You are currently browsing the category archive for the 'Statistics' category.
Taunter Media wrote how the claims that rescission is rare is a claim that should be taken with a grain of salt. Taunter Media breaks down the math:
To understand why 0.5% of the people Assurant covers is a lot of people – a jarring, terrifying, probably criminal lot – you need to understand a little bit of math. You need to understand just enough math to understand what Don and his legal team are not telling you. You need to understand conditional probability. And the folks at Assurant are counting on the fact that you don’t.
So what is being done here is confusing CONDITIONAL probability with absolute probability. Taunter explains why this is important:
Half of the insured population uses virtually no health care at all. The 80th percentile uses only $3,000 (2002 dollars, adjust a bit up for today). You have to hit the 95th percentile to get anywhere interesting, and even there you have only $11,487 in costs. It’s the 99th percentile, the people with over $35,000 of medical costs, who represent fully 22% of the entire nation’s medical costs. These people have chronic, expensive conditions. They are, to use a technical term, sick.
An individual adult insurance plan is roughly $7,000 (varies dramatically by age and somewhat by sex and location).
It should be fairly clear that the people who do not file insurance claims do not face rescission. The insurance companies will happily deposit their checks. Indeed, even for someone in the 95th percentile, it doesn’t make a lot of sense for the insurance company to take the nuclear option of blowing up the policy. $11,487 in claims is less than two years’ premium; less than one if the individual has family coverage in the $12,000 price range. But that top one percent, the folks responsible for more than $35,000 of costs – sometimes far, far more – well there, ladies and gentlemen, is where the money comes in. Once an insurance company knows that Sally has breast cancer, it has already seen the goat; it knows it wants nothing to do with Sally.
If the top 5% is the absolute largest population for whom rescission would make sense, the probability of having your policy cancelled given that you have filed a claim is fully 10% (0.5% rescission/5.0% of the population). If you take the LA Times estimate that $300mm was saved by abrogating 20,000 policies in California ($15,000/policy), you are somewhere in the 15% zone, depending on the convexity of the top section of population. If, as I suspect, rescission is targeted toward the truly bankrupting cases – the top 1%, the folks with over $35,000 of annual claims who could never be profitable for the carrier – then the probability of having your policy torn up given a massively expensive condition is pushing 50%. One in two. You have three times better odds playing Russian Roulette.
So who are the creationists, while Gene Expressions has been doing statistical disaggregation in the blogosphere for a quite a little bit of time, he has gotten particularly interesting lately. His recent post plots out which groups are more likely to reject evolution and there are some surprises:
Not surprisingly, Catholics, Hindus, Buddhists, and Jews are above fifty percent in the evolution acceptance with Buddhist and Hindus having higher percentage than general population in some European countries such as the UK. I, however, was surprised that a slim majority of Orthodox Christians do. I couldn’t gather that from their rhetoric on the matter.
However, who rejects evolution is more surprising. There is an uptick in Mormon rejection of evolution. In fact, Razlib points out that this number has increased by 81% since Mormons have moved to be more identified with conservative Christian Protestants.
Another surprise: Evangelical and traditionally Black churches reject evolution MORE than American Muslims do.
I did notice, however, that Pagans were not included in this survey from Pew.
David Dobbs, over at Nueron Culture, hit on the a lot of the frustration both parents and teachers feel about the school boards and school culture:
A blithe acceptance of clear problems and excessive costs; a constant return to what happy highlights our overspending produces; blindness to how the system’s weaknesses compromise our international competitiveness and our children’s future Our school system lately looks increasingly like our health-care system.
Even when we focus on international competitiveness, the focus is often superficial. The studies don’t control for all kinds of variables from income level to how many people actually attend high level secondary school.
