• Euro Camp: Bayesian Analysis
    April 25, 2016 - May 29, 2016
    7:00 am - 3:00 pm

My First Bayes: A Gentle Introduction To Bayesian Analysis Using MPLUS and 5 Other Programs

The five-day institute sessions will be Monday – Friday from 9:00 a.m. to 5:00 p.m. each day.

Although the ideas of inverse probability and Bayes’ theorem have been longstanding within mathematics, these tools have not been at the forefront of modern-day applied statistics. Specifically, in the 20st century the statistical tools most often used by researchers in the field of psychology are based on frequentist statistics (i.e., p-values and null hypothesis testing). Since the beginning of the 21st century, however, Bayesian statistical methods are slowly creeping into all fields of science and are becoming ever more popular in applied research. This increase is specifically due to recent computational advancements and the availability of Bayesian estimation methods in popular software and programming languages like Mplus. Moreover, the use of Bayesian methods has increased because this estimation framework can handle some commonly encountered problems in orthodox statistics. For example, Bayesian methods can be used for, e.g., producing more accurate parameter estimates and aiding in situations where only small sample sizes are available. Alternatively, some researchers implement Bayesian methods simply because they like the methodology, or believe in the Bayesian way of updating knowledge with new data instead of testing the null hypothesis over and over again assuming nothing is going on in the population.

During this 5-day course you will be gently introduced into Bayesian statistics and you will learn when to use which program. We will mostly using the software Mplus, but we will also ‘play around’ with other software (BIEMS, JASP, MyFirstBayes, RJAGS, MplusAutomation).

Although it is very attractive to use Bayesian statistics, naively applying Bayesian methods can be dangerous for three main reasons: the potential influence of priors, misinterpretation of Bayesian features and results, and improper reporting of Bayesian results. To deal with these three points of potential danger, we will spend a lot of time discussing these issues. You will learn how to use the WAMBS-checklist (When to worry and how to Avoid the Misuse of Bayesian Statistics). The purpose of the questionnaire is to describe 10 main points that should be thoroughly checked when applying Bayesian analysis.

On each day, the morning session consists of lectures, and the afternoon session is a computer lab where the topics of the morning are applied on example data. During the computer labs there is plenty of time to work on your own data and get feedback on your models, especially on Day 5.

Session1_ImgDivider

Preperation

If you are not familiar with the software Mplus or R you are requested to prepare an exercise in advance where you will also be shown how to get the software and how to run some very basic models. The exercise will be send to you after registration. This will save us some time on Day 1.

Session1_ImgDivider

Instructor

Rens van de Schoot, Ph.D. (http://rensvandeschoot.wordpress.com/), is associated professor in Methods and Statistics at Utrecht University, the Netherlands and extra-ordinary professor at North-West University in South Africa. He teaches many Bayesian and Mplus courses all around the world and he organizes Mplus users meetings in the Netherlands (mplus.fss.uu.nl).

Session1_ImgDivider

Audience

Knowledge of regression analysis is required. No previous knowledge of Bayesian analysis is assumed. You do not need to know matrix algebra, calculus, or likelihood theory. Since the course offers a gentle introduction there are hardly any formulas used in the lectures. The main focus is on conceptually understanding Bayesian statistics.

Participants from a variety of fields, including sociology, psychology, education, human development, marketing, business, biology, medicine, political science, and communication, can benefit from the course.

Session1_ImgDivider

Software and Computer Support

Participants should bring a laptop to the course. Before arriving, participants should acquire either the Mplus demo version 7 or higher or the full Mplus version 7 or higher. The computer exercises are based on the demo version, but there will be plenty of time to work on your own dataset and then the full version might be needed.

Also, JAGS, R and Rstudio should be installed on your laptop. Specific instructions will be send before the course takes place.

In addition to a course packet, you will receive a zip file containing all course materials, including PowerPoint slides, exercises, data and scripts, output files, relevant supporting documentation, and recommended readings

Session1_ImgDivider

Syllabus

Monday
9:00 – 10:00Welcome & Introductions
10:00 – 12:00On the first day we will discuss the conceptual differences between default statistics and Bayesian statistics, and the role of priors in a Bayesian model (sensitivity analysis).
12:00 – 1:30Lunch *
1:30 – 4:30In the afternoon you will run your first Bayesian model using the software MyFirstBayes and Mplus.
Tuesday
9:00 – 12:00The second day will be devoted to the WAMBS checklist and how to interpret the results.
12:00 – 1:30Lunch *
1:30 – 4:30Computer exercise applying the WAMBS checklist using Mplus and RJags/RStan.
Wednesday
9:00 – 12:00On the third day we will apply Bayesian statistics to models that are difficult or impossible to be estimated using maximum likelihood (e.g., small samples, approximate measurement invariance, etc).
12:00 – 1:30Lunch *
1:30 – 4:30Computer exercises using Mplus.
Thursday
9:00 – 12:00On the fourth day model fit (posterior predictive p-values) and model selection (BIC, DIC, Bayes factors) will be discussed. We will also discuss testing informative, or inequality constrained, hypotheses.
12:00 – 1:30Lunch *
1:30 – 4:30Computer exercises in JASP, BIEMS and MplusAutomation in R
Friday
9:00 – 12:00On the last day all topics will be summarized and participants can ask advise on their own data.
12:00 – 1:30Lunch *
1:30 – 4:30continued

Session1_ImgDivider

Contact Information

For information on course content, contact Rens van de Schoot a.g.j.vandeschoot@uu.nl

Session1_ImgDivider

Transportation

The location close to exit 30 of the A27 motorway and its own spacious (paid) car park are unique for a hotel in Utrecht. If you want more information please telephone Mitland +31 (0)30 271 58 24.

Directions to Hotel

From Schiphol Airport to Utrecht:
By train (25 minutes; every 15 min)
By taxi (more expensive!!)

Session1_ImgDivider

Lodging

To reserve a room for the event, please email the hotel directly at info@mitland.nl with the reference block code  STAT240416.

Hotel Mitland Booking

Stats Camp has blocked 80 hotel rooms single or double occupancy for the period 24th to 29th of April 2016. The costs of the rooms are € 94,00 per room per night excluding breakfast of € 16,00 per day and city tax of 5% of the room rate.

You will book rooms for yourself along with any guests traveling with you. Please make reservations with the reference “Stats Camp.” When the course rooms are definitely booked you can arrange your camp, hotel and travel reservations. Hotel will keep the room up to 2 months before start date.

Session1_ImgDivider

Dutch Mplus Group Information

Utrecht Mplus Group Information

Venue:  

Venue Phone: +31 (0)30 271 58 24

Venue Website:

Address:
Ariënslaan 1, 3573 PT, Utrecht

Description:

Detailed Travel Directions

Mitland Hotel Utrecht BV
Ariënslaan 1
3573 PT  Utrecht
The Netherlands
T+31 (0)30 271 58 24
F+31 (0)30 271 90 03
Einfo@mitland.nl
Wwww.mitland.nl