Implementing continuous non-normal skewed distributions in latent growth mixture modeling: An assessment of specification errors and class enumeration

Abstract

Recent advances have allowed for modeling mixture components within latent growth modeling using robust, skewed mixture distributions rather than normal distributions. This feature adds flexibility in handling non-normality in longitudinal data, through manifest or latent variables, by directly modeling skewed or heavy-tailed latent classes rather than assuming a mixture of normal distributions. The aim of this study was to assess through simulation the potential under- or over-extraction of latent classes in a growth mixture model when underlying data follow either normal, skewed-normal, or skewed-t distributions. In order to assess this, we implement skewed-t, skewed-normal, and conventional normal (i.e., not skewed) forms of the growth mixture model. The skewed-t and skewed-normal versions of this model have only recently been implemented, and relatively little is known about their performance. Model comparison, fit, and classification of correctly specified and mis-specified models were assessed through various indices. Findings suggest that the accuracy of model comparison and fit measures are dependent on the type of (mis)specification, as well as the amount of class separation between the latent classes. A secondary simulation exposed computation and accuracy difficulties under some skewed modeling contexts. Implications of findings, recommendations for applied researchers, and future directions are discussed; a motivating example is presented using education data.     

The surgical anxiety questionnaire (SAQ): development and validation

Objective: Preoperative anxiety is often assessed using general anxiety measures; existing specific measures might lack content coverage and/or are not psychometrically validated. This study aimed to develop a new self-report measure of surgery-specific anxiety and test its psychometric properties.

Design: The surgical anxiety questionnaire (SAQ) was developed from themes identified in qualitative research and reviewed by an interdisciplinary expert team. It was administered preoperatively to 135 patients (56% female, mean age 51) on the day of surgery alongside additional measures of preoperative anxiety, state anxiety, perceived stress, depression and social desirability. Follow-up assessment was conducted immediately post-surgery and two weeks post-surgery (n?=?114) to examine recovery and predictive validity of the scale.

Results: Factor analysis revealed a three component structure, including: concerns about health (six items), concerns about recovery (four items) and concerns about procedures (four items). Three additional items of relatively high concern were retained in the total score (17 items). The SAQ displayed good reliability, validity (content, construct and predictive) and adequate overall psychometric properties.

Conclusions: Preliminary results suggest that the SAQ is a promising tool for measuring preoperative anxiety and predicting recovery. Recommendations for future research include employing a confirmatory factor analysis and examining test-retest reliability.     

Random word generation reveals spatial encoding of syllabic word length

Existing random number generation studies demonstrate the presence of an embodied attentional bias in spontaneous number production corresponding to the horizontal Mental Number Line: Larger numbers are produced on right-hand turns and smaller numbers on left-hand turns (Loetscher et al.,2008, Curr. Biol., 18, R60). Furthermore, other concepts were also shown to rely on horizontal attentional displacement (Di Bono and Zorzi, 2013, Quart. J. Exp. Psychol., 66, 2348). In two experiments, we used a novel random word generation paradigm combined with two different ways to orient attention in horizontal space: Participants randomly generated words on left and right head turns (Experiment 1) or following left and right key presses (Experiment 2). In both studies, syllabically longer words were generated on right-hand head turns and following right key strokes. Importantly, variables related to semantic magnitude or cardinality (whether the generated words were plural-marked, referred to uncountable concepts, or were associated with largeness) were not affected by lateral manipulations. We discuss our data in terms of the ATOM (Walsh, 2015, The Oxford handbook of numerical cognition, 552) which suggests a general magnitude mechanism shared by different conceptual domains.