## Reliability

NSE recognizes that test reliability is defined as the degree to which the test gives consistent results each time it is given.

In other words, reliability answers the following questions:

1. Can I depend on the test to measure the same outcomes consistently?
2. Given all the other variables being the same, will the test produce the same results again?

NSE uses the Kuder-Richardson 21 formula to calculate reliability coefficients:

r (reliability) = (K)(SD2)-M(K-M)(SD2)(K-1)

K = the number of items in the list
SD = the standard deviation of the scores
M = the mean of the scores

The scores of reliability are judged against a perfect score of 1.00. The closer the reliability coefficient is to 1.00, the better it is. Most standardized tests usually have a reliability coefficient of .90 or above.1

### Reliability Coefficients

#### for the 2015 National Spanish Exam

Level 01 Vocabulary Grammar Achievement Reading Listening Proficiency Total
Regular (N=6761)
Mean Raw Score 61.1 50.7 111.9 56.2 59.2 115.4 227.3
Standard Deviation 20.4 19.2 36.9 19.0 21.6 36.9 68.4
Reliability coefficient 0.953 0.941 0.969 0.942 0.958 0.969 0.981
Outside Experience (N=1533)
Mean Raw Score 71.5 57.2 128.7 63.7 68.6 132.3 261.0
Standard Deviation 21.5 19.9 38.8 18.6 20.9 36.2 69.8
Reliability coefficient 0.965 0.948 0.974 0.943 0.960 0.971 0.984
Bilingual (N=445)
Mean Raw Score 85.1 67.1 152.2 71.9 77.7 149.6 301.8
Standard Deviation 18.1 20.0 35.7 20.4 22.1 39.1 68.9
Reliability coefficient 0.971 0.954 0.976 0.961 0.974 0.980 0.987

Level 1 Vocabulary Grammar Achievement Reading Listening Proficiency Total
Regular (N=37530)
Mean Raw Score 67.7 57.7 125.4 61.7 63.2 124.9 250.3
Standard Deviation 20.3 19.6 37.5 19.0 21.5 37.2 69.2
Reliability coefficient 0.956 0.946 0.972 0.944 0.959 0.971 0.983
Outside Experience (N=4243)
Mean Raw Score 79.5 65.7 145.2 69.5 73.5 143.0 288.2
Standard Deviation 19.1 19.9 36.8 19.8 21.4 38.5 70.0
Reliability coefficient 0.965 0.953 0.976 0.955 0.967 0.977 0.986
Bilingual (N=2025)
Mean Raw Score 85.7 70.2 155.9 73.8 78.1 151.9 307.7
Standard Deviation 18.3 19.7 35.9 22.5 23.2 43.4 72.4
Reliability coefficient 0.973 0.956 0.978 0.971 0.978 0.985 0.989

Level 2 Vocabulary Grammar Achievement Reading Listening Proficiency Total
Regular (N=37164)
Mean Raw Score 57.1 37.9 95.0 69.8 55.9 125.7 220.7
Standard Deviation 18.2 19.8 34.8 21.1 18.1 35.4 63.6
Reliability coefficient 0.935 0.950 0.964 0.962 0.934 0.968 0.978
Outside Experience (N=2118)
Mean Raw Score 68.1 42.4 110.6 73.7 62.5 136.2 246.7
Standard Deviation 20.6 20.4 37.7 21.5 20.0 38.2 68.7
Reliability coefficient 0.958 0.951 0.970 0.968 0.951 0.975 0.982
Bilingual (N=2832)
Mean Raw Score 83.9 52.8 136.7 77.3 71.7 149.0 285.7
Standard Deviation 18.7 19.1 35.2 20.7 19.7 37.2 65.1
Reliability coefficient 0.971 0.941 0.970 0.969 0.957 0.977 0.983

