majority cry out, “Up with universally applicable eating patterns!”? Perhaps not. But since we have seen the impetus behind this goofy philosophy is really new ways to control the choices of the lesser-credentialed, we may yet see it foisted upon us.

Intrade’s Record In Picking Presidents: Is There Market Manipulation?

An “influential forecast” is one in which knowledge of the prediction changes the uncertainty in the thing being predicted. Consider a (respected) political opinion poll which announces Candidate B has an 85% chance of winning an election. Some people supporting Candidate A might hear this and figure the margin is so large that they needn’t bother voting. The result of the vote will edge in the direction of Candidate B.

This isn’t far-fetched. Exit polls for presidential races used to be reported from states in the east while voting continued in the west, but it was felt these polls influenced behavior and so are now withheld from general public knowledge (journalists, better equipped to deal with reality, still know their dark secrets).

Polls are not only error-prone measures of opinion, but they can always be viewed in a predictive sense, as a guess of what the vote percentages will be.

Also of interest are those forecasts produced by prediction markets, such as Intrade, Betfair, and the Iowa Electronics Market (IEM). The price on the presidential race on Intrade is often quoted in the press and taken to be indicative of the status of the race.

Some people are betting the predictive markets like Intrade are not just accurate but influential. That is, some folks have pumped money into the system hoping to drive the price up for a candidate and therefore make that candidate appear viable to the press, which will then dutifully report what it sees. According to this Daily Caller article, market manipulation has happened several times in the past on Intrade, particularly in presidential races.

If Intrade races were fiddled, then their forecast accuracy will have suffered. What of nominee races? In a University of Nottingham dissertation Ian Saxon1 found that Intrade predictions for the 2004 and 2008 Democrate nominee contests were good. He compared Intrade against an average of polls (he also tracked the individual polls, which were not much different than the average). Recall that polls are not forecasting the winner, but the vote percentage.

Intrade predicted a solid Kerry victory, with probabilities (prices normalized to 100) near 100% early on in January 2004 (pic). In the Clinton et al.-Obama matchup, Intrade’s prediction also showed an Obama victory, but perhaps not a quickly as in 2004 considering the price did not near the top until the close of the race.

Intrade predicts Obama victory


Intrade performed their own study of the 2004 Presidential, Bush-Kerry race, and produced this picture:

Intrade predicts a Bush victory, but barely

The events 1-7 are given by Intrade as:

  1. April 03: Coalition troops overtake Baghdad. Major fighting expected to be over
  2. December 03: Saddam Hussein captured in Tikrit
  3. April/May 04: Abu Ghraib prison scandal photos released
  4. June 04: Coalition troops hand over power to Iraqi interim government
  5. July 04: Democratic National Convention
  6. Early September 04: Republican National Convention; Swift Boat Veterans’ ads
  7. September/October 04: John Kerry “wins” Presidential debates

But the Daily Caller claims these undulations might have due to manipulation:

In 2004, recalls Eric Zitzewitz, an associate professor of economics at Dartmouth College who has co-written several papers on prediction markets, “somebody, in the middle of the night, drove the price of the [George W.] Bush re-elect contract — which was probably trading about 60 at the time — down to 15.”

Similar fluctuations were present in the McCain-Obama election in McCain’s favor. According to the Daily Caller, “The now-late founder of Intrade, John Delaney, concluded that the fluctuations were not the result of someone trying to rig the system.” Here’s the picture:

2008 Presidential Race

If manipulation is present, it’s pretty subtle, particularly near the end of the race.

Here’s the latest (as of yesterday) Intrade Chart for Romeny (red)-Obama (blue). Any manipulations? Or is this a good prediction?

Intrade predicts an Obama victory

As of this writing, Intrade has Obama at 57.9%.

Whether or not there is manipulation, Intrade weeks and months before the election is certainly not an infallible guide to who will win.

———————————————————————————

1Intrade Prediction Market Accuracy and Efficiency: An Analysis of the 2004 and 2008 Democratic Presidential Nomination Contests: pdf).

