Correlation of Mini-Mental-State-Examination (MMSE), Syndrom-Kurztest (SKT) and Clock test (CT) scores in patients with cognitive impairment assessed by means of multiple regression and response surface analysis.

The objective of our study was to assess the correlation of routine neuropsychological test results in elderly patients referred to a gerontopsychiatric ward. MMSEs, CTs and SKTs were performed in 94 patients (age: median = 74 years, range = 54-89 years; 64 f, 30 m) with mild to moderate dementia and evaluated retrospectively. Pairwise Spearman rank correlation, multiple regression and response surface analysis were used to assess relations between test results. The scores of all three tests used were reciprocally correlated (P < 0.05) yielding the following pairwise R-values: SKT versus MMSE: -0.77, SKT versus CT: 0.69, MMSE versus Clock test: -0.61. Multiple regression analysis showed a maximum correlation of 0.87 and marked standardised beta values, if SKT was chosen as dependent variable. Test scores could be well fitted to both symmetric linear (SKT = a + b x CT + c x MMSE; R(2) = 0.67, P < 0.01) and non-linear (SKT = a + b x CT + c x MMSE + d x CT(2) + e x MMSE(2) + f x CT x MMSE; R(2) = 0.67, P < 0.01) response surfaces. In conclusion, test scores of SKT, CT or MMSE in patients with dementia showed a marked correlation. In clinical practice the may be considered as almost interchangeable test options.

[Determination of Reliability of Psychometric Tests in Psychiatry Using Canonical Correlation] / Bestimmung der Reliabilität psychometrischer Testverfahren in der Psychiatrie mittels der kanonischen Korrelation.

Test results (raw scores) are composed of an unknown true score and an error term. The error term can be estimated by means of test reliability which is defined by the ratio of true variance and obtained variance. Different estimates of reliability either based on single measurements (e. g. Cronbach's coefficient, split half reliability, Kuder Richardson method) or two measurements (test/retest, inter- or intrarater reliability) are available. Parallel test reliability depends on the correlation of two different tests obtained in one session. Canonical correlation methods allow an extension of the parallel test situation and split half technique. Two or more tests are performed in a sample of subjects. Randomized subsets are correlated using canonical correlation technique. The objective of this study is to estimate the homogeneity of test batteries. 94 patients (64 f, 30 m; age: 54 - 89 ys.) supposed to have dementia were tested using the clocktest (CT, scores: 1 - 5), MMSE (mini mental state examination) and SKT (Syndrom Kurztest). Four (i, j: 1 - 4) subsets of 20 patients each were determined by random and the following characteristics were calculated: Empiric correlation coefficient for n = 94 (R), canonical correlation coefficient (Rcan), eigenvalues (EV) and redundancy (Rnd) of corresponding variable sets. The results of canonical analysis showed canonical correlation coefficients in order of 0.8 to 0.9 (p-values < 0,001). This high internal consistency can be interpreted as a measure of reliability of the test batteries. In conclusion, canonical correlation based on parallel tests splitted in subsets gives information on consistency, i. e. reliability, of test batteries in addition to conventional correlation methods.

[Determination of reliability of psychometric tests in psychiatry using canonical correlation]. / Bestimmung der Reliabilität psychometrischer Testverfahren in der Psychiatrie mittels der kanonischen Korrelation.

Test results (raw scores) are composed of an unknown true score and an error term. The error term can be estimated by means of test reliability which is defined by the ratio of true variance and obtained variance. Different estimates of reliability either based on single measurements (e.g. Cronbach's coefficient, split half reliability, Kuder Richardson method) or two measurements (test/retest, inter- or intrarater reliability) are available. Parallel test reliability depends on the correlation of two different tests obtained in one session. Canonical correlation methods allow an extension of the parallel test situation and split half technique. Two or more tests are performed in a sample of subjects. Randomized subsets are correlated using canonical correlation technique. The objective of this study is to estimate the homogeneity of test batteries. 94 patients (64 f, 30 m; age: 54-89 ys.) supposed to have dementia were tested using the clocktest (CT, scores: 1-5), MMSE (mini mental state examination) and SKT (Syndrom Kurztest). Four (i, j: 1-4) subsets of 20 patients each were determined by random and the following characteristics were calculated: Empiric correlation coefficient for n = 94 (R), canonical correlation coefficient (Rcan), eigenvalues (EV) and redundancy (Rnd) of corresponding variable sets. The results of canonical analysis showed canonical correlation coefficients in order of 0.8 to 0.9 (p-values < 0.001). This high internal consistency can be interpreted as a measure of reliability of the test batteries. In conclusion, canonical correlation based on parallel tests splitted in subsets gives information on consistency, i.e. reliability, of test batteries in addition to conventional correlation methods.