Calculating Reliability of Quantitative Measures

Split-Half Reliability Likert Scale

If you administer a Likert Scale or have another measure that does not have just one correct answer, the preferable statistic to calculate the split-half reliability is coefficient alpha (otherwise called Cronbachs alpha). Coefficient alpha is difficult to calculate by hand. If you have access to SPSS, use coefficient alpha to calculate the reliability. However, if you must calculate the reliability by hand, use the Spearman Brown formula. Spearman Brown is not as accurate, but is much easier to calculate.

Split-Half Reliability Likert Scale

Table1: Multi-item statements to measure students preference with their MBA graduate program at the CAS.
Strongly Agree Strongly Disagree Disagree Agree

Quality Rating

ITEM My advisor is knowledgeable about my program It is easy to get an appointment with my advisor My advisor cares about me as a person My advisor considers me a professional The course requirement for my major are appropriate The course requirements for my major will help me get a better job in my discipline. My graduate program allows me adequate flexibility Upon graduation, I anticipate I will not have any problems finding a position in my discipline. My graduate program need to be updated The quality of the course required in my major is adequate

1 1 1 1 1 1

2 2 2 2 2 2

3 3 3 3 3 3

4 4 4 4 4 4

1 1
1 1

2 2
2 2

3 3
3 3

4 4
4 4

These are the 10 items that measured preference of

MBA graduate program at the CAS

The data for each participant is the code for what they selected for each item: 1 is strongly disagree, 2 is disagree, 3 is agree, and 4 is strongly agree

15 participants took the test (survey)

Split the questions into half. The recommended procedure is to assign every other item to one half of the test. (If you simply take the first half of the items, the participants may have become tired at the end of the questionnaire and the reliability estimate will be artificially lower.)

The first half total was calculated by adding up the scores for items 1, 3, 5, 7, and 9.

The second half total was calculated by adding up the scores for items 2, 4, 6, 8, and 10

Now that we have our two halves of the test, calculate the Pearson Product-Moment Correlation between them.

Now that we have calculated the Pearson correlation between our two halves (rhh = 0.67), we substitute this value for rhh and we can calculate rSB

Interpretation of reliability coefficient

George and Mallery (2003) provide the following rules of thumb: rsb 0.90 Excellent (0.90 and above) rsb 0.80 Good (0.80 0.89) rsb 0.70 Acceptable (0.70 0.79) rsb 0.60 Questionable (0.60 0.69) rsb 0.50 Poor, and (0.50 0.59) rsb < 0.50 Unacceptable (below 0.50)