[1] The first topic deals with fundamental underpinnings of quantitative research (language of research, what is validity, why is it important and what types of validity are distinguished. The topic also addresses ethical issues and principles in research.

[2] Unless a census is feasible and appropriate, sampling becomes a very important aspect. Beware, the most creative statistical analyses will not make up for flawed sampling. Therefore, better think twice about your sampling strategy. The topic also introduces us to the issue of external validity and key terms of sampling such as probability and non-probability sampling.

[3] As a rule quantitative research requires measurement as a type of quantification. According to the main stream concept of measurement in the social sciences, measurement can take place at different levels. These will discussed as well as the consequences for data analysis. Finally, quality criteria of measurement (reliability and validity) will be addressed. Whether you will develop your own measurement instruments or use existing ones, you should know what to look for at the end of this course.

[4] While experiments are becoming more and more popular among social scientists, a lot of data is collected (and can only be collected) through surveys. Thus, we will discuss principles of good survey research (types of surveys, how to select a survey method, how to construct a survey, what kind of questions are appropriate, question phrasing and order, how should a response scale look like, what are the pros and cons of survey research.)

[5] Now that you have an idea what measurement means and what its goals are, we look at selected methods of scaling and index construction. Specifically, we will learn about Thurstone scaling, Likert scaling (very widespread) and Guttman scaling. If there is some time left, we might briefly look at other approaches as well.

[6] Regardless of the type of research you plan to do, design is always fundamental. At first, we discuss internal validity and take about fundamentals of establishing cause and effect. Then we talk about various threats that occur in single or multiple group designs.

[7] It is often argued that experiments are the best way, some say the only way, to investigate causal claims. Thus, the experimental design is of utmost importance. Even if you do not intend to run your own experiments, you may refer to published work using experiments. This unit deals with two-group experimental designs, probabilistic equivalence and random selection and assignment - basics of experimental research.

We will also address factorial designs, the randomized block designs, covariance designs and hybrid experimental designs.

[8] True experiments are not always doable. Then quasi-experimental designs are an option. We will learn about the nonequivalent groups design, the regression-discontinuity design and other quasi-experimental designs

[9 & 10] Once you collected the data, you will be ready for analysis. We will be introduced to data preparation, data description, and elementary statistics such as correlation coefficients.

Furthermore, we will deal with fundamental inferential statistics such as the t-test. The concept of dummy variables will also be explained.

Going full circle, we will come back to conclusion validity, threats to conclusion validity and ways to improve it.

- Analysis I: Conclusion Validity/ Threats to Conclusion Validity/Improving Conclusion Validity/ Statistical Power/ Data Preparation/ Descriptive Statistics/ Correlation;

- Analysis II: Inferential Statistics / The T-Test/ Dummy Variables/ General Linear Model Post test-Only Analysis/ Factorial Design Analysis/ Randomized Block Analysis/ Analysis of Covariance

≥ 82% Attendance Requirement

Attendance of the introductory class is compulsory. Absence without valid excuse may lead to exclusion from the course. Thus, contact the course leader as early as possible, if you know you cannot make the first class.

The grading is based on the following components:

After each unit, there are written tests (referred to as quizzes, each quiz consists of 8 multiple choice or multiple response questions) each covering one topic. There are 10 quizzes with 8 credits for each quiz, thus 10x8=80 credits in total.

For each presentation, the presenting participant(s) receive 20 credits (for topic #3 40 credits because of its length)..

Attendance and active participation are required and expected.

The credits for the quizzes and presentation(s) add up to the total credits. Depending on the number of topics presented (topic #3 counts as two topics in this regard), the following grading keys apply:

• Grading mode 1 (one presentation): 0-60: insufficient; 61-70: 4; 71-79: 3; 80-87: 2; 88+: 1
• Grading mode 2 (two presentations): 0-70: insufficient; 71-80: 4; 81-90: 3; 91-100: 2; 101+: 1
• Grading mode 3 (three presentations): 0-80: insufficient; 81-90: 4; 91-100: 3; 101-110: 2; 111+: 1