![Daniel Lakens](/img/default-banner.jpg)
- Видео 33
- Просмотров 137 677
Daniel Lakens
Добавлен 30 июл 2006
Olmo van den Akker – Preregistration: Past, Present, and Prospects – PoSE 2024
Perspectives on Scientific Error 2024
While preregistration has been lauded as one of the solutions to the replication crisis in psychology, not much empirical evidence is available about its effectiveness. In this set of studies, we aimed to assess whether preregistrations in psychology are sufficiently producible (i.e., they can be conducted based on the information provided in the preregistration) and sufficiently in line with the corresponding publications. We also assessed whether preregistered studies include a lower proportion of positive results than non-preregistered studies, which would be an indication of a preventative effect on questionable research practices like p-hacking an...
While preregistration has been lauded as one of the solutions to the replication crisis in psychology, not much empirical evidence is available about its effectiveness. In this set of studies, we aimed to assess whether preregistrations in psychology are sufficiently producible (i.e., they can be conducted based on the information provided in the preregistration) and sufficiently in line with the corresponding publications. We also assessed whether preregistered studies include a lower proportion of positive results than non-preregistered studies, which would be an indication of a preventative effect on questionable research practices like p-hacking an...
Просмотров: 248
Видео
David F. Urschler - Do we really know what we are talking about? - PoSE 2024
Просмотров 1836 месяцев назад
David F. Urschler - Do we really know what we are talking about? The prevalence of well- and ill-defined psychological constructs in 150 meta-analytic reviews. - Perspectives on Scientific Error 2024 See osf.io/ayfek/ The importance of scientific rigor has been in the spotlight of psychological research in the past decade. For example, previous research has provided comprehensive guidelines to ...
Ana Martinovici - How to detect data fabrication in Qualtrics questionnaires - PoSE 2024
Просмотров 2286 месяцев назад
Ana Martinovici - Is this real data? How to detect data fabrication in Qualtrics questionnaires - Perspectives on Scientific Error 2024 See osf.io/ayfek/ Qualtrics is one of the most used platforms for online data collection. Due to having relatively easy-to-use point-and-click functionalities Qualtrics is used by both researchers and students. Some of these functionalities allow the owner of a...
Catarina Dutilh-Novaes - Mistakes in mathematical proofs - PoSE 2024
Просмотров 2036 месяцев назад
Catarina Dutilh-Novaes - Mistakes in mathematical proofs - Perspectives on Scientific Error 2024 See osf.io/ayfek/ Imre Lakatos famously claimed that mathematical knowledge is produced by a dialectic of ‘proofs and refutations’, whereby a proof-concept is proposed which is then scrutinized to ascertain whether there are counterexamples to individual steps in the proof (local counterexamples) or...
Rink Hoekstra - The Illusion of Objectivity - PoSE 2024
Просмотров 1136 месяцев назад
Rink Hoekstra - The Illusion of Objectivity - Discussing the Hidden Subjectivity in Quantitative Social Science - Perspectives on Scientific Error 2024 See osf.io/ayfek/ In the social sciences, subjectivity is often considered as something that preferably needs to be prevented, while objectivity is seen as an honorable objective. This may explain why quantitative research seems to be considered...
Ian Hussey - The ERЯOR project: A three-prong effort to improve error detection - PoSE 2024
Просмотров 2046 месяцев назад
Ian Hussey - The ERЯOR project: A three-prong effort to improve post publication critique and error detection - Perspectives on Scientific Error 2024 osf.io/ayfek/ By itself and as currently implemented, academic peer review is not up to the task of comprehensively detecting errors in scientific publications, at least in the field of psychology. Error detection typically requires more resources...
Fiona Fidler - Can forecasts of replicability improve peer review? - PoSE 2024
Просмотров 816 месяцев назад
Fiona Fidler - Can forecasts of replicability improve peer review? - Perspectives on Scientific Error 2024 osf.io/ayfek/ Now in its sixth year, the repliCATS project (Collaborative Assessment for Trustworthy Science) has evaluated over 4,000 published social science articles across 8 disciplines, including psychology, economics, and education, as well as many preprints. For each paper, a divers...
Veronika Cheplygina - Shortcuts and shortcomings in machine learning for medical imaging - PoSE 2024
Просмотров 826 месяцев назад
Veronika Cheplygina - Shortcuts and other shortcomings in machine learning for medical imaging - Perspectives on Scientific Error 2024 For slides, see osf.io/ayfek/ The application of machine learning (ML) to medical imaging diagnosis has attracted a lot of attention in recent years, with numerous reports of recognising medical images more accurately than human experts (for an overview see Liu ...
