1. Reliability

2. In Psychological Testing,
Discrepancies between ERROR does not imply
true ability and that a mistake has
measurement of been made. It implies
ability constitute that there will always
errors of be inaccuracy in
measurement. measurements.

3. Tests that are free of
measurement error
Tests that have
are deemed to be too much error
reliable. are deemed to
be unreliable.

4. It is assumed that
each person has a The difference between
true score that the true score and the
would be obtained observed score results
if there were no from measurement
error.
errors in
measurement. X -T= E
Where X – observed score
T- true score
E- error

5. It is assumed that
the true score for
an individual will Because of random error,
however, repeated
not change with applications of the
repeated same test can produce
applications of different scores.
the same test.

6. The standard The standard error of
measurements tell us, on
deviation will be the average, how much the
the standard error score varies from the true
of measurement. score.
In practice, the standard
Remember that the deviation of the observed
standard deviation score and the reliability of
tells us about the the test are used to
estimate the standard
average deviation error of measurement.
around the mean.

7. Federal government guidelines
require that a test be reliable
before one can use it to make
employment and educational
placement decisions (Heubert
and Hauser, 1999).

8. Models of Reliability
Time Sampling: The Is used to evaluate the
Test -Retest Method error associated with
administering a test at 2
different times.
Administer the same test
on 2 well-specified
occassions and find the
correlation between
scores from the 2
administrations.

9. Models of Reliability
Item Sampling: Parallel • Determines the error
Forms Method variance that is
Equivalent Forms attributable to the
Reliability selection of one
Parallel Forms particular set of items
• Compares two
equivalent forms of a
test that measure the
same attribute
• Pearson Product
Moment Correlation

10. Models of Reliability
• Split Half • A test is given and is
divided into halves
Method that are scored
separately. The results
of one half of the test
are then compared
with the results of the
other.
• Odd-even system
• Correlation between
the 2 halves

11. • Kuder-Richardson 20 • Use to calculate for the
Formula (KR20) reliability of the test in
which the items are
dichotomous, scored 0
or 1 (usually for right
or wrong)
• Sum of the product of
people passing each
item times the
proportion of people
failing each item

12. Models of Reliability
• Split Half Method • Spearman- Brown
Formula: use to
correct for the half
length of the test

13. Kuder-Richardson A special case of the
reliability formula that
21 (KR21) does not require the
calculation of the p’s
and q’s., instead it uses
the mean test score
Assumes that all items
are of average
difficulty

14. Coeficient Alpha The most general
Cronbach Alpha method of finding
estimates of reliability
through internal
consistency.

15. How reliable is reliable?
What is “high The answer depends on
the use of the test.
enough”? .70 - .80 are good enough
for the purposes of
basic research.
In CLINICAL SETTINGS,
a .90 reliability index
may not be good
enough; greater than .
95 should be required