*, **, and ***; statistical nonsense at the .00000 level.

Researchers who report statistical significance with *, **, ***, or p values are confusing statistical significance with clinical significance and are wasting time, money, and energy with studies that are either too precise, or more likely too imprecise. Therefore, researchers who value their time, money, and energy should avoid this outmoded statistical procedure, and present alpha to engage in the power calculation.

A dental-facial attractiveness scale. Part I. Reliability and validity.

Since the decision to seek orthodontic treatment is frequently the result of concerns about appearance, assessment of need for treatment should include an impartial evaluation of dental-facial appearance. While some of the standardized techniques for assessing malocclusion have included a consideration of esthetic impairment, they tend to confound this with functional impairment. The purpose of this study was to develop a valid and reliable index that provides relatively objective judgments of dental-facial attractiveness. The subjects in this study were eighth- and ninth-grade children seeking orthodontic treatment and their siblings, and eighth- and ninth-grade children not seeking treatment and their siblings. Photographs of the children were rated for dental-facial attractiveness by lay and dental judges. Children were also assessed for severity of malocclusion by means of the Treatment Priority index. Children seeking treatment were perceived as significantly less attractive than children not seeking treatment. Dental judges rated children seeking treatment as more attractive than did nondental judges. Intraclass reliability coefficients were moderate to high.

A dental-facial attractiveness scale. Part II. Consistency of perception.

A previous report describes the reliability and validity of a scale designed to assess perceptions of dental-facial attractiveness, independent of occlusal function. The purpose of the present study was to assess the consistency of judgments of dental-facial attractiveness (DFA) for sex and race differences in photographed children. Using a five-pont DFA scale, twelve college freshmen (three black females, three black males, three white females, three white males) rated ninety-six photographs of the mouths and jaws of 13- to 14-year-old children (twenty-four black females, twenty-four black males, twenty-four white females, twenty-four white males). No significant mean differences were found between the black and white photographed or between the female and male children photographed. However, means were significantly different for DFA judgments by race and sex of the raters. Black raters judged all photographs to be more attractive than did white raters, and female raters judged all photographs to be more attractive than did male raters. Correlational data are presented describing consistency of perception within rater groups and photographed groups of children.

Why covariance analysis should replace increment analysis of variance in caries studies.

Consider a caries study where experimental units are a) randomly assigned to groups, b) premeasured on DMFS, c) administered a specified treatment depending on group membership, and d) postmeasured on DMFS. Traditional analysis of these data consists of analysis of variance of the increment scores (increment ANOVA). In the place of increment ANOVA, others have suggested analysis of covariance with the postmeasure as criterion and the premeasure of covariate (ANOCOV). The present paper examines and documents the following: 1) Increment ANOVA and ANOCOV test the same null hypothesis. 2) Increment ANOVA and ANOCOV have exactly the same assumptions. 3) Increment ANOVA is usually less precise than ANOCOV. 4) The same concern for violations of assumptions must be expressed with increment ANOVA as with ANOCOV (see No. 2 above). 5) ANOCOV should replace increment ANOVA in caries studies (see points 1-4).

Variables discriminating individuals who seek orthodontic treatment.

Overall, these results support the view that dental-facial esthetics and self-perceptions of occlusal appearance, as well as attitudes toward malocclusion and orthodontic treatment, are important factors in the individual's decision to obtain orthodontic treatment. The data indicate that psychosocial variables not directly related to occlusal problems and treatment, do not add significantly to the description of differences between those who seek treatment and those who do not. While these analyses did not include a number of variables--such as socioeconomic factors or attitudes of significant others--which may also be important in predicting individual response to malocclusion, they do suggest strongly that psychosocial factors directly related to need for treatment are probably most productively assessed in terms of self-perceptions of occlusal appearance and attitudes regarding dental malrelations and their treatment.

Reliability and stability of the orthodontic Patient Cooperation Scale.

