Psych Testing and Assessment -Chapter 5 (Validity)

Question 1

Validity

Answer 1

Agreement between a test score or measure and the quality it is believed to measure.

Question 2

Face Validity

Answer 2

when you look at a test does it appear to be measuring what you think it is measuring

Question 3

Content Validity

Answer 3

The evidence that the content of a test represents the conceptual domain it is designed to cover.

• ->one of the biggest concerns in educational testing (can be influenced by the characteristics of items (vocab) and sampling of items
• ->Needs to be especially considered when testing individuals from different cultures (due to language barriers which may affect reading level/vocab comprehension)

Question 4

Criterion Validity

Answer 4

The evidence that a test score corresponds to an accurate measure of interest. The measure of interest is called the criterion.
–>Criterion is the standard against which the test is compared to

Question 5

Construct Validity

Answer 5

A process used to establish the meaning of a test through a series of studies.
–>Researcher simultaneously defines some construct and develops the instrumentation to measure it

Question 6

Construct Underrepresentation

Answer 6

Failure to capture important components of a construct.

Question 7

Construct-irrelevant Variance

Answer 7

occurs when scores are influenced by factors irrelevant to the construct (ie. test anxiety, reading comprehension, illness, slow reader)
–>we want to avoid having these factors affecting performance (take them into consideration) as this will affect the results of the test (validity)

Question 8

Predictive Validity Evidence

Answer 8

Forcasting function of tests (e.g. college admission-SAT and GPA)

Question 9

Exploratory factor analysis

Answer 9

Estimating (how many factors are there), extracting and deciding

• ->If you have 500-1000 responses and are exploring a topic (that you do not have a tier to guide you) you can run a factor analysis to see how many factors you are measuring based on the responses.
• ->Exploring team work-run a factor analysis on the responses of people to see what factors can be measured (based on their responses) and how these can be grouped
• ->Puts all data into SPSS and SPSS will correlate these items and group them together

Question 10

Confirmatory factor analysis

Answer 10

The degree to which a hypothetical model fits the actual data

Question 11

Validity coefficient

Answer 11

relationship between a test and a criterion; is usually expressed as a correlation.
-coefficients in the range of .30-.40 are commonly considered to be high (rarely exceed .60)

Question 12

Convergent evidence

Answer 12

When a measure correlates well with other tests believed to measure the same construct.

• ->obtained in two ways:
  1) show that a test measures the same things as other tests used for the same purpose
  2) demonstrate specific relationships that we can expect if the rest is really doing its job.

Question 13

Discriminant Evidence (Divergent Validation)

Answer 13

• test should have low correlations with measures of unrelated constructs or evidence for what the test does not measure.
• by providing evidence that a test measures something different from other tests, we also provide evidence that we are measuring a unique construct.
• Indicates that the measure does not represent a construct other than the one for which it was devised.