Question

validity & reliability (q1 - 10)

1. which of the following best defines validity in research?

a. the consistency of results
b. the accuracy of measuring what is intended
c. the ability to generalize findings
d. the use of multiple researchers

1. which of the following best defines reliability in research?

a. the accuracy of a test
b. the consistency of results over time
c. the measurement of unrelated factors
d. the generalization of findings

1. a bathroom scale always shows 5 pounds too heavy, but gives the same error every time. this is an example of:

a. valid but not reliable
b. reliable but not valid
c. both valid and reliable
d. neither valid nor reliable

1. a test that accurately predicts future job performance has high:

a. face validity
b. predictive validity
c. test - retest reliability
d. internal reliability

1. which type of reliability checks consistency between different forms of the same test?

a. test - retest
b. inter - rater
c. split - half
d. alternate forms

1. two researchers observe the same behavior and record similar results. this demonstrates:

a. inter - rater reliability

Explanation:

1. Validity in research is about accurately measuring what is intended. Consistency is related to reliability, generalizing findings is external validity - related, and multiple researchers don't define validity directly.
2. Reliability is the consistency of results over time. Accuracy of a test is more related to validity, measuring unrelated factors is not reliability, and generalization of findings is about validity.
3. The scale gives consistent (same error every time) but inaccurate (always 5 pounds too heavy) results, so it's reliable but not valid.
4. A test that predicts future job - performance well has high predictive validity. Face validity is about appearance of validity, test - retest reliability is about consistency over time, and internal reliability is about consistency within a test.
5. Alternate forms reliability checks consistency between different forms of the same test. Test - retest is about consistency over time, inter - rater is between raters, and split - half is about internal consistency of a single test.
6. When two researchers record similar results for the same behavior, it shows inter - rater reliability.

Answer:

1. B. The accuracy of measuring what is intended
2. B. The consistency of results over time
3. B. Reliable but not valid
4. B. Predictive validity
5. D. Alternate forms
6. A. Inter - rater reliability