Log inSign up
Image
user avatar
Quentin André
@andre_quentin
Assistant Prof. of Marketing @ CU Boulder. Open science, research methods, managerial and numerical cognition. ❤️Python 🐍.
Boulder, CO
quentinandre.net
Joined May 2014
755
Following
2,025
Followers
  • Pinned
    user avatar
    Quentin André
    @andre_quentin
    Mar 27, 2024
    Woke up to the good news that our paper (w/ @nreinholtz) on group sequential designs is accepted at @JCRNEWS ! Want to learn more about designing more efficient and more informative studies? This blog post summarizes the key insights from our paper: quentinandre.net/post/more-effi…
    35K
  • user avatar
    Quentin André
    @andre_quentin
    Apr 24, 2024
    Hate to be *this* guy, but the p-values associated with these outcomes are p = .044, p = .011, p = .008, p = .076, p = .067, p = .094, p = .058, p = .039, p = .064, p = .05, p = .067, p = .014. These results are interesting, but need replicating.
    user avatar
    Derek Thompson
    @DKThomp
    Apr 24, 2024
    New paper from Norway: Banning smartphones in school - significantly decreased doctors visits for psychological symptoms and diseases among girls - reduced bullying among both genders - improved girls’ GPA and attendance rates - largest effect sizes were among the poorest kids
    Image
    152K
  • user avatar
    Quentin André
    @andre_quentin
    May 8, 2020
    Hot take: Open science is not easy. Writing codebooks, documenting code, describing experimental procedures, maintaining a repository takes time and effort. If we want open-science to become mainstream, this investment must be encouraged (rewarded) by institutions and journals.
  • user avatar
    Quentin André
    @andre_quentin
    Jun 2, 2021
    Happy and excited to see this article appear online! I hope it will help correct common misconceptions in how outliers should be removed, and ultimately lead to lower false-positive rates in the literature. doi.org/10.1037/xge000…
    A picture of the abstract of the paper "Outlier Exclusion Procedures Must Be Blind to the Researcher's Hypothesis"
  • user avatar
    Quentin André
    @andre_quentin
    May 29, 2024
    Yeah, why would people commit unethical acts that 1) give you a disproportionately large advantage, are 2) hard to detect and 3) even harder to punish, and 4) that even if caught and punishef, will almost certainly not lead you go to jail or pay fines? It's a mystery.
    user avatar
    Jay Van Bavel, PhD
    @jayvanbavel
    May 29, 2024
    I have such a hard time understanding why people commit scientific fraud. I mean, if you want to commit white collar fraud why would you spend 6 years in grad school, another 2 years as a postdoc, and then go on the tenure track all in the faint hope that your fraud can get a
    22K
  • user avatar
    Quentin André
    @andre_quentin
    Aug 16, 2023
    Uri, Joe and Leif have done the field an immense service by calling out fraud in Gino's work. Now they need our help to fight this outrageous lawsuit. I have chipped in $1,000: Match me if you can. Otherwise every dollar helps!
    Image
    Donate to Support Data Colada's Legal Defense, organized by Simine Vazire
    From gofundme.com
    95K
  • user avatar
    Quentin André
    @andre_quentin
    Oct 17, 2023
    Funnel plots are a useful (depressing?) tool to assess the number of fraudulent/confounded studies in a literature. Preregistered studies of money priming suggest an effect size indistinguishable from zero (doi.org/10.1037/xge000…). How did many studies find g > 1, p < .001?
    Image
    88K
  • user avatar
    Quentin André
    @andre_quentin
    Jun 18, 2023
    Fraud isn't just "people getting publications they don't deserve". It's inflicting invisible, but very real, damage on all the researchers who try to replicate and extent fake papers.
    This Post is from an account that no longer exists. Learn more
    63K
  • user avatar
    Quentin André
    @andre_quentin
    Aug 18, 2022
    New blog post: Can the p-values in a paper all be close to .05 because the researchers have conducted a careful power analysis, and have collected "just enough" participants to get significant results? Not really! Here's why: quentinandre.net/post/large-pva…
  • user avatar
    Quentin André
    @andre_quentin
    Apr 6, 2022
    New blog post on effect sizes: What they are, what we can learn from them, and how we can use them to judge the trustworthiness of research findings! 1/N quentinandre.net/post/a-critica…
  • user avatar
    Quentin André
    @andre_quentin
    Aug 3, 2023
    Our community needs to show unwavering support to Uri, Joe and Leif. Read the blog posts again: There was absolutely nothing personal or defamatory in there. If scientists can be sued for *documenting factual evidence of fraud in datasets*, all is lost for scientific criticism.
    15K
  • user avatar
    Quentin André
    @andre_quentin
    Sep 9, 2023
    Some unsolicited advice after attempting to reproduce the results of 25 marketing papers from their OSF: 1. Rename your variables in Qualtrics! There's absolutely no reason why the variables in your dataset should be named Q.1 through Q.93. It is confusing and error prone.
    28K
  • user avatar
    Quentin André
    @andre_quentin
    Oct 4, 2023
    You also know what didn't happen? Joe Simmons didn't fake his data, and he didn't sue the guy who debunked his paper. But, you know, minor differences.
    Image
    16K
  • user avatar
    Quentin André
    @andre_quentin
    Oct 11, 2023
    Ouch.
    Image
    Image
    Image
    Image
    user avatar
    Stephanie M. Lee
    @stephaniemlee
    Oct 10, 2023
    Harvard just filed a partial motion to dismiss Francesca Gino's lawsuit against it, saying that she failed to state claims for breach of contract and defamation, among other things
    45K