Previous Month | RSS/XML | Current | Next Month

WEBLOG

July 31st, 2024 (Permalink)

Common Misinformation & Slouching Towards Disaster

Things fall apart; the centre cannot hold;
Mere anarchy is loosed upon the world¹

The following selection was published after the debate but before the assassination attempt.
• Timur Kuran, "How 'Misinformation' Becomes Common Knowledge", The Free Press, 7/2/2024

  How did something considered misinformation on Thursday afternoon become common knowledge by Thursday night? The social mechanism that converts supposed misinformation into consensus…involves something ubiquitous: the twin acts of misrepresenting what we know and what we want under perceived social pressures. …[S]uch expressions of insincerity can do serious harm. The Biden-Trump debate and its aftermath provide a powerful case in point. …

  Until [last month]'s CNN debate, a majority of Democrats were afraid to tell a basic truth in public―to say openly what they know about Joe Biden's physical and mental health―for fear of emboldening Donald Trump or taking a position that may seem adverse to their party. So they kept their knowledge of his declining cognitive abilities private and, in public, conveyed impressions and issued reports at odds with their own senses. If they felt that a different candidate had a higher chance of beating Trump, with rare exception they kept that preference hidden and pretended to agree with the idea, repeated ad infinitum, that Biden remained the party's best hope.

  Why did they do this? Fear. Fear, in this case, of being punished by their fellow Democrats. Fear of being punished by a crowd is not unique to Democrats, or liberals, or Americans. It is an innate human response to the dangers of being ostracized, to being cut off from friendships and privileges that are critical to survival. We are born with a need for social acceptance. That need is what drives knowledge falsification and preference falsification.

  Each of these―misrepresenting what you know and what you prefer―is a special form of lying. Most "in the know" Democrats engaged in both over the past few years: knowledge falsification about Biden's decline and preference falsification about whether he should be the party's nominee.

  So even as hardly a day passed without new video clips showing a disoriented and frail Biden, Democrats, aided by swaths of left-leaning media, rushed to dismiss the clips as taken out of context, or as misleading because of the cameraman's perspective, or as malicious misinformation. They would also vilify the producers and spreaders of the videos as MAGA villains out to destroy democracy. In no uncertain terms, qualms about Biden's age or cognitive capacity were treated as unwelcome, even as a betrayal of democracy itself.

  Some inside politics about the problems facing the Democrats in replacing Biden here omitted since that's now a done deal.

  And so, for the first half of 2024, the majority of Democrats who favored Biden's retirement kept their preferences private. As signs of Biden's diminished mental acuity mounted, knowledge and preference falsification trapped Democratic elites. Though [a] few implored Biden to step aside in the months and weeks before the CNN debate, Democratic officeholders and an overwhelming majority of Democratic journalists maintained a facade of unity. To individual doubters, this unity posed an insurmountable obstacle to speaking truthfully. It meant that they were likely to face accusations of betrayal alone, possibly even without backing from friends. Although the private doubters of nominating Biden may have had the edge numerically against his genuine supporters, the doubters had no way to mobilize. Because they kept their private truths hidden, they could not even find each other, much less coordinate their actions and form an effective anti-Biden coalition.

  Knowledge and preference falsification can do far more damage than mere self-censorship. In this case, Democrats close to Biden, and thereby "in the know," deliberately misled their fellow Democrats into thinking that chatter about Biden's deterioration was merely propaganda orchestrated by Republicans and their allies. They circulated cherry-picked videos of choreographed events as ostensible proof that Biden was as sharp as ever. In March, they proclaimed that Biden's State of the Union address, in which he read a prepared speech from a teleprompter, should put to rest questions about his fitness.

  Knowledge and preference falsification pollute the bodies of information that individuals use in developing their understandings of the world and their rankings among options. They misinform the polity about what is known and preferred. They conceal feasible options. They obscure the extent of support for changing direction. In fostering a culture of mendacity, they hinder the identification of discontent and compound the difficulties of forming coalitions among people eager to switch course.

