Basisschooldocenten gezocht voor expert panel

Toetsen geven een indicatie van de mogelijkheden van een leerling, maar schetsen niet een volledig beeld. Om een zo eerlijk mogelijke inschatting te maken van het niveau van (basisschool) leerlingen, richten wij ons in ons onderzoek op de vraag hoe uw inzichten als leerkracht gekoppeld kunnen worden aan de inzichten van toetsresultaten.

Voor dit onderzoek zijn wij op zoek naar enthousiaste PO docenten die lesgeven aan groep 3,4,5,6 of 7 en deel willen nemen aan ons expertpanel. Deelname levert 100 euro op en bestaat uit één expertmeeting (ongeveer 2,5 uur) en een korte opdracht (30 min). U kunt zich opgeven voor vrijdag 14 april 16:00 – 18:30 of woensdag 19 april 15:00 – 17:30. De meeting vindt plaats in Utrecht (eventuele reiskosten worden vergoed).

Interesse? Meer informatie? Stuur vóór 8 april 2017 een facebookbericht via de pagina @oordeelsvormingPO.

Moeten wetenschappers uit hun ivoren toren verhuizen naar een glazen huis op de markt?

ivory-towerHet antwoord op deze vraag staat in het nieuwe boek “Hoe zwaar is licht – en meer dan 100 dringede vragen aan de wetenschap”.

Hier een sneak preview van mijn hoofdstuk ‘Wat zijn de regels van de wetenschap en liggen die voor altijd vast?’:

“Lang… lang geleden, in een dorp hier ver vandaan, stelden de eerste wetenschappers Vragen. Op een dag besloten zij dat Vragen stellen veel beter ging als ze zich terugtrokken uit het dorp en in een ivoren toren gingen werken. Daar konden zij in alle rust zoeken naar mogelijke antwoorden op de Vragen.Mensen uit het dorp kwamen zelden op bezoek en de wetenschappers hadden op hun beurt geen interesse in het dorpsleven. De tijden veranderden, het dorp werd een stad en de stad groeide uit tot een moderne metropool. …”

Benieuwd naar hoe het verder gaat? Lees nu het volledige hoofdstuk!

New in our Mplus Summer School: Should we retract all our papers with cross-lagged panel models?

dontDid you know you no longer should use a standard cross-lagged panel model? Longitudinal mediation analyses using a cross-lagged panel design should ALWAYS account for stable between-person differences with random-intercepts.  Should we then retract all the papers without such random-intercepts…? Ellen Hamaker will answer this question on Day 4 of our Mplus Summer School


Do not wait too long with registering for Week 1. Every year we end up having a long waiting list!

This summer’s 7th Mplus Summer School program will be nothing like the ones before! In the next week, I will occasionally reveal some new details to keep you guessing.

New in our Mplus Summer School: a full day on Mediation Analysis by Milica Miočević

nieuwNew this year will be a day on Mediation Analysis taught by Milica Miočević. Learn why you should not use normal theory confidence limits for testing the significance of the mediated effect, what methods for mediation analysis have the most power, and how to select the appropriate effect size measure for reporting the results of a mediation analysis.

Dr. Milica Miočević is a former student of Prof. David MacKinnon and Prof. Roy Levy. She specializes in Bayesian mediation analysis with manifest and latent variables. In the summer school she will be teaching about mediation analysis in Mplus.

Do not wait too long with registering for Week 1. Every year we end up having a long waiting list!

This summer’s 7th Mplus Summer School program will be nothing like the ones before! In the next week, I will occasionally reveal some new details to keep you guessing.

Sneak peek Mplus Summer School: Why the first day will feel like a roller-coaster

efteling_python_-_panoramioThis summer’s 7th Mplus Summer School program will be nothing like the ones before! In the next week, I will occasionally reveal some new details to keep you guessing.

This year I will be teaching the first day of the summer school. I will gently introduce Mplus using many anecdotes based on my own experience working with Mplus and helping other researcher running their first models. I will tell about great successes of researchers who could finally answer their research questions. But I also have some horror stories about people forgetting to check things and who had to retract their papers. This day will feel like a roller-coaster, but in the end, you will know what things you should never, ever, forget to check when analyzing your data using Mplus.

