Combination rules for homoscedastic and heteroscedastic MANOVA models from multiply imputed datasets.

Classical MANOVA tests do not pose any difficulty when the assumptions on which they are based are satisfied, while the modified Brown-Forsythe (MBF) procedure has low sensitivity to the lack of multivariate normality and homogeneity of covariance matrices. Both methods assume complete data for all subjects. In this paper, we present combination rules for the MANOVA and MBF procedures with multiply imputed datasets. These rules are illustrated by pooling the results obtained with a two-factor multivariate design after applying the two approaches to each of the imputed datasets when the covariance matrices were equal (MI-MANOVA) and when the covariance matrices were unequal (MI-MBF). A Monte-Carlo study was carried out to compare the proposed solution, in terms of type I error rates and statistical power, with the MANOVA and MBF approaches without missing data, and with listwise deletion of missing data followed by the MANOVA approach (LD-MANOVA) and listwise deletion followed by the MBF procedure (LD-MBF). Simulations showed that the type I error rates in all analyses on datasets with missing values (with or without imputation) were well controlled. We also found that the MI-MANOVA approach was substantially more powerful than LD-MANOVA. Moreover, the power of the MI-MANOVA was generally comparable to that of its complete data counterpart. Similar results were obtained for the MI-MBF procedure when covariance matrices were unequal. We conclude, based on the current evidence, that the solution presented performs well and could be of practical use. We illustrate the application of combination rules using a real dataset.

Sample size estimation for heterogeneous growth curve models with attrition.

In this study, two approaches were employed to calculate how large the sample size needs to be in order to achieve a desired statistical power to detect a significant group-by-time interaction in longitudinal intervention studies-a power analysis method, based on derived formulas using ordinary least squares estimates, and an empirical method, based on restricted maximum likelihood estimates. The performance of both procedures was examined under four different scenarios: (a) complete data with homogeneous variances, (b) incomplete data with homogeneous variances, (c) complete data with heterogeneous variances, and (d) incomplete data with heterogeneous variances. Several interesting findings emerged from this research. First, in the presence of heterogeneity, larger sample sizes are required in order to attain a desired nominal power. The second interesting finding is that, when there is attrition, the sample size requirements can be quite large. However, when attrition is anticipated, derived formulas enable the power to be calculated on the basis of the final number of subjects that are expected to complete the study. The third major finding is that the direct mathematical formulas allow the user to rigorously determine the sample size required to achieve a specified power level. Therefore, when data can be assumed to be missing at random, the solution presented can be adopted, given that Monte Carlo studies have indicated that it is very satisfactory. We illustrate the proposed method using real data from two previously published datasets.

Spatial memory extinction differentially affects dorsal and ventral hippocampal metabolic activity and associated functional brain networks.

Previous studies showed the involvement of brain regions associated with both spatial learning and associative learning in spatial memory extinction, although the specific role of the dorsal and ventral hippocampus and the extended hippocampal system including the mammillary body in the process is still controversial. The present study aimed to identify the involvement of the dorsal and ventral hippocampus, together with cortical regions, the amygdaloid nuclei, and the mammillary bodies in the extinction of a spatial memory task. To address these issues, quantitative cytochrome c oxidase histochemistry was applied as a metabolic brain mapping method. Rats were trained in a reference memory task using the Morris water maze, followed by an extinction procedure of the previously acquired memory task. Results show that rats learned successfully the spatial memory task as shown by the progressive decrease in measured latencies to reach the escape platform and the results obtained in the probe test. Spatial memory was subsequently extinguished as shown by the descending preference for the previously reinforced location. A control naïve group was added to ensure that brain metabolic changes were specifically related with performance in the spatial memory extinction task. Extinction of the original spatial learning task significantly modified the metabolic activity in the dorsal and ventral hippocampus, the amygdala and the mammillary bodies. Moreover, the ventral hippocampus, the lateral mammillary body and the retrosplenial cortex were differentially recruited in the spatial memory extinction task, as shown by group differences in brain metabolic networks. These findings provide new insights on the brain regions and functional brain networks underlying spatial memory, and specifically spatial memory extinction. © 2016 Wiley Periodicals, Inc.

Effects of Modeling the Heterogeneity on Inferences Drawn from Multilevel Designs.

