Courses

Below, you will find an overview of courses from the current academic year of this Master's. This overview is meant to give you an idea of what to expect. The course offer may change in the coming academic year.

Year 1, semester 1

Survey data analysis

This course provides a solid foundation in the theory and methods of modern survey methodology. The course is centered around two current debates in survey methodology:
1. Should we use probability-based (design-based) or non-probability based (model-based) samples for inference
2. How do we design a survey as to minimize Total Survey Error

Statistical methods for analyzing from a design-based perspective will be discussed extensively, where the only source of random variation is induced by the sampling mechanism. The basic techniques of survey sampling will be discussed; simple random sampling, stratification, systematic sampling, cluster and multi-stage sampling, and probability proportional to size sampling. The course also covers methods of variance estimation for complex sample designs and several specialized topics. Apart from sampling we also cover unit- and item nonresponse, as well as ways to correct for them using weighting and (multiple) imputation methods.
The course also discusses what to do when design-methods fail, and under what circumstances model-based approaches are preferred. Towards the end of the course we focus on the potential of mixing the two approaches and future developments for survey science

Weekly meetings combine short lecture-style instructions, with short discussions, and exercises in R. This course considers the nature of various general methods, the supporting statistical theory, but also practical applications.

Multivariate statistics for MSBBSS

In this course we will refresh and elaborate on multivariate statistics, like the analysis of variance model including repeated measure analysis, and the regression model including dummy variables, interactions, and logistic regression. It is expected that students have encountered (most of) these models in their bachelor programme but in this course they will be dealt with at a more in-depth level and with a critical reflection on their use.
Furthermore, attention is paid for some special topics that are relevant for all applications of multivariate statistics. These include contrast testing, multiple testing and capitalization on chance and power, as well as bootstrapping and a teaser on Bayesian methods.
Finally, there is ample attention for recent developments and current topics in the area of statistics, including the replication crisis, questionable research practices, the open sience movement, and data science.

Fundamentals of statistics

This course provides an introduction to mathematical statistics that is relevant to empirical research.
The main topics are: mathematical requirements (differentiation, integration, numerical procedures), counting techniques, probability theory, general properties of probability distributions and densities, special probability distributions and densities, expectation, moments, sampling theory, point estimation (properties of estimators, method of moments, least squares estimation, maximum likelihood estimation, Bayesian estimation), hypothesis testing theory and applications (small sample techniques, likelihood ratio test, Wald test), analysis of variance, and regression.

Computational inference with R

Statistical inference based on intensive computation or simulation is an important part of the armamentarium of a statistician. Computational statistics concerns the development, implementation and study of computationally intensive statistical methods. Such methods are often used e.g. in the fields of data visualization, the analysis of large datasets, Monte Carlo simulation, resampling methods such as the bootstrap, permutation methods and various numerical methods of equation solving such as the EM algorithm and Newton-Raphson iteration.
This course will present essential methods in computational statistics in a practical manner, using real-world datasets and statistical problems. In addition to a basic introduction to R, it will include evaluating and comparing the performance of different statistical techniques in a specific setting using simulation and implementing the bootstrap to obtain a standard error estimate which is not available in closed-form. We will also develop more advanced R programming skills skills and the use of the tidyverse environment in R.

At of the end of the course the student:

  • is able to implement and use basic computational methods for statistical inference, as well as more advanced ones such as the bootstrap and permutation test;
  • will have developed fundamental and computationally efficient R programming skills;
  • is able to conduct and report on simulation studies, comparing the performance of statistical methods in specific settings;
  • is familiar with some widely used numerical methods; will be able to translate new statistical methods from the literature into a usable R program.

Year 1, semester 2

Psychometrics

TESTING

  • Written examination of psychometric theory, including classical test theory, generalizability theory, (Bayesian) item response theory and latent regression, Bayesian psychometric modeling. Furthermore, two home assignments based on the computer lab are also graded. The final grade is determined by the written exam (60%) and the two home assignments (20% each).
  • Practical using R to conduct G- and D- study and interpret and report results.
  • Practical using R (including IRT-software) to conduct a linking and dif study and interpret and report results.
  • Practical using R and Jags to conduct IRT-latent regression analysis interpret and report results.
  • Practical using R and Jags to conduct multilevel IRT-latent regression, Bayesian psychometric modeling, analysis interpret and report results.

Relatie tussen de toetsen en leerdoelen
The course gives a broad introduction to the field of psychometrics, followed by a number of advanced topics which give an impression of current developments. The introduction will cover classical test theory, generalizability theory and item response theory (IRT). As applications of IRT, the topics of test equating and differential item functioning will be presented and practiced. These applications will be presented in the framework of maximum likelihood estimation and model testing and the students will learn to use standard state of the art user software. The advanced topics are the combination of Bayesian psychometric methods and complex clustered data. These topics will be addressed in a Bayesian framework, and students will learn to build applications to analyze IRT models using Markov chain Monte Carlo estimation methods. In the lab meetings Jags and R will be used to analyze item response data using Bayesian inference.

Introduction in multilevel and structural equation modelling for MSBBSS

Two techniques that are often encountered are multilevel modeling (MLM) and structural equation modeling (SEM). MLM is appropriate for handling nested data, for instance, patients in hospitals, or occasions in people. MLM can be used to study the within cluster and the between cluster relationships between an outcome variable and predictors. In the lab meetings SPSS and HLM are used. SEM covers both factor analyses and path analyses. It can be used to investigate the underlying factor structure and compare this across groups (i.e., measurement invariance), more complex mediation models, longitudinal data, and to compare distinct theories. In the lab meetings Mplus is used.

