9. RELIABILITY AND VALIDITY RIGHT

Question 1

What is reliability in research?

Answer 1

The consistency or dependability of a measure.

Question 2

What is internal reliability?

Answer 2

The extent to which a measure is consistent within itself.

Question 3

What is external reliability?

Answer 3

The extent to which a measure varies from one use to another.

Question 4

What is split-half reliability?

Answer 4

A test is split into two halves; the results from each half are compared.

Question 5

What is Cronbach’s alpha?

Answer 5

A test that assesses all possible split halves for internal consistency.

Question 6

What does a Cronbach’s alpha > .70 suggest?

Answer 6

High internal reliability.

Question 7

What does R tell us in reliability testing?

Answer 7

How each item correlates with all others and effect of item removal.

Question 8

What is test-retest reliability?

Answer 8

Stability of a test over time using the same participants.

Question 9

What is inter-rater reliability?

Answer 9

Degree to which different raters provide consistent estimates.

Question 10

How to improve inter-rater reliability?

Answer 10

Clear categories, definitions, and rater training.

Question 11

How to improve reliability in general?

Answer 11

Clear items, adequate sample size, appropriate population.

Question 12

What is sensitivity in an experiment?

Answer 12

Ability to detect even a small effect of the IV on the DV.

Question 13

What improves sensitivity?

Answer 13

Large sample size, control of unwanted variability.

Question 14

What is a ceiling effect?

Answer 14

The task is too easy; everyone scores highly.

Question 15

What is a floor effect?

Answer 15

The task is too hard; everyone scores low.

Question 16

What ensures score variation?

Answer 16

Right difficulty level and enough questions.

Question 17

What is face validity?

Answer 17

Whether the test appears to measure what it claims to.

Question 18

What is content validity?

Answer 18

Whether the test covers the full range of the construct.

Question 19

What is construct validity?

Answer 19

The degree to which a test measures the intended psychological concept.

Question 20

What is convergent validity?

Answer 20

Test correlates with others assessing the same construct.

Question 21

What is discriminant (divergent) validity?

Answer 21

Test does not correlate with measures of different constructs.

Question 22

What is criterion validity?

Answer 22

Test reflects a specific set of abilities or predicts a criterion variable.

Question 23

What is concurrent validity?

Answer 23

Test correlates with a validated measure at the same time.

Question 24

What is predictive validity?

Answer 24

Test predicts future performance or behavior.

Question 25

What is internal validity?

Answer 25

Confidence that IV manipulation causes DV changes.

Question 26

3 criteria for causation?

Answer 26

Co-variation, time-order, no alternative explanations.

Question 27

What threatens internal validity?

Answer 27

Intact groups, order effects, extraneous variables, attrition, expectancy.

Question 28

What are intact group threats?

Answer 28

Natural groups may differ systematically.

Question 29

What are order/practice effects?

Answer 29

Better performance from repeated testing.

Question 30

What are fatigue effects?

Answer 30

Poorer performance from tiredness/boredom.

Question 31

How to control order/fatigue effects?

Answer 31

Use counterbalancing.

Question 32

What are differential transfer effects?

Answer 32

One condition affects performance in the next.

Question 33

How to deal with differential transfer?

Answer 33

Use between-subjects or time between conditions.

Question 34

What are extraneous variables?

Answer 34

Uncontrolled variables that influence results.

Question 35

How to control extraneous variables?

Answer 35

Standardisation, randomisation, same environment.

Question 36

What is unequal participant loss?

Answer 36

More dropout in one group affects results.

Question 37

What are expectancy effects?

Answer 37

Participant or experimenter expectations influence results.

Question 38

What combats expectancy effects?

Answer 38

Double-blind procedures.

Question 39

What are demand characteristics?

Answer 39

Cues that reveal the experiment’s purpose.

Question 40

How to reduce demand characteristics?

Answer 40

Deception, naïve participants, between-subjects design.

Question 41

What is ecological validity?

Answer 41

Generalisability of findings to real-life settings.