Psychology 3051 Psychology 305: Theories of Personality Lecture 2.

Psychology 305 1

Psychology 305: Theories of Personality

Lecture 2

Psychology 305 2

Scoring your questionnaire:

1. Reverse score items 3, 5, 8, 9, and 10.

5 14 2

3 = 32 41 5

2. Sum scores across 10 items.

Psychology 305 3

Lecture 2

1. How is research used to test theories? (continued) 2. What types of measures are used to assess

personality?

3. How are the reliability and validity of personality measures assessed?

Research Methods

By the end of today’s class, you should be able to:

1. compare and contrast experiments, correlational studies, quasi-experimental studies, and case studies.

2. apply research methods to distinct hypotheses.

3. distinguish between S-, I-, and B-data.

4. identify the advantages and disadvantages of S-, I-, and B-data.

4

6. distinguish between internal consistency, inter-rater reliability, and test-retest reliability.

7. define face validity.

5

5. describe classical test theory.

6

4. Case Studies

Involve the in-depth examination of the life of one person.

Assessment techniques include:

Observation

Interviews

Administration of standard personality tests

Analysis of written text

How is Research Used to Test Theories? (continued)

7

Ted Bundy, 1946 - 1989

8

Exercise: Application of Research Methods

Construct: Happiness.

Possible operationalizations:

• Measure of life satisfaction.

• Measure assessing the frequency and intensity with which participants experience positive emotions (e.g., joy, contentment, excitement).

• Number of times participants smile.

9

People experience happiness when they have successfully influenced others’ opinions.

Experimental study.

Hypothesis Ideal Research Method

10

Group A

Group B

Random Assignment

Treatment A

Posttest

A Simple Experiment

Treatment B

Posttest

Pretest

11

People experience happiness when they have successfully influenced others’ opinions.

People who report extraordinarily high levels of happiness exhibit a unique constellation of personality characteristics.

People who experience high levels of happiness tend to be more optimistic.

Experimental study.

Case study.

Correlational study or quasi-experimental study.

Hypothesis Ideal Research Method

Psychology 305 12

What types of measures are used to assess personality?

There are three types of personality measures.

1. Personality Measures that Rely Upon Self-Report Data (S-Data)

• Most common method used for measuring personality.

• Data are provided by the participant.

• Data are collected through interviews or questionnaires; questionnaires are most commonly used.

Psychology 305 13

• Unstructured questionnaires require participants to complete open-ended fill-in-the-blank items.

• There are 2 types of questionnaires: Unstructured and structured.

E.g. Twenty Statements Test: Participants complete the statement “I am” 20 times.

Coding involves counting the number of statements that refer to a given characteristic.

Psychology 305 14

• Structured questionnaires require participants to complete items with limited response options.

E.g., True/false items: I like loud and crowded parties ………… T/FI enjoy trying new foods …………………. T/F

E.g., Adjective checklists: adventurous

conservative

E.g., Adjectives or statements accompanied by rating scales:

Psychology 305 15

Using the scale below, indicate how descriptive you believe each of the following traits is of you. Circle the appropriate number to the right of each trait.

1 2 3 4 5Not at all Somewhat Highly

descriptive descriptive descriptive

1. Adventurous 1 2 3 4 52. Ambitious 1 2 3 4 53. Broad-minded 1 2 3 4 54. Conservative 1 2 3 4 55. Extroverted 1 2 3 4 5

Psychology 305 16

Using the scale below, please indicate how much you disagree or agree with the following statements. Circle the appropriate number to the right of each statement.

1 2 3 4 5Strongly Neutral Stronglydisagree agree

1. I feel that I’m a person of worth, at least on an equal basis with others …………………………….. 1 22. I feel that I have a number of good qualities …….. 1 23. All in all, I am inclined to feel that I am a failure …. 1 24. I am able to do things as well as most people …… 1 2

Psychology 305 17

• Rosenberg’s Self-Esteem Scale

Score by reversing “negatively-keyed” items and summing responses to 10 items.

Measures global feelings of self-worth.

Mean score for university undergraduates: 38, SD = 6.2.

Females tend to score slightly lower than males.

Psychology 305 18

The participant can report on his/her private experiences (e.g., emotions, desires, beliefs).

• Advantages of S-Data:

Inexpensive.

The participant can report on his/her personality across diverse contexts; allows for general characteristics to be assessed.

Psychology 305 19

The participant’s responses may be biased (e.g., the participant may exaggerate positive attributes and/or minimize negative attributes).

• Disadvantages of S-Data:

The participant may lack sufficient self-insight to accurately respond to the items.

Psychology 305 20

2. Personality Measures that Rely Upon InformantData (I-Data)

• Typically, informants are asked to complete structured questionnaires similar to those described for S-Data.

• Data are provided by individuals who are well acquainted with the participant.

Psychology 305 21

• Advantages of I-Data:

Informants can report on characteristics that the participant may be unaware of (e.g., social reputation).

Informants’ judgments provide an assessment of the participant’s characteristics in natural settings.

Psychology 305 22

Informants’ judgments are often limited to specific contexts and, therefore, do not allow for the

participant’s general characteristics to be assessed.

