Finding Pure Submodels for Improved Differentiation of Bifactor and Second-Order Models

Several studies have indicated that bifactor models fit a broad range of psychometric data better than alternative multidimensional models such as second-order models (e.g., Carnivez, 2016; Gignac, 2016; Rodriguez, Reise, & Haviland, 2016). Murray and Johnson (2013) and Gignac (2016) argued that this phenomenon is partially due to unmodeled complexities (e.g., unmodeled cross-factor loadings) that induce a bias in standard statistical measures that favors bifactor models over second-order models. We extend the Murray and Johnson simulation studies to show how the ability to distinguish second-order and bifactor models diminishes as the amount of unmodeled complexity increases. By using theorems about rank constraints on the covariance matrix to find submodels of measurement models that have less unmodeled complexity, we are able to reduce the statistical bias in favor of bifactor models; this allows researchers to reliably distinguish between bifactor and second-order models.     

Item Response Models for Examinee‐Selected Items

In some tests, examinees are required to choose a fixed number of items from a set of given items to answer. This practice creates a challenge to standard item response models, because more capable examinees may have an advantage by making wiser choices. In this study, we developed a new class of item response models to account for the choice effect of examinee‐selected items. The results of a series of simulation studies showed: (1) that the parameters of the new models were recovered well, (2) the parameter estimates were almost unbiased when the new models were fit to data that were simulated from standard item response models, (3) failing to consider the choice effect yielded shrunken parameter estimates for examinee‐selected items, and (4) even when the missingness mechanism in examinee‐selected items did not follow the item response functions specified in the new models, the new models still yielded a better fit than did standard item response models. An empirical example of a college entrance examination supported the use of the new models: in general, the higher the examinee's ability, the better his or her choice of items.     

Multiple Indicator Stationary Time Series Models

This article is intended to complement previous research (Sivo, 1997; Sivo & Willson, 1998, in press) by discussing the propriety and practical advantages of specifying multivariate time series models in the context of structural equation modeling for time series and longitudinal panel data. Three practical considerations motivated this article. Unlike Marsh (1993), Sivo and Willson (2000) did not offer multiple indicator (latent order) equivalents to their autoregressive (AR), moving average (MA), and autoregressive-moving average (ARMA) models. Moreover, such models have yet to be discussed, despite Marsh's (1993) advocacy for multiple indicator models in general. Further motivating multiple indicator extensions of the AR, MA, and ARMA equivalent models is the fact that longitudinal studies often collect data on more than 1 related variable per occasion. Such multiple indicator models capitalize on 1 of the chief analytical advantages of structural equation modeling in that measurement error may be estimated directly.     

Alternative models of school effectiveness put to the test

The term “educational effectiveness” designates causal models of educational outcomes that may or may not contain school-level variables. The term “school effectiveness models” is used in the more restricted sense of outcome-oriented models that explicitly contain school-level variables. These models are categorized to a context-input-process-output structure, are multi-level, recognize causal chains, and sometimes include feedback loops. In this chapter the advantages of comprehensive vs. partial school effectiveness models are discussed. Furthermore alternative interpretations of the idea that higher-level variables some way facilitate lower-level variables in the production of educational outcomes are given. The debate concerns: (i) additive vs. interactive models, (ii) direct vs. indirect models, (iii) contextual vs. genuine effects, (iv) additive vs. synergetic interpretations, and (v) recursive vs. non-recursive models. In this chapter the results of empirical research are presented to test the first four completing interpretations. The results indicate that the indirect model is the least productive. The synergetic model looks promising, but more simple interactive models account for almost the same percentage of variance in students outcomes. The actual problem might be that the most likely school effectiveness models are indirect, non-recursive, contextual, synergetic, and interactive at the same time. To avoid complexities in future research decompositions are advocated. And therefore it is contended that organizational variables of interest first be examined on their possible alternative interpretation of cross-level facilitation, before formulating the model.     

