ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1984.tb00796.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

The information transmitted in absolute identification quickly reaches its upper limit as the number of (one‐dimensional) signals, and their range, is increased. Several explanations have been given of this phenomenon, but all aread hocin one way or another. Here we present a ‘memory’ or ‘rehearsal’ interpretation. The basic (psychological) representation of each signal in an absolute identification experiment is assumed to be quite accurate, and independent of the other stimuli used in the experiment. However, the identification of the stimulus presented on a particular trial is relative to a ‘frame’ (usually the range of stimuli in that experiment) that the subject must ‘rehearse’ using a fixed capacity rehearsal system. In special cases, this model reduces to earlier suggestions, but its general motivation seems somewhat lessad hocthan that of earlier ideas, and it is also easily applied to the absolute identification of multivariate signals and to mag

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1984.tb00797.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

Suppose that, with rather few exceptions, the assignment of a number to a stimulus on one trial of a magnitude estimation or category judgement experiment serves as the point of reference for choosing an appropriate assignment on the next trial. This principle of relative judgement—relative to theimmediatecontext—is developed to generate models for both magnitude estimation and category judgement experiments. It is applied, in particular, to the explanation of three, hitherto unrelated, phenomena: these are (a) the limited transmission of information in category judgements; (b) sequential constraints on the resolving power of category judgements; and (c) the autocorrelation of successive numerical magnitude estimates. Finally, some comparison is made between the principle of relative judgement introduced here and other contemporary ideas which have been addressed to one or more of these three critical phenom

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1984.tb00798.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

The essential features that any satisfactory model of categorical judgement must account for are discussed. The implications of the strong evidence for the Thurstone case V model are drawn out. Then evidence for a linear learning model of criterion setting is presented including new data for isobias functions with either response speed deadlines or physical stimulus difference manipulated. A method for extending linear learning models to encompass joint setting of several criteria is suggested. It is shown that an arcsinh transformation of the Thurstone scale produces a scale which is a linear function of stimulus intensity in decibels. The scale parameter of this transformation remains constant for stimulus ranges greater than 18 dB while changing systematically when sequential presentation is manipulated to improve discrimination.

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1984.tb00799.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

Signal detection theory (SDT) requires that the slope of the receiver operating characteristic (ROC) is independent of the probability of signal and noise. But it has been shown that when the rating procedure is applied to detection, the slope of the receiver operating characteristic may increase as a function of the probability of the signal (Schulman&Greenberg, 1970). This presents a serious problem for signal detection theory. This problem is examined in relation to a recent theory of criterion setting (Treisman&Williams, 1984), and an explanation for the effect of signal probability on ROC slope is derived which is compatible with SDT. Further data on the relation between signal probability and ROC slope are reported.

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1984.tb00800.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

Examination assessment can be likened to multi‐attribute models in value theory by treating candidates as alternatives that have to be compared and examination components as the different attributes on which they are assessed. Then the mark combination process is equivalent to a value function, the main difference being that in this context the examiners' judgement is modelled rather than their preferences.This paper consists of five parts. In the first, a formal representation of the problem is given. In the next three sections, three additive representations are studied, each involving a different set of properties for the marks and the combination process. Finally, there is a short discussion and comparison of the three representation

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1984.tb00801.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

A number of models for the analysis of moment structures, such as LISREL, have recently been shown to be capable of being given a particularly simple and economical representation, in terms of the Reticular Action Model (RAM). In contrast to previous treatments, a formal algebraic treatment is provided which shows that RAM directly incorporates many common structural models, including models describing the structure of means. It is also shown here that RAM treats coefficient matrices with patterned inverses simply and generally.

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1984.tb00802.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

Sampling variability of the estimates of factor loadings is neglected in modern factor analysis. Such investigations are generally normal theory based and asymptotic in nature. The bootstrap, a computer‐based methodology, is described and then applied to demonstrate how the sampling variability of the estimates of factor loadings can be estimated for a given set of data. The issue of the number of factors to be retained in a factor model is also addressed. The bootstrap is shown to be an effective data‐analytic tool for computing various statistics of interest which are otherwise intracta

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1984.tb00803.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

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.

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1984.tb00804.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY

摘要:

To test the agreement between two observers who categorize a number of objects when the categories have not been specified in advance, Brennan&Light (1974) developed a statisticA′ and suggested a normal approximation for its distribution. In this paper it is shown that this approximation is inadequate particularly when one, or both, of the observers place a fairly equal number of objects in all of their categories. A chi‐squared approximation to the distribution ofA′ is developed and is shown to work well in a variety of situations.The relative powers ofA′ and the ordinaryX2test for association are dependent on the type of ‘agreement between the observers’ that is assumed. However a simulation for a fairly general type of agreement indicates that theX2test is more powerful. As theX2test is also much easier to apply, it would seem preferable in most

ISSN:0007-1102    

DOI:10.1111/j.2044-8317.1984.tb00805.x

出版商:Blackwell Publishing Ltd    

年代:1984

数据来源: WILEY