This article uses Monte Carlo techniques to examine the effect of heterogeneity of variance in multilevel analyses in terms of relative bias, coverage probability, and root mean square error (RMSE). For all simulated data sets, the parameters were estimated using the restricted maximum-likelihood (REML) method both assuming homogeneity and incorporating heterogeneity into multilevel models. We find that (a) the estimates for the fixed parameters are unbiased, but the associated standard errors are frequently biased when heterogeneity is ignored; by contrast, the standard errors of the fixed effects are almost always accurate when heterogeneity is considered; (b) the estimates for the random parameters are slightly overestimated; (c) both the homogeneous and heterogeneous models produce standard errors of the variance component estimates that are underestimated; however, taking heterogeneity into account, the REML-estimations give correct estimates of the standard errors at the lowest level and lead to less underestimated standard errors at the highest level; and (d) from the RMSE point of view, REML accounting for heterogeneity outperforms REML assuming homogeneity; a considerable improvement has been particularly detected for the fixed parameters. Based on this, we conclude that the solution presented can be uniformly adopted. We illustrate the process using a real dataset.

Multivariate analysis of covariance for heterogeneous and incomplete data.

This article discusses the robustness of the multivariate analysis of covariance (MANCOVA) test for an emergent variable system and proposes a modification of this test to obtain adequate information from heterogeneous normal observations. The proposed approach for testing potential effects in heterogeneous MANCOVA models can be adopted effectively, regardless of the degree of heterogeneity and sample size imbalance. As our method was not designed to handle missing values, we also show how to derive the formulas for pooling the results of multiple-imputation-based analyses into a single final estimate. Results of simulated studies and analysis of real-data show that the proposed combining rules provide adequate coverage and power. Based on the current evidence, the two solutions suggested could be effectively used by researchers for testing hypotheses, provided that the data conform to normality. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Robust tests for multivariate factorial designs under heteroscedasticity.

The question of how to analyze several multivariate normal mean vectors when normality and covariance homogeneity assumptions are violated is considered in this article. For the two-way MANOVA layout, we address this problem adapting results presented by Brunner, Dette, and Munk (BDM; 1997) and Vallejo and Ato (modified Brown-Forsythe [MBF]; 2006) in the context of univariate factorial and split-plot designs and a multivariate version of the linear model (MLM) to accommodate heterogeneous data. Furthermore, we compare these procedures with the Welch-James (WJ) approximate degrees of freedom multivariate statistics based on ordinary least squares via Monte Carlo simulation. Our numerical studies show that of the methods evaluated, only the modified versions of the BDM and MBF procedures were robust to violations of underlying assumptions. The MLM approach was only occasionally liberal, and then by only a small amount, whereas the WJ procedure was often liberal if the interactive effects were involved in the design, particularly when the number of dependent variables increased and total sample size was small. On the other hand, it was also found that the MLM procedure was uniformly more powerful than its most direct competitors. The overall success rate was 22.4% for the BDM, 36.3% for the MBF, and 45.0% for the MLM.

Short and Long-Term Effects on Academic Performance of a School-Based Training in Self-Regulation Learning: A Three-Level Experimental Study.

An experimental study was designed to analyze the effect of school-based training in self-regulation learning strategies on academic performance (Mathematics, Sciences, Language, and English). Class-level variables (i.e., gender, the teacher's teaching experience, class size) were considered and the effects of the intervention were measured at the end of the intervention and 3 months later. A sample of 761 students from 3rd and 4th grades (356 in the control condition and 405 in the experimental condition), from 14 schools, participated in the study. Data were analyzed using three-level analysis with within-student measurements at level 1, between-students within-classes at level 2, and between-classes at level 3. Data showed a positive effect of the intervention on student performance, both at post-test (d = 0.25) and at follow-up (d = 0.33) considering the four school subjects together. However, the effect was significant just at follow-up when subjects were considered separately. Student performance was significantly related to the students' variables (i.e., gender, level of reading comprehension) and the context (teacher gender and class size). Finally, students' gender and level of reading comprehension, as well as the teacher's gender, were found to moderate the effect of the intervention on students' academic performance. Two conclusions were highlighted: first, data emphasize the importance of considering time while conducting intervention studies. Second, more teaching experience does not necessarily translate into improvements in the quality of students' instruction.

Sexual dimorphism in spatial learning and brain metabolism after exposure to a western diet and early life stress in rats.

