Fun with Lancet Math
Lancet math is fun.
For example, many people are scared off from being prosecutors by the allegedly low pay. But according to a new Lancet study, first-year prosecutors in L.A. make over $650,000 a year!
A SiteMeter graph says that this blog has received approximately 80,000 visitors so far this month. But I prefer my Lancet brand SiteMeter, which puts the number at over 1 million!
And men across the country are measuring themselves using Lancet math — and liking the results!
Disturbingly Yellow makes a similar observation about WMDs.
According to Lancet math, I’ve had sexual relations with 0 women this year!
(Zero times zero is still zero.)
AndrewGurn (c37ea2) — 10/12/2006 @ 7:05 amThere is so much wrong with Richard Horton, I don’t know where to begin.
But I’m not going to leave it as if it’s not a big deal. No, I’m going to take it up.
My visceral reaction is we need to revamp our laws in the West: we’re in a battle for the survival of ourselves, our family, and our civilization.
We need to strengthen and enforce our sedition laws so people who knowingly support sworn enemies of our civilization with deed or propaganda are punished up to imprisonment, flogging or death.
(Were the laws in place at the time of his seditious actions) I would apply one of those three sanctions to Dr. Horton.
That’s my visceral reaction. A sober assessment of the definition of sedition suggests that this is an overly broad interpretation and is not justifiable since sedition essentially is: “conduct or language inciting rebellion against the authority of a state.”
This isn’t that. So can I just say I hate the bastard?
Anonymous (9824e6) — 10/12/2006 @ 7:19 amBetter than squelching speech.
Patterico (de0616) — 10/12/2006 @ 7:20 amI agree.
Yet I also maintain the freedom to really despise the man and harbor spitting in his face fantasies.
Which I would never actually do, you understand.
Anonymous (9824e6) — 10/12/2006 @ 7:21 amLast comment… if he was just supporting Hezbollah I would consider him an enemy, but not viscerally hate him to the same degree.
It’s the, “our usual apolitical election time death count,” line that got to me. Have a great day. Keep the fort.
Anonymous (9824e6) — 10/12/2006 @ 7:26 am1) The Lancet claims that their active survey is more accurate than a “passive” system of counting media reports, morgue reports or other lists of the dead (and generally totalling about 50,000 dead in Iraq), which are often grossly incomplete in a war zone. This seems reasonable.
2) To make sure people weren’t making things up, The Lancet asked for and received Death Certificates more than 80% of the time. Also reasonable.
3) But The Lancet fails to see that if 80% of the deaths were recorded by Death Certificate, then a passive accounting of Iraqi Death Certificates should give an accurate accounting.
4) The 95% confidence intervals are pretty tight for this study (meaning no more or less than that random sampling error is small). So could there be any explanation other than stupidity or bad faith to explain how their death figures could be an order of magnitude higher than the passive counts?
DWPittelli (87ad39) — 10/12/2006 @ 8:21 amSo every death gets reported in the media?
Grow up.
please
Seth Edenbaum (5e7461) — 10/12/2006 @ 8:51 amI should have had coffee first.
Since they recieved gor death certificates 80% percent of the time, this supports the accuracy of the study, doesn’t it?
30% of the deaths were caused by coalition forces.
Seth Edenbaum (5e7461) — 10/12/2006 @ 9:44 am‘So could there be any explanation other than stupidity or bad faith to explain how their death figures could be an order of magnitude higher than the passive counts?”
Yes, it’s easy. They most likely didn’t bother to control their sample of families to rigorously ensure it to be an accurate reflection of the entire Iraqi population.
My guess is that they asked around neighborhoods for directions to families who’d lost members, and confined their interview reports to the most dramatic stories.
Insufficiently Sensitive (01397c) — 10/12/2006 @ 9:44 amSeth,
If they got Death Certificates 80% of the time, as they claim, this fact supports that the families were not lying to them about deaths. It does not, however, support The Lancet’s methodology or the randomness of the survey. More important, it totally refutes The Lancet’s basic finding, because other people have been counting Death Certificates and have not come anywhere The Lancet’s count.
DWPittelli (87ad39) — 10/12/2006 @ 10:14 amInsufficiently Sensitive,
I assume you agree that your speculative (but highly plausible) examples amount to “stupidity or bad faith” on the part of the researchers.
