A general model for the analysis of multilevel data

A general model is developed for the analysis of multivariate multilevel data structures. Special cases of the model include repeated measures designs, multiple matrix samples, multilevel latent variable models, multiple time series, and variance and covariance component models.We would like to acknowledge the helpful comments of Ruth Silver. We also wish to thank the referees for helping to clarify the paper. This work was partly carried out with research funds provided by the Economic and Social Research Council (U.K.).     

A method of optimal scaling for multivariate ordinal data and its extensions

This paper develops a method of optimal scaling for multivariate ordinal data, in the framework of a generalized principal component analysis. This method yields a multidimensional configuration of items, a unidimensional scale of category weights for each item and, optionally, a multidimensional configuration of subjects. The computation is performed by alternately solving an eigenvalue problem and executing a quasi-Newton projection method. The algorithm is extended for analysis of data with mixed measurement levels or for analysis with a combined weighting of items. Numerical examples and simulations are provided. The algorithm is discussed and compared with some related methods.Earlier results of this research appeared in Saito and Otsu (1983). The authors would like to acknowledge the helpful comments and encouragement of the editor.     

Beyond principal component analysis: A trilinear decomposition model and least squares estimation

The paper derives sufficient conditions for the consistency and asymptotic normality of the least squares estimator of a trilinear decomposition model for multiway data analysis.     

Alternating least squares algorithms for simultaneous components analysis with equal component weight matrices in two or more populations

Millsap and Meredith (1988) have developed a generalization of principal components analysis for the simultaneous analysis of a number of variables observed in several populations or on several occasions. The algorithm they provide has some disadvantages. The present paper offers two alternating least squares algorithms for their method, suitable for small and large data sets, respectively. Lower and upper bounds are given for the loss function to be minimized in the Millsap and Meredith method. These can serve to indicate whether or not a global optimum for the simultaneous components analysis problem has been attained.Financial support by the Netherlands organization for scientific research (NWO) is gratefully acknowledged.     

Temporal proximity and reinforcement sensitivity in multiple schedules

Distributions of reinforcers between two components of multiple variable-interval schedules were varied over a number of conditions. Sensitivity to reinforcement, measured by the exponent of the power function relating ratios of responses in the two components to ratios of reinforcers obtained in the components, did not differ between conditions with 15-s or 60-s component durations. The failure to demonstrate the “short-component effect,” where sensitivity is high for short components, was consistent with reanalysis of previous data. With 60-s components, sensitivity to reinforcement decreased systematically with time since component alternation, and was higher in the first 15-s subinterval of the 60-s component than for the component whose total duration was 15 s. Varying component duration and sampling behavior at different times since component transition may not be equivalent ways of examining the effects of average temporal distance between components.     

Behavioral contrast in fixed-interval components: effects of extinction-component duration.

Seven albino rats were exposed to a multiple schedule of reinforcement in which the two components (fixed interval and extinction) alternated such that a presentation of the extinction component followed each fixed-interval reinforcement. In baseline sessions, the duration of the extinction component was constant and always one-third of the fixed-interval value. Probe sessions contained a probe segment in which the duration of the extinction component was increased; the response rate in fixed-interval components during the probe segment was compared with the response rate in the segments preceding and following the probe. The effect of increasing the duration of the extinction component was studied under three values of fixed interval: 30 s, 120 s, and 18 s, in three successive conditions. Response rate within fixed intervals was a direct function of duration of the extinction component. Pausing at the beginning of the fixed interval decreased as extinction duration increased. These effects were larger and more consistent for the shorter fixed-interval values (18 s and 30 s). These results indicate a functional relation between relative component duration and responding. For the component providing more frequent reinforcement, this could be stated as an inverse relationship between relative component duration and response rate. This relation is similar to findings regarding the ratio of trial and intertrial duration in Pavlovian conditioning procedures, and suggests that behavioral contrast may be related to Pavlovian contingencies underlying the multiple schedule.     