Prolonged daily intake of Western-type diet rich in saturated fats and sugars, and exposure to early life stress have been independently linked to impaired neurodevelopment and behaviour in animal models. However, sex-specific effects of both environmental factors combined on spatial learning and memory, behavioural flexibility, and brain oxidative capacity have still not been addressed. The current study aimed to evaluate the impact of maternal and postnatal exposure to a high-fat and high-sugar diet (HFS), and exposure to early life stress by maternal separation in adult male and female Wistar rats. For this purpose, spatial learning and memory and behavioural flexibility were evaluated in the Morris water maze, and regional brain oxidative capacity and oxidative stress levels were measured in the hippocampus and medial prefrontal cortex. Spatial memory, regional brain oxidative metabolism, and levels of oxidative stress differed between females and males, suggesting sexual dimorphism in the effects of a HFS diet and early life stress. Males fed the HFS diet performed better than all other experimental groups independently of early life stress exposure. However, behavioural flexibility evaluated in the spatial reversal leaning task was impaired in males fed the HFS diet. In addition, exposure to maternal separation or the HFS diet increased the metabolic capacity of the prefrontal cortex and dorsal hippocampus in males and females. Levels of oxidative stress measured in the latter brain regions were also increased in groups fed the HFS diet, but maternal separation seemed to dampen regional brain oxidative stress levels. Therefore, these results suggest a compensatory effect resulting from the interaction between prolonged exposure to a HFS diet and early life stress.

Selecting the best unbalanced repeated measures model.

This study examined the performance of selection criteria available in the major statistical packages for both mean model and covariance structure. Unbalanced designs due to missing data involving both a moderate and large number of repeated measurements and varying total sample sizes were investigated. The study also investigated the impact of using different estimation strategies for information criteria, the impact of different adjustments for calculating the criteria, and the impact of different distribution shapes. Overall, we found that the ability of consistent criteria in any of the their examined forms to select the correct model was superior under simple covariance patterns than under complex covariance patterns, and vice versa for the efficient criteria. The simulation studies covered in this paper also revealed that, regardless of method of estimation used, the consistent criteria based on number of subjects were more effective than the consistent criteria based on total number of observations, and vice versa for the efficient criteria. Furthermore, results indicated that, given a dataset with missing values, the efficient criteria were more affected than the consistent criteria by the lack of normality.

Influence of the Gap between Substrates in the Laser-Induced Transference of High-Viscosity Pastes.

Laser-induced forward transfer for high-viscosity-of Pa·s-pastes differ from standard LIFT processes in its dynamics. In most techniques, the transference after setting a great gap does not modify the shape acquired by the fluid, so it stretches until it breaks into droplets. In contrast, there is no transferred material when the gap is bigger than three times the paste thickness in LIFT for high-viscosity pastes, and only a spray is observed on the acceptor using this configuration. In this work, the dynamics of the paste have been studied using a finite-element model in COMSOL Multiphysics, and the behavior of the paste varying the gap between the donor and the acceptor substrates has also been modeled. The paste bursts for great gaps, but it is confined when the acceptor is placed close enough. The obtained simulations have been compared with a previous work, in which the paste structures were photographed. The analysis of the simulations in terms of speed allows for predicting the burst of the paste-spray regime-and the construction of a printability map regarding the gap between the substrates.

A robust approach for analyzing unbalanced factorial designs with fixed levels.

The goal of this study was to investigate the performance of Hall's transformation of the Brunner-Dette-Munk (BDM) and Welch-James (WJ) test statistics and Box-Cox's data transformation in factorial designs when normality and variance homogeneity assumptions were violated separately and jointly. On the basis of unweighted marginal means, we performed a simulation study to explore the operating characteristics of the methods proposed for a variety of distributions with small sample sizes. Monte Carlo simulation results showed that when data were sampled from symmetric distributions, the error rates of the original BDM and WJ tests were scarcely affected by the lack of normality and homogeneity of variance. In contrast, when data were sampled from skewed distributions, the original BDM and WJ rates were not well controlled. Under such circumstances, the results clearly revealed that Hall's transformation of the BDM and WJ tests provided generally better control of Type I error rates than did the same tests based on Box-Cox's data transformation. Among all the methods considered in this study, we also found that Hall's transformation of the BDM test yielded the best control of Type I errors, although it was often less powerful than either of the WJ tests when both approaches reasonably controlled the error rates.

Sensitivity of five information criteria to discriminate covariance structures with missing data in repeated measures designs.

BACKGROUNDS: This study analyzes the effectiveness of different information criteria for the selection of covariance structures, extending it to different missing data mechanisms, the maintenance and adjustment of the mean structures, and matrices. METHOD: The Monte Carlo method was used with 1,000 simulations, SAS 9.4 statistical software and a partially repeated measures design (p=2; q=5). The following variables were manipulated: a) the complexity of the model; b) sample size; c) matching of covariance matrices and sample size; d) dispersion matrices; e) the type of distribution of the variable; f) the non-response mechanism. RESULTS: The results show that all information criteria worked well in Scenario 1 for normal and non-normal distributions with heterogeneity of variance. However, in Scenarios 2 and 3, all were accurate with the ARH matrix, whereas AIC, AICCR and HQICR worked better with TOEP and UN. When the distribution was not normal, AIC and AICCR were only accurate in Scenario 3, more heterogeneous and unstructured matrices, with complete cases, MAR and MCAR. CONCLUSIONS: In order to correctly select the matrix it is advisible to analyze the heterogeneity, sample size and distribution of the data.