DWPittelli (87ad39) — 10/12/2006 @ 10:16 amFind me a reference for death certificates specifically and not for varous public sources.
Seth Edenbaum (5e7461) — 10/12/2006 @ 10:28 amYou’re wasting everyone’s time on this but go on.
As with the last Lancet study, the negative response was hot air and gas. Here we go again.
DWPittelli-
I think there’s a plausible exception here to ‘stupidity or bad faith’.
That is the case of true believers: they’re smart enough to get their article into The Lancet, and their good faith in their own cause (of furnishing the worst possible
Insufficiently Sensitive (01397c) — 10/12/2006 @ 10:29 amnewsinformation in hopes of tilting an election) is absolute to the exclusion of any mere scientific methodology.Andrew wrote:
Hmmm: 1 times Lancet = . . .
I’d better not use Lancet math, just in case my darling bride reads this!
Dana (3e4784) — 10/12/2006 @ 11:36 amThe real answer, of course, is that only God knows how many Iraqis have died, and what the number of untimely Iraqi deaths would have been had the sanctions been maintained and Saddam Hussein left in power. I’ll ask the Lord soon, but, given the fact that he has yet to provide six separate numbers between 1 and 49 for me, I am guessing that he might not answer on the Iraqi death count, either.
Since we don’t know, we guess — and it’s pretty obvious that the guesses that have been made are based at least as much on the desired outcome number as any real data. Our friends on the left want the number to be huge, to “prove” it was a mistake to invade Iraq, while conservatives want the number to be low, not only to justify the invasion, but because we don’t want innocent people killed.
I find it . . . interesting . . . that our friends on the left want the number to be high, to justify their position, because having that number high means they want to have had more deaths of innocent people.
Dana (3e4784) — 10/12/2006 @ 11:46 amSeth –
Would that be the last survey where they had a CI (Confidence Index) of 95% for the number of deaths being between 8,100 and 193,000?
Even the study admits in the appendices that cluster interviewing is unreliable for this kind of analysis. No distinction between combatant and non-combatant. Using a tiny sample to estimate pre-invasion mortality rates. This study has holes all over the place before you even reach the part where the researchers say they timed its release for a political goal.
Lojo (20ce31) — 10/12/2006 @ 2:24 pmIIRC, the last survey was undertaken ~2004. At which time, they concluded that there had been 100,000 or so excess deaths (within that 95% confidence interval).
Today, two years later, they are reporting 655,000 or so excess deaths.
Which means that in 2 years, there have been 555,000 excess deaths. Or over 275,000 excess deaths per year. Or 753 excess deaths per day.
Think about that one. 753 additional deaths (over and above old age, disease, normal traffic accidents, etc.) EVERY. SINGLE. DAY.
Just from a public health perspective, you have to wonder how this is possible. You’d be talking about dead everywhere. Watch news footage and video footage from Iraq. Do we see bodies everywhere?
Lurking Observer (ea88e8) — 10/12/2006 @ 2:46 pmDeath rates and death ceritificates
This to go along with the other link I posted previously.
Other questions answered here.
You’ll find most questions raised and dealt with in these posts.
Validity of the techniques used etc.
Read the comments too.
Seth Edenbaum (5e7461) — 10/12/2006 @ 4:49 pmSeth says: “Find me a reference for death certificates specifically and not for varous public sources.”
Here you go, Seth: (Burnham, G., et al., http://www.thelancet.com, 11Oct06, p.2): “At the conclusion of household interviews where deaths were reported, surveyors requested to see a copy of any death certificate and its presence was recorded. Where differences between the household account and the cause mentioned on the certificate existed, further discussions were sometimes needed to establish the primary cause of death.”
(Ibid., p.4): “Survey teams asked for death certificates in 545 (87%) reported deaths and these were present in 501 cases. The pattern of deaths in households without death certificates was no different from those with certificates. Of the 629 deaths reported, 547 (87%) were in the post-invasion period (March, 2003, to June, 2006) compared with 82 (13%) in the pre-invasion period (January, 2002, to March, 2003; table 2).”
