Readers will know I am not a fan of Donald Trump for a variety of reasons, like him constantly saying things which aren't true. That he was elected as president obviously bothers me. I've been trying not to talk about that though. The point of this site is ultimately to explore my belief the world is insane, but Trump's election is too obvious an example.
Still, I can resist only so much. It would be fun to talk about how Trump managed to issue an executive order in a more incompetent manner than has ever been seen before. It would be fun to talk about how Trump claims the cancellation of his meeting with the President of Mexico was mutual because on Twitter he said:
And the guy responded by canceling the meeting. I mean, not only is that an incredibly strained definition of "mutual," it is hard to resist talking about how Trump apparently thinks he negotiated this cancelation via Twitter. Still, I managed. I managed right up until I saw this tweet:
I had to check for myself because that seemed too funny. How could the government fail to include one of its three branches on its White House website? I don't have an answer for that, but I can confirm it is true. The judicial branch no longer has a web page on the White House website.
I've chosen to not get involved in discussions of the current Syrian civil war. Unfortuantely, I am exposed to theses discussions anyway because of the people around me. Normally, I just ignore it. However, sometimes something comes up that I cannot ignore. One examplel is this tweet I came across earlier today:
This tweet includes a screenshot from a piece written by a Nassim Taleb. I've seen his name name has come up in some discussions, but I know almost nothing about him. All I do know is his reporting shown in that screenshot:
Note 2. Recall that I am a statistician. When I took a look at the statistics of the conflicts, most appear to be fabrications inflated by Qatari-funded think tanks and their useful idiots?—?by a mechanism the Indians call “Salma told Sabrina”. For instance, we know that Hama’s toll was not the 30–40,000 people report but the only real evidence is closer to 2,000.
Is wrong and should not be taken seriously. Given Taleb is downplaying a massacre, I thought I'd write a short post about this. Because, you know, downplaying massacres is a bad thing.
I've owed you guys a post for a little while now, and I apologize for how long it's taken. I just can't get past a certain problem. As you may recall, I recently discussed how "correlation is meaningless" in relation to a paper which claimed to demonstrate climate change "deniers" possess certain characteristics. For a quick refresher:
The reason the authors can claim there is a "statistically significant" correlation between these two traits is they collected almost no data from anyone who "denies" climate change. The approach the authors have taken is to draw a line through their data, which is how you normally calculate the relationship between two variables, then extrapolate it out far beyond where their data extends.
There are a lot of ways of describing this approach. When I've previously said correlation is meaningless, I used an example in which I demonstrated a "statistically significant" correlation between belief in global warming and support for genocide. It was completely bogus. I was able to do it because I used the same approach the authors used. Namely:
1) Collect data for any group of people.
2) Determine views that group holds.
3) Find a group which is "opposite" the group you study.
4) Assume they must hold the opposite view of the group you studied on every issue.
This will work with literally any subject and any group of people. You can reach basically any conclusion you want because this approach doesn't require you have any data for the group of people you're drawing conclusions about.
Today I want to move beyond simple correlation coefficients and get into some of the more complex modeling the authors performed. There's a problem though. You see, the results the authors published are impossible to achieve.
I've mostly recovered from a recent illness, and I've working on a new post in line with what I've been discussing recently. I'm still a bit tired though. As such, rather than worry about technical discussions, I wanted to ask a question. John Cook is the proprietor of the Skeptical Science website. Here is a picture of him:
For the last few years, this picture has bugged me. Every time I saw a picture of Cook, I felt like I had seen it him somewhere before. Today, I finally realized why he seemed so familiar. It might be silly/crazy, but... doesn't he kind of look like Donny Osmond?
I'm a bit under the weather so my activity is limited, but I couldn't resist a recent story. Yesterday, I saw a lady named Monica Crowley has said she won't take a job offered by President Elect Donald Trump. The reason is it was recently discovered Crowley was guilty of a significant amount of plagiarism, both in her PhD dissertation and a book she wrote. If you want details, it is easy to find any number of news stories about this.
I don't really care about that. I get plagiarism is bad, and I understand why it would lead to Crowley backing out of a government job. What I don't get is why nobody seems to be talking about the rather coincidental timing of Crowley announcing her decision not to take this job. If you didn't know, yesterday was Martin Luther King Jr. Day.