  The self-imposed Democratic trap shattered in the first few minutes of the CNN debate. … As Biden spoke incoherently, his debility became common knowledge. Suddenly everyone knew―and everyone knew that everyone knew. Because tens of millions of Americans were watching, every viewer understood that all other viewers, whatever their political biases, were witnessing the same thing. No amount of spin could overcome what we were seeing with our own eyes. …

  It may have made all the difference that a huge national audience watched the debate live. If the debate had not been televised, with only the press witnessing it, reporters might have been able to spin the exchange as a win for Biden by focusing on Trump's wild exaggerations and his non-answers, along with some Biden mini-quotes that seem coherent on paper. In other words, the out-in-the-open, live nature of the debate may have been critical to generating the common knowledge of Biden's current state.

  One thing is certain: the discovery by Democratic elites of Biden's deterioration on Thursday night was mostly feigned. Individually and collectively, they chose not to convey truthfully what they knew or what decisions they considered necessary for electoral success. They knew. But like many human beings faced with the consequences of telling the truth, they opted to misinform.

  I think that Kuran overestimates the amount of lying to others and underestimates the amount of lying to oneself that occurred. One reason the debate was shocking for so many Democrats is that they had managed to convince themselves that there was nothing wrong with the president. If people in Biden's inner circle realized the extent of his decline, why in the world did they ask for and agree to this "self-imposed Democratic trap"? Why not refuse all offers to debate? I was surprised that the Biden campaign agreed to debate at all when some prominent Democrats were calling on the president to refuse to do so².

  There were many excuses that Biden could have invoked to evade the debates, including that it was beneath the president's dignity to debate a convicted felon. Of course, the Democrats would have faced some criticism for refusing to debate, but it would have been far less than they faced afterwards, and probably would not have included forcing Biden to drop out of the race.

  I can think of only two reasons why those in the Biden campaign instead agreed to this suicide mission of a debate: they genuinely thought that Biden could pull it off, or they were intentionally sabotaging their own campaign. While it's possible that the debate was the result of a successful internal effort to force Biden out of the campaign, it seems more likely that they really believed he could do it. Never underestimate the power of self-deception.

  ---

• James B. Meigs, "How the Secret Service Failed", City Journal, 7/19/2024

  It took only minutes for conspiracy theories to start flooding social media when news broke on July 13 that a sniper had almost assassinated former president Donald Trump. Some conservatives asked whether U.S. Secret Service agents assigned to the Butler, Pennsylvania, campaign rally were actually plotting Trump's demise. Left-leaning partisans suspected the shooting was somehow faked to garner sympathy for the candidate. According to the media monitoring site NewsGuard, appearances of the words "inside job" and "staged" surged more than 3,000 percent on the X platform immediately after the shooting.

  It's easy to understand why the public seeks more compelling narratives to explain this shocking event. The facts known so far are hard to accept…. Every aspect of the Secret Service's catastrophic failure on July 13 should be investigated by Congress, by independent researchers, and, one hopes, by a nonpartisan commission of the type that investigated the 1979 Three Mile Island nuclear meltdown and the 1986 space shuttle Challenger disaster. Investigators should keep open minds regarding even the most outré theories; almost anything is possible, after all. But I suspect the answers uncovered by an honest inquiry will strike many as surprisingly―even unbelievably―mundane. That's the upshot of most disaster investigations: rather than discovering intricate plots or amoral villains, investigators usually find simple mistakes made by ordinary people who've been numbed by routine and blinded by all-too-human cognitive biases. …

  We usually assume that big disasters are caused either by massive mechanical breakdowns or by some sort of deliberate recklessness―even malfeasance―on the part of those involved. (Conspiracy theories fall in that latter category.) …

  A rule of thumb behind many conspiracy theories is that big effects require big causes, so people are reluctant to believe that a lone loser could assassinate a president of the United States or almost assassinate a former president. However, it's common knowledge that big effects are often the result of small causes, which is the basis for the old poem:

