Richard A. Charter

Psychometric Properties of the Folstein Mini-Mental State Examination

Criterion-referenced (Livingston) and norm-referenced (Gilmer-Feldt) techniques were used to measure the internal consistency reliability of Folstein’s Mini-Mental State Examination (MMSE) on a large sample (N = 418) of elderly medical patients. Two administration and scoring variants of the MMSE Attention and Calculation section (Serial 7s only and WORLD only) were investigated. Livingston reliability coefficients (rs) were calculated for a wide range of cutoff scores. As necessary for the calculation of the Gilmer-Feldt r, a factor analysis showed that the MMSE measures three cognitive domains. Livingston’s r for the most widely used MMSE cutoff score of 24 was .803 for Serial 7s and .795 for WORLD. The Gilmer-Feldt internal consistency reliability coefficient was .764 for Serial 7s and .747 for WORLD. Item analysis showed that nearly all of the MMSE items were good discriminators, but 12 were too easy. True score confidence intervals should be applied when interpreting MMSE test scores.

Meaning of reliability in terms of correct and incorrect clinical decisions: the art of decision making is still alive.

Examples using cut-off scores are presented to show the effects of measurement error (unreliability) on making correct and incorrect clinical decisions. These decisions are presented in terms of true positives (TPs), true negatives (TNs), false positives (FPs), and false negatives (FNs). A discussion of the difficulty in establishing reliability standards is presented.

REVISITING THE STANDARD ERRORS OF MEASUREMENT, ESTIMATE, AND PREDICTION AND THEIR APPLICATION TO TEST SCORES '

In 1979 Dudek presented a simplification of Lord and Novicks 1968 work on standard errors and their application to test scores. However, the standard error of measurement has continued to be misinterpreted. The interpretations of the standard errors of measurement, estimate, and prediction are presented. The use of confidence intervals and their importance to test score interpretation are discussed.

Is Tinnitus a Psychological Disorder

There have been consistent reports in the psychosomatic literature indicating that a patients perception of tinnitus as well as differential response to various treatment modalities may be affected by personality variables. The present study examined several personality correlates of subjective tinnitus in forty-five male patients referred to the Audiology Clinic of a large VA Medical Center with constant tinnitus of at least six months duration. Information was also collected on etiology, onset and chronicity, medications, prior treatment and related medical problems. Four standard psychological tests (MMPI, Cattels 16 PF, Rotters Locus of Control and Holmes and Rahe Life Stress Scale) were administered to all patients in the study, in addition to a comprehensive audiologic and otologic evaluation. Correlational analyses were used to examine the relationship between personality profiles and the demographic, medical and audiologic data. The expected psychosomatic characteristics of this patient population did not emerge as had been predicted from previous reports in the literature. Findings suggest that tinnitus may have an unwarranted reputation as a psychopathological disorder. Therefore, conventional psychotherapy may be of limited efficacy whereas standard audiologic treatment approaches may be more promising.

Averaging internal consistency reliability coefficients

Seven approaches to averaging reliability coefficients are presented. Each approach starts with a unique definition of the concept of “average,” and no approach is more correct than the others. Six of the approaches are applicable to internal consistency coefficients. The seventh approach is specific to alternate-forms coefficients. Although the approaches generally produce unequal averages, a Monte Carlo study found little difference among the average reliabilities calculated by the first six approaches. The first three approaches may be especially useful for reliability generalization studies.

Fear of death, death attitudes, and religious conviction in the terminally ill

The way in which an individuals belief system about death affects fear of death (FOD) has been largely neglected in the thanatology literature. The present study addresses the dimension of certainty or uncertainty with which beliefs about death are held and examines the way in which such attitudes might affect the FOD in dying patients. Twenty terminally ill patients were administered three FOD measures and a death perspective scale which assessed eight death attitudes. FOD among the terminally ill at both the conscious and fantasy level was low. Increased age was associated with declining conscious FOD, independent of life expectancy. Of the eight death perspectives, the attitudes toward death as afterlife-of-reward most directly tap the dimension of certainty or uncertainty. A significant curvilinear relationship emerged between this death perspective and FOD, suggesting that beliefs are a less critical determinant of death fear than is the certainty with which these beliefs are held. The study raises research and clinical issues pertinent to understanding FOD in dying patients.

Confidence Intervals for True Scores: Is There a Correct Approach?

Five well-known confidence interval approach es were presented and scrutinized for the pur pose of determining which approach is cor rect. Two theoretical conceptualizations for confidence intervals were presented. The con clusion was reached that two of the approaches were correct and the others were conceptually unsound. The correct approaches are: (a) the standard error of measurement centered on the obtained score, and (b) the standard error of estimate centered on the estimated true score.

It is Time to Bury the Spearman-Brown “Prophecy” Formula for Some Common Applications

The restrictive assumption of classical parallelism for the Spearman-Brown formulas makes them obsolete when the two-part alpha and coefficient alpha formulas can be used. The alpha coefficients require the less restrictive assumption of essential tau-equivalence. Even small reliability differences produced by the Spearman-Brown and alpha coefficient formulas on the same data can result in large applied differences.

The Relationship between Two Methods of Evaluating an Examinee's Difference Scores

The “nonoverlapping intervals” and “reliable difference” approaches for assessing difference scores are compared and shown to be consistent alternatives when the proper z is used to construct confidence intervals. Formulas for computing the probabilities of correct interpretation (power), overinterpretation, misinterpretation, and underinterpretation for four popular confidence interval approaches and the reliable difference approach are presented. The probability formulas show that the intuitive inference concerning the statistical significance level of nonoverlapping intervals is incorrect. The limitations of the nonoverlapping intervals approach in applied situations are discussed. It appears that in most situations the reliable difference is the easiest to apply.

CONFIDENCE INTERVAL PROCEDURES FOR RETEST, ALTERNATE-FORM, VALIDITY, AND ALPHA COEFFICIENTS

Formulas for constructing confidence intervals for retest, alternate-form, validity, and alpha coefficients are given. Examples are provided.