And if you don't know why that matters, well, Martin Luther King Jr. was a cheat. He only got his PhD due to a massive amount of plagiarism. Not only was a approximately a third of his PhD dissertation copied from other sources, but King resorted to plagiarism in many of his other papers. For his dissertation, King borrowed especially heavily from a previous graduate student's dissertation. He even had the audacity to praise the dissertation he plagiarized in his own dissertation! to make things even stranger, that student, Jack Boozer, had the same graduate adviser as King. It's remarkable King's adviser didn't notice one of his students copied thousands of words written by another of his students.
There's a lot more to both plagiarism stories, but the details aren't important. Martin Luther King Jr. is celebrated as a hero with most people not knowing, much less caring, about him cheating many times and to significant extents. Now, even as he's celebrated, a person is being shamed out of a job in the new president's administration due to plagiarism.
So remember folks, plagiarism is bad. Sort of.
I had planned to upload a post today continuing my discussion of the misuse and abuse of statistics to claim to prove groups of people possess certain traits. I'm scrapping that plan though. My head has been killing me the last few days. That makes it too difficult for me to try to explain issues involving multivariate regressions in a clear manner.
Instead, I'd like to discuss something simpler. You may know I hold a rather negative view of the recent rise in "fact checkers" as I view what they publish as usually being little more than op-eds using the fig leaf of "fact checking" to try to gain more credibility than they deserve. Yesterday, I came across a piece discussing that via this tweet:
I know Jose Duarte a bit due to his criticisms of certain papers used in the global warming debate. Given I knew he and I share some views, I was curious to see he had to say about "fact checking." Unfortunately, what he said is quite wrong.
I've written a post titled, "Correlation is Meaningless" once before. It makes the same basic point I made in a recent post discussing the PhD dissertation by one Kirsti Jylhä. I'm going to continue my discussion of Jylha's work today to examine more of a phenomenon where people misuse simple statistics to come up with all sorts of bogus results. In Jylha's case, it undercuts much of the value of her PhD.
My last post highlighted a strange aspect of discussion of recent claims of Russian involvement in cyberattacks against the Demoncratic National Committee (DNC), the governing body of the United States Democratic party. Namely, a government report detailing aspects of the attacks has been misinterpreted/misrepresented as intending to provide evidence of Russian involvement when in reality it is merely discussing details of the nature of the attacks.
This misinterpretation has many causes, but one important aspect is report has been disseminated with text like:
On October 7, 2016, the Department Of Homeland Security (DHS) and the Office of the Director of National Intelligence (DNI) issued a joint statement on election security compromises. DHS has released a Joint Analysis Report (JAR) attributing those compromises to Russian malicious cyber activity, designated as GRIZZLY STEPPE.
The JAR package offers technical details regarding the tools and infrastructure used by Russian civilian and military intelligence services (RIS).
The first paragraph attributes the attacks to Russian activity, but the next paragraph does not follow up on that point. It merely refers to "technical details regarding the tools and infrastructure used by" Russians. A person might be forgiven for thinking this has some connection to the case in the former paragraph, but it is in fact a different issue.
This report does contain attribution of Russian involvement, but it does not claim to offer evidence to support that attribution. This is fundamental point has escaped most people discussing the report. Today, I'd like to highlight some of the resulting misinformkation.
Happy New Year everybody!
With it being New Year's Eve, I didn't intend to write any posts. I've started my annual funeral pyre for the year since passed, and I plan on sitting outside and enjoying it for the evening. That'll be followed by celebrations and gatherings tomorrow. I hope you guys have plans you'll enjoy as much.
A couple months ago I contacted a scientist asking to examine the data used in three papers which made up the bulk of her PhD dissertation. The initial response contained this:
Thank you very much for your email and interest in our publications.
We follow ethical guidelines from the American Psychological Association, and we are happy to share our data to other competent researchers. Would you please indicate your background and outline how you plan to use the data?
Which struck me as odd as I have no idea how one would determine which people are "competent researchers." I was pessimistic about this response as it seemed like this might be used as an excuse for not sharing data with me, but fortunately, the issue of whether or not I am a "competent" researcher never came up again.
After examining the data for these three papers, I came to the conclusion the papers were fundamentally flawed in a way which invalidated their analysis and conclusions. I informed the author of this thesis of my concerns and tried to give her time to examine the issue privately. I believe several months was long enough so now I'd like to discuss the matter in public. Hopefully, this will demonstrate I am in fact competent.