Based on the feedback we received last we made the first day a bit more relaxed with extra time for Q&A sessions. In the afternoon we have a very competent team ready to assist you with the exercises. Do not wait too long with registering for Week 1. because every year we end up having a long waiting list!


Sneak Peek Mplus Summer School: Nothing’s Like You Used To Know

As seven is a lucky number, we decided to push our luck this year. This summer’s 7th Mplus Summer School program will be nothing like the ones before! In the next week, I will occasionally reveal some new details to keep you guessing.

For now, I will just casually mention something about ‘innovative new topics’ … 😉

Symposium at M3 conference accepted

What the Dutch can do with prior information (and you too) – to be presented at the Modern Modeling Methods (M3) conference 

Bayes is growing in all disciplines! This is one of the results found by van de Schoot, Winter, Ryan, Zondervan-Zwijnenburg and Depaoli (in press) in an extensive systematic review. There are many different reasons why one might choose to use Bayes (e.g., the use of priors, estimating otherwise intractable models, modeling uncertainty, etc.). They found in this review that the use of Bayes has increased and broadened in the sense that this methodology can be used in a flexible manner to tackle many different forms of questions.

In this symposium we will show a broad range topics that can be tackled by using prior information. We start off with an evaluation of Bayesian estimation for small sample problems, when is it a solution and what are some pitfalls? Thereafter we discuss a new method to judge experts based on their elicited prior beliefs. To provide proof of concept an application is presented ranking regional directors in a large financial institution. To conclude, an innovative way of testing replication of hypothesis using prior predictive p-values is presented and illustrated. Online tools are made available so that you too can start using this method.

Bayesian Structural Equation Models with Small Samples
Authors: Sanne Smid, Dan McNeish, Rens van de Schoot
Presenting author: Sanne Smid

Bayesian estimation is frequently mentioned in the literature as a solution for small sample problems. When the Bayesian analysis settings are adapted to the specific research situation, problems can be overcome and Bayesian estimation can indeed be a solution for small sample problems. However, if just default settings are used, Bayesian estimation can perform worse than Maximum Likelihood estimation: default non-informative priors can become highly informative priors when samples are small and variance estimates can become extremely high. This are some of the main findings of the systematic review we carried out. In this review, we included papers in which a simulation study was used to investigate and compare the performance of Bayesian parameter estimation to Maximum Likelihood estimation in structural equation models with small sample sizes. The goal was to investigate whether Bayes should be used instead of Maximum Likelihood for SEM when the sample size is small. A total of n = 4977 records was identified in different searches. After removal of duplicates, n = 3548 abstracts were screened and n = 475 full-text articles were retrieved. In the end, we were left with n = 24 papers, in which a total of n = 29 simulation studies are described that met our inclusion criteria. We conclude that Bayesian estimation can have advantages for small samples in comparison to Maximum Likelihood estimation. However, researchers should always adapt the settings for the analysis to the specific research situation. This also includes thinking about priors: never rely on default priors when the sample size is small.

Keywords: Bayesian estimation, small samples, systematic review


Using the Data Agreement Criterion to Rank Experts’ Beliefs
Authors: Duco Veen, Diederick Stoel, Rens van de Schoot
Presenting Author: Duco Veen

Experts possess information and predictions can be a manifestation of this knowledge. In this presentation the use of priors to evaluate the relative merit of multiple sources of expert information in a decision making process will be discussed. We show how to elicit experts’ beliefs and represent these in the probabilistic form of a prior distribution, one for each expert. Representing beliefs in the form of a prior distribution allows experts to express appropriate (un)certainty, capturing aleatory and epistemic uncertainty. For this purpose a two-step digitized elicitation procedure was designed and evaluated using a pilot study and user feasibility study. The Data Agreement Criterion (DAC), a prior-data conflict measure as developed by Bousquet (2008), was adapted to allow simultaneous evaluations of multiple priors, i.e., the experts’ beliefs, in the light of new data. We show that the adapted version of the DAC can be used to rank experts based on their level of prior-data conflict. The resulting ranking can be used in the evaluation of expertise and assist decision makers in quantifying the relative importance sources of expert information. Behavior of the adapted DAC will be evaluated. Proof of concept by means of an empirical study, ranking regional directors in a large financial institution on their predictions of average turnover per professional will be presented. In conclusion, the two-step elicitation procedure and the adapted DAC are shown to be valid for the evaluation and ranking of experts’ beliefs.

