Estimate the reliability index and the Cronbach coefficient alpha for each of the eight domains of CSF-36 based on the study described in Example10.4. Assess whether each item is coherently associated with the other remaining items.

 Example10.4

Transcribed Image Text:

Example 10.4 The SF-36 has been translated into many foreign languages and used in more than 40 countries as part of the international quality-of-life assessment project (Lubetkin et al., 2003, Wang et al., 2006). A study was conducted to evaluate the performance of a Chinese version of SF-36, or CSF-36, when used to assess health-related quality of life (HRQOL) for patients with hypertension, coronary heart diseases, chronic gastritis, or peptic ulcer in mainland China (Yang et al., 2012). As noted earlier, the SF-36 instrument has eight domains, which can further be aggregated into the Physical and Mental Health subscales. In this study, there were 534 patients from the aforementioned four disease groups: 157 with hypertension, 133 with coronary heart disease, 124 with chronic gastritis, and 120 with peptic ulcer. The patients ranged in age from 16 to 86, with a mean age of 54.7. Shown in Table 10.2 are the estimates of Cronbach coefficient a and ICC based on the original ten items, as well as the nine remaining items after one of them is removed, for the PF domain of the CSF-36. The two versions of the estimates of the coefficient a are nearly indistinguishable. Thus, removing an item from this domain has a negligible effect