(Ibid., p.7): “Families could have reported deaths that did not occur, although this seems unlikely, since most reported deaths could be corroborated with a certificate. However, certificates might not be issued for young children, and in some places death certificates had stopped being issued; our 92% confirmation rate was therefore deemed to be reasonable.”
Ajay (daeec9) — 10/12/2006 @ 5:00 pmCrooked Timber has an explanation for why the ‘official’ death tally and the Lancet study differ so much: death certificates are pretty reliably produced for next-of-kin at the level of “hospital, morgue or coroner”, however, the certificates are not reliably transmitted to the central government. A couple points regarding that explanation.
1. CT provides no links to corroborate the explanation. Such links would be helpful to those who wish to understand rather than just accept the authority of a Lancet study with a notably large error margin.
2. The study of Burnham et al. appeals to the death certificates to answer objections about the reliability of testimony. But if the certificates are a more reliable standard (if they weren’t the appeal is useless), then why not dispense with testimony and simply inspect the records of those issuing the death certificates at the level of “hospital, morgue or coroner”? Presumably such a data set would be easier to gather, more reliable (respecting both the survey teams and those surveyed), and more extensive.
3. Is the one year interval prior to the invasion of Iraq adequate/representative?
I ask because among other things female adult cancer deaths spike though they remain roughly the same for the other three categories. Why?
4. My understanding (R. Garfield 1999 Columbia U study and M. Ali and I. Shah 2000 Lancet study) is that sanctions impacted children badly. Does Burnham et al. reflect this in its numbers before and after the 2003 invasion? According to Ali and Shah the Shia south had child mortality rates of 131/1000 and the Kurdish north had rates of 72/1000. Or did things suddenly improve for children between 2000 and 2003 only to have the war set back Iraq’s progress? If Burnham et al. is not consistent with those two earlier studies, then what is the reason and does any such inconsistency skew the 2006 study?
The study of Ali and Shah was intended to do for sanctions and child mortality what the study of Burnham et al. was intended to do for the war and its aftermath and overall mortality. Was there a tradeoff where violent deaths (200,000 year) became worse but the sanctions related deaths (35,000 per year according to R. Garfield) became less? If not why is that?
Ajay (daeec9) — 10/12/2006 @ 6:12 pmIf this website had existed at the time of the OJ Simpson trial, this is where all the “Go O.J.” bots would have gathered to deny the validity of the DNA evidence.
Asinistra (7478dd) — 10/12/2006 @ 6:13 pm– “Extrapolation” (Ding!) …The Holy grail of pre-ordained results….
– I don’t trust this “study”, not because of the ludicrous math, but because there’s no mention of our rapacist murdering thirst for their oil….Sans that, it just doesn’t carry the same weight….
Big Bang Hunter (9562fb) — 10/12/2006 @ 7:22 pmI used Lancet math on my checkbood and it came out with One million, eight hundred thousand, six hundred and sixty five dollars as a balance. I wrote a check for two thousand dollars and the dam* bank bounced the check. Said I only had One thousand, eight hundred, and sixty six dollars in my account. Think i’ll be able to convince them they are wrong or that the new math taught by a world famous professors made me do it. LMAO
Scrapiron (a90377) — 10/12/2006 @ 8:23 pm– Scrap….Maybe its just that your bank manager doesn’t appriciate the fine art of “Extrapolation” (Ding!).
Big Bang Hunter (9562fb) — 10/12/2006 @ 10:42 pmCharacteristic # 11. of the “14 Characteristics of Fascism”
11. Disdain for Intellectual and the Arts–Fascist nation tend to tpromote and tolerate open hosility to higher education, and academia. It is not uncommon for professors and other academics to be censored or even arrested (or ridiculed*) Free expression in the arts is openly attacked, and government often refuse to fund arts.
*I added that.
source of article this excerp is taken from:
blubonnet (8d9f79) — 10/13/2006 @ 1:12 amhttp://www.thirdworldtraveler.com/Fascism/14_Characteristics_Fascism.html
Beautiful Blubonnet wrote:
*I added that.
So, if we do not find “professors and other academics” censored or arrested, we can’t be fascist, right? If our government funds the arts, we can’t be fascist, correct?
You’ll not, I would hope, that even the most ridiculous and offensive of the academics, people like Ward Churchill and Peter Singer, have been neithere censored nor arrested. And I assume that you are aware that the federal government contains the National Endowment for the Arts, which does fund (so-called) art.