Keywords: Bayesian statistics, Data Agreement Criterion, decision making, elicitation, experts, prior-data conflict, ranking


Testing ANOVA replications by means of the prior predictive p-value
Authors: Mariëlle Zondervan-Zwijnenburg, Rens van de Schoot, Herbert Hoijtink
Presenting author: Mariëlle Zondervan-Zwijnenburg

Replication concerns an original study and a new study. The original study leads to hypotheses for the new study. These hypotheses can, for example, concern the ordering of group means, specific differences between group means, or specific values for the group means based on the original study. The current study explains how we can test replication of these hypotheses by means of the prior predictive p-value. We illustrate the application of the prior predictive p-value with an example. Additionally, we explain how to calculate the required sample size for the new study such that power for the replication test is sufficient. Both the replication test, and the sample size calculator are made available as online applications. As such, the current study supports researchers that want to adhere to the call for replication studies in the field of psychology.

Keywords: ANOVA, comparison of means, power analysis, prior predictive p-value, replication study


With many thanks to Duco Veen who coordinated the submission procedure!

Presentation about GRoLTS-Checklist

At the Meeting of the Working Group SEM (16 and 17 March 2017; Ghent, Belgium) I will present about the Guidelines for Reporting on Latent Trajectory Studies.

March 16 at 14:15-14:45

Abstract: Estimating models within the mixture model framework, like Latent Growth Mixture Modeling (LGMM) or Latent Class Growth Analysis (LCGA), involves making various decisions throughout the estimation process. This has led to a high variety of how results of latent trajectory analysis are reported. To overcome this issue, using a four-round Delphi study, we developed Guidelines for Reporting on Latent Trajectory Studies (GRoLTS). The purpose of GRoLTS is to present criteria that should be included when reporting the results of latent trajectory analysis across research fields. We have gone through a systematic process to identify key components that, according to a panel of experts, are necessary when reporting results for trajectory studies. We applied GRoLTS to 38 papers where LGMM/LCGA was used to study trajectories of post-traumatic stress after a traumatic event.

By: Rens van de Schoot, Marit Sijbrandij, Sonja D. Winter, Sarah Depaoli & Jeroen K. Vermunt

Will this be the future of analyzing data?

> Dear computer, I have a question

> Dear researcher, welcome! At this moment there are 246 others who are also asking a question, how can I help you?

>> Here you can find a screenshot of my data, can you provide me the most important question I can answer with this data?

> Let me think about it…

This is:
A) Highly wanted
B) Not ethical


The very first female inaugural address at Utrecht University and the most recent one

Another Friday, another episode of the Deep-Thinking-project.

johanna_westerdijk_-_portrait_detail_-_university_museum_utrecht_-_0285-1853Today it is exactly 100 years ago, that the very first female inaugural address was given by Johanna Westerdijk at Utrecht University. Back then a female professor was rare, but also today it is not so common as you would think it to be. Especially in a country as in the Netherlands with a strong participation of women in the labor market, in academia there is still a gender imbalance.

Not so long ago, together with Hans Sonneveld and Mara Yerkes,  we conducted a study on gender inequality among PhD-students and early career researchers in the Netherlands. Just like in many other studies we also observed the existence of a gender gap. But we also concluded that in the Netherlands, luckily, we are catching up at greater speed when compared to other countries. Apparently, we are on the right track, not there yet, but (slowly?) going in the right direction at the very least. This is all with many thanks to our first female professor who paved the road for all the women who want to become full professor, just like ‘our’ Irene Klugkist today. Many congratulations to Prof. Klugkist!