Environmental enrichment effects after early stress on behavior and functional brain networks in adult rats.

Early life stress is associated with long-term and pervasive adverse effects on neuroendocrine development, affecting normal cognitive and emotional development. Experimental manipulations like environmental enrichment (EE) may potentially reverse the effects of early life stress induced by maternal separation (MS) paradigm in rodents. However, the functional brain networks involved in the effects of EE after prolonged exposure to MS have not yet been investigated. In order to evaluate possible changes in brain functional connectivity induced by EE after MS, quantitative cytochrome c oxidase (CCO) histochemistry was applied to determine regional brain oxidative metabolism in adult male rats. Unexpectedly, results show that prolonged MS during the entire weaning period did not cause any detrimental effects on spatial learning and memory, including depressive-like behavior evaluated in the forced-swim test, and decreased anxiety-like behavior. However, EE seemed to alter anxiety- and depression-like behaviors in both control and MS groups, but improved spatial memory in the latter groups. Analysis of brain CCO activity showed significantly lower metabolic capacity in most brain regions selected in EE groups probably associated with chronic stress, but no effects of MS on brain metabolic capacity. In addition, principal component analysis of CCO activity revealed increased large-scale functional brain connectivity comprising at least three main networks affected by EE in both MS and control groups. Moreover, EE induced a pattern of functional brain connectivity associated with stress and anxiety-like behavior as compared with non-enriched groups. In conclusion, EE had differential effects on cognition and emotional behavior irrespective of exposure to MS. In view of the remarkable effects of EE on brain function and behavior, implementation of rodent housing conditions should be optimized by evaluating the balance between scientific validity and animal welfare.

Influence of initial mathematical competencies on the effectiveness of a classroom-based intervention.

BACKGROUND: Students commonly struggle with mathematics and mathematical problem-solving. Therefore, it is necessary to design and implement interventions aimed at improving these essential components of learning. Furthermore, the outcomes of these interventions can vary significantly and appear to be a function of a student's initial competencies in mathematics. AIM: This study attempts to analyse the influence of initial levels of mathematics competency with respect to the benefits of a specific intervention known as the Integrated Dynamic Representation (IDR). SAMPLE: Participants were 288 students (aged 6-8 years) who were divided according to their levels of mathematics competency (low-medium-high). METHODS: Students were assigned to the two primary intervention groups, experimental group (EG; students who received the IDR intervention) and control group (CG; students who followed the traditional instructional methods). All participants completed the Test of Early Mathematics Abilities (TEMA-3) both before and after the intervention. RESULTS AND CONCLUSIONS: Although all the three competency levels of the EG improved, the progression was different for each level. Results showed that students with low competency level improved substantially more than the students with medium and/or high baseline competency level.

Influence of environmental enrichment on the volume of brain regions sensitive to early life stress by maternal separation in rats.

BACKGROUND: Exposure to maternal separation (MS) in rodents may have long-lasting consequences for the structure and function of several brain regions, eventually associated with alterations in cognition and emotion later in life. Post-weaning environmental enrichment (EE) has been reported to ameliorate the detrimental effects of exposure to early life stress mainly in the hippocampus. METHOD: In vivo magnetic resonance imaging (MRI) was applied to evaluate possible volumetric changes in the dorsal and ventral hippocampus, the medial prefrontal cortex and the dorsal striatum of 90-day-old male rats after daily MS for 240 min from postnatal days 2-21. RESULTS: No significant volume changes were found in the selected brain regions in MS animals as compared with an age-matched control group. However, additional groups of control and MS animals with EE from days 21-60 showed significant volume increases in the medial prefrontal cortex and the ventral hippocampus as compared to the groups without EE. In addition, general hemispheric asymmetry was found in the volume of the brain regions measured. CONCLUSIONS: Our results demonstrate that EE could have differential effects depending on previous exposure to MS and on the development of brain lateralization.

Promoting School Engagement in Children with Cerebral Palsy: A Narrative Based Program.