  For want of a nail a shoe was lost,
  For want of a shoe a horse was lost,
  For want of a horse a rider was lost,
  For want of a rider a message was lost,
  For want of a message a battle was lost,
  For want of a battle a war was lost,
  For want of a war a kingdom was lost,
  All for want of a horseshoe nail.³

  Back to the reading:

  In the hours and minutes before an organization falls into chaos…the managers and workers involved don't usually think they are flouting rules or courting disaster. They assume that they are following routine procedures. And they are as shocked as the rest of us when everything falls apart. Such disasters are also typically a long time in coming. Researchers find that over time, even high-performance organizations such as NASA gradually cut corners, take on greater risks, and allow workers to grow complacent. When disaster strikes such organizations, it isn't usually because of a single spectacular mistake but rather a long series of small decisions that progressively shaved safety margins and dulled alertness.

  In other words, the straws built up until the final straw "broke the camel's back".

  Was that the case with the Secret Service's failure to protect Trump? It's too soon to say. But congressional investigators would be wise to keep the lessons of disaster science in mind. … It is important to identify failures of top leadership as well as any dereliction of duty on the part of agents at the rally. But if we hope to restore the USSS to competence, it is not enough to single out wrongdoers in this incident; we also need to understand the institutional pressures that have degraded the once-venerated agency's effectiveness. …Congress should not fall into the trap of thinking that firing a few lax performers will fix the problems at the USSS. …

  "Disaster science" is a bad name for this area of study since it encourages paying attention only to those case when something goes badly wrong. The focus on disasters is understandable because disasters are expensive, both in loss of human life and other valuables. However, the difference between a disaster, a near disaster, and a success is often a matter of luck rather than conduct. The assassination attempt on Trump was, in fact, a near disaster rather than a disaster, as it could easily have been much worse. It was sheer good luck that Trump turned his head at the right moment and the bullet clipped his ear rather than killed him; but it may have been sheer bad luck that there was a bullet there to clip his ear.

  It's important to study near disasters in order to understand why disasters happen, and it's even worth studying successes since a history of many past successes may lead to a complacency that contributes to disaster. How many rallies has Trump had over the past several years without any problems? I don't know, but it must be scores, even hundreds.

  Here are some questions Congress and other investigators should ask.

  How unusual were the decisions made on July 13? For outside observers, the poor decisions and lack of urgency that USSS agents on the scene showed seem inexplicable. … Congress should seek records from other campaign events to see whether such lax practices have in fact become more commonplace. …

  What competing goals might have undermined the agency's focus? …[T]he purpose of the agency is to protect key politicians, not to advance other social goals.

  More broadly, is the Secret Service spread too thin? … In any high-risk field, having too many conflicting priorities can undermine attentiveness.

  Is the Secret Service ignoring the "weak signals" of trouble? … [F]or years the Secret Service has sent out its own weak signals―and not-so-weak signals―that its operations are sloppy and undisciplined. … No doubt, most USSS agents are dedicated professionals. But the agency as a whole appears to be anything but a High Reliability Organization. Congress should demand a new approach.

  Why are Secret Service operations so disorganized? Conspiracy theorists say that it is not credible that Secret Service agents and local law enforcement officers made so many maddening mistakes on July 13. (And certainly, the possibility that they were merely following instructions must be explored.) But it is more likely that the loose organization and poor communications seen that day are typical for the agency. Many post-disaster investigations show that the organizational problems leading to a particular deadly incident had been present for years―but noticed only when the catastrophe finally occurred. Congress should explore whether that was the case in Butler. …

  Also, previous rallies in which no assassination attempt occurred should be compared to this one: were there differences between those events and this one other than the fact that in this one a wannabe assassin showed up? It may well be that the only reason Trump wasn't shot earlier is that no one tried. If there are other differences, did they make the difference between successful protection and a near assassination?