Models of Self-regulated Learning: A review

Questions connected with the regulation of one's own cognitive processes attract increasing numbers of researchers in psychology, as evidenced by the several different models of self-regulation that have been developed over the past two decades. The aim of this article was to present and compare the latest models of self-regulated learning (SRL), including those by Boekaerts, Borkowski, Pintrich, Winne and Zimmerman. The models were compared on four criteria (i.e. background theories, definitions of SRL, components included in the models and empirical work). The results show that theoretical background is an important differentiating feature. The two models that resembled each other more than any other two models (i.e. Pintrich and Zimmerman) were inspired by the same background theory (i.e. social cognitive theory). On the other hand, the models that differed most from the other models (i.e. Borkowski and Winne) were also theoretically the farthest removed ones.     

Mixed linear model approaches for analyzing genetic models of complex quantitative traits

New approaches based on general mixed linear models were presented for analyzing complex quantitative traits in animal models, seed models and QTL (quantitative trait locus) mapping models. Variances and covariances can be appropriately estimated by MINQUE (minimum norm quadratic unbiased estimation) approaches. Random genetic effects can be predicted without bias by LUP (linear unbiased prediction) or AUP (adjusted unbiased prediction) methods. Mixed-model based composite interval mapping (MCIM) methods are suitable for efficiently searching QTLs along the whole genome. Bayesian methods and Markov Chain Monte Carlo (MCMC) methods can be applied in analyzing parameters of random effects as well as their variances. Projects supported by NSFC (39670390, 39893350) and the NIH Grant GM32518     

Fit of Different Models for Multitrait-Multimethod Experiments

In the past, several models have been developed for the estimation of the reliability and validity of measurement instruments from multitrait-multimethod (MTMM) experiments. Suggestions have been made for additive, multiplicative and correlated uniqueness models, whereas recently Coenders and Saris (2000) suggested a procedure to test these models against one another. In this article, the different models suggested for the analysis of MTMM matrixes have been compared for their fit to 87 data sets collected in the United States (Andrews, 1984; Rodgers, Andrews, & Herzog, 1992), Austria (Koltringer, 1995), and the Netherlands (Scherpenzeel & Saris, 1997). As most variables are categorical, the analysis has been carried out on the basis of polychoric-polyserial correlation coefficients and of Pearson correlations. The fit of the models based on polychoric correlations is much worse than the fit of models based on product moment correlations, but in both cases a model that assumes additive method effects fits most data sets better than the other models, including the so-called multiplicative models.     

Chemistry Teachers’ Knowledge and Application of Models

Teachers’ knowledge and application of model play an important role in students’ development of modeling ability and scientific literacy. In this study, we investigated Chinese chemistry teachers’ knowledge and application of models. Data were collected through test questionnaire and analyzed quantitatively and qualitatively. The result indicated as follows: (1) Chemistry teachers’ knowledge of some known chemistry models was limited; (2) Chemistry teachers preferred those models that were vivid when they chose models; (3) Teachers’ modeling process was incomplete; (4) Teachers adopted a general pattern when applying models in chemistry teaching. The findings have implications for teacher education.     

The Impact of Field Trips and Family Involvement on Mental Models of the Desert Environment

This study examined the mental models of the desert environment held by fourth‐ and seventh‐grade students in the USA and whether those mental models could be affected by: (1) classroom field trips to a desert riparian preserve, and (2) interaction with family members at the same preserve. Results generally indicated that students in this study were resolute in their models and that field trips did not impact the types of models students adhered to. Twenty‐three seventh‐grade students who self‐selected to participate in a Family Science Club with their parents did demonstrate a shift in their mental models and developed significantly more sophisticated models over time. A critical implication of the study is that unless transformation of mental models of the environment is an explicit goal of instruction, simple exposure to the environment (even within the context of life science instruction) will not transform understandings of how organisms within an environment act and interact interdependently.     

