Using segmented linear regression models with unknown change points to analyze strategy shifts in cognitive tasks

Some years ago, Beem (1993, 1995) described a program for fitting two regression lines with an unknown change point (Segcurve). He suggested that such models are useful for the analysis of a variety of phenomena and gave an example of an application to the study of strategy shifts in a mental rotation task. This technique has also proven to be very fruitful for investigating strategy use and strategy shifts in other cognitive tasks. Recently, Beem (1999) developed SegcurvN, which fitsn regression lines with (n - 1) unknown change points. In the present article we present this new technique and demonstrate the usefulness of a three-phase segmented linear regression model for the identification of strategies and strategy shifts in cognitive tasks by applying it to data from a numerosity judgment experiment. The advantages and shortcomings of this technique are evaluated.     

A method to analyze the spatial distribution of behavior

This article presents a method comprising an experimental environment, infrared detection system, data collection and processing software, behavior categories, and suggested quantitative analysis methods for studying some spatial properties of behavior. In the chamber, the location of a rat is determined at regular intervals by a 24 × 24 grid of infrared beams; the status of each line used interactively to determine changes in the environment are stored on disk for later analysis. From the status of the receptors, the computer decodes the location of objects in the chamber, and a binary 576-cell matrix is obtained for each sample. The series of matrices allows a number of behavior categories to be defined includingexploration, activity, andtime allocation. Exploration curves and time allocation surfaces are compared using a goodness-of-fit test; activity is assessed with time-series methods. Potential applications to psychological, pharmacological, and ethological research are considered.     

An elicitation method for multiple linear regression models

This paper describes a method of quantifying subjective opinion about a normal linear regression model. Opinion about the regression coefficients and experimental error is elicited and modeled by a multivariate probability distribution (a Bayesian conjugate prior distribution). The distribution model is richly parameterized and various assessment tasks are used to estimate its parameters. These tasks include the revision of opinion in the light of hypothetical data, the assessment of credible intervals, and a task commonly performed in cue-weighting experiments. A new assessment task is also introduced. In addition, implementation of the method in an interactive computer program is described and the method is illustrated with a practical example.     

A nonparametric method to analyze interactions: The adjusted rank transform test

Experimental social psychologists routinely rely on ANOVA to study interactions between factors even when the assumptions underlying the use of parametric tests are not met. Alternative nonparametric methods are often relatively difficult to conduct, have seldom been presented into detail in regular curriculum and have the reputation - sometimes incorrectly - of being less powerful than parametric tests. This article presents the adjusted rank transform test (ART); a nonparametric test, easy to conduct, having the advantage of being much more powerful than parametric tests when certain assumptions underlying the use of these tests are violated. To specify the conditions under which the adjusted rank transform test is superior to the usual parametric tests, results of a Monte Carlo simulation are presented.     

Fitting linear models to ordinal responses

The distribution of an ordinal response can be modelled as a grouping of an underlying quantitative variable whose mean is a linear function of explanatory variables. Possible distributional assumptions about the underlying quantitative response are compared. An iteratively reweighted least squares algorithm for parameter estimation in these models is described in detail and variances and tests of hypotheses are given. Two data sets are analysed to illustrate the methods.     

Using information criteria to determine the number of regimes in threshold autoregressive models

Threshold autoregressive models can be used to study processes that are characterized by recurrent switches between two or more regimes, where switching is triggered by a manifest threshold variable. In this paper the performance of diverse information criteria for selecting the number of regimes in small to moderate sample sizes (i.e., n=50,100,200) is investigated. In addition it is investigated whether these information criteria can be used to determine whether the residual variances are identical across the regimes. It is concluded that for small sample sizes should be preferred, while for larger sample sizes either BIC or should be considered: The latter is the only information criterion that includes a penalty for the unknown threshold parameters.     

An evolutionary approach to support decision making with linear decision models

In this paper we consider decision problems that can be described as linear decision models. These models have been traditionally solved using linear programming, fuzzy linear programming, multiple-objective linear programming or ‘what-if’ analysis. Using these approaches, one encounters a number of difficulties. We propose an ‘evolutionary approach’ to overcome these difficulties. In the proposed approach the decision maker does not have to precisely specify the model (i.e. the objective functions, the RHS values, etc.) at the beginning of the solution procedure. In fact, the model evolves as the solution procedure proceeds.     