This study assessed the efficacy of an educational program focused on the promotion of school engagement in children with Cerebral Palsy. A 9 weeks, narrative-based intervention program, with a pre-post neuropsychological and self-report evaluation, was developed with a dual focus: a self-regulation theoretical model and executive function stimulation. Fifteen children with Cerebral Palsy participated in the study. Results showed a significant main effect of time (F(2.82) = 6.04, p = 0.0066, partial η2 = 0.30; F(2.82) = 9.91, p = 0.0006, partial η2 = 0.41; F(2.82) = 26.90, p < 0.0001, partial η2 = 0.66) in the three dimensions of school engagement. Findings indicate that the program to train self-regulated competences and executive function skills was efficacious in promoting school engagement in children with Cerebral Palsy. Educational implications were discussed.

The impact of three types of writing intervention on students' writing quality.

Students' writing constitutes a topic of major concern due to its importance in school and in daily life. To mitigate students' writing problems, school-based interventions have been implemented in the past, but there is still a need to examine the effectiveness of different types of writing interventions that use robust design methodologies. Hence, the present study followed a longitudinal cluster-randomized controlled design using a multilevel modeling analysis with 370 fourth-grade students (nested in 20 classes). The classes were randomly assigned to four conditions: one comparison group and three writing types of writing interventions (i.e., week-journals, Self-Regulation Strategy Development (SRSD) instruction and SRSD plus Self-Regulated Learning (SRL) program using a story-tool), with five classes participating in each condition. Data supports our hypothesis by showing differences between the treatment groups in students' writing quality over time. Globally, the improvement of students' writing quality throughout time is related to the level of specialization of the writing interventions implemented. This is an important finding with strong implications for educational practice. Week-journals and writing activities can be easily implemented in classrooms and provides an opportunity to promote students' writing quality. Still, students who participated in the instructional programs (i.e., SRSD and SRSD plus story-tool) exhibited higher writing quality than the students who wrote week-journals. Current data did not find statistical significant differences between results from the two instructional writing tools.

Eudaimonic Well-Being and Coping with Stress in University Students: The Mediating/Moderating Role of Self-Efficacy.

The importance of personal psychological resources in preventing academic stress has enjoyed little attention to date, despite the high rates of stress that exist among university students. This article analyzes the effect of eudaimonic well-being on the use of adaptive strategies for coping with academic stress. Moreover, it analyzes the role of self-efficacy as a mediator and moderator of this relationship. In the mediation model, gender is included as a co-variable; in the moderation model, gender is included as a moderator. A total of 1402 university students participated in the study. The data were gathered through validated self-report instruments. The mediation analyses were performed using the PROCESS module of the statistical package, SPSS. The moderating effects of self-efficacy and gender were analyzed through hierarchical regression analysis. The results indicate that self-efficacy partially mediates but does not moderate the relationship between eudaimonic well-being and adaptive coping strategies. This finding reveals the benefits of using these two personal resources to enhance effective coping with academic stress while attending university.

[Power comparison of new tests to analyze repeated measures data]. / Comparación de la potencia de nuevos enfoques para analizar datos de medidas repetidas.

This work compares the sensitivity of five modern analytical techniques for detecting the effects of a design with measures which are partially repeated when the assumptions of the traditional ANOVA approach are not met, namely: the approach of the mixed model adjusted by means of the SAS Proc Mixed module, the Bootstrap-F approach, the Brown-Forsythe multivariate approach, the Welch-James multivariate approach and Welch-James multivariate approach with robust estimators. Previously, Livacic-Rojas, Vallejo and Fernández found out that these methods are comparable in terms of their Type I error rates. The results obtained suggest that the mixed model approach, as well as the Brown-Forsythe and Welch-James approaches, satisfactorily controlled the Type II error rates corresponding to the main effects of the measurement occasions under most of the conditions assessed.

How Do Student Prior Achievement and Homework Behaviors Relate to Perceived Parental Involvement in Homework?

This study investigated how students' prior achievement is related to their homework behaviors (i.e., time spent on homework, homework time management, and amount of homework), and to their perceptions of parental involvement in homework (i.e., parental control and parental support). A total of 1250 secondary students from 7 to 10th grade participated in the study. Structural equation models were fitted to the data, compared, and a partial mediation model was chosen. The results indicated that students' prior academic performance was significantly associated with both of the students' homework variables, with direct and indirect results linking achievement and homework behaviors with perceived parental control and support behaviors about homework. Low-achieving students, in particular, perceived more parental control of homework in the secondary grades. These results, together with those of previous research, suggest a recursive relationship between secondary school students' achievement and their perceptions of parental involvement in homework, which represents the process of student learning and family engagement over time. Study limitations and educational implications are discussed.