MCMI-II scoring: weighted and unweighted algorithms

This brief report examines the relationship between the scale scores derived through weighted and unweighted item scoring on the Millon Clinical Multiaxial Inventory-II (MCMI-II). The inventories of 356 subjects across three samples were scored using weighted and unweighted algorithms. Correlations between the weighted and unweighted MCMI-II scales were found to approach unity. This casts doubt on whether the weighting system has substantial effect on the profiles that are generated or on reducing interscale correlations.     

An MCMI-II item-level component analysis: personality and clinical factors

The Millon Clinical Multiaxial Inventory, Version 2 (MCMI-II) was released to replace the MCMI-I. Research into the factor structure of the items of the MCMI-I showed components consistent with the underlying construction theory. No such work has been done with the new MCMI-II. For this study, we analyzed the personality disorder and clinical syndrome items across two subject samples. For 579 Veterans Administration patients and 492 normal college students, six personality factors were identified. The samples shared Hostility, Histrionic/Schizoid, Dependent, Compulsive, and a Sadistic variant. For the clinical syndrome items, eight factors were isolated for veterans and seven for normals. Depression, Alcohol Abuse, Drug Abuse, Crying, and Mania were shared factors. Most of the factors were found to be highly consistent with MCMI-II scale keyings.     

MCMI-II report style and bias: profile and validity scales analyses

This study examines the behavior of the Millon Clinical Multiaxial Inventory-II (MCMI-II) in the face of various response styles and biases. The profiles and validity configurations of eight different test-taking styles were analyzed. Four hundred MCMI-II inventories (50 for each of the following categories) were administered or generated to produce the following: (a) normal endorsement by subjects, (b) fake good for administrative reasons, (c) fake good for clinical reasons, (d) fake bad administratively, (e) fake bad clinically, (f) 50% true/50% false computer generated, (g) 95% true computer generated, and (h) 95% false computer generated. Good statistical and clinically relevant separation of the profiles was found for normal, fake good, fake bad, and the randomly generated profiles with 44% of the variance predicted. The percentage of profiles identified by validity scales, however, was modest.     

MCMI-II Item Weights: Their Lack of Effectiveness

Millon Clinical Multiaxial Inventory II (MCMI-II; Millon, 1987) results from 134 patients were scored twice; with and without the item weights. The results showed that the correlations between the weighted and unweighted versions of the same scales were extremely high, exceeding .90 in all cases. Furthermore, weighting did not significantly reduce the correlations among the scales, either within each of the four syndrome/pattern categories of the MCMI-II, or between categories. It is concluded that item weighting reduces the access of the MCMI-II by clinicians, without increasing its psychometric properties.     

Pathological gambling and personality disorders: a pilot-study with the MCMI-II

In this paper, the most frequent personality disorders related to pathological gambling are described. A sample of 50 pathological gamblers, who were assessed with the MCMI-II before treatment, and of 50 normative subjects from general population with the same demographic features (age, sex and socioeconomic level) was selected. According to the results, the 40% of clinical sample (versus the 14% of normative sample) showed at least one personality disorder. The most prevalent one was the Narcissistic (32%), followed by the Antisocial and Passive-Aggressive (16% each one of them). Furthermore, the gamblers with personality disorders presented an average of 2.2 disorders and tended to be more impulsive. Likewise pathological gamblers abused of alcohol, showed a mild anxiety and were not so adapted to everyday life as much as the control group. Finally, implications of this study for clinical practice and future research in this field are commented upon.     

Borderline and schizophrenic patients: A comparison using the MCMI-II

In the present study we examined the Millon Clinical Multiaxial Inventory-II scores of psychiatric patients with a diagnosis of either borderline personality disorder (BPD;n=13) or schizophrenia (n=13). The analyses revealed that the BPD patients were significantly elevated on a number of scales in addition to the Borderline scale. The second goal of this study was to assess the discriminative validity of the Borderline and Thought Disorder Scales with both base rate (BR) cutoffs and the number of endorsed prototypic items. The Borderline scale demonstrated the most diagnostic power when using BR cutoffs, whereas the Thought Disorder scale performed poorly, no better than chance levels, with all cutoffs.This research was supported by Social Sciences and Humanities Research Council of Canada Grant 410-89-0335 and by a grant from the Department of Research and Programme Evaluation, Brockville Psychiatric Hospital. The authors thank Renate Simmons for her assistance.     

