Multiple regression analysis for categorical data with an illustrative application in personnel selection.

Discusses a unified approach to the analysis of categorical data. The procedure is appropriate whenever 1 set of categorical variables can be regarded as dependent and a 2nd set is identified as predictor variables. The approach is identical to the traditional logit analysis model, but for computational convenience the procedure can be modeled in the more general log-linear framework. (16 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Controlling for stimulus dominance in dichotic listening tests: A modification of !l.

Dichotic listening procedures have been used to assess cerebral lateralization in normal Ss. One particularly useful technique is the use of stimuli that fuse into a single percept. Although this procedure has many advantages over other dichotic listening methods, it is particularly susceptible to stimulus dominance, which acts as noise in a S's response data, thus reducing the power of any statistical test of the ear advantage. It is proposed that the solution to this problem is a log-linear analysis of the response data to yield a λ-type index (λ*) that is a measure of ear dominance independent of stimulus dominance. Details of the analysis are provided, as well as a sample analysis of data collected from 104 right-handed and 30 left-handed Ss. Comparisons are drawn between the log-linear analysis and other methods that have been proposed to control for stimulus dominance in this single-response dichotic fusion procedure. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The wedge, the fork, and the chain: Modeling dependency concepts using manifest categorical variables.

This article is concerned with modeling concepts of causal dependency. Example concepts are the wedge, the fork, and the chain. The wedge concept proposes that there is more than 1 way to arrive at a particular outcome. The fork concept proposes that there can be more than 1 outcome linked to a particular antecedent event. The chain concept proposes serial causation. This article focuses on modeling manifest categorical variables using nonstandard log-linear models. The models include 2 parts. The 1st part is the so-called base model. It specifies the variable relationships that (a) underlie a particular model and (b) are not part of the concept under study. The 2nd part specifies contrasts for the patterns of variable categories that represent a particular dependency concept. Data examples present models of sleep disorders, long-term effects of risks in early childhood, and career motivation. The discussion proposes extensions and further developments of models and relates this modeling approach to configural frequency analysis and cell means models. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Doppler echocardiographic method to determine early and late diastolic filling volume separately. Validation and relationship between filling velocity and volume

The advantage of modelling agreement on a categorical scale among observers rather than using summarizing indices is now well established. However, analysis of agreement among more than two observers is essentially based on pairs of observers. We present a global and partial agreement modelling approach derived from the quasi-independence and quasi-symmetry log-linear models. This approach addresses high order interactions in the contingency table rather than two-way interaction in the pairwise agreement approach. Pairwise, global and partial agreement models were applied to the detection by six pathologists of three lesions in biopsy specimens arising from patients suspected to be affected by Crohn's disease. The global and partial agreement approach surpasses the pairwise agreement approach, especially if there is heterogeneity among ratings.     

Nonstandard log-linear models.

This article demonstrates several useful varieties of nonstandard log-linear models. Some can be derived as nonhierarchical models by deleting lower-order effects in hierarchical models, but most often they will arise as the result of special hypotheses that the researcher wants to test. Three approaches to testing nonstandard models, partitioning chi-square, creating homogeneous subgroups, and the model matrix approach, are illustrated on a variety of data sets. It is assumed that the reader has been exposed to the general area of log-linear models, is familiar with dummy and effect coding of categorical variables in the usual regression framework, and knows how to express models in matrix form. A brief summary of the standard approach to log-linear models and of coding methods is provided for readers needing a review. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Multilevel Methods for Modeling Observed Sequences of Family Interaction.

Observation of interaction plays a central role in family research. This article discusses how to analyze sequential data generated by discrete microcoding methods to test hypotheses about family interaction. Current methods for studying sequential data are presented, and their limits are discussed. Building on recent applications of contingency table analysis to such data, a multilevel log-linear model is presented that can specify and estimate indicators of individual behavioral tendencies and antecedent-consequent relationships among behaviors, both within and across samples of families. An example of this method is presented using data from a study of couples facing job loss. Potential extensions of this framework for future research are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Testing hypotheses about ordinal interactions: Simulations and further comments.

This paper elaborates on several issues related to testing for the presence of ordinal interactions, as described by Bobko (1986). First, the philosophy underlying Bobko's approach is explicitly stated and compared with the traditional approach to testing for the presence of interactions. Second, two modifications of Bobko's approach are described. Third, the procedures for testing ordinal interactions are compared (on the basis of Type I and Type II error rates) with each other as well as to the traditional analysis of variance (ANOVA) approach. All variants of Bobko's procedure have comparable power across different sample sizes and experimental effect sizes. These procedures differ, however, in their likelihood of falsely concluding that an ordinal pattern is present. The traditional ANOVA approach (a) is noticeably lacking in power for detecting ordinal interactions and (b) commonly identifies significant main effects but not an interaction when, in fact, an ordinal interaction is present in the population. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Macrotransport-solidification kinetics modeling of equiaxed dendritic growth: Part II. Computation problems and validation on INCONEL 718 superalloy castings

