Friday, February 24, 2017

Friends Don't Let Friends Do Stats

A recent story by NBC News [sic]

Female Doctors Outperform Male Doctors, According to Study

Patients treated by women are less likely to die of what ails them and less likely to have to come back to the hospital for more treatment, researchers reported Monday.
If all doctors performed as well as the female physicians in the study, it would save 32,000 lives every year, the team at the Harvard School of Public Health estimated.
Thus does NBC summarize the paper "Comparison of Hospital Mortality and Readmission Rates for Medicare Patients Treated by Male vs Female Physicians" by Yusuke Tsugawa, MD, MPH, PhD; Anupam B. Jena, MD, PhD; Jose F. Figueroa, MD, MPH; et al.

(I wish I knew who Et Al. was. Gets his name on a lot of papers, it seems.)

NBC "News" tells us
“The data out there says that women physicians tend to be a little bit better at sticking to the evidence and doing the things that we know work better.”
Apparently male doctors practice medicine regardless of what the evidence dictates. Worse, they are paid more for their foolish and dangerous behavior.

Alas, Tsugawa and his co-authors did not actually measure how doctors practiced. So even if the 30-day mortality and readmission rates differed between male and female doctors, the researchers had no way of knowing why they differed; and ipso facto neither would NBC. Someone was blowing smoke because the newsmog cannot abide a story that doesn't give a paradigm-conforming reason. Sticking to the evidence? Forsooth..
Design, Setting, and Participants  We analyzed a 20% random sample of Medicare fee-for-service beneficiaries 65 years or older hospitalized with a medical condition and treated by general internists from January 1, 2011, to December 31, 2014. We examined the association between physician sex and 30-day mortality and readmission rates, adjusted for patient and physician characteristics and hospital fixed effects (effectively comparing female and male physicians within the same hospital). As a sensitivity analysis, we examined only physicians focusing on hospital care (hospitalists), among whom patients are plausibly quasi-randomized to physicians based on the physician’s specific work schedules. We also investigated whether differences in patient outcomes varied by specific condition or by underlying severity of illness.
That just sounds scientificalistic as all hell, dunnit? And hospitalists? Who knew? TOF always thought they were "doctors."
Conclusion: Patients treated by female physicians had lower 30-day mortality (adjusted mortality, 11.07% vs 11.49% …) and lower 30-day readmissions (adjusted readmissions, 15.02% vs 15.57% …) than patients cared for by male physicians, after accounting for potential confounders.
It is important to realize that the researchers were not as bold as the newsreaders. They wrote under Key Points:
Differences in practice patterns between male and female physicians, as suggested in previous studies, may have important clinical implications for patient outcomes.
TOF notes a few cautions:

Caution #1. The mortality difference was 11.1% vs. 11.5%. We caution you not to clutch your pearls too tightly over this chasm-like gap.

Caution #2. These were "adjusted percentages." That means the actual percentages were something else and the researchers tweaked the numbers to make them "all else being equal." That is, the reported %'s are the result of a model. The uncertainty of the model was not mentioned. One suspects it may have been more than 0.4%-points.

Caution #3. There were about 1,000 "all elses" that were equalized. These are called co-variates in stat-lingo. That's a heckuva lot of co-variates, leading to the possibility of multi-collinearity. This is when two or more covariates are themselved correlated with each other. If this happens, the model is over-determined and the estimates may be flawed. One is more likely to obtain an uninterpretable swamp. Did they check the Variance Inflation Factors and eliminate superfluous covariates? Inquiring minds want to know.

Caution #4. NBC simply said "patients," but the mean age of these patients was about 80 years old and the first rule of sampling is that the results cannot be generalized to populations that were not subjected to the sampling.

Caution #5. Female doctors were about 5 years younger on average, and female docs also treated many fewer patients on average than men. This implies women docs had more time per patient.

Caution #6.  The report says, “female physicians treated slightly higher proportions of female patients than male physicians did.” Since females tend to live longer than males, especially at advanced age, this would present as a higher survival rate for the patients of female doctors, not because of the doctors' skills but because of the patients' longevity. Is that the reason? TOF does not know, and neither do you or NBC.
One species of "Fake News" is when the reporter doesn't know what he's writing about, which is often the case, especially in technical subjects. The problem is that most scientific papers are wrong.
Most published scientific research papers are wrong, according to a new analysis. Assuming that the new paper is itself correct, problems with experimental and statistical methods mean that there is less than a 50% chance that the results of any randomly chosen scientific paper are true. -- New Scientist
Most clinical researchers, while experts in their fields, are not experts in statistics and tend to find significant results that aren't there, especially if they want to find them. What is almost as bad, if not worse, is when they took Intro to Stats back in college and learned a cook-book approach to "number crunching." The on-going obsession with p-values and tests of significance often overlooks two things:
  1. Statistical significance is not causal significance.
  2. Statistical significance applies to the parameters of the model, not to the actual data.
Therefore, findings from such models tend to be overconfident.

Thursday, February 23, 2017


When his step-daughter heard the news she reportedly told him, “My gosh, Harold, you’re a hero,” to which replied “No, I was a Marine.”

Last Sunday, we were having lunch with Pere at the Key City Diner, and Pere remarked that he knew exactly where he was 72 years earlier on that exact day. "I was playing in the sand," he said.

That sand was the black volcanic sand of Iwo Jima.

He used to tell my brothers and me that in the famous photo above:
I just located a good spot and said “Put it right here guys”, then moved on to give them cover.

He was just joshing us. He was elsewhere on the island at that time, but one time in the Smithsonian when the flag was on exhibit, he recalled how much it meant to the Marines on the front line to see that huge banner go up. It meant they would no longer need to worry about being shot in the back by snipers on the mountain. There was an earlier flag, he told us, but it was too small to see at a distance, so they put one up that no one could mistake. 

