# Formal models

## 33 important questions on Formal models

### How do we call a simplified representation of the world that aims to explain observed data?

### What is the difference between a formal- and an informal model?

- A formal model is a mathematical description of the relationship between variables that you expect to hold. It specifies relationships
- an informal model is a verbal explanation of relations between variables.

### What are the advantages of a formal model?

- It can sharpen theories by pointing out overlooked research problems
- a model is more complete in conceptualizing psychological problems compared to a linear regression for example.
- models have higher external validity since they are more of an inter individual measure, compared to an experimental procedure controlling natural covariate variables.

- Higher grades + faster learning
- Never study anything twice
- 100% sure, 100% understanding

### How do we call it when a model captures not only the variance that results from the cognitive process of interest but also that from random error?

### Why is overfitting a problem?

- An overfitted model is perfect in fitting the existing data, but does a poor job in predicting new data.
- a fitted model doesn't fit the existing data as well, but grasps the main tendencies making it better equipped to predict new observations

### How do we call the ability of a model to predict new data?

### How do we call a model’s inherent flexibility that enables it to fit diverse patterns of data?

### Which factors contribute to a model's complexity?

- The number of free parameters it has
- how the parameters are combined in it: the functional form.

### What problems can arise when designing and testing models?

- The irrelevant specification problem
- the bononi paradox
- the identification problem.

### Describe the irrelevant specification problem.

### Describe the bononi paradox

### Describe the identification problem

### Describe the Yerkes-Dodson law

### What are the different steps taken ideally in reasoning about theory through NHST?

- There is a theory, your substantial hypothesis
- research hypothesis: reason how the theory would occur in this (artificial) situation
- statistical hypothesis: H0 and Ha based on theory.

### How do we call it when the theory is almost a literal reformulation of the experimental findings?

### Which three types of circular reasoning are there?

- Repeating the premise as the conclusion
- premises presupposes the truth of the conclusion (begging the question)
- premise is logically/semantically equal to the conclusion (rewriting the premise)

### When do people trade on equivocation in reasoning about theories?

### Which fallacies are used in NHST in reasoning about theories?

- False dilemma: either accept your null hypothesis or your theory is correct
- common practice: compare your p level to an alpha level because everyone is doing it.
- straw man: testing your theorie on a null hypothesis, there's always a bit of correlation or a bit of difference. so you find significance when you find any difference

### Why is:

if theory p, then observation q

observation q

therefor theory p

not correct, and how should it be?

what is correct is:

if theory p, then observation q

- observation q

therefor not theory p

### What is an important question to ask to when determining the truth of a theory based on a research?

### How do we call it when people tend to interpret results in a way that fits their very specific theory when a more general theory could also hold?

### How do we call a concise statement about how we believe the world to be?

### What is the use of a theory?

### Which characteristics does a good theory have?

- breadth
- coherence and consistency
- Descriptive adequacy
- originality
- precision and interpretability

- prediction and falsifiability
- postdiction and explanation
- parsimony

- rationality
- usability

### Which characteristic of a good theory is described: is the theory new or is it a restatement of an existing theory?

### Which characteristic of a good theory is described: does each component of the theory fit logically into a coherent whole with others, and is it consistent with theories in other domains?

### Which characteristic of a good theory is described: does the theory accord with the data?

### Which characteristic of a good theory is described: is the theory precise and understandably written?

### Which characteristic of a good theory is described: is the theory formulated that critical tests can be developed to test it?

### Which characteristic of a good theory is described: does the theory apply to a broad range of phenomena?

### Which characteristic of a good theory is described: does the theory have applied implications?

### Which characteristic of a good theory is described: does the theory make claims about the mind that seem reasonable?

### Why is "a is correlated with b" less falsifiable than "a is positively correlated with b"?

The question on the page originate from the summary of the following study material:

- A unique study and practice tool
- Never study anything twice again
- Get the grades you hope for
- 100% sure, 100% understanding