Bayesian statistics

In this course the theory and practice of Bayesian data analysis will be introduced. Attention will be given to the difference between classical and Bayesian inference. The following topics will be subsequently be discussed: density of the data, prior and posterior distribution; classical and Bayesian p-values and their flaws; Bayesian estimation; model selection using the DIC; and, model selection using the Bayes factor. In the lab meetings JAGS and R will be used to analyze empirical data using the Bayesian approach.

Introduction to Biomedical Statistics

In clinical research, the research question drives the research design and analysis. Research questions can essentially be of either etiological, diagnostic, prognostic or therapeutic nature and research designs are often either observational or experimental. This course addresses the most common designs in clinical research and their impact on inference and statistical analysis. It will address epidemiological designs, such as case-control, cohort and cross-sectional designs and clinical trials. It will also cover some common statistical analyses that are often found in clinical research (e.g. survival analysis and meta analysis), and design issues specific to clinical trials. Upon completion, students will be able to translate the research question into an appropriate design and statistical analysis plan.

Year 2, semester 1

Elective courses and Research experience

Year 2 of the MS-programme includes an elective with 15 EC (credit points) = workload of two regular courses. You attend one or more relevant courses outside the M&S-programme. Options are for instance courses in one of the other Master's programmes in our Graduate school (e.g. a Development and Socialisation in Childhood and Adolescence or Social Health Psychology course). Also other areas (e.g., philosophy of science, mathematics, epidemiology) can be considered. It is also possible to take courses on Survey Methodology, Educational Measurement offered by University of Twente (course code 201500150), or from the track European Master in Official Statistics. Another option is to do a traineeship that is unrelated to the Master’s thesis project but relevant to the field of MS as such, so you get extra experience in conducting scientific research.

Research seminar

The course “Research Seminar” takes place in the first and second semester of the second year. It runs along:

  • “Markup languages” (MSBBSS10);
  • “Preparation master’s thesis” (MSBBSS12);
  • “Master’s thesis” (MSBBSS13).

To ensure enough personal attention while monitoring the thesis progress throughout the year, the class is divided in subgroups (denoted mentor groups) of approximately 5 students. Students within a mentor group will also, regularly, provide peer feedback to one or more members of their group. Other meetings are with all students, or, with half of the students. See the schedule below for an overview of all meetings throughout the academic year.

Markup languages and reproducible programming in statistics

This course gives an overview of the state-of-the-art in statistical markup, reproducible programming and scientific digital representation. Students will get to know the professional field of statistical markup and its innovations and challenges. It consists of meetings in which students will learn about markup languages (LaTeX and Markdown), learn efficient programming with R Markdown, experience developing Shiny web apps, get to know version control with Git and will create and maintain their own data archive repository and personal (business card) page through GitHub. Combining these lectures, the students get acquainted with different viewpoints on marking up statistical manuscripts, areas of innovation, and challenges that people face when working with, analyzing and reporting (simulated) data. Knowledge obtained from this course will help students face multidimensional problems during their professional career.

Note that for external parties, costs for participation may be involved.

Students will need their own laptop computer. Students should have experience in programming with R and should be familiar with the IDE RStudio.

Preparation for the Master's Thesis

The preparation for the Master's thesis (15 EC) will take place in the first semester of the second year. You carry out a research project that prepares for the research project carried out in the Master's thesis . The preparation for the thesis runs along with the research seminar. It has the following aims:

  1. to master the state of the art in methodology and statistics with respect to the research topic chosen.
  2. to master research skills in the area of methodology and statistics with respect to the research topic chosen.
  3. to develop experience in writing.

Year 2, semester 2

Elective courses and Research experience

Year 2 of the MS-programme includes an elective with 15 EC (credit points) = workload of two regular courses. You attend one or more relevant courses outside the M&S-programme. Options are for instance courses in one of the other Master's programmes in our Graduate school (e.g. a Development and Socialisation in Childhood and Adolescence or Social Health Psychology course). Also other areas (e.g., philosophy of science, mathematics, epidemiology) can be considered. It is also possible to take courses on Survey Methodology, Educational Measurement offered by University of Twente (course code 201500150), or from the track European Master in Official Statistics. Another option is to do a traineeship that is unrelated to the Master’s thesis project but relevant to the field of MS as such, so you get extra experience in conducting scientific research.

Research seminar

The course “Research Seminar” takes place in the first and second semester of the second year. It runs along:

  • “Markup languages” (MSBBSS10);
  • “Preparation master’s thesis” (MSBBSS12);
  • “Master’s thesis” (MSBBSS13).

To ensure enough personal attention while monitoring the thesis progress throughout the year, the class is divided in subgroups (denoted mentor groups) of approximately 5 students. Students within a mentor group will also, regularly, provide peer feedback to one or more members of their group. Other meetings are with all students, or, with half of the students. See the schedule below for an overview of all meetings throughout the academic year.

Master's Thesis

Writing a Master's thesis is a major objective in the second year of the Methodology and Statistics programme. You write a thesis in the form of a scientific publication that can be submitted to a scientific journal. The course aims to learn you the skills to;

  • study the theory and available literature available in the research field of the thesis (Knowledge and Understanding);
  • formulate a research problem that is well embedded in the state of the art in the research field of the thesis (Applying);
  • use appropriate methods to investigate, evaluate, and address the chosen research problem (Judgment);
  • report theory, literature, research problem, research method, research outcomes and illustrations in the form of a scientific publication that can be submitted to a scientific journal (Communication).

Criteria for the evaluation of the Master's thesis are: 

  1. it is embedded in previous research and literature on the topic of the thesis.
  2. it includes a theoretical elaboration of the research problem, 
  3. it includes an appropriate approach to solve and provide an answer to the research problem.