Here is a post from the Auld Blogge from a decade ago, with some updates and corrections.:

Thursday, February 16, 2017

The war on science continues some more: A tale of two headlines

"California Drought Is Made Worse by Global Warming, Scientists Say."  -- NYTimes Aug 2015
Global warming caused by human emissions has most likely intensified the drought in California by 15 to 20 percent, scientists said on Thursday, warning that future dry spells in the state are almost certain to be worse than this one as the world continues to heat up. . . .  The paper provides new scientific support for political leaders, including President Obama and Gov. Jerry Brown of California, who have cited human emissions and the resulting global warming as a factor in the drought.
"A Climate Change Warning for California's Dams."  -- NYTimes Feb 2017
Scientists have said for years that a warming atmosphere should lead to more intense and frequent storms in many regions. 
So the theory predicts that California will become drier and that it will become wetter. Is there nothing this theory cannot predict, at least after the fact?

The war on science continues

This study explored the gendered nature of STEM higher education institution through a feminist critical discourse analysis of STEM course syllabi from a Midwest research university. I explored STEM syllabi to understand how linguistic features such as stance and interdiscursivity are used in the syllabus and how language and discourses used in the syllabus replicate the masculine nature of STEM education. Findings suggest that the discourses identified in the syllabi reinforce traditional STEM academic roles, and that power and gender in the STEM syllabi are revealed through exploration of the themes of knowledge, learning, and the teaching and learning environment created by the language used in the syllabus. These findings inform and extend understanding of the STEM syllabus and the STEM higher education institution and lead to recommendations about how to make the STEM syllabus more inclusive for women.
No foolin'. People get degrees for stuff like this, complete with the pseudo-scientific jib-jab intended to make it seem as if the conclusions were dispassionately arrived at. But does anyone suppose the "researcher" approached the subject with no expectation of what the "findings" would be? 
Of course, the author is not in university, but in the universities School of Education, which hardly counts as such. (/snark) 
Initial exploration of the STEM syllabi in this study did not reveal overt references to gender, such as through the use of gendered pronouns. However, upon deeper review, language used in the syllabi reflects institutionalized STEM teaching practices and views about knowledge that are inherently discriminatory to women and minorities by promoting a view of knowledge as static and unchanging, a view of teaching that promotes the idea of a passive student, and by promoting a chilly climate that marginalizes women.
IOW, there was no actual sexism in the course syllabi, so we have to read "deeper" in order to discover it, because the author dang-well knows it got to be there.
Instead of promoting the idea that knowledge is constructed by the student and dynamic, subject to change as it would in a more feminist view of knowledge, the syllabi reinforce the larger male-dominant view of knowledge as one that students acquire and use make [sic] the correct decision.
The idea that objectivity and scientific rigor are somehow beyond the women (and minorities, we are assured) is the most insulting and sexist comment TOF sees in the paper! How the student constructs the knowledge of, say, topological function spaces or particle dynamics is left as an exercise to the reader. Well, if there's no such thing as objective truth, then Nelly bar the door.
What's next? Creationists get to construct their own truths about biology?  Pfui, sez TOF.

Monday, February 13, 2017

Rule of Law

PROLEGOMENON. Once upon a time, TOF noted that Jerry Falwell had accused the Inquisition of killing several millions of heretics during the Middle Ages. TOF merely observed that this now-forgotten figure would have meant the slaughter of virtually the entire population of the continent, despite the Inquisition not being present in about half the countries. (There was no Inquisition for example in England, Scandinavia, most of Germany and northern France.) Falwell's figures were therefore being used as exclamation points rather than as actual historical estimates. 

The response by far too many commentators was to accuse TOF of championing and supporting the Inquisition. It was as if some who had said "No, Hitler's minions did not kill 100 million Jews as you claim; it was closer to 6 million." And the reaction would be "So! You are defending Nazism!" 

But criticism of an argument is not a defense of the matter being argued. 

Given this caution, let us continue.  

Thursday, February 9, 2017

Fake News of the Day

NBC (and one supposes, other outlets) reports that Kellyanne Conway, apparently a flack with the current administration, committed a serious breach of ethics by endorsing a product. She is reported to have said on a TV news show, "Go buy Ivanka’s stuff!" referring to a clothing line that uses Ivanka Trump's name for marketing. Nordstrom's, which had recently dropped the line, said that their decision was a purely business decision, and this claim was repeated without being verified.

There was no mention of the vociferous boycott movement initiated late last year that targeted (among others) Nordstrom's precisely because they carried good bearing Ivanka Trump's name.…/…/14/boycott-targets-trump-retailers/

Noting the propensity of news shows to quote only isolated sentences or even one or two words, clipped and pruned, and often distracted by graphics-in-motion on the screen, it may be useful to look at Conway's entire statement. Finding people who speak in whole paragraphs is unusual enough, since thoughts are carried in paragraphs, not in individual words, that we should treasure the occasion. TV news evidently prefers the micro-sound bite because it leaves more time for shampoo commercials and other important stuff.

In the interview, Conway said in response to Nordstrom's action:
“I do find it ironic that you have got some executives all over the internet bragging about what they have done to her and her line, and yet, they are using the most prominent woman in Donald Trump’s, you know, most prominent his daughter, using her, who has been a champion for women empowerment of women in the workplace, to get to him. I think people could see through that. Go buy Ivanka’s stuff! I hate shopping, and I will go get some myself today.”
This sounds a bit different than a product endorsement. It sounds more like a defiance of the calls to boycott someone's wares because of what someone else (her father) has said or done.

New Story from Michael F. Flynn

 Greetings All.    Mike (Dad) has a new story in the July/August edition of Analog . I know Analog is available on Kindle store and Analog ...