Guest essay by Eric Worrall.
JoNova reports on a hilarious error in Lewandowsky’s paper “The Role of Conspiracist Ideation and Worldviews in Predicting Rejection of Science” . The calculated age of survey respondents has reportedly been skewed by one “outlier” who claimed to have been born in the palaeolithic, 32,757 years ago.
Raw data – line 607, http://websites.psychology.uwa.edu.au/labs/cogscience/documents/PLOSONE2013Data.csv
Lewandowsky was informed of this error over a year ago – and has reportedly done nothing to address this glaring problem with his calculations and conclusion.
According to Jo Nova;
“Lewandowsky, Gignac and Oberauer put out a paper in 2013 which was used to generate headlines like ‘Climate sceptics more likely to be conspiracy theorists’. The data sample is not large, but despite that, it includes the potential Neanderthal, as well as a precocious five year old and some underage teenagers too. The error was reported on Lewandowsky’s blog over a year ago by Brandon Shollenberger, then again by Jose Duarte in August 2014. Nothing has been corrected. The ages are not just typos, they were used in the calculations, correlations and conclusions. The median age was 43 but the mean age was a flaming neon 76. One wildly old person in the data skewed the correlation for age with nearly everything:
That one data point – the paleo-participant – is almost single-handedly responsible for knocking out all the correlations between age and so many other variables. If you just remove the paleo-participant, leaving the minors in the data, age lights up as a correlate across the board. Further removing the kids will strengthen the correlations.”
Worst of all, the bad data has apparently led to a demonstrably erroneous conclusion. According to Jose Duarte,
“This would be a serious problem in any context. We cannot have minors or paleo-participants in our data, in the data we use for analyses, claims, and journal articles. It’s even more serious given that the authors analyzed the age variable, and reported its effects. They state in their paper:
— “Age turned out not to correlate with any of the indicator variables.”
This is grossly false. It can only be made true if we include the fake data. If we remove the fake data, especially the 32,757-year-old, age correlates with most of their variables. It correlates with six of their nine conspiracy items, and with their “conspiracist ideation” combined index. It also correlates with views of vaccines – a major variable in their study. See the graph below.”
http://www.joseduarte.com/blog/how-one-paleo-participant-can-change-the-outcome-of-a-study
Lets hope that Lewandowsky finally takes action to correct the error, and amends the erroneous conclusion of his paper, which is inferred from Lewandowsky’s analysis of the grossly defective data. Of course, while he’s at it, I’m sure we could suggest a few other defects with Lewandowsky’s work which he could correct.
Discover more from Watts Up With That?
Subscribe to get the latest posts sent to your email.
Is the figure able to be divided by nine, if so it is a transposition. One of the first calculations I learned when I started in banking many years ago, when I couldn’t balance till or branch. Example 36 or 63 difference 27 = 9 x 3, easy mistake to make. My local bank today had never heard of it, training or lack there of. I was able to explain to her why she didn’t balance, in a couple of seconds, when I overheard a conversation about “why can’t I balance this teller position”. DUHHHHH!!!!!!!
That transposition test doesn’t require the two numbers to be divisible by 9, the test is whether the remainder when divided by 9 is the same. Or the difference of the two is divisible by 9.
And of course, the 9 divisibility test is to sum all the digits in the number and repeat with the new number until you get a single digit. If that’s 9, it’s divisible by 9, otherwise it’s the remainder when divided by 9.
3 + 2 + 7 + 5 + 7 = 24; 2 + 4 = 6. Not divisible by 9.
And has nothing to do with the issue at hand….
They have a lake upside down in their data, does anyone expect them to fix this?
I have published in PlosOne, and I can assure you, I had to address rigorous peer review questions to get the papers accepted. I have already contacted PlosOne about this paper and told them how outrageous it is that most scientists are held to high standards, but Lewandowsky and the peer reviewers and editor(s) involved convert all of it into a joke. I am more than angry, and if this is not resolved quickly, I will be contacting the Editor in Chief and editorial board personally (face-to-face, if necessary).
Scientists in fields other than climate science really mostly do no know the damage that this one research field is doing by converting science to politics and by throwing standards of science out the window. On the plus side, I would like to assure readers here that other fields are not affected to the degree we see in climate science. When your work may result in the life or death of people or animals whose treatments are influenced by your work, it tends to keep you a little more concerned about validity and accountability.
Do that. And please let us know how it goes.
Because right now, the paper(s) you’ve had published in PlosOne are worthless.
The Journal has lost all credibility and moral authority.
They should have asked about the exploitation of children in the survey (as well as spotting the elderly respondent).
And the fact the journal has no ethical controls is surely worse than merely being incompetent.
I guess you’ve forgotten about Diederick Stapel.
