摘要:

It is shown that results of categorical judgement experiments cannot simultaneously conform to a single process signal detectability model and to the recently proposed two process attention band model. Since there is substantial evidence for the Thurstone case V version of the signal detectability model for categorical judgement of prothetic continua, it is argued that the attention band model cannot apply to such judgements. Methods are presented for calculating all the parameters of the attention band model from a single categorical judgement task where the physical stimuli are widely separated.

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1980.tb00773.x

出版商:Blackwell Publishing Ltd    

年代:1980

数据来源: WILEY

摘要:

The comparative testing of models of cognitive judgements has previously been done bypost hocparameter estimation on data gathered without feedback. If on any trial within an experiment responses are tested against competing models, and feedback is provided to the subject on his partial consistency with a currently best‐fitting model, then under some conditions behavioural and parameter convergence may be stochastically achieved. An algorithm SIMFBS with parameter convergence potential is described and its performance examined on up to five models of similarity, with various forms of memory built into the algorith

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1980.tb00774.x

出版商:Blackwell Publishing Ltd    

年代:1980

数据来源: WILEY

摘要:

Threshold models assumeJdiscrete sensory states, which are related to responses by a probabilistic response rule. The paper discusses how we can refute threshold models withJsmall without imposinga prioriconstraints on the response rule. An argument due to Krantz is extended and applied to a sinusoid‐in‐noise detection task with randomly varying signal strengths. When five subjects are tested in this task, it is shown thatJneeds to be at least 3 for four subjects and at least 4 for

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1980.tb00775.x

出版商:Blackwell Publishing Ltd    

年代:1980

数据来源: WILEY

摘要:

Simple plurality voting allows the surprising possibility that a majority of a committee or an electorate may prefer one of the defeated alternatives to the plurality winner. Relatively little attention has been devoted to this paradox (which is distinct from Condorcet's ‘paradox of voting’) since the 18th century. With seven‐person committees choosing among three alternatives, the theoretical probability of its occurrence is shown to be 0.126 in a completely uniform culture in which all preference rankings are equally likely. The observed relative frequency was, however, found to be 0.020 when 70 university students who were randomly assigned to 10 seven‐person groups ranked 20 triplets of randomly chosen girls' names, and this was significantly lower (P<0.001) than the theoretical probability in a completely uniform

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1980.tb00776.x

出版商:Blackwell Publishing Ltd    

年代:1980

数据来源: WILEY

摘要:

Five simple models of the implicit social process whereby a group combines individual preferences into a collective decision are investigated: plurality, majority, proportionality, equiprobability and highest expected value. For each model, an expression is developed which provides the probability that a group selects a given alternative, as a function of (i) group size, (ii) number of alternatives and (iii) the set of probabilities governing the likelihood with which a group member advocates each alternative. Predictions yielded by the probability expressions are used as the basis for a comparison of the models.

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1980.tb00777.x

出版商:Blackwell Publishing Ltd    

年代:1980

数据来源: WILEY

摘要:

Expressions are developed for the probability that a group chooses a particular course of action in each of four complex social decision scheme models: majority with proportionality, majority with equiprobability, plurality with proportionality and plurality with equiprobability. A method of discriminating by experiment among a number of social decision scheme models is suggested involving, where feasible, experimenter manipulation of individual member preference probabilities.

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1980.tb00778.x

出版商:Blackwell Publishing Ltd    

年代:1980

数据来源: WILEY

摘要:

Many ‘distribution‐free’ statistical tests using very different computational procedures can be viewed as special cases of two general tests based on the principle of analysis of variance by ranks. The first test, due to Bernard&Van Elteren (1953), is a general test for any differences among the samples. The second test evaluates trends and contrasts between the samples. The two general procedures embrace popular tests by Friedman, Kruskal, Cochran, Spearman, Wilcoxon, Mann&Whitney, Dixon&Mood, Page and Marascuilo&McSweeney as well as chi‐square tests for contingency tables whose dependent variable is in the form of dichotomous or rankable categories. The system can be used to generate convenient computational formulac for a range of new designs, to express popular procedures in a unified notation, as a teaching aid to illustrate the relationships among tests and as the basis for a simple computer program to analyse data from any design within the

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1980.tb00779.x

出版商:Blackwell Publishing Ltd    

年代:1980

数据来源: WILEY

摘要:

The set of all formally equivalent Bradley–Terry–Luce models for pair comparison and uniqueness of their corresponding scales are characteri

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1980.tb00780.x

出版商:Blackwell Publishing Ltd    

年代:1980

数据来源: WILEY

摘要:

An item‐sampling model that takes the effect of guessing into account was used to calculate the number of items and the cutting score a test should have to make a decision of mastery or non‐mastery with prescribed precision. The results show that the required number of items is markedly larger than suggested by similar approaches not using the number of alternatives of the items as a parameter. It is concluded that multiple choice tests of usual length are highly fallible decision a

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1980.tb00781.x

出版商:Blackwell Publishing Ltd    

年代:1980

数据来源: WILEY

摘要:

A simple technique is proposed for the description and analysis of the patterns of error customarily found in tasks requiring subjects to interpolate between explicit or implicit reference values. The error patterns can be characterized by two parameters. One parameter reflects any consistent tendency to make positive or negative errors overall while the other reflects the difference in error between the two halves of the interpolation interval. The style of analysis advocated is quantitatively descriptive of the error patterns and leads to a simplification of subsequent statistical analysis of the results.

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1980.tb00782.x

出版商:Blackwell Publishing Ltd    

年代:1980

数据来源: WILEY