An MCMI-II Item-Level Component Analysis: Personality and Clinical Factors

The Milton Clinical Multiaxial Inventory, Version 2 (MCMI-II) was released to replace the MCMI-I. Research into the factor structure Of the items of the MCMI-I showed components consistent with the underlying construction theory. No such work has been done with the new MCMI-II. For this study, we analyzed the personality disorder and clinical syndrome items across two subject samples. For 579 Veterans Administration patients and 492 normal college students, six personality factors were identified. The samples shared Hostility, Histrionic/ Schizoid, Dependent, Compulsive, and a Sadistic variant. For the clinical syndrome items, eight factors were isolated for veterans and seven for normals. Depression, Alcohol Abuse, Drug Abuses Crying, and Mania were shared factors. Most of the factors were found to be highly consistent with MCMI-II scale keyings.     

MCMI-II Report Style and Bias: Profile and Validity Scales Analyses

This study examines the behavior of the Millon Clinical Multiaxial Inventory-II (MCMI-II) in the face of various response styles and biases. The profiles and validity configurations of eight different test-taking styles were analyzed. Four hundred MCMI-II inventories (50 for each of the following categories) were administered or generated to produce the following: (a) normal endorsement by subjects, (b) fake good for administrative reasons, (c) fake good for clinical reasons, (d) fake bad administratively, (e) fake bad clinically, (f) 50% true/50% false computer generated, (g) 95% true computer generated, and (h) 95% false computer generated. Good statistical and clinically relevant separation of the profiles was found for normal, fake good, fake bad, and the randomly generated profiles with 44% of the variance predicted. The percentage of profiles identified by validity scales, however, was modest.     

Diagnosing personality disorders: an examination of the MMPI-2 and MCMI-II

Personality disorders are highly prevalent in clinical populations and affect outcomes across all forms of intervention. This investigation examined the diagnostic efficiency of two widely used, self-report measures of personality disorder (MMPI-2; Butcher, Dahlstrom, Graham, Tellegen, & Kaemmer, 1989; MCMI-II; Millon, 1987), as compared to a structured interview (SCID-II; Spitzer et al., 1987) diagnosis. The measures were administered to 150 residential and outpatient volunteer subjects. Persons with primary organic or psychotic-spectrum disorders were excluded from participation. Results were variable across disorders measured, with low to moderate levels of diagnostic agreement observed. The MCMI-II appears to be a more sensitive measure, whereas the MMPI-2 is more specific. The two self-report measures demonstrated greater convergence with each other than with the interview measure. Both the MMPI-2 and MCMI-II were more accurate at identifying the absence of a given disorder. Although overall diagnostic powers exist at acceptable levels. the results suggest that diagnoses generated by self-report versus interview are not interchangeable.     

Comparison of MCMI-II and 16PF Validity Scales

We administered the Millon Clinical Multiaxial Inventory-II (MCMI-II; Millon, 1987) and the Sixteen Personality Factors Inventory (16PF; Cattell, Eber, & Tatsuoka, 1970) to 131 outpatients in marital therapy and tested the correlation between the validity scales of the two instruments. The results indicated that MCMI-II Disclosure and Debasement scales were positively correlated with the 16PF Fake-Bad scale and negatively correlated with the 16PF Fake-Good scale. The MCMI-II Desirability scale was significantly correlated with the 16PF Fake-Good scale.     

