Richard G. Lomax

The Effect of Varying Degrees of Nonnormality in Structural Equation Modeling

This simulation study investigated the robustness of structural equation modeling to different degrees of nonnormality under 2 estimation methods, generalized least squares and maximum likelihood, and 4 sample sizes, 100, 250, 500, and 1,000. Each of the slight and severe nonnormality degrees was comprised of pure skewness, pure kurtosis, and both skewness and kurtosis. Bias and standard errors of parameter estimates were analyzed. In addition, an analysis of variance was conducted to investigate the effects of the 3 factors on several goodness-of-fit indexes. The study found that standard errors of parameter estimates were not significantly affected by estimation methods and nonnormality conditions. As expected, standard errors decreased at larger sample sizes. Parameter estimates were more sensitive to nonnormality than to sample size and estimation method. Chi-square was the least robust model fit index compared with Normed Fit Index, Nonnormed Fit Index, and Comparative Fit Index. Sample sizes of 100 or more are recommended for accurate parameter estimates.

Young Children's Concepts about Print and Reading: Toward a Model of Word Reading Acquisition.

THE AUTHORS tested theoretical models of the development of print concepts and word reading. Eighteen measures of print concepts and word reading were obtained from 81 children three to seven years of age. A five-component model hypothesized from previous findings fit the data better than a fouror two-component model. The five component model included a concepts-about-print component which influenced a graphic awareness component, which in turn influenced a phonemic awareness component, which influenced a grapheme-phoneme correspondence knowledge component, which ultimately influenced a word reading component; in addition, concepts about print also influenced grapheme-phoneme correspondence knowledge. According to results of developmental analyses, children expand their knowledge in each of these print components with age.

Instrumentality, task value, and intrinsic motivation: Making sense of their independent interdependence

Abstract The relationships among instrumentality, task value, and intrinsic orientation were investigated among undergraduate students. The sample comprised 207 undergraduates who were participating in a lower-division human development course. Results confirm that endogenous instrumentality is an independent construct, which—although related to task value and intrinsic motivation—is empirically and theoretically distinguishable. Results suggest that the present orientation of intrinsic motivation and task value (as measured by the MSLQ) may serve a different motivational function than the more future oriented endogenous instrumentality.

Longitudinal Pathways Linking Adolescent Reports of Maternal and Paternal Attachments to Psychological Well-Being

Examined in this study were the relations between adolescent ratings of parental attachment (affective quality of parental relationship and parental fostering of autonomy)and self-reported psychological well-being over the 1-year period from the eighth to the ninth grade. Through structural equation modeling, relations between adolescent perceptions of parental attachments and psychological well-being (positive view of self and low levels of depressive symptoms) at Grades 8 and 9 were tested separately for girls and for boys. Adolescent ratings of maternal and paternal attachment at Grade 8 contributed to changes in well-being I year later for boys only. Adolescent boys `ratings of well-being at Grade 8 were associated with changes in ratings of attachment to father from the eighth to the ninth grade.

The Dimensionality of Language Ability in Young Children

The purpose of this study was to empirically examine the dimensionality of language ability for young children (4-8 years) from prekindergarten to third grade (n = 915), theorizing that measures of vocabulary and grammar ability will represent a unitary trait across these ages, and to determine whether discourse skills represent an additional source of variance in language ability. Results demonstrated emergent dimensionality of language across development with distinct factors of vocabulary, grammar, and discourse skills by third grade, confirming that discourse skills are an important source of variance in childrens language ability and represent an important additional dimension to be accounted for in studying growth in language skills over the course of childhood.

On Combining Apples and Oranges: A Response to Stahl and Miller

In responding to Stahl and Miller’s article, “Whole Language and Language Experience Approaches” ( Review of Educational Research, Spring 1989), we argue that Stahl and Miller misrepresented concepts related to emergent literacy and inadequately defined whole language. We further argue that whole language approaches of the 1980s and language experience approaches of the 1960s and 1970s are not equivalent. Therefore, results of studies showing a superiority of basal approaches over language experience approaches cannot be used to make inferences about a superiority of basal approaches over current whole language approaches as Stahl and Miller do in their discussion. Finally, the studies included in Stahl and Millers meta-analysis have insufficient information about the nature of instruction to draw the conclusion (as Stahl and Miller do) that there is a need for a more systematic approach to decoding than whole language provides.