This led me to thinking about something that was being discussed over at Bridging Differences: Why people, including public policy makers, so easily fooled into education quarkery. Diane Ravitch has noticed that teacher bashing has become part of this as well in recent years:
Teacher-bashing has become the motif of the day. It is usually cloaked in some high-minded rhetoric that pretends to praise teachers. Say the bashers: We need great teachers; great teachers can solve all our problems; great teachers can close the achievement gap; if you don’t have great teachers, you are doomed; blah, blah, blah. What they really mean—read between the lines—is that they think most of the teachers we now have are no good. We have to start firing the stragglers, the ones whose kids don’t get high test scores. The theory is that—emulating Jack Welch at GE—we should fire the bottom 10 percent every year, and over time we will have a staff of “great” teachers because all the bums will be gone.
I have noticed this too. Despite the fact that education levels of the teacher don’t seem to have a direct and clear correlation to student achievement nor does traditional certification. The skills sets of a good teacher and an outstanding academic overlap, but they are not necessarily the the same. Daine goes on:
Part of the reasoning is founded on the belief that recent graduates of the Ivy League colleges (aka the best and the brightest) will fill the ranks of the teaching corps and recruitment of “great” teachers will not be a problem. I am still trying to understand the math. Teach for America brings in 5,000 or so teachers a year; there are 3 million teachers in America. I don’t believe that Harvard, Yale, Princeton, Brown, and Berkeley will ever supply enough teachers to fill the need for new teachers. Nor am I persuaded that someone will definitely be a great teacher just because he or she graduated from a highly selective college. I know people, as I am sure you do, who are utterly brilliant, highly educated, with degrees from the best colleges, who were failures in the classroom. And I know superb teachers who graduated from state universities.
While the evidence used here is anecdotal, the above link does lend some legitimacy to it.
So who does Mrs. Ravich blame:
One other thing: You mention the hype and spin that we often see in the media. It seems that many journalists won’t write about education unless they can find a miracle to write about. So they find a teacher or a school where kids who were completely indifferent to learning were suddenly transformed by the inspiration of one teacher or one school. A classroom full of sullen thugs turns into mathematical geniuses or poets. When people see this narrative again and again, they must wonder why every teacher is not performing similar miracles. After all, they went to the movies and they saw an existence proof. And, as many of our illustrious peers often say, “If it can happen in one school, it can happen in all schools.”
And this she points out the sort of strange ways that people in the US are trying to fix the schools which are NOT based on models from Asian and European countries with a much higher success rate. Instead we get the typical laundry list of reforms loved by either conservatives, romantics, and teacher’s unions… all of which are sort of nutty or highly optimistic as a miracle cure:
The great mystery is why so many people are so gullible about miracle cures when it comes to education. They certainly don’t expect miracles in any other part of their life. But the schools just can’t seem to shake this belief that all children will learn to the highest standards when: 1) all teachers are great teachers; 2) every school has a brilliant leader as principal; 3) every superintendent has an M.B.A.; 4) every school is run by entrepreneurs; 5) every school is organized around a theme; 6) every school is small; 7) all schools are charters. I know that multiple-choice questions are supposed to have only four answers. In this case, I could have added another 10 or 20.
Both the pseudo-progressive model and the pseudo-business model don’t apply as easily as most people who live with a school system but work outside are prone to thinking. So we are left with oblivious school boards AND oblivious political crusaders in education. The real fixes used by other countries are complicated and require reforms not just to American schools, but to American social ideas. We could look to countries like Japan, or even highly successful school systems like Canada’s or Finland’s and see what the differing variables are. But that requires both qualitative and non-superficial quantitative research (there is a cult of the quantitative in American education, but often it is only skin deep… it compares numbers without really looking at the validity of generalisability of those numbers and without controlling for a myriad of outside factors).
Yet, I think we have to lesson to Deborah Meier’s respond to Diane Ravitch as well:
Many reasons, no doubt, including a natural inclination to believe there is some way to know what’s happening out there in the big world, and gullibility is perhaps better than instinctively dismissing it all. The kind of healthy skepticism you and I are talking about is not, I’d argue, a natural part of our evolutionary make-up. Probably through most of human history we didn’t depend on any media—but that which our own senses, and our neighboring allies agreed upon as truth. There’s no way I can check out most of what makes up my “immediate” environment today, and no amount of voracious reading could assure me that I had it right. After all, books, too, are part of “the media” and must be read with a proper skepticism. And on and on.
