Statistical Analysis, Reliability of the SGRQ in CPA
We investigated the internal consistency of the SGRQ and each dimension using the Cronbach a coefficient; a correlation > 0.7 was assumed to indicate that questions within a dimension are likely to measure the same construct. We measured test-retest reliability using intraclass correlation coefficient (ICC) of the SGRQ and of each of its dimensions. Viagra online canadian
Additionally, we compared the mean difference between two different measurements as described by Bland and Altman.
To examine the convergent validity, total and dimensional scores of the SGRQ were correlated with the MRC dyspnea score, SF-36 PCS score, SF-36 MCS score, FEV1 , FEVj% predicted, and FVC. The discriminating validity was also investigated using either the median of SGRQ total and activity dimension scores or mean of the SGRQ symptom and impact dimension between the CPA bands, MRC dyspnea grades, and the general health condition as judged by a respiratory physician.
Difference in medians of the nonparametric data (total SGRQ and activity dimension scores) between CPA severity bands, MRC dyspnea grades, and health-condition grades were examined using the Kruskal-Wallis test; analysis of variance was used to examine the difference in means of parametric data (SGRQ symptoms and impact dimension scores). Difference in medians of total SGRQ and activity dimension scores between CPA grades 1 vs 3 were investigated using the Mann-Whitney U test, and an equivalent, independent sample t test was used to examine difference in means of SGRQ symptoms and impact dimension scores.
Canadianhealthcaremall Pharmacy always ready to help solve your health problems. Only quality products, fast delivery. We are always online.
The Pearson correlation coefficient was used to examine the correlation of symptom and impact domains with SF-36 PCS, SF-36 MCS, FEVj% predicted, and FVC. The Spearman correlation coefficient was used to examine the correlation of total SGRQ and activity scores with MRC dyspnea scores, SF-36 PCS score, SF-36 MCS score, FEV:% predicted, and FVC. The paired test was used to compare the mean scores of the total and dimensional SGRQ scores at both visits. The association of CPA severity with impairment in health status was also investigated using linear and binary multivariate analysis. Data analysis was performed using SPSS version 15 (IBM Corp).