In Part I of the article, a new analytical model that describes solidification of equiaxed dendrites was presented. In this part of the article, the model is used to simulate the solidification of INCONEL 718 superalloy castings. The model was incorporated into a commercial finite-element code, PROCAST. A special procedure called microlatent heat method (MLHM) was used for coupling between macroscopic heat flow and microscopic growth kinetics. A criterion for time-stepping selection in microscopic modeling has been derived in conjunction with MLHM. Reductions in computational (CPU) time up to 90 pct over the classic latent heat method were found by adopting this coupling. Validation of the model was performed against experimental data for an INCONEL 718 superalloy casting. In the present calculations, the model for globulitic dendrite was used. The evolution of fraction of solid calculated with the present model was compared with Scheil’s model and experiments. An important feature in solidification of INCONEL 718 is the detrimental Laves phase. Laves phase content is directly related to the intensity of microsegregation of niobium, which is very sensitive to the evolution of the fraction of solid. It was found that there is a critical cooling rate at which the amount of Laves phase is maximum. The critical cooling rate is not a function of material parameters (diffusivity, partition coefficient,etc.). It depends only on the grain size and solidification time. The predictions generated with the present model are shown to agree very well with experiments.     

Cross-strand side-chain interactions versus turn conformation in beta-hairpins

A series of designed peptides has been analyzed by 1H-NMR spectroscopy in order to investigate the influence of cross-strand side-chain interactions in beta-hairpin formation. The peptides differ in the N-terminal residues of a previously designed linear decapeptide that folds in aqueous solution into two interconverting beta-hairpin conformations, one with a type I turn (beta-hairpin 4:4) and the other with a type I + G1 beta-bulge turn (beta-hairpin 3:5). Analysis of the conformational behavior of the peptides studied here demonstrates three favorable and two unfavorable cross-strand side-chain interactions for beta-hairpin formation. These results are in agreement with statistical data on side-chain interactions in protein beta-sheets. All the peptides in this study form significant populations of the beta-hairpin 3:5, but only some of them also adopt the beta-hairpin 4:4. The formation of beta-hairpin 4:4 requires the presence of at least two favorable cross-strand interactions, whereas beta-hairpin 3:5 seems to be less susceptible to side-chain interactions. A protein database analysis of beta-hairpins 3:5 and beta-hairpins 4:4 indicates that the former occur more frequently than the latter. In both peptides and proteins, beta-hairpins 3:5 have a larger right-handed twist than beta-hairpins 4:4, so that a factor contributing to the higher stability of beta-hairpin 3:5 relative to beta-hairpin 4:4 is due to an appropriate backbone conformation of the type I + G1 beta-bulge turn toward the right-handed twist usually observed in protein beta-sheets. In contrast, as suggested previously, backbone geometry of the type I turn is not adequate for the right-handed twist. Because analysis of buried hydrophobic surface areas on protein beta-hairpins reveals that beta-hairpins 3:5 bury more hydrophobic surface area than beta-hairpins 4:4, we suggest that the right-handed twist observed in beta-hairpin 3:5 allows a better packing of side chains and that this may also contribute to its higher intrinsic stability.     

Strategies for the selection of log-linear models

In a multidimensional contingency table strategies have been proposed to build log-linear models using either stepwise methods or standardized estimates of the parameters of the saturated model. Brown (1976) proposed a two-step procedure to screen effects and then test a subset of models. Alternate methods of model building are discussed with respect to the final choice of model and with respect to intermediate information available to the data analyst during the selection process.     

Commentary on Steinley and Brusco (2011): Recommendations and cautions.

I discuss the recommendations and cautions in Steinley and Brusco's (2011) article on the use of finite models to cluster a data set. In their article, much use is made of comparison with the K-means procedure. As noted by researchers for over 30 years, the K-means procedure can be viewed as a special case of finite mixture modeling in which the components are in equal (fixed) proportions and are taken to be normal with a common spherical covariance matrix. In this commentary, I pay particular attention to this link and to the use of normal mixture models with arbitrary component-covariance matrices. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

A neurocognitive model of the ethical decision-making process: Implications for study and practice.

The field of business ethics is entrenched in a cognitive approach that portrays the ethical decision-making process as a completely deliberate and reasoned exercise. In light of growing concerns about the veracity of this approach, I build upon current knowledge of how the brain functions to present a neurocognitive model of ethical decision making. The model suggests that ethical decision making involves 2 interrelated yet functionally distinct cycles, a reflexive pattern matching cycle and a higher order conscious reasoning cycle, and thereby describes not only reasoned analysis, but also the intuitive and retrospective aspects of ethical decision making. The model sparks research in new areas, holds significant implications for the study of ethical decision making, and provides suggestions for improving ethical behavior in organizations. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The use and misuse of chi-square: Lewis and Burke revisited.