  These are some of the questions Monday's House Oversight Committee hearing should ask. And more far-reaching investigations should follow. Their findings will be crucial to reforming the Secret Service, an agency that had run off-track long before July 13. And a better understanding of that day's events might even help put some conspiracy theories to rest. In the end, of course, the best way for federal officials to counter conspiracy theories is to be competent at their core jobs.

---

Notes:

1. William Butler Yeats, "The Second Coming", The Poetry Foundation (1920)
2. For a couple of examples, see: Bryan Metzger, "Top Democratic senator says Biden should 'think twice' before agreeing to debate Trump: 'It's just an opportunity for him to display his extremism'", Business Insider, 1/8/2024
3. This is a traditional poem whose author is unknown, and you'll see shorter versions of it, but I prefer this longer version.

---

Disclaimer: I don't necessarily agree with everything in these articles, but I think they're worth reading as a whole. In abridging them, I've sometimes changed the paragraphing.

---

July 24th, 2024 (Permalink)

Health News Headlines May Increase Risk of Death

Here's the headline and first sentence of a recent article in Newsweek magazine:

Common Snack Foods May Increase Risk of Death

Eating a diet rich in ultra-processed foods may increase your risk of dying by 10 percent, new research suggests.¹

There are three problems with this headline. First, there's the hedging word "may", which signals that the evidence for the headline claim is weak.

Forbes magazine has a similar headline but with a different hedge:

High Consumption Of Ultra-Processed Foods Linked To Greater Mortality Risk²

"Link" is a word, along with "association", that is used to indicate a statistical correlation between two events; in this case, high consumption of "ultra-processed foods"―whatever those are―and death. However, a correlation is very weak evidence of causation, since many things are correlated that are not causally related.

In addition to the hedging, there's a second issue: both "increase" and "greater" are dangling comparatives³. "Greater" than what? "Increase" from what? You might well think that these headlines mean that if you eat these "ultra-processed foods"―that is, junk food―your risk of death will increase. But, as we will see, the study actually compared two different groups of people.

In addition to being a dangling comparative, "increase" is a causal word meaning that eating junk food causes a rise in mortality risk. However, the word "link" in the headline warns us that the evidence is a correlation, not causation.

The third and final issue is that we're all going to die, so the risk of death is 100%. Does Newsweek contend that if you eat junk food your risk of dying will rise to 110%? The meaningless claim that some bad thing "increases the risk of dying" is a common one in health news headlines; for example, here's one from the Today show from earlier this year:

Sitting all day increases risk of death.…⁴

So, if you sit all day eating ultra-processed foods, you're doomed.

Unsurprisingly, both of the above articles were based on a press release with the following headline:

Intake of ultra-processed foods linked with increased risk of death⁵

So, you really can't blame the reporters for using "linked" or "increased risk of death". Instead, you may be disappointed that whoever writes press releases for the American Society for Nutrition, which put out this news release, is as innumerate as the editors at news magazines.

Let's turn now to the release itself to see how afraid of dying from eating junk food we should be. The first paragraph reads: "In a new study, older adults who reported consuming higher amounts of ultra-processed foods…were about 10% more likely to die over a median follow-up of 23 years compared with those who consumed less processed food." That is, the higher risk of death was not a lifetime risk―which is 100%―but a risk over the follow-up period.

So, "ten percent" was not an increase at all, since an increase would mean that the risk rose over the course of the study. Rather, it is the result of a comparison between two groups: "The researchers analyzed overall rates of death among those who were in the 90th percentile for consumption of ultra-processed foods at baseline versus those in the 10th percentile…." The 90th percentile means those who consume more junk food than 90% of those studied, whereas the 10th percentile are those whose consumption was lower than 90%. What about the rest of us who eat diets somewhere between these two extremes?

