Critical thinking about psychological measurement

Question 1

How does campbell define measurement?

Answer 1

The result of a process of assigning numbers such that

• Each object is represented by a single number
• The sum of two assigned numbers (+=_) represents of objects objecte (e.g, laying two rods end to end)

Question 2

What name is given to Campbell’s theory of measurement? (2)

Answer 2

The representational theory of measurement/

Question 3

What is meant by concatenation?

Answer 3

Adding two assigned values of a measurement which represent objects objecte

Question 4

The central idea of representational theory is that __________ mirror ______

Answer 4

Numerical relations; Empirical relations

Question 5

What was the verdict from the committee from the British association for the advancement of science regarding whether psychological measurements were actually measurements?

Answer 5

No verdict

Question 6

What did Stevens add to measurement theory

Answer 6

He added measurement levels (ordinal nominal interval ratio etc)

Question 7

How did Stevens define measurement?

Answer 7

The assignment of numerals according to a rule

Question 8

The stronger the scale level, the _______________________

Answer 8

Less you can do with the assigned numbers without breaking the mirror

Question 9

How does this rule affect how we use statistical tests?

Answer 9

Parametric tests such as t-test and ANOVA are sensitive to transformations that change distances between scale points
As a result, nonlinear transformations will change one’s conclusions

Question 10

Why can’t you transform the data such that the distances between scale points change for a t test?

Answer 10

Because the data are at the interval level of measurement, so only linear transformations are admissable

Question 11

Evaluate Steven’s rules (3)

Answer 11

• reasoning behind stephen’s rules is strong and makes a lot of sense
• Good argument for non-parametric statistics because these are not sensitive to nonlinear transformations
• Clever people who know what they are doing can still obtain sensible results

Question 12

How can you deal with this issue?

Answer 12

• one way is through the concept of robustness
• Transform you data according to the transformations you think should not matter
• Rerun the analysis
• If conclusions don’t change, they are robust and you’re in good shape
• If conclusions do change, investigate why and reconsider your scales (very often they are robust)