Gerit Pfuhl - Do Norwegian publishing incentives lead to questionable research practices? PoSE 2024
Просмотров 996 месяцев назад
Gerit Pfuhl - Do Norwegian publishing incentives lead to questionable research practices? - Perspectives on Scientific Error 2024 The way from data to publishing is distorted by incentives. In Scandinavia journals are classified into levels, and the higher the level the more points a publication earns. At the same time, these "better" journals are often journals that publish novel and significa...
Aurélien Allard - Theory building and replicability - PoSE 2024
Просмотров 2906 месяцев назад
Aurélien Allard - Theory building and replicability: on the value of basic facts without theoretical foundations - Perspectives on Scientific Error 2024 For slides, see osf.io/ayfek/ The last 10 years have seen increased attention paid to the reproducibility of scientific experiments. This focus on reproducibility has met some pushback. One particularly interesting backlash from a philosophical...
Christian Hennig - Understanding statistical inference based on models that aren't true - PoSE 2024
Просмотров 1706 месяцев назад
Christian Hennig - Understanding statistical inference based on models that aren't true - Perspectives on Scientific Error 2024 For slides, see osf.io/ayfek/ Statistical inference is based on probability models, and most of the theory behind it assumes these models to be true. But models are idealisations, and it makes little sense to postulate that they are literally true in reality. Models ar...
Sample Size Justification - Durham - 04 June 2021
Просмотров 1,8 тыс.3 года назад
Sample Size Justification - Durham - 04 June 2021
Risky Predictions by Daniel Lakens
Просмотров 8963 года назад
In this video I explain why risky predictions are more impressive than less risky predictions. More severe tests of hypotheses (for example by performing one-sided tests, or tests of range predictions) have important advantages over NHST.
Pre-Registration by Daniel Lakens
Просмотров 8773 года назад
In this video we discuss the benefits of preregistration, especially when it comes to formalizing error control, and preventing flexibility in the data analysis. This video is part of my free online course on statistics: www.coursera.org/learn/statistical-inferences
Replication Studies by Daniel Lakens
Просмотров 1,8 тыс.3 года назад
Discussion of the importance of replications in science, the replication crisis, and what the goal of replication studies is. This video is part of my free online course on statistics: www.coursera.org/learn/statistical-inferences
Do You Really Want to Test a Hypothesis? by Daniel Lakens
Просмотров 2,8 тыс.4 года назад
Do You Really Want to Test a Hypothesis? by Daniel Lakens
Type 1 Error Control by Daniel Lakens
Просмотров 1,1 тыс.4 года назад
Type 1 Error Control by Daniel Lakens
Bayesian Inference for Binomial Proportions by Daniel Lakens
Просмотров 3,5 тыс.4 года назад
Bayesian Inference for Binomial Proportions by Daniel Lakens
Binomial Likelihoods by Daniel Lakens
Просмотров 4414 года назад
Binomial Likelihoods by Daniel Lakens
Sample Size Justification by Daniel Lakens
Просмотров 13 тыс.4 года назад
Sample Size Justification by Daniel Lakens
Type 1 and Type 2 errors by Daniel Lakens
Просмотров 2,1 тыс.4 года назад
Type 1 and Type 2 errors by Daniel Lakens
What is a p-value? by Daniel Lakens
Просмотров 39 тыс.4 года назад
What is a p-value? by Daniel Lakens
Frequentist, Likelihood, and Bayesian Approaches to Statistical Inferences by Daniel Lakens
Просмотров 8 тыс.4 года назад
Frequentist, Likelihood, and Bayesian Approaches to Statistical Inferences by Daniel Lakens
Interview Zoltan Dienes on Statistics and Philosophy of Science
Просмотров 3,1 тыс.8 лет назад
Interview Zoltan Dienes on Statistics and Philosophy of Science
Interview Daniel Simons on Pre-Registration
Просмотров 6448 лет назад
Interview Daniel Simons on Pre-Registration
Get started with the perfect t test
Просмотров 1,7 тыс.9 лет назад
Get started with the perfect t test
Thank u for all da efforts
I cannot read the slides, please fix it!
Promo-SM 😘
This is the best video on p-value ever I watched.
thank you so much! i have to present a study this week that deals with pet-peese and all those other statistical methods, and this helped a lot!
Very helpful, thank you so much! :)
Wow. Calm and cool with precision. Love you sir.
what is difference between the Bayesian MAP estimator and the frequentist maximum likelihood estimator
3:42 That is an interesting mathematical approach.
Loved it! Thank you!