While the researchers controlled for obesity, smoking, and some other variables, there are surely many differences between the junk food junkies in the 90th percentile and the health food nuts in the 10th percentile. Perhaps the former are generally careless about their health, whereas the latter are extremely conscientious hypochondriacs. In any case, it's not obvious what relevance this study has to anyone who falls in neither of these two groups, and that's most of us.

Finally, do health news headlines really increase your risk of dying? The fact is that there's just about as much evidence that they do as that eating a lot of junk food will do so⁶. Perhaps the Surgeon General should require warnings on all such articles: "Reading health news articles can be hazardous to your health."

---

Notes:

1. Pandora Dewan, "Common Snack Foods May Increase Risk of Death", Newsweek, 7/2/2024
2. Anuradha Varanasi, "High Consumption Of Ultra-Processed Foods Linked To Greater Mortality Risk", Forbes, 7/12/2024
3. See: Dangling Comparative, 10/16/2023
4. Caroline Kee, "Sitting all day increases risk of death. These exercises can help reduce harm", Today, 2/6/2024
5. "Intake of ultra-processed foods linked with increased risk of death", EurekAlert!, 6/30/2024
6. See: Ben Schiller, "Consuming Health-Related News Could Make You Sick (If You Believe It)", Co.Exist. This is the Internet Archive copy of the article from 6/11/2013; the article itself appears to be no longer online.

---

July 13th, 2024 (Permalink)

Wet or Whet?

While I was in Phnom Penh, some time in 1988, a senior official told me that in order to guarantee my next visa, I should avoid writing about the ruling party, the Cambodian People's Revolutionary Party, and about military matters. I guess it was enough to wet my appetite.¹

"To wet" is a familiar verb meaning to make something moist with water or some other liquid, and "wet" is also the related adjective for the resulting state of the wetted object². "To whet", in contrast, is a less familiar verb meaning to make something sharper³, and the adjective for the result of whetting is the past participle "whetted". Both "wet" and "whet" are pronounced the same, though one might put a bit more breath behind the "w" in "whet".

Nowadays, "whet" most often occurs in the idiom "to whet one's appetite", meaning to increase it. Because "wet" and "whet" are pronounced the same, those who have only heard the phrase and never seen it written down are likely to spell it "wet". They also have a handy folk explanation of its meaning available, because when the appetite increases, the mouth produces saliva making it wet. They may think that "wetting your appetite" means making your mouth water, though it's your mouth and not your appetite that gets wet.

In contrast, "whetting" your appetite means to make it keener, as if it were a knife stabbing you in the stomach. Of course, an appetite is not the sort of thing that can literally be sharpened, but an intense hunger may feel like the stab of a knife in the stomach, and the stronger the appetite the "sharper" that metaphorical stab. This metaphor goes back at least to the 17th century⁴, whereas the more recent one involving wetness of the mouth appears to be an ad hoc explanation for a simple misspelling.

The only reference book I've found that lists "wet the appetite" as a mistake is Bill Bryson's⁵. Maybe the phrase has become so frequent that it's no longer considered an error by lexicographers, which is one of the dangers of "descriptive" lexicography, namely, that a sufficiently frequent "error" becomes linguistic change.

I tried the sentence "When I eat out, I start with an appetizer to wet my appetite" in several free online spelling and grammar checking programs, and none flagged "wet" as an error. So, here's a spelling mistake that your computer's spelling checker is not likely to catch, and that's exactly the type of error you should add to your mental spell-checker.

---

Notes:

1. Jacques Bekaert, Cambodian Diary: Tales of a Divided Nation, 1983-1986 (1997), p. 3.
2. "Wet", Cambridge Dictionary, accessed: 7/12/2024.
3. "Whet", Cambridge Dictionary, accessed: 7/12/2024.
4. Gary Martin, "Whet your appetite", Phrase Finder, accessed: 7/13/2024.
5. Bill Bryson, Bryson's Dictionary of Troublesome Words: A Writer's Guide to Getting it Right (2002), under "whet one's appetite."