Level 3 Vocabulary Grammar Achievement Reading Listening Proficiency Total
Regular (N=29166)
Mean Raw Score 54.9 44.2 99.2 64.8 54.5 119.3 218.5
Standard Deviation 16.6 16.6 29.6 17.7 19.5 32.8 56.0
Reliability coefficient 0.920 0.920 0.948 0.937 0.944 0.960 0.971
Outside Experience (N=1973)
Mean Raw Score 65.0 46.7 111.7 66.8 63.0 129.8 241.5
Standard Deviation 20.7 17.5 34.2 18.9 21.6 36.3 63.7
Reliability coefficient 0.956 0.928 0.963 0.947 0.960 0.970 0.979
Bilingual (N=2958)
Mean Raw Score 84.3 57.8 142.1 68.3 72.9 141.1 283.3
Standard Deviation 18.6 17.7 33.1 19.2 21.4 37.0 60.3
Reliability coefficient 0.971 0.931 0.967 0.951 0.967 0.974 0.980

Level 4 Vocabulary Grammar Achievement Reading Listening Proficiency Total
Regular (N=16629)
Mean Raw Score 52.6 40.5 93.1 62.4 69.7 132.1 225.2
Standard Deviation 19.8 19.7 34.5 19.2 20.1 35.3 62.6
Reliability coefficient 0.946 0.948 0.963 0.946 0.957 0.969 0.977
Outside Experience (N=1165)
Mean Raw Score 61.5 42.8 104.4 64.5 74.9 139.5 243.8
Standard Deviation 21.7 19.1 35.7 20.8 21.3 38.4 66.5
Reliability coefficient 0.959 0.943 0.966 0.957 0.968 0.976 0.981
Bilingual (N=2334)
Mean Raw Score 76.5 56.4 132.9 68.1 81.2 149.3 282.2
Standard Deviation 18.8 18.7 33.6 20.7 19.5 36.6 60.7
Reliability coefficient 0.959 0.939 0.965 0.959 0.970 0.977 0.980

Level 5 Vocabulary Grammar Achievement Reading Listening Proficiency Total
Regular (N=5712)
Mean Raw Score 59.4 46.4 105.9 62.7 68.4 131.1 237.0
Standard Deviation 21.7 19.3 36.4 20.3 21.1 37.7 67.3
Reliability coefficient 0.958 0.943 0.967 0.953 0.961 0.973 0.981
Outside Experience (N=517)
Mean Raw Score 68.9 47.2 116.1 65.1 72.5 137.6 253.7
Standard Deviation 22.1 18.8 36.2 21.0 20.2 37.3 66.4
Reliability coefficient 0.966 0.939 0.968 0.958 0.961 0.974 0.981
Bilingual (N=1540)
Mean Raw Score 82.9 59.8 142.7 69.4 76.7 146.1 288.8
Standard Deviation 16.1 17.1 29.3 21.6 19.6 37.8 58.1
Reliability coefficient 0.955 0.927 0.957 0.964 0.963 0.977 0.979

Level 6 Vocabulary Grammar Achievement Reading Listening Proficiency Total
Regular (N=507)
Mean Raw Score 67.8 50.8 118.6 68.2 73.4 141.6 260.2
Standard Deviation 20.4 18.9 35.0 19.2 19.3 35.4 63.1
Reliability coefficient 0.957 0.940 0.965 0.951 0.957 0.972 0.980
Outside Experience (N=108)
Mean Raw Score 73.8 52.3 126.1 66.8 73.9 140.7 266.7
Standard Deviation 19.4 18.8 31.5 23.4 23.2 43.4 64.7
Reliability coefficient 0.958 0.939 0.958 0.969 0.974 0.983 0.981
Bilingual (N=442)
Mean Raw Score 86.6 65.6 152.2 72.4 77.3 149.7 301.9
Standard Deviation 13.7 16.4 26.3 21.5 20.5 39.4 53.9
Reliability coefficient 0.947 0.925 0.952 0.966 0.968 0.981 0.977

1John A. Kaufhold, Basic Statistics for Educational Research (New York: iUniverse, Inc., 2007) pp. 43-46.