Textbook Notes (280,000)
CA (160,000)
UTSC (20,000)
Psychology (10,000)
PSYB30H3 (500)
Chapter 4

Chapter 4.docx


Department
Psychology
Course Code
PSYB30H3
Professor
Connie Boudens
Chapter
4

This preview shows page 1. to view the full 5 pages of the document.
Personality - Chapter 4
1
personality assessment - the measure of the individual characteristics of a person ; most
commonly used are personality tests
What Makes a Good Personality Test?
developers of a personality test must demonstrate that the test is valid and reliable, and
specify the conditions, populations and cultures the test applies to
must also provide theoretical background and research evidence confirming that the test is
related to certain outcomes
biggest difference between fake and real personality tests is that legitimate personality tests
have reliability, validity and generalizability, backed by research evidence
Test Reliability: Generalizability Across Time, Items and Raters
reliability is a prerequisite for validity
reliability - an estimate of how consistent a test is: A good test gives consistent results over
time, items or raters
we want to know that a test gives consistent results in all of these situations: across time,
across items and across raters
a way to check to see if a test has temporal consistency reliability is to have respondents
take the test a second time to see if their scores are similar - demonstrate by test-retest
reliability
a way to check internal consistency reliability is to see if different items of the test give
similar results - demonstrate by parallel forms reliability; make up two versions of a test
that were comparable and check to see that the scores on the parallel forms of the test were
similar - split -half reliability; split a test in half and see if test-takers' scores on one half
correlated with scores on the other half - Cronback's alpha; a statistic that estimates: the
generalizability of the score from one set of items to another, make sure an alpha of .70 to .80
and even higher when designing tests that will be used to compare/judge individuals
make sure our measures are reliable across multiple raters - to check for interrater
reliability - have 2 separate judges rate the personality or behavior of a 3rd person - if the
raters are consistent in their judgements then these correlations ought to be high
Test Validity
validity - the extent to which a test measures what it is supposed to measure
a test has validity if it is grounded in research evidence, that is, if it correlates with some
standard
every test must have construct validity - measure the theoretical concept it was designed to
measure
a test has face validity when it appears to measure the construct of interest - useful under two
conditions
You're Reading a Preview

Unlock to view full version

Only page 1 are available for preview. Some parts have been intentionally blurred.

Personality - Chapter 4
2
first, face validity is important for personnel testing, or other situations where the
cooperation and motivation of the test-taker can affect the results of a test - test-takers try
harder and take a test more seriously if they can see how a test is related to the content of job
second, useful when researchers are developing a new measure of a concept - they will
administer their test to respondents and see which items are actually related to the trait or
concept the researcher wants to measure
criterion validity - determines how good a test is, by comparing the results of the test to an
external standard like another personality test or some behavioral outcome
check to see if our test is similar to other tests of the same construct or to tests of related
constructs - this establishes convergent validity
we want to make sure that our test is different from tests of constructs that we theorize to be
unrelated to the one we are interested in - discriminant validity
Barnum Effect - when people falsely believe that invalid personality tests are actually good
measures of personality because they contain feedback so general that it applies to any
people at the same time
Test Generalizability
generalizability - establishes the boundaries or limitations of a test - we cannot use a test for
a use other than what it was intended, nor administer the test to a group of people it was not
validated on
Personality Tests
Types and Formats of Personality Tests
divided into two kinds: self-report and performance-based. once called objective tests and
projective tests
self report tests, respondents answer questions about themselves
performance based tests use an unstructured formant in which participants must respond to a
stimulus in as much detail as they would like - respondents must project their own meanings,
significances, patterns, feelings, interpretations, concerns, or worldviews on to the stimulus
Self-Report Tests
self-report personality measures may use a dichotomous two-choice scale (eg. true/false,
yes/no) or a Likert-typing rating scale
Likert rating scales might ask participants to rate their agreement (strongly agree/disagree),
degree (very little), similarity (uncharacteristic of me to characteristic of me) , or frequency
(never/always) using a scale, such as a 5 or 7 point scale
tests with a forced-choice formant present respondents with a limited number of choices
rather than a rating scale (ex: true/false)
You're Reading a Preview

Unlock to view full version