MCMI-II borderline personality disorder in anorexia and bulimia nervosa

The aim of the present study is to explore the MCMI-II personality style and MCMI-II possible disorder of borderline personality (BPD) in various groups of women. 93 patients-31 anorexia nervosa restricting subtype (ANr), 31 anorexia nervosa binge-eating/purging subtype (ANp), and 31 bulimia nervosa purging subtype (BNp); 31 women at high risk for eating disorder or symptomatic control group (S-CG) and 31 without known pathology or not symptomatic control group (NS-CG)-completed the Spanish version of the MCMI-II. The results revealed: (1) clinically significant borderline personality traits [74>Base Rate (BR) <85]: 16.1% ANr, 12.9% ANp, and 45.2% BNp versus 3.2% of the S-CG and none of the NS-CG; (2) possible disorder (BR>84): 29% ANr, 41.9% ANp and 29% BNp. According to the MCM-II, women with BNp displayed more BPD traits than possible disorder (though these were more severe). However, the probability of a possible disorder was higher in ANp (more disorders than traits).     

MCMI-II profiles of women with eating disorders: a cluster analytic investigation

A three-factor model of personality pathology was investigated in a clinical sample of 183 female patients in an outpatient eating disorders treatment program. Cluster analysis of MCMI-II personality scales (Millon, 1987) yielded three distinct personality profiles, which were consistent with previous studies. First, 16.9% of the sample comprised a High Functioning cluster, which manifested no clinical elevations on the MCMI-II and had significantly lower scores on the Eating Disorder Inventory (EDI; Garner; 1991) scales than the other two clusters. Second, 49.1% of the sample comprised an Undercontrolled/Dysregulated cluster. Finally, the remaining 34% of the sample comprised an Overcontrolled/Avoidant cluster. This final cluster had significantly higher EDI Ineffectiveness scale scores than the Undercontrolled/Dysregulated cluster group. Cluster membership was not associated with eating disorder subtype, suggesting that there is considerable variance in personality pathology within eating disorder diagnostic categories.     

Bias and Millon clinical multiaxial inventory (MCMI-II) diagnosis

In the current study, the degree of bias is calculated for each of the personality disorder and clinical syndrome scales of the MCMI-II. In general, most of the MCMI-II scales are prone to only mild or moderate biases. However, the paranoid personality disorder, somatoform, bipolar: manic, thought disorder, and delusional disorder scales are prone to severe biases. When the MCMI-II is utilized to make diagnostic decisions, bipolar and schizophrenic disorders are apt to be grossly underestimated. The implications of bias in diagnostic prevalence rates are discussed and an equation is offered which provides for adjustments to be made when the percentage of positive MCMI-II test results are used to determine prevalence rates for clinical or research populations. The observation is made that imperfect sensitivity and specificity for the MCMI-II scales will result in inaccurate estimates of personality disorders and clinical syndromes when the MCMI-II is used to survey various populations.     

MCMI-II diagnosis of borderline personality disorder: base rates versus prototypic items.

The Millon Clinical Multiaxial Inventory-II (MCMI-II) profiles of 26 psychiatric inpatients diagnosed as having borderline personality disorders were compared with profiles of 42 patients with no personality disorders. The borderline group scored significantly higher on the following scales: Disclosure (X), Debasement (Z), Passive-Aggressive (8A), Self-Defeating (8B), Borderline (C), and Major Depression (CC). Differences approaching significance were also found on substance abuse measures: the Alcohol Dependence (B) scale and Drug Dependence (T) scale. These findings are consistent with criteria established in the Diagnostic and Statistical Manual of Mental Disorders (3rd ed., rev. [DSM-III-R]; American Psychiatric Association, 1987) and the results of other studies utilizing the MCMI-II. In addition, diagnostic efficiency of Scale C was assessed at various cutoff points defined by either base rate (BR) scores or the number of prototypic items endorsed. The greatest efficiency was found when a cutoff of seven or more prototypic items was utilized, with nearly 80% of the patients correctly classified. Results are discussed in terms of their relevance for further research.     