Reviews the proper use of the Pearson chi-square for analyzing contingency tables. The 1949 article by D. Lewis and C. J. Burke, who cited 9 sources of error in the use of chi-square, is updated. Since the publication of that article, statisticians have addressed the question of the minimal size of expected cell frequencies. This problem has been examined from 2 perspectives: tests of association hypotheses in contingency tables and testing goodness-of-fit hypotheses. Under certain conditions, expected cell frequencies less than 5 do not substantially alter the Type I error rate. Supplementary and alternative approaches to the chi-square, including those involving log- and log-linear models, log-likelihood ratio, partitioning, comparison of individual proportions, and analysis of ordered categories, are discussed. Emphasis is placed on techniques that are of use to the practicing researcher who often deals with qualitative ordered and unordered data. (96 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Linker DNA and H1-dependent reorganization of histone-DNA interactions within the nucleosome

We have employed a site-directed photochemical cross-linking procedure to precisely map interactions between nucleosomal DNA and the C-terminal tail of core histone H2A. We find that this tail has the potential to contact multiple sites within the nucleosome and that these contacts are dependent upon the configuration of the complex. This tail contacts DNA near the dyad axis within nucleosome core particles but rearranges to a site near the edge of the nucleosomal DNA when linker DNA is present. Moreover, in the presence of linker histone H1 the contacts near the edge of the nucleosome but not at the dyad are further rearranged. In addition, we present further evidence for the suggestion that the binding of linker histone causes a subtle but global change in core histone-DNA interactions within the nucleosome [Usachenko, S. I., Gavin, I. M., and Bavykin, S. G. (1996) J. Biol. Chem. 271, 3831-3836].     

A truncated poisson regression model with applications to occurrence of adenomatous polyps

Adenomatous polyps are considered as the dominant precursor lesion of colorectal cancer. A phase III colorectal cancer prevention trial, conducted by the Arizona Cancer Center, concerns the ability of wheat bran fibre supplement to reduce the recurrence of adenomatous polyps. All participants in the study are to have had colorectal polyps detected and removed during a baseline (qualifying) colonoscopy within three months prior to enrolment. In this paper, our interest focuses on occurrence of adenomatous polyps at the baseline colonoscopy. We use a truncated Poisson model to fit these types of data. We develop a regression model to assess the effects of explanatory factors on the positive counting variable. We fit truncated Poisson parameters by a log-linear regression model and estimate regression parameters by the maximum likelihood procedure. Finally, we apply it to the baseline colonoscopy data from the Wheat Bran Fiber study.     

Numerical analysis of metal transfer in gas metal arc welding

The present article describes a numerical procedure to simulate metal transfer and the model will be used to analyze the transport processes involved in gas metal arc welding (GMAW). Advanced Computational fluid dynamics (CFD) techniques used in this model include a two-step projection method for solving the incompressible fluid flow; a volume of fluid (VOF) method for capturing free surface; and a continuum surface force (CSF) model for calculating surface tension. The electromagnetic force due to the welding current is estimated by assuming several different types of current density distribution on the free surface of the drop. The simulations based on the assumption of Gaussian current density distribution show that the transition from globular to spray transfer mode occurs over a narrow current range and the size of detached drops is nonuniform in this transition zone. The analysis of the calculation results gives a better understanding of this physical procedure. Comparisons between calculated results and experimental results are presented. It is found that the results computed from the Gaussian assumption agree well with those observed in experiments.     

Testing for segregation distortion in the HLA complex

One of the long-standing issues in HLA research is whether there is segregation distortion in the HLA complex in human populations. In this paper we study some simple statistical models aimed at detecting segregation distortion. We present a statistic to test the Mendelian null hypothesis of equal transmission probabilities. To assess the possible contribution of multiple alleles to segregation distortion, we employ a specific log-linear model for transmission probabilities equivalent to the Bradley-Terry model in the literature of paired comparisons. We also provide a simple method for detecting a single allele effect, if present.     

Three-Dimensional Analysis of Lateral Pile Response using Two-Dimensional Explicit Numerical Scheme

A procedure for exploiting a two-dimensional (2D) explicit, numerical computer code for the 3D formulation of dynamic lateral soil-pile interactions is considered. The procedure is applied to two models using simultaneous computation of a series of plane strain boundary value problems, each of which represents a horizontal layer of soil. The first model disregards the shear forces developed between the horizontal layers, and may be considered as a generalized Winkler model. The second model takes account of these forces by coupling the behavior of the horizontal layers. Several verification problems for a single pile and pile groups in a homogeneous soil layer modeled as a viscoelastic material were solved and compared to known solutions in order to assess the reliability of the models. Excellent agreement was observed between results of the present analyses and existing solutions.