A correction to the hierarchical regression analysis used by Smyth: A comment on Pedhazur.

The author acknowledges that E. J. Pedhazur (see record 1984-13952-001) correctly pointed out errors in the present author's (see record 1983-07281-001) use of ANCOVA via hierarchical regression analysis in a study on psychopathology as a function of neuroticism. One of the conclusions reached in the study required modification once the errors were corrected. That is, J. Reyher's (1962) paradigm did produce psychopathology in highly hypnotically susceptible Ss, but the Ss' neuroticism did not influence their reports of psychopathology. (5 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

At random: Sense and nonsense.

"It is often said that psychologists are captivated by the magic of words." One example of this is the epidemic use by psychologists of the word 'design.' " "Despite glib talk about using factor analysis to test hypotheses, practically no users of factor analysis ever test hypotheses." A psychologist may "trudge off weighted down with a box full of statistical tools in search of a research problem that permits him to display skill with his tools." Most psychologists "without intentional eavesdropping know that occasionally their theory oriented colleagues simply discard all data of an experiment as bad data if not in agreement with the theory, and start over. The theory is, of course, always good." The theorist who has the one and only approach and solution to all, or nearly all, psychological problems "tends to lure those among us who have a low tolerance for the ambiguity that flourishes in psychology." This "model business is nothing more than a new name for old hat stuff… . The question of the usefulness of mathematical models and, to a certain extent, the value of high powered statistical techniques is debatable." (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Sense and nonsense in the treatment of exocrine pancreatic insufficiency

Application of pancreatic digestive enzymes is indicated in cases of a quantitatively decreased exogenous secretion or an asynchronous secretion of enzymes with regard to the duodenal passage of chyme. A clear indication for therapy is a proven steatorrhea, a relative indication loss weight of and/or uncharacteristic abdominal discomfort in patients with proven pancreatic disease, i.e. chronic pancreatitis. Uncharacteristic abdominal discomfort alone, which is regarded as a consequence of 'maldigestion' without proven pancreatic disease, is not an indication for therapy. To prevent a destruction of exogenously applied lipase by gastric acid and to enable a synchronous gastroduodenal passage of the enzymes together with food, acid-protected micropellets or -tablets with an ideal diameter around 1.4 mm containing high amounts of lipase are requested. In cases of anacidity i.e. gastrectomy or type-A gastritis, lipase rich 'conventional' enzymes applied as granulate are sufficient. Combinations (pancreatic enzymes with bile acids) or fungal lipases have either more side effects (diarrhea) or are less efficient when compared to porcine enzymes. Acid-resistant microbial lipases may be useful in the near future. Application of pure proteases or pancreatic enzymes with high concentrations of proteases as treatment of pain in chronic pancreatitis ('negative feedback regulation') are a rather expensive form of treatment when compared to analgetics and are probably ineffective.     

Comment on Hitt's analysis.

W. D. Hitt's (see record 1969-16600-001) analysis of a 1963 symposium, while ostensibly directed at the behaviorism–phenomenology controversy, aimlessly gathers remnants of the Würzburg controversy, the nomothetic–idiographic debates of the 1950s, clinical–statistical arguments about prediction, and C. P. Snow's 2 cultures. It also fails to characterize phenomenology accurately by describing it as American. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Stress-related appraisals: A regression analysis.

Conducted 2 studies with 70 male undergraduates that attempted to demonstrate the relative importance of different cognitive appraisals that have a bearing on the amount of stress reported by Ss in an ego-threatening situation. The 1st study scaled a set of stimuli, the related difficulty of which was used to order the stimuli for the 2nd study. In the 2nd study, different appraisal antecedents to stress were assessed. Results of path analysis show that the most important single appraisal related to anticipated stress was that of stimulus difficulty or aversiveness. This held irrespective of trait anxiety, although high anxious Ss used their perception of stimulus aversiveness even more in their later expectations of stress. Only anticipated stress predicted actual perceived stress. Conclusions are drawn about the adequacy of present formulations of the cognitive appraisal process of stress and potential reasons for the effectiveness of cognitively based treatment strategies for stress. (French summary) (20 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The complex nature of unique and shared effects in hierarchical linear regression: Implications for developmental psychology.

Hierarchical linear regression and related techniques, such as commonality analysis, path analysis, and linear structural equation models with mediator variables, are often used to determine the extent to which the influence of an exogenous variable on a dependent variable, A, is "unique" to this exogenous variable, or "shared with" another predictor variable, B. The authors formally show that shared and unique effects are related to the partial correlation between A and B controlling for the exogenous variable. We discuss the implications of this property of hierarchical linear regression with a special consideration of the role of chronological age in developmental psychology and warn against the uncritical use of hierarchical linear regression procedures. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Children's spatial analysis of hierarchical patterns: Construction and perception.

Two experiments were reported that aimed at investigating the development of spatial analysis of hierarchical patterns in children between 3 and 9 years of age. A total of 108 children participated in the drawing experiment, and 224 children were tested in a force-choice similarity judgment task. In both tasks, participants were exposed to consistent and inconsistent targets for short (300-ms) and long (3-s) durations. The drawing task showed that 3-year-old children either preferred to draw the local level or reproduced both levels in a nonintegrated manner. Coordination between the 2 processes started to emerge at 4 years of age, and 6-year-old children produced essentially correct integrated responses. The similarity judgment task confirmed that local processing dominated at 3 years of age. Preference for global processing appeared at 5 years of age, and it gained in strength later. Significant effects of stimulus consistency and stimulus duration were also found. In particular, the use of inconsistent patterns in the similarity judgment task revealed a phenomenon of local-to-global interference in the 3-year-olds. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Locating anger in the hierarchical structure of affect: Comment on Carver and Harmon-Jones (2009).