Using generalized additive (mixed) models to analyze single case designs

This article shows how to apply generalized additive models and generalized additive mixed models to single-case design data. These models excel at detecting the functional form between two variables (often called trend), that is, whether trend exists, and if it does, what its shape is (e.g., linear and nonlinear). In many respects, however, these models are also an ideal vehicle for analyzing single-case designs because they can consider level, trend, variability, overlap, immediacy of effect, and phase consistency that single-case design researchers examine when interpreting a functional relation. We show how these models can be implemented in a wide variety of ways to test whether treatment is effective, whether cases differ from each other, whether treatment effects vary over cases, and whether trend varies over cases. We illustrate diagnostic statistics and graphs, and we discuss overdispersion of data in detail, with examples of quasibinomial models for overdispersed data, including how to compute dispersion and quasi-AIC fit indices in generalized additive models. We show how generalized additive mixed models can be used to estimate autoregressive models and random effects and discuss the limitations of the mixed models compared to generalized additive models. We provide extensive annotated syntax for doing all these analyses in the free computer program R.     

Using the linear mixed model to analyze nonnormal data distributions in longitudinal designs

Using a Monte Carlo simulation and the Kenward–Roger (KR) correction for degrees of freedom, in this article we analyzed the application of the linear mixed model (LMM) to a mixed repeated measures design. The LMM was first used to select the covariance structure with three types of data distribution: normal, exponential, and log-normal. This showed that, with homogeneous between-groups covariance and when the distribution was normal, the covariance structure with the best fit was the unstructured population matrix. However, with heterogeneous between-groups covariance and when the pairing between covariance matrices and group sizes was null, the best fit was shown by the between-subjects heterogeneous unstructured population matrix, which was the case for all of the distributions analyzed. By contrast, with positive or negative pairings, the within-subjects and between-subjects heterogeneous first-order autoregressive structure produced the best fit. In the second stage of the study, the robustness of the LMM was tested. This showed that the KR method provided adequate control of Type I error rates for the time effect with normally distributed data. However, as skewness increased—as occurs, for example, in the log-normal distribution—the robustness of KR was null, especially when the assumption of sphericity was violated. As regards the influence of kurtosis, the analysis showed that the degree of robustness increased in line with the amount of kurtosis.     

Logistic latent trait models with linear constraints

Two linearly constrained logistic models which are based on the well-known dichotomous Rasch model, the ‘linear logistic test model’ (LLTM) and the ‘linear logistic model with relaxed assumptions’ (LLRA), are discussed. Necessary and sufficient conditions for the existence of unique conditional maximum likelihood estimates of the structural model parameters are derived. Methods for testing composite hypotheses within the framework of these models and a number of typical applications to real data are mentioned.     

Inference in regression models of heavily skewed alcohol use data: a comparison of ordinary least squares, generalized linear models, and bootstrap resampling.

Analysis of alcohol use data and other low base rate risk behaviors using ordinary least squares regression models can be problematic. This article presents 2 alternative statistical approaches, generalized linear models and bootstrapping, that may be more appropriate for such data. First, the basic theory behind the approaches is presented. Then, using a data set of alcohol use behaviors and consequences, results based on these approaches are contrasted with the results from ordinary least squares regression. The less traditional approaches consistently demonstrated better fit with model assumptions, as demonstrated by graphical analysis of residuals, and identified more significant variables potentially resulting in theoretically different interpretations of the models of alcohol use. In conclusion, these models show significant promise for furthering the understanding of alcohol-related behaviors.     

Multivariate multiple regression analyses: a permutation method for linear models

A multivariate extension of a univariate procedure for the analysis of experimental designs is presented. A Euclidean-distance permutation procedure is used to evaluate multivariate residuals obtained from a regression algorithm, also based on Euclidean distances. Applications include various completely randomized and randomized block experimental designs such as one-way, Latin square, factorial, nested, and split-plot designs, with and without covariates. Unlike parametric procedures, the only required assumption is the randomization of subjects to treatments.     

