German Exercise Materials for Methods I

A Workbook Focused on Practice

My new (German-language) workbook follows exactly this principle. It is independently published via KDP¹:

https://amzn.eu/d/50tjI7G

The workbook contains 113 exercises with full solutions, covering the following topics:

• Everyday Psychology vs. Scientific Psychology
  
• Philosophy of Science
  
• Measurement and Testing
  
• Observation and Survey Methods
  
• Experimental Design
  
• Measures of Central Tendency and Dispersion
  
• Correlation
  
• Regression
  
• Probability Theory
  
• Confidence Intervals
  
• Significance Tests
  
• Analysis of Variance (ANOVA)
  
• Meta-Analysis

Example: Levels of Measurement

Consider levels of measurement as an example.

In Bortz’s classic textbook, levels of measurement are defined via formal axioms — but without any exercises.
In more intuitively oriented textbooks (e.g., Bühner & Ziegler, BZ, or Sedlmeier & Renkewitz, SR), levels of measurement are illustrated with memorable examples. Again, however, there are no exercises.

In both cases, exercises are only available after registering on the Pearson website. After registering, I am presented with the following message:

“Please note that teaching materials are exclusively reserved for registered instructors and teachers. You cannot access these materials.”

For SR, the new edition no longer contains exercises at all. Exercises from older editions can only be accessed—somewhat awkwardly—via
https://www.pearson.de/studium/produkte/extras-online/dlm
by manually entering the ISBN. In total, there are six exercises on levels of measurement.

For BZ, I unfortunately could not locate the promised exercises at all.

Both books are excellent introductions to the topic. But without exercises, it is difficult to know what you actually understand — and what you don’t.

From my teaching experience, working through at least a dozen examples is necessary to really understand levels of measurement.
My workbook currently includes 18 exercises, plus three additional tasks on permissible transformations — all with solutions.

For example:

What is the level of measurement in the following case?

Healthy (=1), Neurotic (=2), Psychotic (=3)

Be careful — there are two possible correct answers.

Detailed Solutions

Are you also annoyed by books that include exercises but no solutions?
How are you supposed to check whether your answer is correct?

In my workbook, every exercise is solved in a model-like manner, exactly as I would grade it in an exam.
More difficult tasks are explained in detail and often include references to additional sources.

Consider this example:

In a study by Greeley (1994), the infidelity rate of men in the USA was estimated at 21%, with a 95% confidence interval from 0.18 to 0.24. Why would it be incorrect to say that the true population value lies within this interval with a probability of 95%?

This question cannot be answered adequately in a single sentence — although many instructors attempt to do so. Often, the explanation is limited to: “The true value is either inside the interval or not, so no probability statement can be made.”

But what does that actually mean?

In my solution, I refer to three in-depth discussions on Stack Exchange that address this exact issue. At the same time, I provide a concise explanation:

In the frequentist framework, the true population value is assumed to be a fixed constant, not a random variable. Therefore, probability statements cannot refer to the true value itself. When constructing a confidence interval, we must assume that the true population value is known (in this example, 21%). If we were to compute 100 confidence intervals, the true value would always remain 21%. The probability statement refers to the intervals, not to the parameter.

Saying that the true value lies within a fixed interval (e.g., from 18% to 24%) with a certain probability would imply that the true value changes while the interval remains constant — which is nonsensical in this context.

In the solution, I also briefly discuss an alternative framework in which such probability statements are meaningful — Bayesian statistics — while pointing out its own assumptions and limitations.

Free License

The workbook is published under a free license (CC BY-SA). This means that anyone may use, modify, and redistribute the exercises, provided that the license is retained and the source is properly cited. This greatly facilitates collaboration among instructors.

Regular Updates

The workbook is updated at least once per year, as I actively use it in my own teaching. Existing material is improved, and new exercises are continuously added.