At 5:50 i am reading Fisher's own words, so I doubt these are incorrect. It is unclear from your comment what I would have said that is wrong - I strongly doubt I made a mistake.
Fantastic explanation
Thanks
Thank you Daniel. Your explanation of the “p” values is the best of all the explanations I have seen. I like your method of presentation. I subscribed! I like your examples. You are an fantastic teacher. I am so glad I found your channel.
Hi Daniel, what do you mean ANOVA 2X2X2? If I have pair wise data T1 and T2 for 10 categories with each category having different number of observations, will alpha for two sample test across category inflate?
How can I present sample size on tables indicating percentages thanks for the response
You make very good videos. Thank you.
Thanks for putting this together.
Oooh, math can be explained in Guru style sign me in!!
I want to do meta analysis....for the first time...pls hlp
Sir could you share your email address
Thank you so much. I learned a lot.
Truly Amazing....
The deadface delivery of the pre-cognition and paranormal distribution joke literally had me cackling i love you so much (thank you for giving us so much amazing free knowledge, from your amazing coursera course in general to all these amazing vdieos and even your blog!!! you're amazing and i appreciate you tremendously)
Marvelous. thanks a ton!
I've been through about 20 presentations on P for my nursing students here in Africa, this is by far the best!
thanks
Are there more videos in this format to come?
This comment goes beyond the original scope of the video, but it is related. Using the binomial distribution to calculate the likelihood of observing certain combinations of significant/non-significant results of hypothesis tests assumes that the hypothesis tests (even under the null hypothesis) are independent from each other. This is a useful approximation in practice, but isn't necessarily accurate for all combinations of hypothesis tests. If someone knows some general theorems on this topic, I'd love to hear about them. Otherwise, you can do Monte Carlo methods to check if two tests are independent under the null hypothesis.
Somewhat implicit in how you introduced likelihoods is that the choice of distribution matters, thus the likelihood (and consequently Fischer information) of a parameter is also given the choice of model. I think the binomial distribution is an excellent choice for this video for pedagogical reasons.
AT 8:29 an approach called "sequential analysis" is recommended. There may be ways to evaluate data 'as it comes in', but the recommendation that was given in this video is not appropriate. If you collect data until you have a statistically significant result, you are P-hacking.
I recommend you look up my statistics papers on sequential analysis to learn why you are wrong. Too many people still just do mindless statistics.
@@DanielLakens I am willing to read one of your papers on sequential analysis. Which one do you think makes the best case for sequential analysis?
@@galenseilis5971 Here you go psyarxiv.com/x4azm/ For a book length treatment link.springer.com/10.1007/978-3-319-32562-0
@@DanielLakens I read your paper, and rewatched the part of this video on sequential analysis. I was wrong in the first place about what you were claiming. By "sequential analysis" I had thought you were referring to increasing the sample size until a (conventional) P-value less than alpha is achieved, however that is not what you are claiming in this video or in the psyarxiv.com/9yegd/ paper. Rather you are referring to increasing sample size while also controlling for Type I error. The former is a type of P-hacking, the latter is not. The paper discusses different approaches including decision boundaries, spending functions, conditional power, and Bayesian predictive power. I have not read the sources you cite on these methods to understand their tradeoffs, but an optimal stopping criterion for sample size is desirable if it can be derived.
@@DanielLakens I just refreshed the page and saw the links you responded with. I think my previous comment resolves the misunderstanding, but I may read these later. Thank you.
Thank you so much for thinking through this and for posting this video!
Very interesting and clear content! By any chance, is there a place where you talk about the underlying assumptions of these bias correction techniques? Or do you have any ressource to advise?
This is an amazing insight. Thanks!
Thank you very much for such wonderful lectures!
This was very informative and helpful. Thanks!!!
Clear, concise, and to the point. This has to be the best explanation of Bayesian thinking.
Well explained. Thanks, Daniel. Cheers from the Technical University of Denmark!
Very informative 💜 🌿 ❤️
Thank you, Zoltan is such an interesting Scientist. Thank you for this interview Daniel, my Sons also enjoy his boxing instruction.
Thank you!
Amazing, thanks!
Fantastic.... Thanks for sharing.
Why it is said that the smaller the p-value the stronger the evidence against null hypothesis? I thought the opposite to be true. Can someone explain this?
Amazing explanation...I must say Stats is taking us close to philosophy
Great interview
Great job! You explained a frustration of mind very very well! I could never find the words, but you obviously have! Little thing to boost your creditability especially if you are criticizing other scientists, the word "data" is plural.
mamzing!! mama miyaaa
Btw, Thomas Bayes was a priest. Good video though!
Who would dislike this?