MIXED LINEAR MODEL APPROACHES FOR ANALYZING GENETIC MODELS OF COMPLEX QUANTITATIVE TRAITS

ＩＮＴＲＯＤＵＣＴＩＯＮＭａｎｙｇｅｎｅｔｉｃｍｏｄｅｌｓｂａｓｅｄｏｎｔｈｅａｐｐｒｏａｃｈｏｆＡＮＯＶＡ (ａｎａｌｙｓｉｓｏｆｖａｒｉａｎｃｅ)ｗｅｒｅｄｅｖｅｌ ｏｐｅｄｂｙＦｉｓｈｅｒ(1 92 5) .Ｓｏｍｅｏｆｔｈｅｓｅｍｏｄｅｌｓ,ｅ.ｇ .ＮＣｄｅｓｉｇｎＩａｎｄＩＩ(Ｃｏｍｓｔｏｃｋｅｔａｌ.,1 952 ;Ｈａｌｌａｕｅｒｅｔａｌ.,1 981 ) ,ｄｉａｌｌｅｌｍｏｄｅｌｓ(Ｙａｔｅｓ,1 94 7;Ｇｒｉｆｆｉｎｇ,1 956;ＧａｒｄｎｅｒａｎｄＥ ｂｅｒｈａｒｔ,1 966) ,ａｒｅｓｔｉｌｌｗｉｄｅｌｙｕｓｅｄｂｙｐｌａ…     

双模式硕士研究生培养制度初探

建议全日制统考硕士学位研究生的培养,实行“研究型”与“职业型”双模式制度。全文由四部分组成：(1)实行双模式培养制度的必要性;(2)双模式培养制度的主要内容;(3)双模式培养制度的运作方式;(4)实行双模式培养制度的成本与收益分析?     

Rotenone induces more serious learning and memory impairment than α-synuclein A30P does in Drosophila

Parkinson’s disease (PD) is a heterogenous disease caused by multifactorial etiology. PD is characterized by the loss of dopaminergic (DA) neurons in the substantia nigra and the accumulation of Lewy bodies. In this study, two Drosophila PD models by exposing Drosophila to rotenone (sporadic PD models) are proposed, and the human α-synuclein A30P protein (family PD models) in Drosophila is expressed respectively. Both models recapitulated the main human PD symptoms including the loss of dopaminergic neurons...     

Do Teachers Consider Advice? On the Acceptance of Computerized Expert Models

The literature suggests that simple expert (mathematical) models can improve the quality of decisions, but people are not always eager to accept and endorse such models. We ran three online experiments to test the receptiveness to advice from computerized expert models. Middle- and high-school teachers (N = 435) evaluated student profiles that varied in several personal and task relevant factors. They were offered (Studies I and II), or could ask for (Study III), advice from either expert models or human advisors. Overall, teachers requested and followed advice of expert models less frequently than advice from humans. Task-relevant factors (task difficulty) seem to be more salient than personal factors for teachers’ willingness to receive advice.     

Applying and Interpreting Mixture Distribution Latent State-Trait Models

Latent state-trait (LST) models are commonly applied to determine the extent to which observed variables reflect trait-like versus state-like constructs. Mixture distribution LST (M-LST) models relax the assumption of population homogeneity made in traditional LST models, allowing researchers to identify subpopulations (latent classes) with differing trait- and state-like attributes. Applications of M-LST models are scarce, presumably because of the analysis complexity. We present a step-by-step tutorial for evaluating M-LST models based on an application to mother, father, and teacher reports of children’s inattention (n = 811). In the application, we found three latent classes for mother and father reports and four classes for teacher reports. All reporter solutions contained classes with very low, low, and moderate levels of inattention. The teacher solution also contained a class with high inattention. Comparable mother and father (but not teacher) classes exhibited similar levels of trait and state variance.     