Neuroticism,coping and change in MCMI-II clinical syndromes: test of a mediator model

The aim of the study was to examine prospectively whether coping mediated the relation between Neuroticism and change in different clinical mental syndromes. Assessments were conducted with 154 former psychiatric outpatients six and seven years after their initial contact with an outpatient clinic. Dispositional coping mediated the relation between Neuroticism and change in four of the nine clinical scales of the Millon Clinical Multiaxial Inventory (MCMI-II) (Millon, 1987). High Neuroticism led to coping strategies of disengagement and the venting of emotions and to a lack of problem-focused coping, which in turn translated into a relative increase on the MCMI-II scales. The mediator model of coping was found to apply to the MCMI-II scales "somatoform disorder’, ‘dysthymia’, ‘alcohol dependence’ and ‘thought disorder’. Results are discussed under the perspective of an integration of the positions of the transactional theory of stress and personality psychology. .     

The MCMI provides a good assessment of DSM-III disorders: the MCMI-II will prove even better

Although the arguments that Widiger, Williams, Spitzer and Frances muster in their appraisal of MCMI-DSM-III relationships appear compelling, the study employed to furnish empirical support for their thesis may be seriously flawed and the item content approach they propose as a validation model is judged logically and psychometrically deficient. A rejoinder with supportive data are presented to demonstrate both the substantive parallels and the clinical concordance that exist between MCMI and DSM-III criteria. On the basis of theory development and ongoing research, a new MCMI-II assessment instrument will be forthcoming. A brief summary of this updated inventory's rationale and empirical grounding is provided.     

Factor analysis of MCMI-II and PACL basic personality scales in a college sample

This study examined factor dimensions common to the eight basic personality scales of the Millon Clinical Multiaxial Inventory-II (MCMI-II; Millon, 1987) and Personality Adjective Check List (PACL; Strack, 1987, 1990). Subjects were 140 college students (65 men and 75 women). MCMI-II weighted raw scores (WRS) and WRS corrected for number of items endorsed true by regression were employed for analysis along with PACL T-scores. Principal components analyses with varimax and direct oblimin rotations were carried out separately on the two sets of MCMI-II and PACL scores. MCMI-II and PACL scales measuring the same personalities were usually correlated most highly with each other, although some divergences were noted. WRS yielded three bipolar dimensions and a fourth unipolar method factor that loaded only the five MCMI-II scales that were strongly correlated with number of items endorsed true. Residual scores yielded a more meaningful set of three bipolar dimensions labeled Social Introversion-Extraversion, Emotionality-Restraint, and Social Dominance-Submissiveness, without the method factor, that were very similar to personality dimensions found separately in the two tests. More research is needed to clarify the response bias issue in the MCMI-II and to further explicate similarities and differences between the MCMI-II and the PACL.     

Factor Analysis of MCMI-II and PACL Basic Personality Scales in a College Sample

This study examined factor dimensions common to the eight basic personality scales of the Millon Clinical Multiaxiat Inventory-II (MCMI-II; Millon, 1987) and Personality Adjective Check List (PACL; Strack, 1987, 1990). Subjects were 140 college students (65 men and 75 women). MCMI-II weighted raw scores (WRS) and WRS corrected for number of items endorsed true by regression were employed for analysis along with PACL T-scores. Principal components analyses with varimax and direct oblimin rotations were carried out separately on the two sets of MCMI-II and PACL scores. MCMI-II and PACL scales measuring the same personalities were usually correlated most highly with each other, although some divergences were noted. WRS yielded three bipolar dimensions and a fourth unipolar method factor that loaded only the five MCMI-II scales that were strongly correlated with number of items endorsed true. Residual scores yielded a more meaningful set of three bipolar dimensions labeled Social IntroversionExtraversion, Emotionality-Restraint, and Social Dominance-Submissiveness, without the method factor, that were very similar to personality dimensions found separately in the two tests. More research is needed to clarify the response bias issue in the MCMI-II and to further explicate similarities and differences between the MCMI-II and the PACL.     

Scoring formulas and probability considerations

Bayes' theorem of inverse probability is made the basis of a general equation for scoring objective examinations. The equation so obtained is evaluated by assuming a binomial distribution of examinee knowledge and guessing tendency. A graphical illustration of the application of this equation to a hypothetical test situation is presented. The limitations inherent in the use of Bayes' theorem make it inadvisable to recommend the practical use of the equation unless future experimental evidence indicates an increase in scoring validity which more than compensates for the increase in scoring difficulty.