Testing a stochastic foraging model in an operant simulation: Agreement with qualitative but not quantitative predictions

An operant simulation of foraging through baited and empty patches was studied with 4 pigeons. On a three-key panel, side keys were designated as patches, and successive opportunities to complete 16 fixed-ratio 10 schedules on side keys were defined as encounters with feeders. In a random half of the patches in any session, some of the fixed-ratio 10 schedules yielded reinforcement (baited feeders) and the other schedules yielded nonreinforcement (empty feeders). In the other half of the patches, all feeders were empty. Pigeons could travel between patches at any time by completing a fixed-ratio schedule on the center key. An optimal foraging model was tested in Experiments 1 and 2 by varying center-key travel time and number of baited feeders in baited patches. The ordinal predictions that number of feeders visited in empty patches would increase with travel time and decrease as number of baited feeders increased were supported, but pigeons visited far more feeders in empty patches than the optimal number predicted by the model to maximize energy/time. In Experiment 3, evidence was found to suggest that the number of empty feeders encountered before the first baited feeder in baited patches is an important factor controlling leaving empty patches.     

On the sampling theory roundations of item response theory models

Item response theory (IT) models are now in common use for the analysis of dichotomous item responses. This paper examines the sampling theory foundations for statistical inference in these models. The discussion includes: some history on the stochastic subject versus the random sampling interpretations of the probability in IRT models; the relationship between three versions of maximum likelihood estimation for IRT models; estimating versus estimating -predictors; IRT models and loglinear models; the identifiability of IRT models; and the role of robustness and Bayesian statistics from the sampling theory perspective.A presidential address can serve many different functions. This one is a report of investigations I started at least ten years ago to understand what IRT was all about. It is a decidedly one-sided view, but I hope it stimulates controversy and further research. I have profited from discussions of this material with many people including: Brian Junker, Charles Lewis, Nicholas Longford, Robert Mislevy, Ivo Molenaar, Donald Rock, Donald Rubin, Lynne Steinberg, Martha Stocking, William Stout, Dorothy Thayer, David Thissen, Wim van der Linden, Howard Wainer, and Marilyn Wingersky. Of course, none of them is responsible for any errors or misstatements in this paper. The research was supported in part by the Cognitive Science Program, Office of Naval Research under Contract No. Nooo14-87-K-0730 and by the Program Statistics Research Project of Educational Testing Service.     

Stochastic ordering using the latent trait and the sum score in polytomous IRT models

In a restricted class of item response theory (IRT) models for polytomous items the unweighted total score has monotone likelihood ratio (MLR) in the latent trait. MLR implies two stochastic ordering (SO) properties, denoted SOM and SOL, which are both weaker than MLR, but very useful for measurement with IRT models. Therefore, these SO properties are investigated for a broader class of IRT models for which the MLR property does not hold.In this study, first a taxonomy is given for nonparametric and parametric models for polytomous items based on the hierarchical relationship between the models. Next, it is investigated which models have the MLR property and which have the SO properties. It is shown that all models in the taxonomy possess the SOM property. However, counterexamples illustrate that many models do not, in general, possess the even more useful SOL property.Hemker's research was supported by the Netherlands Research Council, Grant 575-67-034. Junker's research was supported in part by the National Institutes of Health, Grant CA54852, and by the National Science Foundation, Grant DMS-94.04438.     

Multivariate stochastic processes compatible with “aspect” models of similarity and choice

Various recent works have developed feature or aspect models of similarity and preference. These models are more concerned with the fine detail of the judgment process than were prior models, but nevertheless they have not in general developed an underlying stochastic process compatible with the assumed structure. In this paper, we show that a particular class of multivariate stochastic processes, namely those associated with the Marshall-Olkin multivariate exponential distribution, generates several of these models. In particular, such stochastic processes (appropriately interpreted) yield Tversky's elimination by aspects model, Edgell and Geisler's (normal) additive random aspects model, and Shepard and Arabie's additive cluster model.This work was supported by Natural Science and Engineering Research Council of Canada Grant A8124 to A.A.J. Marley.     