Now, are certain professors criticized? Why, yes, of course they are. Surely the “free expression” you think is so important to the arts also extends to us poor, uneducated, non-professor types; aren’t we free to criticize the professors?
Indeed, if our society did not “tolerate open hosility” to some people in higher education, would that not mean opur society was oppressing the freedom of expression?
Surely you are not suggesting that once someone achieves the rank of professor, he is or should be automatically extended immunity from criticism?
Dana (3e4784) — 10/13/2006 @ 4:58 amBonnet –
“Characteristic # 11. of the “14 Characteristics of Fascism”
11. Disdain for Intellectual and the Arts–Fascist nation tend to tpromote and tolerate open hosility to higher education, and academia. It is not uncommon for professors and other academics to be censored or even arrested (or ridiculed*) Free expression in the arts is openly attacked, and government often refuse to fund arts.”
*coughLarrySummerscough*
Lojo (20ce31) — 10/13/2006 @ 6:55 am– Part of the SP plan is to send forth “Unimpeachable” sources, stifling critique. It’s not working out so well, so they’re pissed. Berlin politic’s of the 30’s has an uphill struggle in an enlightened electorate. But hey, like all forms of mental illness, doing the same thing over, and over, and over, may one day get their lies accepted.
Big Bang Hunter (9562fb) — 10/13/2006 @ 8:22 amYou fascists better stop questioning your betters. You will never be free unless you accept our authority.
blownbonnet (959fea) — 10/13/2006 @ 8:52 pm“Disdain for” certainly fits on your derision of that MIT funded, Johns Hopkins University operation, peer-reviewed article, put out by a prestigious medical journal, LANCET, is what your attitude is toward something that is painfully unsettling, that we as the United States have done to an innocent nation based on intentional lies by a corrupt war-profiteering administration, that disregards law and governmental procedures. HE IS A FUCKING OUTLAW. By international standards!
Yes, we still have the right to speak out. There are restrictions that are growing on and upon (trampling over) our right to free expression though. “Free speech zones” are now designated for protests while the corporate MSM (having a back-scratchin fest w/ Bu$hco)cameras are not particularly within range of the protests. Millions protested worldwide in March 2003, but the ignorant trusting ones believing in the purity of Bu$hco and the MSM remained ignorant.
Another example of our freedom of expression is from the many liberal photo-journalists prohibited from photographing things that show the damning truth of the ineptitude, self-serving greed, and arrogant bumbling of the Bu$h regime.
Katrina victims were prohibited from speaking to journalists for example, because they were told they would lose the trailers.
These are just some of the things that have started to disappear. Habeous corpus, Geneva Convention regard, the MIDDLE CLASS, and more, but I don’t have all day here to cover it, not that it should be anything you are lacking awareness of, but just apparently excusing.
Google up the preceding events in Hitler’s gradual full grasp of power. It’ll sound familiar.
Here is a word from James Madison:
blubonnet (8d9f79) — 10/14/2006 @ 12:59 am“If tyranny and oppression come to this land, it will be in the guise of fighting a foreign enemy.”
Dana, thank you for being such a gentleman, despite our varying ways of seeing things. Admittedly, I do become unhinged. How could you not, though?
blubonnet (8d9f79) — 10/14/2006 @ 1:04 amHow could I not what, Blu? Become unhinged, or be a gentleman?
If I have decnt manners, it’s because my moter reared me right. As for becoming unhinged, I managed to remain tightly fastened to my hinges during the eight miserable years of the Clinton Administration, which I disliked as much as you are displeased with the current one.
Dana (1d5902) — 10/15/2006 @ 12:23 pmErr, my mother reared me right; I’m not sure what a “moter” is.
Our esteemed host has no idea how many times I wish I could edit my own comments here! 🙂
Dana (1d5902) — 10/15/2006 @ 12:25 pmThe Lancet study numbers and the wisdom of the decision to invade Iraq…
What those who accept the Lancet numbers unquestioningly are saying is that, if we account for population differences, Iraq has suffered between 3½ and 7 times as many civilian casualties as did the Third Reich. For the numbers to have been realisti…
Common Sense Political Thought (819604) — 10/15/2006 @ 4:03 pmDon’t hold back so much, blubonnet. Tell us what you really think. You sound a lot like my grandfather when he was asked to loan something he didn’t want to or to do something he didn’t want to. He’d say, “sorry, I’ve got to grease my pliers.”
