Furr Psychometrics Ch.1

Two reasons that psychologists measure a behaviour

1. they are interested in that specific behaviour in its own right

2. as a way of assessing unobservable psychological attributes

constructs

internal attributes or characteristics that cannot be directly observed but are useful for describing and explaining behavior

latent variables

interchangeable with "constructs"

operational definitions

the operations or procedures that we use to measure these hypothetical constructs

According to Chronbach, a psychological test is...

"a systematic procedure for comparing the behavior of two or more people"

three important components of tests

1. they involve a behavioural sample of some kind

2. the behavioral samples must be collected in some systematic way

3. the purpose of the tests is to detect differences between people

Six ways that tests can vary from each other

1. content (e.g. aptitude, achievement, intelligence, personality, etc.)

2. Response required (open ended vs. closed ended

3. method of administration (e.g. individual vs. group)

4. Use (e.g. criterion referenced vs. norm-referenced)

5. Timing (e.g. speeded vs. power)

6. The meaning of "indicators" (e.g. reflective/effect vs. formative/causal)

(CRMUTT)

(page 9) Scores on norm-referenced tests can be valuable when:

1. the reference sample is representative of some population

2. the relevant population is well-defined

3. the person being tested is a member of the relevant population

criterion-referenced tests

a cutoff test score is established as a criterion and is used to sort people into groups of either above the criterion or below it.

criterion-referenced tests are seen in which settings?

in which a decision must be made about a person's skill level

norm-referenced tests

used to understand how a person compares with other people

speeded tests

time-limited tests

power tests

type of performance test with items of varying difficulty but with adequate time to take the test

reflective (or effect) indicators

hypothetical constructs determines, in part, a person's responses to the items on the test

True or false: in a power test, it is assumed that there is a high probability that each question will be answered correctly.

False; speeded tests make this assumption; power tests are about measuring achievement.

formative (or causal) indicators

indicators are used to quantify something, but the indicators are not viewed as being "caused" by the construct, but are in part, exactly what defines the construct

Most procedures outlined in this book are relevant mainly for scores based on (choose one):

a. formative indicators

b. reflective indicators

c. causal indicators

d. effect indicators

e. both a. and c.

f. both b. and d.

f. both b. and d.

psychometrics

the science concerned with evaluating the attributes of psychological tests

Three attributes of psychological tests that are of the most interest to us. (page 11)

1. the type of information generated by particular interest

2. reliability

3. validity

Challenges in psychological measurement

1. complexity of concepts

2. participant reactivity

3. observer expectancy/bias

4. composite scores

5. score sensitivity

6. (lack of) awareness of psychometrics

complexity of concepts

the difficulty of capturing the important aspects of human psychological attributes in a single number or score

participant reactivity

people's knowledge that they are being observed or assessed can cause them to react in ways that obscure the meaning of their behavior

Forms of participant reactivity

demand characteristics, social desirability, malingering

demand characteristics

changing behavior to accomodate the researcher

social desirability

A tendency to give socially approved answers to questions about oneself.

malingering

the participant changes their behaviour to convey a poor impression to the person doing the measurement

observer/expectancy bias

expectation and bias effects

composite scores

scores of individual items are added up to create a composite score. This is a problem because of what is written in chapter 2

score sensitivity

refers to a measure's ability to discriminate between meaningful amounts of the dimension being measured

(e.g. using a yardstick to measure a strand of hair, or using "good" and "bad" as options for the participant in a psychological test. There may be many experiences between good and bad that exist but are not asked about)

differential psychology

the study of individual differences (includes intelligence, aptitude, personality and more)

Galton is closely associated with both ____________ and _____________________.

psychometrics; differential psychology