Evaluating Structural Equation Models for Categorical Outcomes: A New Test Statistic and a Practical Challenge of Interpretation

This research is concerned with two topics in assessing model fit for categorical data analysis. The first topic involves the application of a limited-information overall test, introduced in the item response theory literature, to structural equation modeling (SEM) of categorical outcome variables. Most popular SEM test statistics assess how well the model reproduces estimated polychoric correlations. In contrast, limited-information test statistics assess how well the underlying categorical data are reproduced. Here, the recently introduced C₂ statistic of Cai and Monroe (2014) is applied. The second topic concerns how the root mean square error of approximation (RMSEA) fit index can be affected by the number of categories in the outcome variable. This relationship creates challenges for interpreting RMSEA. While the two topics initially appear unrelated, they may conveniently be studied in tandem since RMSEA is based on an overall test statistic, such as C₂. The results are illustrated with an empirical application to data from a large-scale educational survey.     

Psychometric evaluation and normative data for a Swedish version of the Patient Health Questionnaire 15‐Item Somatic Symptom Severity Scale

The lack of an available Swedish version of the Patient Health Questionnaire 15‐Item Somatic Symptom Severity Scale (PHQ‐15) motivated the present psychometric evaluation of such a version as well as providing normative data for the PHQ‐15. Data from 3,406 individuals who took part in the Västerbotten Environmental Health Study in Sweden were used. The respondents constitute a random sample, aged 18 to 79 years, stratified for age and sex. They responded to a Swedish translation of the PHQ‐15 as well as the Hospital Anxiety and Depression Scale, the Perceived Stress Scale, and the Shirom Melamed Burnout Questionnaire for assessment of convergent validity. The distribution of PHQ‐15 scores was positively skewed and mesokurtic in shape, and the internal consistency of the PHQ‐15 was satisfactory. Correlation coefficients between PHQ‐15 score and the measures of anxiety, depression, stress and mental/physical exhaustion indicate satisfactory validity. Normative data for PHQ‐15 scores as well as for categories of somatic symptom severity are provided. The favorable psychometric properties of the Swedish version of the PHQ‐15 suggest use of this instrument for quantification of somatization in Swedish and similar populations, and has the advantage of available normative data.     

Interpreting cross-sectional data on stages of change

Abstract

The vast majority of studies investigating stage theories of health behaviour such as the transtheoretical model have used a cross-sectional research design. Participants are classified into stages and compared on theoretically relevant variables. This paper discusses the proper interpretation of cross-sectional data on stages of change. Linear patterns are not consistent with the stage model assumption that different causal factors are important at different stages but discontinuity patterns (patterns that do not show consistent increments or decrements across stages) can be diagnostic of a stage model. Researchers who use cross-sectional designs should specify predictions concerning the patterns to be expected under a stage model and under possible rival models, and interpret their data accordingly. Wherever possible, they should conduct prospective longitudinal and experimental studies which enable stronger inferences to be drawn.     

A normative study of the Children’s Color Trails Test (CCTT) in the Cypriot population

Background: The Children’s Color Trails Test (CCTT) is a neuropsychological test that measures attention, divided attention, and speed of mental processing. It has been increasingly used in the assessment of children in cross-cultural environments for neurological and psychiatric disorders such as seizures and closed head injuries, learning and/or language disabilities, attention deficit/hyperactivity disorder, children with manganese exposure, and children diagnosed with HIV virus. However, there is a paucity of studies presenting normative data. The aim of the present study was to provide normative data for the CCTT in the Cypriot population. Methods: A total of 709 native Cypriot children aged 7–16 years, recruited from various public schools across the island, took part in the study. Exclusion criteria involved the existence of neurological, psychiatric, cardiological, and metabolic diseases, premature birth, history of maternal alcohol and drug abuse during pregnancy, low birth weight, hearing loss, visual problems, native language other than Greek, and abnormality in fine-motor movements. Results: Age and gender were found to be important factors for the interpretation of scores in all CCTT variables. Older children required less time and exhibited fewer errors, near misses, and prompts compared to younger children. There was a consistent pattern of a 3–4 seconds improvement (less time in seconds) in the CCTT completion time as age increased. Conclusions: CCTT is a promising tool for the measurement of attention in the native Cypriot population. Further research is needed in children diagnosed with various neurological and psychiatric diseases in order to estimate validity of the CCTT in clinical populations.     

The Microcomputer as Perceptual Tool:

The microcomputer as a medium of instruction is not inherently better or worse than any other medium be it lecture, television, print or practical experience. However, the microcomputer can simultaneously present instruction and collect data on student performance. In order for educators to evaluate the success of instruction presented by computer they must use the microcomputer as a perceptual tool to more sensitively monitor and modify the educational process. Thoughtful consideration of monitoring data by special educators promises to make the microcomputer a revolutionary aspect of school instruction. Such an educational revolution can extend to the delivery of special services provided that the time and ancillary supports needed to utilize performance are made available to school personnel.     

Feature importance in feature generation and typicality rating

Many theoretical models of cognition are based on the assumption that cognitive processes and representations are hierarchically structured. The issue of whether these hierarchies are mere constructs or conceptual tools, or whether they have psychological and neurological reality, is addressed. Theories across a range of cognitive domains are reviewed and four kinds of evidence are considered: behavioural, neuropsychological, ontogenetic, and logical. Logical constraints are identified in relation to operating principles of control, access, economy and analogy. The general characteristics of hierarchical structures and their advantages and disadvantages are discussed.     

A Thurstonian Analysis of Preference Change

This paper presents a Thurstonian model for the analysis of preference change. Preferences are expressed in the form of rankings, possibly with ties. A vector-autoregression framework is used to investigate relationships between past and current rankings. It is shown that this approach yields a parsimonious and easily interpretable representation of individual preference differences in time-dependent ranking data. A detailed analysis of the 1992 National Election Study illustrates the proposed approach.     

Fluctuations of answer and confidence rating in a general-knowledge problem task: Is confidence rating a result of direct memory-relevant output monitoring?

In order to examine whether confidence rating is a result of direct memory-relevant output monitoring, a general-knowledge test was used. A question set was answered in experimental session 1, and the same question set was employed in session 2. Subjects chose one answer from two alternatives. No significant difference in answer accuracy was found between sessions, which suggests that identical information processing was carried out, and that any difference between sessions was based on probabilistic fluctuation. The major results were as follows: (a) In both sessions, answer accuracy was an increasing function of confidence. (b) Answer-change rate (rate of different answers to the same question between sessions) decreased monotonically with confidence. (c) The distributions of confidence rating in session 2, conditional on the rating in session 1, were nearly identical in no-answer-change and answer-change cases. These results suggest that confidence rating is not a result of monitoring memory-relevant output itself but an estimation of possibility of answer fluctuation.