I said, “but Grandpa, your pliers don’t get greased and you never grease them after you say that.” He replied, “any excuse is good enough when you don’t want to do something.”
I see that for you any excuse is good enough to bash Bush. BDS must be a terrible, terrible burden.
JorgXMcKie (4068d7) — 10/15/2006 @ 5:29 pmEight miserable years of economic prosperity and a balanced federal budget; good God, man; how in the world did you manage to keep your sanity?!
Ironically, though few are making the comparison, the number kiiled as a result of America’s invasion of Iraq has not yet reached the number that likely died as a result of the economic sanctions during the Clinton years. One difference between the Bush and the Clinton administrations is that the latter didn’t run from the truth, as then-U.S. ambassador to the United Nations Madeleine Albright said when confronted with the estimates: “I think this is a very hard choice. But the price, we think, is worth it.”
Of course, back then the deaths of an estimated 1 million Iraqi civilians wasn’t quite as interesting to the American Congress and American media as one ruined blue dress.
So what’s worse: running from an awful truth or trying to justify one? For the dead, what difference does it make?
Rick (c4e376) — 10/15/2006 @ 5:56 pmOf course, the estimates of the number killed by sanctions were wildly exaggerated.
Patterico (de0616) — 10/15/2006 @ 6:07 pmWe have no reliable way of knowing if the deaths attributed to the sanctions are “wildly exagerated,” as there is no reliable way to accurately determine the number that died as a result of the sanctions. The problem is compounded because it’s hard to decide if one should attibute deaths arising from drinking contaminated water to the bombing of a water treatment plants (as was done during GW 1 by the US) or to the sanctions that compromised their repair as well as the availability of antibiotics to treat the subsequent dysentary.
The Lancet numbers are based upon better data, but by all reasonable estimates, hundreds of thousands of children died that probably wouldn’t have died if not for the first war and the sanctions that followed, and those numbers are just for the children. One can quibble over whether it was the war or what followed that caused the deaths, but either way, the numbers are still undeniably huge.
Rick (c4e376) — 10/15/2006 @ 6:43 pmBy all reasonable estimates?
What is unreasonable about Matt Welch’s piece, which strongly disagrees?
Of course, if hundreds of thousands of children were dying under sanctions, what does that say about the justification for the war?
Patterico (de0616) — 10/15/2006 @ 6:55 pmYou tell me, Patterico. The war was justified to Americans based upon Saddam’s WMD, his ties to Al Qaeda, and an “emminent threat” to America. I really don’t recall Bush, Cheney, or Rumsfeld justifying it on by the deaths of children due to sanctions; do you?
Yes, Patterico; by all reasonable estimates. From Welch’s piece as you linked above:
And here’s more from The Nation:
Rick (ea2ac3) — 10/15/2006 @ 7:24 pm[…] Is it possible that Patterico really doesn’t know how sampling works? This entry was posted on Sunday, October 15th, 2006 at 7:30 pm and is filed under Idiocy. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site. Home» […]
appletree » Blog Archive » We Must End Innumeracy in America (1dfa1f) — 10/15/2006 @ 7:30 pmRick–
That’s only part of the story on sanctions. It’s also worth noting that the expansion of the oil-for-food program had to effect of greatly diminishing the death toll caused by the sanctions. So even though the total number who died because of the sanctions is quite high, the annual toll was relatively low by the time Bush decided to invade.
Here’s what the CIA has to say about it:
gordo (f978aa) — 10/15/2006 @ 7:41 pmRick, your claim was
and the Welch piece doesn’t support that. Welch concludes:
The expert whom you quoted blamed the 1991 war for 1/4 of deaths ranging in number from slightly over 100,000 to 350,000 worst-case. 1/4 of any number in that range is less than 100,000, not “hundreds of thousands.”
I am not going to be drawn into another endless repetitive debate with you. Anyone who questions what either of us is saying is invited to read Welch’s piece, which I link above.