Gender differences in sweat lactate

Abstract Sweat rate may affect sweat lactate concentration. The current study examined potential gender differences in sweat lactate concentrations because of varying sweat rates. Males (n=6) and females (n=6) of similar age, percentage body fat, and maximal oxygen consumption (VO2max) completed constant load (CON) cycling (30 min – approximately 40% VO2max) and interval cycling (INT) (15 1-min intervals each separated by 1 min of rest) trials at 32 (1) °C wet bulb globe temperature (WBGT). Trials were preceded by 15 min of warm-up (0.5 kp, 60 rpms) and followed by 15 min of rest. Blood and sweat samples were collected at 15, 25, 35, 45, and 60 min during each trial. Total body water loss was used to calculate sweat rate. Blood lactate concentrations (CON ≅ 2 mmol · l−1, INT ≅ 6 mmol · l−1) and sweat lactate concentrations (CON and INT ≅ 12 mmol · l−1) were not significantly different (P > 0.05) at any time between genders for CON or INT. Overall sweat rates (ml · h−1) were not significantly different (P > 0.05) between trials but were significantly greater (P ≤ 0.05) for males than for females for CON [779.7 (292.6) versus 450.3 (84.6) ml · h−1] and INT [798.0 (268.3) versus 503.0 (41.4) ml · h−1]. However, correcting for surface area diminished the difference [CON: 390.7 (134.4) versus 277.7 (44.4) ml · h−1, INT: 401.5 (124.1) versus 310.6 (23.4) ml · h−1 (P ≤ 0.07)]. Estimated total lactate secretion was significantly greater (P ≤ 0.05) in males for CON and INT. Results suggest that sweat rate differences do not affect sweat lactate concentrations between genders.

Emergent literacy profiles of preschool-age children with specific language impairment

The primary aim of the present study was to explore the heterogeneity of emergent literacy skills among preschool-age children with specific language impairment (SLI) through examination of profiles of performance. Fifty-nine children with SLI were assessed on a battery of emergent literacy skills (i.e., alphabet knowledge, print concepts, emergent writing, rhyme awareness) and oral language skills (i.e., receptive/expressive vocabulary and grammar). Cluster analysis techniques identified three emergent literacy profiles: (1) Highest Emergent Literacy, Strength in Alphabet Knowledge; (2) Average Emergent Literacy, Strength in Print Concepts; and (3) Lowest Emergent Literacy across Skills. After taking into account the contribution of child age, receptive and expressive language skills made a small contribution to the prediction of profile membership. The present findings, which may be characterized as exploratory given the relatively modest sample size, suggest that preschool-age children with SLI display substantial individual differences with regard to their emergent literacy skills and that these differences cannot be fully determined by childrens age or oral language performance. Replication of the present findings with a larger sample of children is needed.

Utilization of Sample Weights in Single Level Structural Equation Modeling

ABSTRACT. Complex survey designs often employ multistage cluster sampling designs and oversample particular units to ensure more accurate population parameter estimates. These issues must be accommodated in the analysis to ensure accurate parameter estimation. Incorporation of sample weights in some statistical procedures has been studied. However, research on the behavior of sample weights on estimates, standard errors, and fit measures in latent variable models is negligible, and studies examining methodology on latent variable modeling applications using extant data are rare. Using the Beginning Postsecondary Students Longitudinal Study 1990/92/94, the authors found, with mixed results, that a statistically significant difference exists in estimates and fit indices when weights and designs are applied versus when they are ignored.

An Application of Generalizability Theory to Observational Research

Observational data were collected over a period of 120 school days from 11 elementary level, self-contained, learning disabilities classrooms (N = 105), using the Student-Level Observation of Beginning Reading (SOBR) system. Various studies were conducted to evaluate the generalizability of 10 observational measures. The major findings were that: observers were well-trained such that reliable and unbiased observations of student behavior were obtained through the use of a single observer; student behavior as observed over 30 occasions was extremely stable; and a high stability coefficient would be obtained even for five one-hour observation sessions randomly sampled from the school year. Implications for future generalizability studies of observational data are also discussed.