• Disadvantages of I-Data:

Informants are unaware of many of the participant’s private experiences (e.g., emotions, desires, beliefs).

Informants’ judgments may be biased (e.g., a mother may overlook the negative attributes of her child).

Psychology 305 23

3. Personality Measures that Rely Upon BehaviouralData (B-Data)

• Data may be collected in either natural or laboratory settings.

• Data are collected through the researcher’s direct observation of the participant.

Psychology 305 24

• Advantages of B-data collected in natural settings:

(a) Natural settings:

The observations provide an assessment of the participant’s characteristics in naturally-occurring situations.

• The researcher observes the participant engage in his/her daily activities (e.g., observes the participant at home, has the participant complete a daily diary).

The data are not subject to the biases inherent in S-data and I-data.

Psychology 305 25

• Disadvantages of B-data collected in natural settings:

Events that the researcher wishes to observe may not occur.

Costly.

The presence of the researcher may influence the participant’s behaviour.

Psychology 305 26

• The researcher observes the participant in the laboratory.

(b) Laboratory settings:

• Three types of B-data are collected in the laboratory:

1. The participant’s overt behavioural reactions.

2. The participant’s covert physiological reactions (e.g., heart rate, galvanic skin response).

3. The participant’s responses to projective tests (e.g., Rorschach Ink Blot Test).

Psychology 305 27

Example of the Rorschach Ink Blot Test:

Psychology 305 28

• Advantages of B-data collected in laboratory settings:

The data are not subject to the biases inherent in S-data and I-data.

Allows the researcher to control extraneous influences on the participant’s behaviour.

Allows the researcher to observe the participant’s reactions to events that are not likely to occur in

natural settings.

Psychology 305 29

• Disadvantages of B-data collected in laboratory settings:

The results are difficult to generalize to naturally-occurring situations.

The presence of the researcher may influence the participant’s behaviour.

Psychology 305 30

How are the reliability and validity of personality

• In order to accurately assess a given personality characteristic, the measure that is used (whether it is based on S-, I-, or B-data) must be both reliable and valid.

Refers to the consistency with which a measure assesses a given construct across repeated measurements.

• Reliability

measures assessed?

Psychology 305 31

Method for increasing the reliability of a measure:

Theoretically, the error associated with one assessment should cancel out the error associated with another assessment.

Include multiple assessments of the construct of interest within the measure.

Psychology 305 32

Thus, for measures that rely upon

(a) S-data: Include more than one item.

(b) I-data: Include more than one item and/or use more than one informant.

(c) B-data: Make more than one observation and/or use more than one observer.

Psychology 305 33

1. I like to work alone rather than in groups.

2. I keep a schedule every day.

3. I tend to seek out leadership roles.

4. I never leave a task unfinished.

5. I’m a bad loser.

6. Hard work pays off in the long run.

7. I feel my best is never good enough.

8. I have high expectations for myself.

9. I continually strive for excellence.

10. It’s important for me to know I’m doing my best.

Psychology 305 34

The reliability of a measure is assessed in three ways.

1. Internal consistency:

• Relevant for multi-item questionnaires (S- or I-data).

• Reflects the degree to which the items that comprise the questionnaire are consistent with one another (i.e., tap the same underlying construct).

Psychology 305 35

(b) Cronbach’s alpha reliability coefficient: Involves calculating the correlation between each pair of items and averaging the resulting correlations; most

common method for assessing internal consistency; acceptable alpha for a questionnaire > .75.

• The internal consistency of a questionnaire is assessed in two ways:

(a) Split-half reliability coefficient: Involves splitting the items in half and calculating the correlation between participants’ scores on the two halves.

Psychology 305 36

2. Inter-rater reliability:

• Relevant for studies in which two or more individuals rate the participant on a given characteristic or

behaviour (S-, I-, or B-data).

• In the case of S-data, the raters are coders scoring participants’ responses to interviews or unstructured questionnaires; in the case of I-data, the raters are informants; in the case of B-data, the raters are

researchers.

Psychology 305 37

• Reflects the degree to which the scores provided by different raters are consistent with one another (i.e., the degree to which there is consensus among the raters).

• Involves calculating the correlations between the scores provided by different raters.

Psychology 305 38

3. Test-retest reliability:

• Relevant for all types of measures (S-, I-, or B-data).

• Reflects the degree to which the scores participants obtained in one test administration are consistent with the scores they obtained in a second test

administration.• Involves calculating the correlation between the scores participants obtained in the first test administration and the scores they obtained in the second test administration.

Psychology 305 39

Refers to the degree to which a measure assesses the construct it is intended to measure.

• Validity (or Construct Validity)

A measure that is reliable may or may not be valid; a reliable measure may bear no relationship to the construct it was intended to measure.

Psychology 305 40

The validity of a measure may be established by demonstrating that it possesses one or more of the following forms of validity.

1. Face validity:

• Refers to the degree to which a measure appears to tap the construct under study.

• E.g., Rosenberg’s Self-Esteem Scale.

All in all, I am inclined to feel that I am a failureOn the whole, I am satisfied with myself

Psychology 305 41

Lecture 2

1. How is research used to test theories? (continued) 2. What types of measures are used to assess

personality?

3. How are the reliability and validity of personality measures assessed?

Research Methods