Patterico (de0616) — 10/15/2006 @ 7:47 pmA conclusion from Welch that reads: “at least…more than 100,000 deaths” does not contradict or even “strongly disagree” with Garfield’s estimates of 350,000 excess deaths of just children alone. Most of those deaths were not directly attributed to the war, but to the sanctions that followed. I also invite those interested to read Welch’s article as well as The Nation’s for another perspective on the same thing.
Rick (ea2ac3) — 10/15/2006 @ 8:24 pmIt was overstating it to say it “strongly disagrees” with your conclusion — I was going from memory and remembering his conclusion that sanctions contributed to around 100,000 deaths. Looking it over again he does say “at least.” But you have overstated matters as well to say most reasonable estimates say hundreds of thousands were killed directly by sanctions and the first war.
Patterico (de0616) — 10/15/2006 @ 8:35 pmAs was I, Patterico. Ironic, isn’t it? I’m assailing a policy under Clinton and you’re trying to, if not defend, at least mitigate it.
Rick (c7fbdd) — 10/15/2006 @ 9:08 pmI don’t see it that way. I’m just going for accuracy.
In fact, you can see it as an attack on Clinton if you like. My major memory from the article was that Welch said that Albright was terribly irresponsible to simply go along with the 60 Minutes accusation re the effect of sanctions, and that her answer cost us a lot of enemies in the Arab world.
Patterico (de0616) — 10/15/2006 @ 9:12 pmAs am I. And, no, it’s not an attack on Clinton, it’s a criticism of his policies; there is a difference, you know.
As far as making “enemies in the Arab world”…well, we both know whose policies have done that the most.
Rick (c7fbdd) — 10/15/2006 @ 9:19 pmSure. George W. Bush. 9/11 was conceived and planned on his watch. During the Clinton era, Arabs loved us.
Also, whether Arabs are our enemies is a result of our policies. It’s not the Arabs’ fault.
Patterico (de0616) — 10/15/2006 @ 10:04 pmI agree…how dare we fabricate all those myths that we were hated before Bush…back in the Clinton days (this is when Iraqi children were playing in the rainbows and the chocolate and such…and being fed as agreed via the Oil for Food program) things were going swimmingly and the Iraqis were fat and happy. How dare Bush get the Eastern world to decry our values and lifestyle choices…this administration sure blindsided us by creating such hatred…
The Stout Republican (f758e9) — 10/15/2006 @ 10:39 pmhttp://unstats.un.org/unsd/seriesa/354.asp
The UN, based on actual records of death placed the mortality rate in Iraq in the year 2000 at 7.8/1000, they also estimated that it was an ndercount and estimated a death rate at 8.8/1000.
Lancet magically concluded that the mortality rate in Iraq had declined to 5.5/1000 by 2002.
To shift the mortality rate in Iraq by one requires 68 deaths a day.
Lancet uses a baseline mortality of 5.5 and a post march 2003 mortality of 13.7
Lancet is claiming an average of 557 excess deaths a day.
Soldier's Dad (6c0068) — 10/16/2006 @ 8:32 amLancetMath aka LibMath should be consigned to the same dustbin as Ebonics and consensual math, a system where the right answer was determined by majority rule.
LibMath provides some figures that are accepted by the true believer as facts and serve to butress talking points that bubble up from the leftist ooze to be recited by big network news readers.
How many remember the number that was once bandied about by the number of ‘children’ killed by guns on a typical day. Would-be gun grabbers would show these numbers in TV spots that showed a toddler climbing up to a closet shelf to get daddy’s .45. Yet what was the definition of ‘children’ used to obtain such a frightening factoid? Did it include only toddlers or did it include violent street thugs old enough to shave and drive? This is a rhetorical question and the LibMath in question was tantamount to an outright lie.
While the source was respected, it is not uncommon for a person with an agenda to supmit an article to a professional journal that is only tangentially related to the basic goals of the group and escape extensive peer review.
While the medical profession is seen as a healing profession, it has had its bad apples, such as Doctors Mengeles and ‘Double-O’ Swango. The late Soviet money launderer Armand Hammer was trained as an MD but a botched abortion (for which daddy Hammer took the rap) led him to go in other avenues.
Arthur Downs (0833d4) — 10/23/2006 @ 8:56 am