我国特殊教育师资职前培养模式研究的回顾与展望

特殊教育师资职前培养模式的形成、发展受社会政治、经济发展的影响,在不同社会历史时期,其培养模式也有所不同。本文按时间顺序分三个阶段对21世纪前我国特殊教育师资职前培养模式的发展进行了深入探讨、反思,即:(1)旧中国的“师傅带徒弟”和“师范班”模式;(2)新中国成立初期特教师资培养是空白;(3)二十世纪八十年代至世纪末的“中等特殊师范教育”和“高等特殊师范教育”模式。并对未来特殊教育师资职前培养新模式的产生提出了展望。     

Risk behaviors and resiliency within physically abused adolescents

OBJECTIVE: This study examines the relationship between physical abuse and several risk behaviors, and thriving behaviors, and the relationship between potential protective factors and engagement in risk and thriving behaviors among victims of physical abuse. Three categories of potential protective factors were examined: (1) individual characteristics, (2) family processes, and (3) extra-familial factors. We expected that high levels of protective factors would reduce engagement in risk behaviors (i.e., alcohol use, tobacco use, drug use, sexual activity, antisocial behavior, attempted suicide, and purging) among abused adolescents. RESULTS: Across all the risk behaviors, abused adolescents reported a higher frequency of engagement than non-abused adolescents. Several protective factors were identified for the seven risk behaviors. Peer group characteristics was a significant predictor in all seven of the logistic regressions, followed by positive school climate (six models), religiosity (five models), other adult support (five models), family support (four models), view of the future (two models), and involvement in extra-curricular activities (two models). The variance accounted for by the models ranged from 2% (risk behavior of purging) to 26% (risk behavior of alcohol use and antisocial behavior). CONCLUSIONS: The findings indicate that, with the exception of sexual activity, the majority of abused adolescents were not engaging in risk behaviors; however, significantly more abused adolescents were engaging in risk behaviors than their non-abused counterparts. In addition, that protective factors were found to exist at various levels of the adolescents' ecology has strong implications for practice.     

How Often Is the Misfit of Item Response Theory Models Practically Significant?

Standard 3.9 of the Standards for Educational and Psychological Testing ( 1999 ) demands evidence of model fit when item response theory (IRT) models are employed to data from tests. Hambleton and Han ( 2005 ) and Sinharay ( 2005 ) recommended the assessment of practical significance of misfit of IRT models, but few examples of such assessment can be found in the literature concerning IRT model fit. In this article, practical significance of misfit of IRT models was assessed using data from several tests that employ IRT models to report scores. The IRT model did not fit any data set considered in this article. However, the extent of practical significance of misfit varied over the data sets.     

Influence of Constructivist Professional Development on Chemistry Content Knowledge and Scientific Model Development

The purpose of this study was to explore the relationship between teachers’ (N = 69) participation in constructivist chemistry professional development (PD) and enhancement of content (CK) and pedagogical content knowledge (PCK) (representational thinking and conceptual change strategies) and self-efficacy (PSTE). Quantitative measures assessed CK, PCK, and PSTE. Document analysis focused on PCK. Elementary teachers gained CK, PCK, PSTE, and designed lessons to advance thinking from macroscopic to abstract models. Middle/secondary teachers gained PSTE, PCK, and introduced macroscopic models to develop understanding of previously taught abstract models. All implemented representational thinking and conceptual change strategies. Results suggest that: (1) constructivist PD meets the needs of teachers of varying CK, and (2) instruction should connect representational models with alternative conceptions, integrating radical and social constructivism.     

How Useful are our Models? Pre-Service and Practicing Teacher Evaluations of Technology Integration Models

We report on a survey of K-12 teachers and teacher candidates wherein participants evaluated known models (e.g., TPACK, SAMR, RAT, TIP) and provided insight on what makes a model valuable for them in the classroom. Results indicated that: (1) technology integration should be coupled with good theory to be effective, (2) classroom experience did not generally influence teacher values and beliefs related to technology integration, (3) some models may be more useful to teachers than others, (4) the widespread use of a model does not necessarily reflect usefulness, (5) useful models for teachers should engender real-world, concrete application, and (6) visual appeal of a model is largely subjective, but some visual representations might convey notions of practicality. Conclusions should be used to help researchers and practitioners understand the practical application value of technology integration models in real-world settings.