Italian Scientists Convicted! Shocked That Their Predictions Were Heeded

Do you feel that chill? It’s from a fell wind issuing from an Italian judge’s courtroom, where he has just sent a group of seismologists and one politician to the hoosegow for, it is said, failing to predict the deadly L’Aquila earthquake in 2009.

“Science” has been iced. Why, if scientists are held responsible for some of their whackier propositions, then they might not make them so freely. And nobody wants that. Right, Gav? From the WSJ:

“The concern is this could have a very chilling effect for future scientists in seismology,” said Joanne Padrón Carney, director of the Office of Government Relations at the American Association for the Advancement of Science. “Where does the responsibility lie? It’s really a political question, a process question, not just a science question,” she said.

The story is however more complicated (we originally covered it here and here). Turns out that there was this Italian guy peddling quack earthquake forecasts, based on the radon emitted from burning cat entrails or some such thing. As with all false seers, he was right sometimes and wrong most times, but his fans only remembered his successes.

He predicted there would be quakes in L’Aquila, an area which had been experiencing a multiplicity of small tremors, which caused many indigenous populants to grow dizzy with fear. So a commission of government officials paid visit to six certified seismologists who pooh-poohed the quack and said there was only a low chance of an earthquake.

L’Aquila earthquake

According to Nature:

What happened outside the meeting room may haunt the scientists, and perhaps the world of risk assessment, for many years. Two members of the commission, Barberi and De Bernardinis, along with mayor Cialente and an official from Abruzzo’s civil-protection department, held a press conference to discuss the findings of the meeting. In press interviews before and after the meeting that were broadcast on Italian television, immortalized on YouTube and form detailed parts of the prosecution case, De Bernardinis said that the seismic situation in L’Aquila was “certainly normal” and posed “no danger”, adding that “the scientific community continues to assure me that, to the contrary, i’s a favourable situation because of the continuous discharge of energy”. When prompted by a journalist who said, “So we should have a nice glass of wine,” De Bernardinis replied “Absolutely”, and urged locals to have a glass of Montepulciano.

Oops. The New York Times weighed in with an expert:

The statement by the official, who is not a seismologist, violated a cardinal rule of risk communication, which is that those involved should speak only to their expertise, said Dennis Mileti, an emeritus professor of behavioral science at the University of Colorado at Boulder. “This person should not have been speaking,” said Dr. Mileti, who has studied risk communication.

Yes, we often find officials keeping silent on important matters of the day. Anyway, the earthquake came and killed and after the funerals people remembered the wine quip. Fingers were pointed, collars were fingered, a trial was ordered. Guilty! The judge gave the six scientists who had the conclave with De Bernardinis six whopping years in prison.

But the trial was not, contrary to many discussions, because the scientists failed to predict the quake. The prosecutor, one Picuti, said (in Nature), “The basis of the charges is not that they didn’t predict the earthquake. As functionaries of the state, they had certain duties imposed by law: to evaluate and characterize the risks that were present in L’Aquila…They were obligated to evaluate the degree of risk given all these factors and they did not.”

“This isn’t a trial against science,” insists [surgeon and local resident] Vittorini, who is a civil party to the suit. But he says that a persistent message from authorities of “Be calm, don’t worry”, and a lack of specific advice, deprived him and others of an opportunity to make an informed decision about what to do on the night of the earthquake. “That’s why I feel betrayed by science,” he says. “Either they didn’t know certain things, which is a problem, or they didn’t know how to communicate what they did know, which is also a problem.”

The busted Italian forecast was of the Bobby “Don’t Worry Be Happy” McFerrin, there-is-no-reason-for-concern kind. And those fellows paid the price. But what of the opposite endless end-of-the-world predictions that besiege us from otherwise sober scientists who assure us that our very breath is killing us? They ever going to be hauled before the (earthly) judge?

False negatives are surely more costly than false positives, but it would be nice if there were a measure of responsibility tied to predictions.

————————————————————————————

Nature article: “At Fault?” by Stephen S. Hall, vol 477, 15 September 2011, pp264-269.

