Leif Nelson
speaker
57 appearances
2 recordings
1 series
first heard Dec 2024
last heard Jan 2025
Leif Nelson’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsNo recordings in the last 12 months.Older appearances are listed below; set an alert to hear about the next one.
Appearances
Or you run a study where there's three treatments, condition A, condition B, and condition C, but in the end you drop condition B and you don't even talk about it, you just compare A to C.
And then there are things that are mildly statistical, but in a very relaxed way. Well, we collected this data, but it's kind of skewed. It has some outliers. and you say, we should eliminate those outliers, or we should Windsorize the outliers, which is basically truncating them down to a lower high number.
Or you could run them through an algorithm where you say, oh, let's transform them with a logarithm or with a square root. And those are all decisions that are justifiable. They're not crazy. It's just, if you have a consideration of reporting one variable or the other,
and one variable makes your hypothesis look good, and the other variable makes your hypothesis look less good, you end up reporting the one that looks good, either because you're being self-serving, or honestly, because you'd say, like, I'm not sure which one is better, but my hypothesis tells me it should be the one that looks good, and that one looks good. It's probably the better measure.
And here's Simonson.
These will be things that can be as simple as a typo. where someone's writing up their report and the means are actually 5.1 and 5.12, but instead someone writes it down as 51.2. And you're like, wow, that's a huge effect, right? And no one corrects it because it's a huge effect in the direction that they were expecting. And so literally a typo might end up in print.
And that's before we get to anything like fraud, like the active fabrication of data or manipulation of data.
Yeah. Well, Stephen, you were asking a question that is pretty heavy and one that I'm not particularly well-equipped to answer. If you'd asked me five years ago, I think I would have been more refined in my answer and I would have said, no, that's not a slippery slope problem. There's a slippery slope between I collect five measures and report one versus I collect 10 measures and I report one.
That's slippery slope. But making up data feels qualitatively different. And I still largely stand by that view. But there have been enough anecdotes that other people, whistleblower types, have presented to us that sound a lot more like someone says, yeah, you know, at first you do the thing where you drop some measures or drop a condition or you remove the outliers.
And then also you take participant 35 and you change their answer from a 7 to a 9. You're like, whoa, that last one doesn't sound the same. But maybe there's some psychology for that, that it feels like it's an extension.
The very first blog post we posted was about identification of fraudulent data in a paper published 10 years ago. And that one was discovered because Yuri had made a chart for a totally different paper where he was mining data from multiple published studies to just make a chart. And I looked at his figure of this other research group's data and said, that seems unusual.
I want to go read that paper. And so I read the paper and then looked at that data set. In that one, it had collected data on a nine-point interval scale, so people can answer one, two, three, up through nine. And there were numbers in the data set that were things like negative 1.7. And so you say, oh, okay, we're done. Nothing fancy.
Once you open the data set, you can then close it and say it's broken.
Professor Gino has indicated that she has done nothing wrong. And we have said that the data in those four papers contain evidence that strongly suggests that there is fraud.
Bridging the gap between those two positions is this other entity, Harvard University. We only know what they've said outwardly, which is that they've put her on administrative leave, and they've recommended the retraction of those four papers, or the retraction of three plus an amendment to a previously retracted paper.
Certainly scary. Scary because it's so unfamiliar. I found out from talking, basically I was exchanging emails with a reporter. And so between these emails, she came back to me and was like, well, now given the lawsuit, would you like to add a new comment? And I was basically like, what, what lawsuit are you talking about?
And so it's like this devastating thing to be like, oh my God, it's like the whole house is collapsing and no one told me.
Showing 41–57 of 57 · page 3 of 3
← Previous