Patient cooperation is recognized as an important factor in the outcome of orthodontic treatment. In order to predict patient cooperation, there have been numerous studies which have examined its correlates in orthodontic treatment. However, few, if any, of these studies have considered the reliability or stability of their patient cooperation measures. Hence, the correlates found or not found are suspect. The present article reports on the internal consistency and stability of the Orthodontic Patient Cooperation Scale (OPCS). Using the responses of practicing orthodontists, a list was generated of ten patient behaviors frequently considered in evaluating a patient's cooperation. Subjects were eighth- and ninth-grade students undergoing orthodontic treatment, who were rated by their own orthodontists after 2 months and 6 months of treatment. The internal consistency for the scale was estimated to be 0.71 (N = 44) at 2 months and 0.80 (N = 45) at 6 months. The correlation between scores at 2 months and at 6 months was 0.58 (N = 44), which may be considered to be a conservative estimate of the long-term stability of the scale. In summary, the OPCS has adequate internal consistency and reasonably stable scores over a 4-month period. As such, it should prove useful in studies looking for predictors of patient cooperation and in studies examining the relationship of patient cooperation and outcome of treatment.

Validity of an orthodontic treatment priority index to measure need for treatment.

In establishing the validity of an index for identifying individuals needing orthodontic treatment, we must concern ourselves with the construct validity of the measure. Since it is clear that the relevant theory concerning need for treatment must include esthetics and the accompanying social and psychological characteristics, the construct validation of an index to measure need for treatment must include tests of hypotheses with these dimensions. If we consider a child's self-perception of occlusion as a psychological variable and another person's perception of a child's occlusion as a social variable, theory relevant to an index of need for treatment would hypothesize that each should correlate positively with need for treatment. Subjects were eighth and ninth grade students from a metropolitan area in western New York State. Fifty-two of the children were planning to obtain orthodontic treatment, and 102 were not. Data were also obtained, whenever possible, from both parents and from a sibling (if any) nearest in age to the child. Data were collected in one session by a trained interviewer who used a structured interview and also photographed the child's teeth and jaws. In addition, the child was given an orthodontic Treatment Priority Index (TPI) examination by a dentist enrolled in a graduate program in orthodontics, who had previously been trained and standardized in the use of the TPI. In addition, to the TPI, scores obtained included three psychological measures and eight social measures. Each of the psychological and social variables correlated significantly with TPI at the 0.05 level, with values ranging from 0.21 to 0.54 and a median value of 0.42. On the basis of these correlations, evidence is presented for the construct validity of the TPI when measuring need for treatment.

Inter-examiner reliability in caries trials.

A statistical model is given for representing the several components of variability present in measurements (e.g., DMFS scores) given by examiners to patients. Methods for making inferences about the intraclass correlation coefficient of reliability are presented and illustrated on a real set of data. The proper analysis of data from a reliability study is shown to depend on the planned design and analysis of the clinical or field trial to be conducted following the reliability trial.

The use of analysis of covariance to increase precision wtih DMFS measures.

For an experimental study with pre- and post-DMFS measures two methods of analysis were compared with respect to precision. It is shown that for large sample size, the analysis of covariance with the post-DMFS measure as criterion and the pre-DMFS measure as the covariate will be more precise than the analysis of variance of increment scores as the value of beta differs from 1. When beta is approximately 1, the two techniques will have essentially the same precision. The dental researcher interested in precision is advised, therefore, to use analysis of covariance with the pre-DMFS measure as the covariate and the post-measure as criterion rather than the traditional analysis of variance of increment scores. For large sample size, the precision of the former will tend to be at least that of the latter. The researcher is not encouraged to use analysis of covariance with the increment as the criterion; if the procedure increases precision over analysis of variance of the increments, it merely indicates that analysis of covariance (with the post-measure as criterion) should have been used originally.

Estimating examiner consistency with DMFS measures.

Within- and between-examiner reliability estimates were considered for standardization data. However, within-examiner stability was demonstrated to be the important measure of examiner consistency in the clinical trial because it directly affects the precision of the study. Finally, an argument is also made against the use of reversal rates in the assessment of examiner consistency.