And, indeed, while we all have a “right” to our opinion, it’s an empty right if that’s all it is, or maybe a dangerous right!
Those of us in the scientific skeptic community have been saying this for years, but often hedging our bets on the last caveat. Mrs. Meier’s does hit at a problem I have had with education research… we almost always use real classes as labs without consent–done by school board fiat or administration initiative or by struggling state-wide directions:
The question for educators then is how to use those long years toward such ends. And, simultaneously, how to educate the larger public, as we learn more ourselves, as to why these newfangled innovations are worth doing. They cannot be imposed upon an unwilling public, or parents—because that in itself can’t happen in a democracy for very long. We tried it once with “new math” and lost fairly quickly, although I’m still of the belief we were on the right track a half-century ago. It’s also tricky to “experiment” on children—to admit that we truly don’t entirely know whether our new approach will get us where we want to go, but bear with us!
That’s why I’m for such experiments not being imposed, but being studied carefully and applied to volunteers. The voluntary part goes against “random sample experimenting,” etc., but that’s a limitation we need to accept. Of course, since the “traditional” paths are in fact still unproven experiments, I want the right to opt out of them for my kids, too. (That’s where some form of controlled choice enters into my equation.)
And lastly, Mrs. Meier’s hits on the cult of superficial quantification:
We’ve settled for the idea that democracy, and the U.S. economy, are safe if only we match our competitors’ test scores and more or less close test score gaps, and that this can be accomplished if we frighten people or reward people into just putting their minds to it.
Of course, in fact, they don’t just work harder under such pressure, they actually work “smarter.” But their “smarts” are almost entirely devoted to figuring out how to crunch the data in such a way that they win the reward, whether in fact, it produces better educated citizens or not, and in many cases, whether it truly even produces better “data.” Generally, the mayor also controls the way in which the data is developed, weighted, and reported.
They end up good at the Wall Street “game,” and begin to believe, as those on Wall Street probably did, that better numbers equal a stronger economy, and better test scores equal a better educated citizenry!
So why are fads so dominant in education? We really don’t have a clear grasp of what we actually mean by a good education OR how to meaningfully assess it. We don’t have a skeptical public and public schooling is necessarily politicized. Ideological confirmation. Media Myths. Bad social science going unquestioned because it confirms our ideological beliefs.
It’s a skeptic’s nightmare, and yet, outside of battling for keeping Creationism out of the science, most skeptics don’t give it the same consideration they do other quackery.
Reasonable Doubts recently released a podcast on Dr. Luke Galen’s Profile of the Godless at CFI Michigan and CFI international. Dr. Galen combined several prior studies with an extensive study on non-belief with a large enough sample to go into sub-populations of unbelief.
Dr. Galen also produced this pdf of his statistical research so easy disaggregation of the data can be done.
Here’s some interesting facts about Humanists in CFI: most people who identify as humanists will primarily identify as atheists when pressed, humanists and atheists had stronger contentment ratings than agnostics and “spiritual but not religious” types, humanists tended to be five years older than atheists (although both tended to be in their 40s in the median and average), and that humanists tended to take a more “agreeable” attitude towards the community.
However, Dr. Galen’s research does seem to indicate that despite the fact that people have a less of a stigma against non-believers if they used words other than atheists, non-theists tended to define themselves as a oppositional movement.
My speculation on the implications is that voices like that of Paul Kurtz, Sherwine Wine, and even A.C. Grayling have been displaced by voices like Sam Harris or Richard Dawkins. Also many people in the late forties came out of moderate religious households in the late 1950s and early 1960s, but people raised in the 1970s and 1980s grew up in polarized households.
One thing this leads me to worry about is that if we move away from being a marginalized group in the larger society we will many people lose a sense of direction.
What flaw I see in Dr. Galen’s study is that it almost strictly focuses on nontheists with formal group affiliations, but this misses probably a majority of the non-religious who have no such formal ties.
