Commentary on high-performance computing and statistical analysis: From large-scale data analysis to smoothing functions

High-performance computing becomes essential to statistical analysis when the database is massive or the number of computations per data element is large. Albert F. Anderson (1997) discusses the application of high-performance computing to massive databases; J. O. Ramsay’s (Ramsay, Heckman, & Silverman, 1997) estimation problems potentially require large numbers of computations per data element.     

Interactive versus passive dynamics and the exploratory analysis of multivariate data

In two experiments, we examined subjects’ ability to infer structure from three-dimensional data presented dynamically in interactive versus passive mode and in static scatterplots. Accuracy of estimating the number of clusters in three-dimensional data sets was measured for each of these conditions, as a function of cluster discriminability.     

A mobile computing solution for collecting functional analysis data on a Pocket PC

The present paper provides a task analysis for creating a computerized data system using a Pocket PC and Microsoft Visual Basic. With Visual Basic software and any handheld device running the Windows Moble operating system, this task analysis will allow behavior analysts to program and customize their own functional analysis data-collection system. The program will allow the user to select the type of behavior to be recorded, choose between interval and frequency data collection, and summarize data for graphing and analysis. We also provide suggestions for customizing the data-collection system for idiosyncratic research and clinical needs.     

Statistics,data analysis and Psychometrika: Major developments

Approximately 15% of all papers appearing inPsychometrika during the period 1960–1984 have been statistical or data analytic in nature. While these papers cover a very wide range of issues and are technically quite similar to those appearing in other major statistical journals, collectively they possess features which make them identifiablyPsychometrika.     

IBM research in interactive data mining and scientific computing

A number of research and development efforts from IBM are described in the areas of data mining and visualization of large data sets. Some useful principles for data mining and visualization are discussed, and a few research programs and available products are described. In addition, the current IBM line of hardware and support software for scientific computing is briefly described.     

CDF-XL: computing cumulative distribution functions of reaction time data in Excel

In experimental psychology, central tendencies of reaction time (RT) distributions are used to compare different experimental conditions. This emphasis on the central tendency ignores additional information that may be derived from the RT distribution itself. One method for analysing RT distributions is to construct cumulative distribution frequency plots (CDFs; Ratcliff, Psychological Bulletin 86:446–461, 1979). However, this method is difficult to implement in widely available software, severely restricting its use. In this report, we present an Excel-based program, CDF-XL, for constructing and analysing CDFs, with the aim of making such techniques more readily accessible to researchers, including students (CDF-XL can be downloaded free of charge from the Psychonomic Society’s online archive). CDF-XL functions as an Excel workbook and starts from the raw experimental data, organised into three columns (Subject, Condition, and RT) on an Input Data worksheet (a point-and-click utility is provided for achieving this format from a broader data set). No further preprocessing or sorting of the data is required. With one click of a button, CDF-XL will generate two forms of cumulative analysis: (1) “standard” CDFs, based on percentiles of participant RT distributions (by condition), and (2) a related analysis employing the participant means of rank-ordered RT bins. Both analyses involve partitioning the data in similar ways, but the first uses a “median”-type measure at the participant level, while the latter uses the mean. The results are presented in three formats: (i) by participants, suitable for entry into further statistical analysis; (ii) grand means by condition; and (iii) completed CDF plots in Excel charts.     

Sponsorship: Organizational,sponsor, and refugee perspectives

Canada inaugurated a unique sponsorship program through the Immigration Act of 1976. Twelve-month sponsor support creates both an initial bond and a friendship network projecting beyond the formal undertaking. Since the Southeast Asian wave in 1979–80, sponsorships have declined in frequency and in public visibility. More recently, variations of the sponsorship model involve shared responsibility with the federal government and local community organizations to widen the base of sponsor support and to alleviate burden in complex cases. Future policy directions may invite newcomers to assume a greater role in shaping their own resettlement pathways through transnational linkages. Also, centres such as places of worship should accommodate widely-used programs (health, labour market orientation) to bridge wider community services with newcomer idioms and customs.     

Reliability analysis of observational data: Problems,solutions, and software implementation

In the reliability analysis literature, little attention has been given to the various possible ways of creating a basis for the comparison required to compute observer agreement. One needs this comparison to turn a sequential list of behavioral records into a confusion matrix. It is shown that the way to do this depends on the research question one needs to answer. Four methods for creating a basis for comparison for the computation of observer agreement in observational data are presented. Guidelines are given for computing observer agreement in a way that fits one’s goals. Finally, we discuss how these methods have been implemented in The Observer software. The Observer 4.1 supports all the methods that have been discussed. Most of these methods are not present in any other software package.     