Effect of Daily Life Reward Loop Functioning on the Course of Depression

Engagement in activities increases positive affect (Reward Path 1), which subsequently reinforces motivation (Reward Path 2), and hence future engagement in activities (Reward Path 3). Strong connections between these three reward loop components are considered adaptive, and might be disturbed in depression. Although some ecological nomentary assessment (EMA) studies have investigated the cross-sectional association between separate reward paths and individuals’ level of depression, no EMA study has looked into the association between individuals’ reward loop strength and depressive symptom course. The present EMA study assessed reward loop functioning (5x/day, 28 days) of 46 outpatients starting depression treatment at secondary mental health services and monitored with the Inventory of Depressive Symptomatology—Self-Report (IDS-SR) during a 7-month period. Results of multilevel regression analyses showed significant within-person associations for Reward Path 1 (b = 0.21, p < .001), Reward Path 2 (b = 0.43, p < .001), and Reward Path 3 (b = 0.20, p < .001). Stronger average reward loops (i.e., within-person mean of all reward paths) did not relate to participants’ improvement in depressive symptoms over time. Path-specific results revealed that Reward Paths 1 and 2 may have partly opposite effects on depressive symptom course. Together, our findings suggest that reward processes in daily life might be best studied separately and that further investigation is warranted to explore under what circumstances strong paths are adaptive or not.     

Penalized optimal scaling for ordinal variables with an application to international classification of functioning core sets

Ordinal data occur frequently in the social sciences. When applying principal component analysis (PCA), however, those data are often treated as numeric, implying linear relationships between the variables at hand; alternatively, non-linear PCA is applied where the obtained quantifications are sometimes hard to interpret. Non-linear PCA for categorical data, also called optimal scoring/scaling, constructs new variables by assigning numerical values to categories such that the proportion of variance in those new variables that is explained by a predefined number of principal components (PCs) is maximized. We propose a penalized version of non-linear PCA for ordinal variables that is a smoothed intermediate between standard PCA on category labels and non-linear PCA as used so far. The new approach is by no means limited to monotonic effects and offers both better interpretability of the non-linear transformation of the category labels and better performance on validation data than unpenalized non-linear PCA and/or standard linear PCA. In particular, an application of penalized optimal scaling to ordinal data as given with the International Classification of Functioning, Disability and Health (ICF) is provided.     

Contrast and reallocation of extraneous reinforcers as a function of component duration and baseline rate of reinforcement

Four pigeons responded on multiple schedules arranged on a “main” key in a two-key experimental chamber. A constant schedule component was alternated with another component that was varied over conditions. On an extra response key, conjoint schedules of reinforcement that operated in both components were arranged concurrently with the multiple schedule on the main key. On the main key, changes in reinforcement rate in the varied component were inversely related to changes in response rates in the constant component (behavioral contrast). On the extra key, some reinforcers were reallocated between components, depending on the schedules in effect on the main key in the varied component. In the varied component, the obtained rates of reinforcement on the extra key were inversely related to main-key reinforcement rate. In the constant component, extra-key reinforcer rates were positively related to main-key reinforcer rates obtained in the varied component, and were not a function of response rates on the extra key. In two comparisons, the rate at which components alternated and the value of the main-key schedule in the constant component were varied. Consistent with earlier work, long components reduced the extent of contrast. Reductions in contrast as a function of component duration were accompanied by similar reductions in the extent of reinforcer reallocation on the extra key. In the second comparison, lowering the rate of reinforcement in the constant component increased the rate at which extra-key reinforcers were obtained, reduced the extent of reinforcer reallocation, and reduced contrast. Overall, the results are consistent with the suggestion that some contrast effects are due to the changes in extraneous reinforcement during the constant component, and that manipulations of component duration, and manipulations of the rate of reinforcement in the constant component, affect contrast because they influence the extent of extraneous reinforcer real-location.     

Decompositions and biplots in three-way correspondence analysis

In this paper correspondence analysis for three-way contingency tables is presented using three-way generalisations of the singular value decomposition. It is shown that in combination with Lancaster's (1951) additive decomposition of interactions in three-way tables, a detailed analysis is possible of the deviations from independence. Finally, biplots are shown to produce powerful graphical representations of the results from three-way correspondence analyses. An example from child development is used to illustrate the theoretical developments.