---

July 8th, 2024 (Permalink)

The Trump Bump

In the entry after last month's presidential debate I said that I expected polls taken afterwards to show a "Trump bump", and also possibly a bump for independent candidate Robert F. Kennedy, Jr.¹ So, in this entry I'm going to examine those national polls taken after the debate to see the size of the bumps if any received by both Trump and RFK, Jr.

First of all, some polls are only head-to-head match-ups between Trump and Biden, which won't tell us anything about RFK, Jr.'s support, so let's look at them first. I count eleven such polls taken since the debate², all but one of which show Trump ahead, and the average Trump lead is a bit more than three percentage points³. However, that's not the bump.

The bump is not measured by how much Trump is ahead in the polls, but by how much Trump's percentage increased after the debate. For comparison purposes, I looked at the eleven most-recent national polls finished prior to the debate⁴, and Trump had an average lead in those of 1.5 percentage points. Since Trump's average lead increased to a little over three points, that means the bump was only about 1.5-2 points, which is not too impressive.

Moreover, Trump's lead is barely significant at the three percentage point margin of error typical of most national polls. However, what should be worrying Democrats most is that none of these polls show Biden ahead, and Trump's lead ranges from zero―in the one tie―to six points. So, even though Trump's lead may be small, it's highly unlikely that it's the result of sampling error, since the error would have to be in the same direction in ten out of eleven polls.

Turning now to those polls that include RFK, Jr., I count nine national post-debate polls that include him among the candidates, with his percentages ranging from a low of five to a high of sixteen points⁵, averaging slightly over ten. In only one of them did he poll high enough to qualify for the second debate, but the pollster―Forbes/HarrisX―is not one of those listed by CNN as acceptable to qualify for last month's debate⁶ and, presumably, the September debate⁷.

Again, RFK, Jr.'s bump, if any, is the difference between his current average and his pre-poll average. Looking at the seven most recent polls that included him and were released prior to the debate⁴, his average was a little less than eight percentage points. So, his bump was about the same as Trump's, and not big enough to get him over the hump and into the last debate. However, there's a little over two months before that debate, so it's still possible that his polling may yet exceed 15% in four approved polls.

I still suspect that the September debate will be cancelled, at least if Joe Biden is the Democratic nominee.

---

Notes:

1. After the Debate, 6/29/2024. See: "The Second Debate".
2. "2024 General Election: Trump vs. Biden", Real Clear Polling, accessed: 7/6/2024. The Morning Consult has, amazingly, had two polls since the debate, so I'm only counting the most recent one.
3. This is RCP's current average of the most recent polls. I don't know why RCP averages only eleven polls, but that so happens to be the number so far after the debate, omitting the earliest Morning Consult one, as explained in the previous note.
4. When there were multiple polls by the same organization, I included only the most recent one.
5. "Presidential General Election Polls 2024", Real Clear Polling, accessed: 7/7/2024.
6. Michael Williams, "Here's what it takes to qualify for the June 27 CNN presidential debate", CNN, 5/16/2024.
7. Ivan Pereira, "Next Biden-Trump presidential debate will be in September on ABC", ABC News, 6/27/2024. This is the most recent article I could find on the second debate from ABC, but it's completely uninformative on the qualification rules.

---

July 1st, 2024 (Permalink)

Child's Play?

A stack of children's blocks is on a table. These blocks are cubes of solid wood painted a single, solid color: blue, red, green, yellow, etc. You don't know how many blocks are in the stack except that there are at least three. The top block in the stack is painted green, whereas the block at the bottom of the stack is yellow, but you don't know the color of any of the blocks in the middle.

So, here's the problem: Is a green block on top of a non-green block in the stack? Non-green, of course, is any of the other colors: blue, red, yellow, orange, etc. By "on top of" I mean that one block rests on the top of the other, touching it, and not simply above it.

Hint 1

Hint 2

Solution

---

Previous Month | RSS/XML | Current | Next Month