C. S. Carver and E. Harmon-Jones (see record 2009-02580-003) have presented considerable evidence to support their argument that “anger relates to an appetitive or approach motivational system, whereas anxiety relates to an aversive or avoidance motivational system” (p. 183). However, they have failed to take sufficient account of the extensive psychometric data indicating that anger is strongly related to anxiety (and other negative affects) and more weakly associated with the positive affects. Considering all of the available evidence, the most accurate conclusion is that anger shows both approach and avoidance properties. Moreover, viewed in the context of the hierarchical structure of affect, some evidence suggests that the nonspecific component of anger (i.e., its shared variance with the other negative affects) is primarily related to the aversive or avoidance motivational system, whereas its specific component (i.e., its unique qualities that distinguish it from other negative affects) has a stronger link to the appetitive or approach system. The author concludes by considering the broader implications of these data for affective structure. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

State of the art in sequential analysis: Comment on Lichtenberg and Heck.

Comments on the discussion of J. W. Lichtenberg and E. J. Heck (see record 1986-30903-001) on methods to analyze sequential data in the context of counseling process research. The present author outlines the state-of-the-art developments in sequential analysis, including unidirectional and bidirectional tests, tests of dominance, between-group and overtime tests, and tests for systems with more than 2 participants. In addition, a number of caveats for conducting a sequential analysis are presented. (16 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Sample size and multiple regression analysis.

Despite the development of procedures for calculating sample size as a function of relevant effect size parameters, rules of thumb tend to persist in designs of multiple regression studies. One explanation for their persistence may be the difficulty in formulating a reasonable a priori value of an effect size to be detected. This article presents methods for calculating effect sizes in multiple regression from a variety of perspectives and also introduces a new method based on an exchangeability structure among predictor variables. No single method is deemed superior, but rather examples show that a combination of methods is likely to be most valuable in many situations. A simulation provides a 2nd explanation for why rules of thumb for choosing sample size have persisted but also shows that the outcome of such underpowered studies will be a literature consisting of seemingly contradictory results. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Comment on a distribution-free factorial design analysis.

The distribution-free method for analyzing the results of factorial design experiments proposed by Wilson is examined. It is concluded that the student who is familiar with analysis of variance procedures can handle the special problem proposed by Wilson without recourse to the elaboration of chi-square formulas. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Outliers and influential data points in regression analysis.

Because the results of a regression analysis can be sensitive to outliers (either on y or in the space of the predictors), it is important to be able to detect such points. The author discusses and interrelates the following 4 diagnostics that are useful in identifying outliers: studentized residuals, the hat elements, Cook's distance, and Mahalanobis distance. Guidelines are given for interpretation of the diagnostics. Outliers will not necessarily be influential in affecting the regression coefficients. (27 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

An analysis of hierarchical processing in visual perception.

Perception is viewed as a process in which attributes of a stimulus are analyzed in step-wise fashion. 2 experiments with 19 undergraduates, were carried out in which the attributes of spatial location and identity were examined for 2 types of materials. Results indicate that identification of letters requires more stimulus energy than identification of lines. There were no differences between identification of lines, localization of lines, or localization of letters. In general, results support a hierarchical processing hypothesis. (French summary) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Parallel and competitive processes in hierarchical analysis: Perceptual grouping and encoding of closure.

The role of perceptual grouping and the encoding of closure of local elements in the processing of hierarchical patterns was studied. Experiments 1 and 2 showed a global advantage over the local level for 2 tasks involving the discrimination of orientation and closure, but there was a local advantage for the closure discrimination task relative to the orientation discrimination task. Experiment 3 showed a local precedence effect for the closure discrimination task when local element grouping was weakened by embedding the stimuli from Experiment 1 in a background made up of cross patterns. Experiments 4A and 4B found that dissimilarity of closure between the local elements of hierarchical stimuli and the background figures could facilitate the grouping of closed local elements and enhanced the perception of global structure. Experiment 5 showed that the advantage for detecting the closure of local elements in hierarchical analysis also held under divided- and selective-attention conditions. Results are consistent with the idea that grouping between local elements takes place in parallel and competes with the computation of closure of local elements in determining the selection between global and local levels of hierarchical patterns for response. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Analogical problem solving: A hierarchical analysis of procedural similarity.

Similarity between source analogues and target problems is a central theme in the research on analogical transfer. Much of the theorizing and research has focused on the effects of superficial and structural similarity on transfer. The present research is an attempt to analyze systematically another critical type of similarity, namely, procedural similarity, and to examine its effects on the executing process. Participants viewed a schematic picture as a source model, interpreted its conceptual meaning, and then attempted to solve a problem to which the conceptual information from the source model could be applied. The results indicate that the ease with which a source solution was implemented was largely determined by the abstraction level at which a solution was shared by a source analogue and the target problem. The degree of procedural similarity was also found to influence the executing process in analogical transfer. A conceptual model concerning the function of procedural similarity as a utilizational constraint in analogical problem solving is proposed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)