Split-half reliability
Test associations between randomly assigned survey items
Split-half reliability is another form of internal consistency reliability. A basic assumption of split-half reliability is that the two halves of the test should yield similar true scores and error variances. This comes from another assumption that the test items are focused on the construct.
To use split-half reliability, take a random sample of half of the items in the survey, administer the different halves to study participants, and run analyses between the two respective "split-halves." A Pearson's r or Spearman's rho correlation is run between the two halves of the instrument. Then, these coefficients are entered into the Spearman-Brown formula to yield the split-half reliability coefficient. This equation gives an aggregate measure of reliability after the instrument has been split into separate instruments.
To use split-half reliability, take a random sample of half of the items in the survey, administer the different halves to study participants, and run analyses between the two respective "split-halves." A Pearson's r or Spearman's rho correlation is run between the two halves of the instrument. Then, these coefficients are entered into the Spearman-Brown formula to yield the split-half reliability coefficient. This equation gives an aggregate measure of reliability after the instrument has been split into separate instruments.
The steps for conducting split-half reliability in SPSS
1. Researchers have randomly assigned survey items into one of two equal "halves." They have entered the data in a within-subjects fashion.
2. Click Analyze.
3. Drag the cursor over the Scale drop-down menu.
4. Click on Reliability Analysis.
5. Click on the first "half" variable to highlight it.
6. Click on the arrow to move the variable into the Items: box.
7. Click on the second "half" variable to highlight it.
8. Click on the arrow to move the variable into the Items: box.
9. Click on the Statistics button.
10. In the Descriptives for table, click on the Item, Scale, and Scale if item deleted boxes to select them.
11. Click Continue.
12. Click on the Model: drop down menu.
13. Click on Split-half to select it.
14. Click OK.
2. Click Analyze.
3. Drag the cursor over the Scale drop-down menu.
4. Click on Reliability Analysis.
5. Click on the first "half" variable to highlight it.
6. Click on the arrow to move the variable into the Items: box.
7. Click on the second "half" variable to highlight it.
8. Click on the arrow to move the variable into the Items: box.
9. Click on the Statistics button.
10. In the Descriptives for table, click on the Item, Scale, and Scale if item deleted boxes to select them.
11. Click Continue.
12. Click on the Model: drop down menu.
13. Click on Split-half to select it.
14. Click OK.
The steps for interpreting the SPSS output for split-half reliability
1. Look at the Reliability Statistics table, in the Spearman-Brown Coefficient, Equal Length row. This is the Spearman-Brown coefficient associated with the items. It needs to be more than .80 to be acceptable.
Click on the Principal Components Analysis button to continue.
Statistician For Hire
DO YOU NEED TO HIRE A STATISTICIAN?
Eric Heidel, Ph.D. will provide statistical consulting for your research study at $100/hour. Secure checkout is available with PayPal, Stripe, Venmo, and Zelle.
- Statistical Analysis
- Sample Size Calculations
- Diagnostic Testing and Epidemiological Calculations
- Psychometrics