Vous êtes sur la page 1sur 10

Ch.

6: Reliability and
Validity in Measurement
and Research

Rosnow, Beginning Behavioral Research, 5/e. Copyright 2005 by Prentice Hall

Validity and Reliability

Validity: How well does the


measure or design do what it
purports to do?
Reliability: How consistent or
stable is the instrument?

Is the instrument dependable?

Rosnow, Beginning Behavioral Research, 5/e. Copyright 2005 by Prentice Hall

Random and Systematic


Error

Random Error: Chance fluctuations

Tend to cancel out over repeated


measurements.

Systematic Error: Fluctuations that


are slanted in a particular
direction.

Also known as bias

Rosnow, Beginning Behavioral Research, 5/e. Copyright 2005 by Prentice Hall

Types of Reliability

Test-Retest Reliability: Degree of


temporal stability of the instrument.

Assessed by having instrument completed by


same people during two different time
periods.

Alternate-Forms Reliability: Degree of


relatedness of different forms of test.

Used to minimize inflated reliability


correlations due to familiarity with test items.

Rosnow, Beginning Behavioral Research, 5/e. Copyright 2005 by Prentice Hall

Types of Reliability (cont.)

Internal-Consistency Reliability:
Overall degree of relatedness of all
test items or raters.

Also called reliability of components.

Item-to-Item Reliability: The reliability


of any single item on average.

Judge-to-Judge Reliability: The reliability


of any single judge on average.

Rosnow, Beginning Behavioral Research, 5/e. Copyright 2005 by Prentice Hall

Spearman-Brown Formula

Used to estimate the internal consistency


of a test or judges overall.
nr
SB
ii
The formula is: R

1 n 1 rii

Where:
RSB = the overall internal consistency reliability
n = the total number of items in the test
r = the average intercorrelation among the
ii
items or among the judges.
Rosnow, Beginning Behavioral Research, 5/e. Copyright 2005 by Prentice Hall

Reliability, Replication, and


External Validity

External Validity: The generalizability


of an inferred causal relationship.
The dependability of causal
generalizations is based on replicable
findings.

But how know if have replicated a


finding?
Role of the effect size.

Rosnow, Beginning Behavioral Research, 5/e. Copyright 2005 by Prentice Hall

Validity in Test and


Instrument Construction

Content Validity: Is the relevant


material adequately sampled?
Criterion Validity: How well does
the test correlated with outcome
criteria?

Concurrent Validity
Predictive Validity

Rosnow, Beginning Behavioral Research, 5/e. Copyright 2005 by Prentice Hall

Construct Validity in Test


Development

Construct Validity: What does the


test really assess?

Does the test have the ability to


discriminate?

Establishing construct validity

Convergent validity
Discriminant validity

Rosnow, Beginning Behavioral Research, 5/e. Copyright 2005 by Prentice Hall

Validity and Causal


Inference in Experimental
Design

External Validity
Construct Validity: The validity of the
hypothetical idea linking the IV and
DV.
Statistical Conclusion Validity: Are the
statistical conclusions well-grounded?
Internal Validity: Ability to rule out
plausible rival hypotheses.

Rosnow, Beginning Behavioral Research, 5/e. Copyright 2005 by Prentice Hall

Vous aimerez peut-être aussi