As one of the people who knows the alleged 32757 year old man, I was called upon to validate his age but stopped short of confirming his 32757 years. I’ve only known the man for 26411 years, there’s just no way to confirm his age. He is known to exaggerate from time to time.
Sincerely,
Thag the forager/hunter
Third cave from the stream, near the oozing tar pit.
White rock canyon, next to the big tree.
Homo Erectus welcome if you check your club before entering cave.
[trimmed, vulgar. .mod]
a 9 year old could more competently fake their “data”
Since this is a “climate change study” would you settle for a 14 year old minus a 5 year old?
Thanks, Jo, Eric.
I know it is not polite to laugh at the mentally ill, but the author is not ill, just a fraud.
From the loaded questions to the treatment of the data, this is is a fraud.
That is what you get when you cover-up an initial, maybe unintentional, blunder like AGW; You end up lying, self-destroying.
[trimmed, off-subject. .mod]
Wow. Can somebody see what I am doing wrong. This is unbelievable.
Worrall tells me that Lewandowsky has made a mistake and then he steers me to a website that says with the mistake the conclusions don’t match what Lewandowsky said, and with the mistakes removed, the data matches what Lewandowsky said.
I mean really, can’t you people think for yourselves? Sheesh.
Sorry you can’t follow the article, Pippen. The rest of us seem to have no trouble with it.
Well DB. Please show me the data that indicates that Lewandowsky actually paid attention to the Paleo data at all. Because I think he removed the data and they never paid attention to it. Or he just use medians for everything so the outlier data wouldn’t affect anything.
for Pippen –
— “Age turned out not to correlate with any of the indicator variables.”
This is grossly false. It can only be made true if we include the fake data. If we remove the fake data, especially the 32,757-year-old, age correlates with most of their variables. It correlates with six of their nine conspiracy items, and with their “conspiracist ideation” combined index. It also correlates with views of vaccines – a major variable in their study. See the graph below.
I smell a rat- a setup. Devious once, twice, easily devious thrice.
How did you like my mock- serious conspiracy theory?
A suggestion: –
The results are real entries by slightly cynical respondents.
Have you ever typed in stupid answers to daft questions?
In addition if you spot a silly ever then probed to see how far it goes?
Plenty of people will refuse to answer personal questions so if there is no escape choice you get twaddle. Bank, earnings, age, gender, political party, weight, loads and loads of these.
My point is that stupidity might explain things. Sense would be excluding outliers from the computation but providing them with the data, together with the reasons why they were excluded.
Stupidity might explain the data entry mistake, but what explains the retention of said erroneous data?
Some people have a sense of humor maybe?
I would love to have a cave woman in one of my papers. One of those feisty cave liber babes, of course.
@Pippen Kool
One must have a sense of humor in order to use erroneous data?
Hmm… I don’t see that as a laughing matter.
First. Scientists have a sense of humor.
Second. If he didn’t use the data if it doesn’t matter.
Third. If he used medians it wouldn’t even affect anything.
You guys are complaining about DATA that didn’t affect the result. So deal with it.
The Pippen fool is being an enabler of bad data, by making excuses. But it’s not funny.
There is no exuse for this blunder, but even more egregious, there is NO excuse for not correcting it by now.
Pippen Kool,
The conclusions are wrong because it included a blatantly false respondent’s age. That is funny, yes.
But it is not a joke made by the author’s of the paper.
The author’s of the paper are the joke – as is the journal – and the peer reviewers.
We should learn who the peer reviewers are. They may be reviewing other papers and pushing more junk science. They may even be allowed to teach!
They should be exposed.
@Pippen
“First. Scientists have a sense of humor.”
Maybe so, but they are not supposed to be comedians.
Second. If he didn’t use the data if it doesn’t matter.
IF? He did use the data, it’s in his paper, in his spreadsheets, his conclusions.
Third. If he used medians it wouldn’t even affect anything.
IF? IF? He did use the data, it’s in his paper, in his spreadsheets, his conclusions.
Sometimes being stupid is funny, sometime not.
How should he correct the case? Leaving out this particilar answser might mean that you have to leave out a true believer of all of these conspiracies. Or filling in an age number that is kind of a normal operating procedure in climate science?p
Well, let’s look at the underaged five who replied, and the overage that replied.
Are they real?… Born to lose ….
CO2-believers aren’t real Never in a million years they are. Faith is one thing Theories of Science an other.
Return to sender every so called study of CO2-believers
until
they climed every mountain
Good luck charm is one thing, but WHERE HAVE ALL THE MONEY GONE?????
From the British Medical Journal on Wakefields Vaccine paper.
