Test-Retest Reliabilty Presenation.pptx

Test-Retest Reliability using Pearson r

1. Test-Retest Reliability

2. Reliability A value that expresses the degree to which a test consistency produces the same result.

3. Types of Reliability Measures Measure of Internal Consistency Measure of Stability with Equivalence Measure of Equivalence Measure of Stability

4. Measure of Internal Consistency SPLIT HALF PROCEDURE: Give the test once. Score Equivalent half of the test. (e.g. odd and even numbered items) STATISTICAL MEASURE: Pearson r and Spearman-Brown Formula

5. Measure of Internal Consistency KUDER-RICHARDSON PROCEDURE: Give the test once, then correlate the proportion/percentage of the students passing and not passing a given item. STATISTICAL MEASURE: Kuder-Richardson Formula 20 and 21

6. Measure of Internal Consistency CORNBACH COEFFICIENT ALPHA PROCEDURE: Give the test once, then estimate the reliability by using the standard deviation per item and standard deviation of the test scores. STATISTICAL MEASURE: Kuder-Richardson Formula 20

7. Measure of Stability and Equivalence TEST-RETEST WITH EQUIVALENT FORMS PROCEDURE: Give parallel form of test, with increased time interval between forms. STATISTICAL MEASURE: Pearson r

8. Measure of Equivalence EQUIVALENT FORMS PROCEDURE: Give parallel form of test at the same time between forms STATISTICAL MEASURE: Pearson r

9. Measure of Stability TEST-RETEST PROCEDURE: Give a test twice to the same group with any time interval between sets, from several minutes to several years STATISTICAL MEASURE: Pearson r

10. TEST-RETEST RELIABILITY Description: Measures the stability of score between two points of time within the same participants. How it is Measured: The Correlation between response in Time 1 and Time 2.

11. Pearson Product Moment Correlation FORMULA:   Whereas; N = number of respondents/examinee X = score in the test (Test 1) Y = score in the retest (Test 2)

12. TEST-RETEST: Measure of Stability using Pearson r STUDENTS N X Y XY 1 50 51       2 43 42       3 48 48       4 45 44       5 40 41       6 47 47       7 52 51       8 39 38       9 44 43       10 43 42       11 41 41       12 46 45       13 39 39       14 51 50       15 49 48       SUMMATION (           X Y     XY STUDENTS N X Y XY 1 50 51       2 43 42       3 48 48       4 45 44       5 40 41       6 47 47       7 52 51       8 39 38       9 44 43       10 43 42       11 41 41       12 46 45       13 39 39       14 51 50       15 49 48                 X Y XY Example: This test is for the reliability of teacher made test using the statistical measure Pearson R.

13. STUDENTS N X Y XY 1 50 51       2 43 42       3 48 48       4 45 44       5 40 41       6 47 47       7 52 51       8 39 38       9 44 43       10 43 42       11 41 41       12 46 45       13 39 39       14 51 50       15 49 48       SUMMATION (           X Y     XY STUDENTS N X Y XY 1 50 51       2 43 42       3 48 48       4 45 44       5 40 41       6 47 47       7 52 51       8 39 38       9 44 43       10 43 42       11 41 41       12 46 45       13 39 39       14 51 50       15 49 48                 X Y XY FORMULA:   Whereas; N = number of respondents/examinee X = score in the test (Test 1) Y = score in the retest (Test 2)

14. STUDENTS N X Y XY 1 50 51 2500 2601 2550 2 43 42 1849 1764 1806 3 48 48 2304 2304 2304 4 45 44 2025 1936 1980 5 40 41 1600 1681 1640 6 47 47 2209 2209 2209 7 52 51 2704 2601 2652 8 39 38 1521 1444 1482 9 44 43 1936 1849 1892 10 43 42 1849 1764 1806 11 41 41 1681 1681 1681 12 46 45 2116 2025 2070 13 39 39 1521 1521 1521 14 51 50 2601 2500 2550 15 49 48 2401 2304 2352 SUMMATION ( 677 670 30817 30184 30495 X Y     XY STUDENTS N X Y XY 1 50 51 2500 2601 2550 2 43 42 1849 1764 1806 3 48 48 2304 2304 2304 4 45 44 2025 1936 1980 5 40 41 1600 1681 1640 6 47 47 2209 2209 2209 7 52 51 2704 2601 2652 8 39 38 1521 1444 1482 9 44 43 1936 1849 1892 10 43 42 1849 1764 1806 11 41 41 1681 1681 1681 12 46 45 2116 2025 2070 13 39 39 1521 1521 1521 14 51 50 2601 2500 2550 15 49 48 2401 2304 2352 677 670 30817 30184 30495 X Y XY FORMULA:   Whereas; N = number of respondents/examinee X = score in the test (Test 1) Y = score in the retest (Test 2)

15. STUDENTS N X Y XY 1 50 51 2500 2601 2550 2 43 42 1849 1764 1806 3 48 48 2304 2304 2304 4 45 44 2025 1936 1980 5 40 41 1600 1681 1640 6 47 47 2209 2209 2209 7 52 51 2704 2601 2652 8 39 38 1521 1444 1482 9 44 43 1936 1849 1892 10 43 42 1849 1764 1806 11 41 41 1681 1681 1681 12 46 45 2116 2025 2070 13 39 39 1521 1521 1521 14 51 50 2601 2500 2550 15 49 48 2401 2304 2352 SUMMATION ( 677 670 30817 30184 30495 X Y     XY STUDENTS N X Y XY 1 50 51 2500 2601 2550 2 43 42 1849 1764 1806 3 48 48 2304 2304 2304 4 45 44 2025 1936 1980 5 40 41 1600 1681 1640 6 47 47 2209 2209 2209 7 52 51 2704 2601 2652 8 39 38 1521 1444 1482 9 44 43 1936 1849 1892 10 43 42 1849 1764 1806 11 41 41 1681 1681 1681 12 46 45 2116 2025 2070 13 39 39 1521 1521 1521 14 51 50 2601 2500 2550 15 49 48 2401 2304 2352 677 670 30817 30184 30495 X Y XY FORMULA:   SOLUTION:  

16. SOLUTION:   r = 0.99

17. Interpretation VALUE DESCRIPTIVE EQUIVALENCE 0.00 = zero correlation 0.01 – 0.20 = negligible correlation 0.21 – 0.40 = low correlation 0.41 – 0.70 = moderate correlation 0.71 – 0.90 = high correlation 0.91 – 0.99 = very high correlation Note: To pass a reliability test for a teacher-made test result should be 0.85 and above.

18. RESULTS   r = 0.99 INTERPRETATION: The r value is 0.99 denotes a very high relationship. This implies that the students who got a very high scores in the first administration of the test, got a very high score in the second administration of the test. Likewise, those who got low scores in the first administration of the test got low scores in the second administration of the test. Hence, the test is highly reliable