Risk Analysis And Over Certainty: Classical vs. Bayesian vs. Predictive Statistics

There are two main uses of statistics by civilians, defined as folks who use statistics, who may have even had a class or two in the subject, but who are not statisticians1. These two are:

  1. Differences between means
  2. Differences between proportions

Examples of (1): marketing trial with two groups, A and B; or a drug trial, or psychological, educational, or sociological study, or dozens of other similar academic exercises, and on and on (and on some more). Gist is there are two groups and one wants to test whether the means of these two groups are “different” from one another.

Examples of (2): pretty much the same: marketing trial with two groups, C and D; or a drug trial, or psychological study, etc. Gist is there are two groups and one wants to test whether the proportion of “successes” is “different” from one trial to the other.

There are two main ways data analysis proceeds: the classical, hypothesis-testing, p-value way, or Bayesian posterior examination. Both ways lead to too much certainty. And then there’s the predictive way. Let’s look at some examples.

Differences between means

Two groups, A and B, are observed; data are taken from both. A t-test is run which asks the (unnecessary2) question, “Are the means different?” The first plot below shows us an example: yes, the two means are different, with a p-value of 0.00015. Pretty small! And would lead any researcher to conclude his theory is true. And be pretty darn confident about that judgment.

But he’d be way too certain, as we shall see.

Differences between means

A Bayesian would eschew the t-test and opt to tell us of the posterior probability that the parameter for B is larger than the parameter for A. That probability is 0.99994, which is pretty high and allows us to conclude that, yes, the parameter for B is probably larger than the parameter for A. But notice the second plot, which is of the parameters, over the range of the observed data. The difference in the parameters might surely be real (it has a 99.994% chance), but the parameters aren’t the data. They’re just parameters, and are unobservable. The real data is a lot more variable than the Bayesian analysis lets on.

The predictivist goes one step further and says, What do I care about parameters? What’s the chance, given the old observations, that new data for B will be larger than new data for A? That probability is not as high as 0.99994; indeed, it’s much, much smaller. It’s only 0.651. The difference between the Bayesian posterior analysis and the predictive judgment is given in the third plot.

It’s still true that there is a 65% chance that B is bigger than A, but it’s not as sure a thing as the p-value or posterior would have had you believe. This is a much better measure of the inherent uncertainty in the problem. And a much fairer way to look at things.

Differences between proportions

Two groups, C and D, are observed; data are taken from both. A chi-square is run which asks the (unnecessary2) question, “Are the proportions different?” The first plot below shows us an example: yes, the two proportions are different, with a p-value of 0.035. Small. Again, this would lead any researcher to conclude his theory is true. And again be fairly sure about that judgment.

But as before, he’d be too certain.

The Bayesian again tells of the posterior distributions, giving us a probability a the parameter for D is larger than C of 0.983. Wow! Those parameters sure have a large chance of being different. But…

Again, the parameters are plotted (second picture) on the range of proportions we’d expect to see if new data were to be taken. Suddenly the difference doesn’t look as big.

The predictivist calculates the probability that in another sample—that is, in new data—the chance there would be more Ds than Cs. That probability is 0.87, which is high, but is not as high as 0.983, and which is what the final picture shows.

There isn’t as much difference between 87% and 98% as in the means test, and maybe big enough not to change any decision you’d make. But it might be enough to change somebody’s decision, and the difference is surely large enough to make it to the bottom line, if these proportions have anything to do with money.

Conclusion

The old ways of looking at things guaranteed over-certainty. The probability one thought there were real differences were always higher—sometimes much higher—than the inherent chance there were differences.

—————————————————————————-

1Note to regular readers: I’m always looking for ways to show the difference between the old and new. Maybe this demonstration fits the bill. I liked it better when it was in my head than on the page. Everything here is purposely telegraphic. I really just want to know if the pictures make sense. This post is really for fellow travelers.

2We know the means, or proportions, are different just by looking. We don’t need statistics to tell of what we already know. Yet this is how most analysis proceeds.

« Older posts Newer posts »

© 2014 William M. Briggs

Theme by Anders NorenUp ↑