On Friday, a morning news show in Australia had some harpie going off on a tangent when talking about some seminars on vaccines causing autism to be given in Australia. She went on to say its like doubting the climate scientists. A pity someone seeking to educate the gullible was unaware that the the original Wakefield paper went through the peer review process without a hitch but failed the test of a single layman being on top of his game.
I cannot remember her name, but she is an American. There are calls for her visa to be rejected. I don’t think that is fair. I feel she should be given airtime in Aus to show how much of a loony she is. The link to autism has been repeatedly debunked. However, as climate change alarmism is rife it Aus, she will have many followers.
“The link to autism has been repeatedly debunked”
the lead author of a CDC study used to “debunk” the autism link came out a few months ago and revealed he deleted data from his study that would have shown a link, and was ashamed he did it. now if there is no link why would the CDC have to pressure the scientists to delete data that showed otherwise?
google “William Thompson” or go here:
http://www.cnn.com/2014/08/27/health/irpt-cdc-autism-vaccine-study/
“Deer shows how Wakefield altered numerous facts about the patients’ medical histories”- this statement has been shown to be bunk. there was no fraud, Deer either doesn’t understand the difference between the “red book” and the GPs notes or he twisted facts with innuendo to create a hit piece on wakefield. Lewandowsky gets published when he clearly shouldn’t because he supports the establishment position, Deer gets published when he clearly shouldn’t because he supports the establishment position. read wakefield’s heavily referenced and footnoted book to establish the facts of the matter. the lesson here is that it is good for your career if you support the establishment and bad if you don’t, pretty simple and obvious really.
I’m grateful Lewandowsky never got a degree in accounting, or in any profession where his work might have real world consequences. Seriously, what a waste of tax dollars on this clown.
For those who want to play with the data set in R — this paper might give you some guidance…
http://www.jstatsoft.org/v20/i03/paper/
Some simple stuff to play with — e.g.:
# ——————————————–
#Once you download and save the data — alter the location to read the data
# 2-Way Frequency Table
PLOSONE2013Data <- read.csv("~/Climate/Lewandowsky/PLOSONE2013Data.csv", stringsAsFactors=FALSE)
View(PLOSONE2013Data)
pl <- PLOSONE2013Data
# http://www.statmethods.net/stats/frequencies.html
pl2 <- pl[pl$age <120,]
pl2 =18,]
# 993 of 1001 rows left
attach(pl2)
mytable <- table(pl2$CseriousDamage, pl2$CYDiana) # A will be rows, B will be columns
mytable # print table
margin.table(mytable, 1) # A frequencies (summed over B)
margin.table(mytable, 2) # B frequencies (summed over A)
prop.table(mytable) # cell percentages
prop.table(mytable, 1) # row percentages
prop.table(mytable, 2) # column percentages
# http://www.statmethods.net/advstats/ca.html
# installed ca library
library(ca)
fit <- ca(mytable)
print(fit) # basic results
summary(fit) # extended results
plot(fit) # symmetric map
plot(fit, mass = TRUE, contrib = "absolute", map =
"rowgreen", arrows = c(FALSE, TRUE)) # asymmetric map
# ——————————————————
fwiw
One line came out wrong… selecting only those older than or = to 18
This line: pl2 =18,]
Don’t forget the minors included in the data. Including the two14 year olds that believed in the moon hoax conspiracy in this paper…
Minors!
“Only participants who completed all items and passed the attention-filter question were retained for analysis. Median age of respondents retained for analysis was 43.0 (Q1: 30.0, Q3: 55.0). There were 501 male and 500 female respondents. The data set is available at the first author’s webpage, http://www.cogsciwa.com“.
My father in law is 90 and now finds it a bit difficult to concentrate.
This 32,757 year old chap is doing really well………apparently he answered the attention-filter question without any problem.
“Funding: This project was supported by funds from the School of Psychology at the University of Western Australia under the auspices of the Adjunct Professor scheme. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.”
And nice to see public monies being well spent
Unfortunately the paper is successful.
As propaganda.
The errors were pointed out a year ago with no response. Asking a propagandist to correct errors is like asking beavers to stop hurting trees.
At least including a 32,757-year-old doesn’t raise any ethics rules issues. Whereas the inclusion of a 5-year-old and 6 teenagers under the age of 18 should have rung warning bells. Nice to have further evidence of how closely the UWA monitors such things…
Whether or not the minutiae of a bogus scientific claim is later corrected by genuine scientists is immaterial to the MSM. The simplistic ‘headline-grabber’ is already published and out there. And as far as the grant recipients are concerned, it’s ‘Mission Accomplished.’ Millions have swallowed the bait.
At this point, the only correction that should be applied to his work involves a pack of matches and some lighter fluid.
The errors of their ways are the means to their noble cause end.