The Columbia Supervision Project: data from the dyad

Anonymous questionnaires were sent to all candidates and supervisors at the Columbia University Center for Psychoanalytic Training and Research (hereafter "Columbia"). Questions focused on the four domains most emphasized in the literature on supervision: logistical issues; the "teach or treat" question; the evaluatory function of the supervisor; and the affective experience of supervision. By coding the questionnaires, anonymity of respondents was maintained while allowing for a matched pair of analyses of supervisors and supervisees. Return rate was over 85 percent. In general, rates of satisfaction with supervision were high, and candidates and supervisors agreed on such issues as the "teach or treat" question, as well as the technical and theoretical frame of reference of the supervisor. However, there were striking disagreements between candidates and supervisors as to the role of the supervisor, what candidates find useful in supervision, the evaluatory function, and the relation between supervision and progression to graduation. Although 50 percent of candidates reported anxiety about receiving credit for cases, this was not routinely discussed in supervision, and the supervisory relationship itself was not discussed in over 50 percent of dyads. Despite high overall satisfaction ratings, 25 percent of candidates said they wished they had a different supervisor for the case, and 75 percent believed that a candidate who asked to switch supervisors would be labeled problematic. In contrast, over 75 percent of supervisors reported that switching supervisors carries no stigma. In a follow-up study conducted one year later, many candidates reported that they feared reprisals for switching, and some reported that their training analysts advised against "rocking the boat." Candidates felt that participating in the study emboldened them to think more openly about supervision and in some cases to make changes.     

A multilevel analysis of the self-presentation theory of social anxiety: Contextualized, dispositional, and interactive perspectives

According to self-presentation theory, social anxiety is determined by impression motivation and impression efficacy. However, researchers have not evaluated the theory’s applicability from contextual and dispositional perspectives in an integrated manner, nor have they examined a fundamental interactive facet of the theory. In three studies, we examined these issues using hypothetical situations and experience sampling methodology. Results demonstrated the theory’s applicability at the contextual and dispositional level, providing insight into people’s general tendencies to experience social anxiety and their momentary experiences of social anxiety. Results also revealed the predicted interaction between impression motivation and impression efficacy - high impression efficacy weakens the association between impression motivation and social anxiety. These studies expand understanding of the personological and situational factors that drive social anxiety.     

An APL system for interactive data analysis: Histograms,correlation, and regression

This report describes an APL system for file-oriented univariate analysis, correlation, and regression analysis. The correlation and regression processes permit analyses of an unlimited number of cases, if the cases are arranged in tables small enough to be processed one at a time in a workspace. Support functions are also given for a menu-based processing system designed to support a broad range of analyses. The functions offer features such as subset selection, data transformation, and exclusion of invalid items.     

Hierarchical classes: Model and data analysis

A discrete, categorical model and a corresponding data-analysis method are presented for two-way two-mode (objects × attributes) data arrays with 0, 1 entries. The model contains the following two basic components: a set-theoretical formulation of the relations among objects and attributes; a Boolean decomposition of the matrix. The set-theoretical formulation defines a subset of the possible decompositions as consistent with it. A general method for graphically representing the set-theoretical decomposition is described. The data-analysis algorithm, dubbed HICLAS, aims at recovering the underlying structure in a data matrix by minimizing the discrepancies between the data and the recovered structure. HICLAS is evaluated with a simulation study and two empirical applications.This research was supported in part by a grant from the Belgian NSF (NFWO) to Paul De Boeck and in part by NSF Grant BNS-83-01027 to Seymour Rosenberg. We thank Iven Van Mechelen for clarifying several aspects of the Boolean algebraic formulation of the model and Phipps Arabie for his comments on an earlier draft.     

Depression in children: Parent,teacher, and child perspectives

Depressed and nondepressed children were found to differ in the types of behavior problems manifested at home and at school. Children rated as depressed by their parents on the Personality Inventory for Children evidenced significantly more conduct problems, anxiety, impulsive hyperactivity, learning problems, psychosomatic problems, perfectionism, and muscular tension at home than children rated as nondepressed. Depressed children were rated by their teachers as displaying more inattentionpassivity than nondepressed children. A significant but modest relationship was found between parent report and child selfreport of the child's depression. Depressed children attributed positive events to external causes and negative events to internal causes significantly more than did nondepressed children. The specificity of these results to depression was also examined;the particular features of childhood depression are compared to the features of adult depression. The investigators would like to thank Jim McFerren and Ralph Zalazar for their work as research assistants and David Watson for his help with the statistical analyses. The helpful comments of Eric Klinger and Auke Tellegen are gratefully acknowledged. The cooperation of Dr. Loren Benson, director of personnel services of the Hopkins School District #274; Mr. Edward Ryshavy, principal of Glen Lake Elementary School; and the teachers of that school is greatly appreciated.     

Air pollution, weather, and violent crimes: concomitant time-series analysis of archival data

Archival data covering a 2-year period were obtained from three sources in order to assess relations among ozone levels, nine measures of meteorological conditions, day of the week, holidays, seasonal trends, family disturbances, and assaults against persons. Confirming results obtained in laboratory studies, more family disturbances were recorded when ozone levels were high than when they were low. Two-stage regression analyses indicated that disturbances and assaults against persons were also positively correlated with daily temperatures and negatively correlated with wind speed and levels of humidity. Further, distributed lag (Box-Jenkins) analyses indicated that high temperatures and low winds preceded violent episodes, which occurred more often on dry than humid days. In addition to hypothesized relations, it was also found that assaults follow complaints about family disturbances, which suggests that the latter could be used to predict and lessen physical violence. It was concluded that atmospheric conditions and violent episodes are not only correlated but also appear to be linked in a causal fashion. This conclusion, however, was qualified by a discussion of the limitations of archival data and concomitant time-series analysis.