Chapter 3 Flashcards
3 types of measures used in behaivoral research
- Observational measures
- psysiological measures
- Self-report measures
Observational measures
Involve the direct observation of behavior
Physiological measures
Measures internal processes that are not directly obserbvable- such as heart rate brain activity and hormonal chynages- with sophisticated equipment
Self-report measures
The replies people give to questionairs and interviews, which may provide information about the respondent’s thoughts, feelings, or behavior
Cognitive self report measures
Measure what people think about something
Affective self report measures
Involve participants responses regarding how they feel
Psychometrics
The study of psychological measurement
Nominal scale
The numbers that are assigned to participants’ behaivors or characteristics are essential labels
Ordinal scale
The rank ordering of a set of scores that reflect a participants’ behaivors or characteristics
Interval scale
Equal differences between number reflect equal differences between participants on the characteristics being measured
Ratio scale
Has a true zero point, and involves real numbers that can be added, subtracted, multiplied, and divided
Reliability
Refers to the consistency or dependability of a measuring technique
Observed score=
True score+measurement error
True score
The score that the participant would have obtained if out measures were perfect and we were able to measure whatever we were measuring without error
Measurement error
The result of factors that distort the observed score that that it isn’t precisely what it should be
5 major catagories contributing to measurement error
- Transient states
- stable attributes
- Situational factors
- Characteristics of measure
- Mistakes
Transient state ex.s
Mood, health, level of fatigue, feelings
Stable attributes ex.s
Personality characteristics
Situational factors ex.s
Environment, how animals are handled, demeanor of researchers involved , room temperature, light, noise, crowding
Characteristics of measure
Ambiguous questions, measures that induce fatigue, fear or pain
Mistakes
Mistakes in recording data, improper numbers or responses entered
Reliability=
True score variance/total variance
Correlation coefficient
A statistic that expresses the strength of the relationship between two measures on a scale of 0.00-1.00
Test-retest reliability
The consistency of a participants responses on a measure overtime
Interitem reliability
The degree of constituency among items on a scale
Item-total correlation
The correlation between a particular item and the sum of all other items on a scale
Split-half reliability
An index of interitem reliability, in which the researcher divides the items on a scale into 2 sets, obtained a total score for each set, and then calculated the correlation of scores between these two sets.
Interrater reliability
Involves the consistency among 2+ researchers or a serve or record participant’s behavior
4 ways to increase reliability of measure
- Standardize administration of procedure
- clarify instructions and questions
- train observers
- Minimize errors in coding and entering data
Validity
The extent to which a measurement procedure actually measures what it is intended to measure
3 types of validity
- face validity
- construct validity
- Criterion- related validity
Face validity
Refers to the extent to which the measurement technique appears, on the face of it, to measure what it is designed to measure
Construct validity
Whether a particular measure relates as it should to other measures
Hypothetical constructs
Entities that cannot be directly observed but are inferred not he basis of empirical evidence
Convergent validity
A measure should correlate with other measures that it should correlate with
Discriminate validity
A measure should not correlate with measures it should not correlate with
Criterion-related validity
The extent to which a measure allows us to distinguish among participants not he basis of a particulate behaivoral criterion
Concurrent validity
The two measures are administered at roughly the same time
Predictive validity
The measure’s ability to distinguish people on a relevant behaivoral criterion at some point int he future.
Test bias
Occurs when a particular measure is not equally valid for everyone who takes the test