A general approach to categorical data analysis with missing data,using generalized linear models with composite links

A general approach for analyzing categorical data when there are missing data is described and illustrated. The method is based on generalized linear models with composite links. The approach can be used (among other applications) to fill in contingency tables with supplementary margins, fit loglinear models when data are missing, fit latent class models (without or with missing data on observed variables), fit models with fused cells (including many models from genetics), and to fill in tables or fit models to data when variables are more finely categorized for some cases than others. Both Newton-like and EM methods are easy to implement for parameter estimation.The author thanks the editor, the reviewers, Laurie Hopp Rindskopf, and Clifford Clogg for comments and suggestions that substantially improved the paper.     

A Newton procedure for conditionally linear mixed-effects models

This article reviews Newton procedures for the analysis of mean and covariance structures that may be functions of parameters that enter a model nonlinearly. The kind of model considered is a mixed-effects model that is conditionally linear with regard to its parameters. This means parameters entering the model nonlinearly must be fixed, whereas those entering linearly may vary across individuals. This framework encompasses several models, including hierarchical linear models, linear and nonlinear factor analysis models, and nonlinear latent curve models. A full maximum-likelihood estimation procedure is described. Mx, a statistical software package often used to estimate structural equation models, is considered for estimation of these models. An example with Mx syntax is provided.     

A marginal maximum likelihood method for the vector threshold model to analyze dichotomous choice data

Abstract: At least two types of models, the vector model and the unfolding model can be used for the analysis of dichotomous choice data taken from, for example, the pick any/ n method. The previous vector threshold models have a difficulty with estimation of the nuisance parameters such as the individual vectors and thresholds. This paper proposes a new probabilistic vector threshold model, where, unlike the former vector models, the angle that defines an individual vector is a random variable, and where the marginal maximum likelihood estimation method using the expectation-maximization algorithm is adopted to avoid incidental parameters. The paper also attempts to discuss which of the two models is more appropriate to account for dichotomous choice data. Two sets of dichotomous choice data are analyzed by the model.     

A path-analytic strategy to analyze psychoanalytic treatment effects

This paper introduces a path-analytic strategy to analyze psychoanalytic treatment effects. A simple causal model is used to analyze a well-known case study by Charles Brenner. Application of even this simple model to the case study sharpens causal inferences that may be validly made, highlights important aspects of the psychoanalytic process and builds a foundation for further model development.     

Generalized linear models with ordinally‐observed covariates

An ordinally‐observed variable is a variable that is only partially observed through an ordinal surrogate. Although statistical models for ordinally‐observed response variables are well known, relatively little attention has been given to the problem of ordinally‐observed regressors. In this paper I show that if surrogates to ordinally‐observed covariates are used as regressors in a generalized linear model then the resulting measurement error in the covariates can compromise the consistency of point estimators and standard errors for the effects of fully‐observed regressors. To properly account for this measurement error when making inferences concerning the fully‐observed regressors, I propose a general modelling framework for generalized linear models with ordinally‐observed covariates. I discuss issues of model specification, identification, and estimation, and illustrate these with examples.     

Fitting cross-classification table data to models when observations are subject to classification error

Individuals are classified in a cross-classification table where two behavioral observations on each individual determine the classification. The problem is to test certain structural models assumed to underlie the cross-classified observations. A minimum chi-square test procedure is proposed.     

Statistical inference in generalized linear mixed models: A review

We present a review of statistical inference in generalized linear mixed models (GLMMs). GLMMs are an extension of generalized linear models and are suitable for the analysis of non‐normal data with a clustered structure. A GLMM contains parameters common to all clusters (fixed regression effects and variance components) and cluster‐specific parameters. The latter parameters are assumed to be randomly drawn from a population distribution. The parameters of this population distribution (the variance components) have to be estimated together with the fixed effects. We focus on the case in which the cluster‐specific parameters are normally distributed. The cluster‐specific effects are integrated out of the likelihood so that the fixed effects and variance components can be estimated. Unfortunately, the integral over the cluster‐specific effects is intractable for most GLMMs with a normal mixing distribution. Within a classical statistical framework, we distinguish between two broad classes of methods to handle this intractable integral: methods that rely on a numerical approximation to the integral and methods that use an analytical approximation to the integrand. Finally, we present an overview of available methods for testing hypotheses about the parameters of GLMMs.