Some subordinates are more equal than others: Play fihgting amongst adult subordinate male rats

Adult male rats living together form dominance relationships, with one dominant and the remainder adopting subordinate roles. In previous studies, it was shown that in adult male pairs, the subordinate rat initiates more playful contacts and retains a more juvenile response to the playful contacts by the dominant. In this experiment, triads were used to examine the play between subordinate males. The subordinates directed fewer playful contacts to each other than to the dominant rat, and there was a symmetrical play relationship between the subordinates. After the dominant was removed from the colony, one subordinate became the dominant. Playful interactions amongst these pairs increased, with the subordiante intiating more playful contacts than the dominant. Furthermore, from a similarly low frequency of juvenile-type response to playful contact to each other when in triads, the subordinate in the dyads increased its frequency of juvenile responses to the dominant partner. This supports the hypothesis that the playful behavior of subordinate male rats towards the dominant is an adaptive response, playful behavior of subordinate male rats towards the dominant is an adaptive response, serving a “friendship maintenance” function. Finally, when in triads, one subordinate was more playful with the dominant than the other subordinate. It was the least playful subordinate that was the most likely to become the dominant. This sugests that within a colony, not all subordinates are the same. © 1993 Wiley-Liss, Inc.     

Fighting experiences and natural killer cell activity in male laboratory mice

There is currently much interest in the potential impact of psychological factors on immune responses. An attempt was made to assess the effects of dominant/subordinate polarity in male mice on the cytotoxic activities of their natural-killer (NK) cells. On the basis of repeated agonistic encounters, categories of subordinate and dominat animals were selected. These animals were compared with manipulated controls (introduced to a novel test cage without an opponent on each occasion) and undisturbed controls (who remained in isolation without manipulation). In terms of NK activity, immunosuppression was observed in both dominant and subordinate categories when compared to undisturbed controls. There were, however, no differences between the fighting exposed subjects and the manipulated controls, suggesting that stress accounts for any changes. © 1994 Wiley-Liss, Inc.     

Effects of prior agonistic experience on risk assessment and approach behavior evoked by familiar or unfamiliar conspecific odors

Risk assessment and appetitive behaviors in response to familiar and unfamiliar conspecific odors were measured in mice rendered dominant or subordinate by a series of resident-intruder encounters. Subordinate mice showed elevated levels of risk assessment in response to the odors of both familiar dominant and unfamiliar males. These behaviors were almost totally absent among dominant males exposed to familiar subordinate or unfamiliar male odors. Subordinate mice showed a marginally significant elevation in latencies to approach familiar, but not unfamiliar, dominant odors. Dominant and subordinate mice spent comparable amounts of time in the cage area containing familiar antagonist odors, however, and the durations of subordinates were mildly elevated, rather than decreased, when unfamiliar conspecific odors were present. There were no group differences in any of the appetitive behaviors. These findings suggest that apparent preferences for conspecific odors may arise from quantitatively and/or qualitatively differing emotional states. The inclusion of risk assessment measures is suggested to be a useful adjunct for studies of olfactory preference/rejection. © 1994 Wiley-Liss, Inc.     

When is the Wilcoxon–Mann–Whitney procedure a test of location? Implications for effect-size measures

The Wilcoxon–Mann–Whitney procedure is invariant under monotone transformations but its use as a test of location or shift is said not to be so. It tests location only under the shift model, the assumption of parallel cumulative distribution functions (cdfs). We show that infinitely many monotone transformations of the measured variable produce parallel cdfs, so long as the original cdfs intersect nowhere or everywhere. Thus there are infinitely many effect sizes measured as shifts of medians, invalidating the notion that there is one true shift parameter and thereby rendering any single estimate dubious. Measuring effect size using the probability of superiority alleviates this difficulty.     

Crafting Mosaics: Person-Centered Religious Influence and Selection in Adolescent Friendships

This research addresses the intersection of two key domains of adolescents’ lives: religion and peer networks. Religion scholars argue that religion is multi-faceted and better understood by focusing on combinations of indicators (i.e., mosaics), versus a variable-centered approach. We adopt this framework and investigate the interplay between religion and peer networks, both in how religious mosaics are shaped by friends and how religious profiles affect friend selection dynamics. With data from two schools in the National Longitudinal Study of Adolescent Health, we estimate religious mosaics using latent class analysis (LCA) to identify profiles consisting of combinations of commonly available survey-based measures of religious attitudes, behaviors, and identities. Finding evidence of theoretically expected profiles, we then use stochastic actor–based models (SABMs) to investigate network dynamics for these LCA-based religious profiles. We demonstrate how the profile data can be integrated within the SABM framework to evaluate processes of friend selection and influence. Results show evidence of adolescents influencing one another's religious mosaics, but not selecting friends on that basis.