An analysis of learning data which distinguishes between initial preference and learning ability

Several sets of learning data furnished by I. Krechevsky have been analyzed in terms of meaningful parameters of the learning curve, and the changes in the frequency distributions of these parameters with changes in the experimental conditions have been studied. One of the parameters represents the animal's initial preference for the light or dark, the other represents learning ability. The analysis shows that destruction of about ten or fifteen per cent. of the cortex, increases the animal's preference for the light and decreases the learning ability slightly. By ordinary methods of analysis, it is not possible to discover thatboth initial preference and learning ability have been changed by any given factor.The author wishes to acknowledge financial assistance from the Social Science Research Committee of the University of Chicago in the completion of this study.     

Influence analysis for the factor analysis model with ranking data

Influence analysis is an important component of data analysis, and the local influence approach has been widely applied to many statistical models to identify influential observations and assess minor model perturbations since the pioneering work of Cook (1986) . The approach is often adopted to develop influence analysis procedures for factor analysis models with ranking data. However, as this well‐known approach is based on the observed data likelihood, which involves multidimensional integrals, directly applying it to develop influence analysis procedures for the factor analysis models with ranking data is difficult. To address this difficulty, a Monte Carlo expectation and maximization algorithm (MCEM) is used to obtain the maximum‐likelihood estimate of the model parameters, and measures for influence analysis on the basis of the conditional expectation of the complete data log likelihood at the E‐step of the MCEM algorithm are then obtained. Very little additional computation is needed to compute the influence measures, because it is possible to make use of the by‐products of the estimation procedure. Influence measures that are based on several typical perturbation schemes are discussed in detail, and the proposed method is illustrated with two real examples and an artificial example.     

Logistic growth curve analysis in associative learning data

We propose an alternative statistical method, logistic growth curve analysis, for the analysis of associative learning data with two or more comparison groups. Logistic growth curve analysis is more sensitive and easier to interpret than previously published methods such as χ² or ANOVA, which require the data to be collapsed into individual total scores or proportion of responses over time. Additionally, this type of analysis better fits the typical graphical representation of associative learning data. An analysis is presented where associative learning data from honeybees are analyzed using the three techniques, and the accessibility and power of the logistic growth curve analysis is highlighted. Accepted after revision: 14 November 2000 Electronic Publication     

The dread factor: how hazards and safety training influence learning and performance

On the basis of hypotheses derived from social and experiential learning theories, we meta-analytically investigated how safety training and workplace hazards impact the development of safety knowledge and safety performance. The results were consistent with an expected interaction between the level of engagement of safety training and hazardous event/exposure severity in the promotion of safety knowledge and performance. For safety knowledge and safety performance, highly engaging training was considerably more effective than less engaging training when hazardous event/exposure severity was high, whereas highly and less engaging training had comparable levels of effectiveness when hazardous event/exposure severity was low. Implications of these findings for theory testing and incorporating information on objective risk into workplace safety research and practice are discussed.     

Convergent and discriminant relationships between factor matrices of motor performance and arousal data.

An experimental study was conducted to demonstrate the value of a procedure for analyzing motor performance data. A sample of 156 subjects practiced on two instruments for motor learning while arousal data were recorded. Each set of data was submitted to an analysis of principal components and four components resulted for each set of data. Similarity coefficients were calculated for pairs of component matrices after rotation to maximum similarity. The similarity coefficients exhibit a consistent pattern which provides meaningful information concerning influence of experimental conditions on performance data.     

Separation of data as a principle in factor analysis

Two systems of factor analysis—factoring correlations with units in the diagonal cells and factoring correlations with communalities in the diagonal cells—are considered in relation to the commonly used statistical procedure of separating a set of data (scores) into two or more parts. It is shown that both systems of factor analysis imply the separation of the observed data into two orthogonal parts. The matrices used to achieve the separation differ for the two systems of factor analysis.     

Measuring intention in language learning: a confirmatory factor analysis

Intention in language learning has not been studied effectively in research on second language (L2) learning. The goal is to fill this gap by designing and testing a measure of L2 learning intention. The scale was differentiated into two distinct but correlated components, goal intention and implementation intention, within the L2 context. The two intention scales were examined for reliability and validity using a series of standard psychometric procedures. A confirmatory factor model was then constructed and tested with a sample of 333 senior high school and college students. The results showed that a modified model had good psychometric characteristics and reasonable fit to the data.     

A factor analysis of intra-task performance on two psychomotor tests

There are indications that even during the short time of administration of a single psychomotor test, the ability or abilities sampled may shift materially in importance. It then becomes important to know the stages in which these fluctuations occur, the stage at which the test is most complex, and the stage at which the test most nearly measures one ability at a time. This paper describes an application of factorial methods to this problem. Factor analysis of inter-trial correlations on two models of the Rudder Control Test revealed three factors, Steadiness-Control, Precision of Movement, and Strength. The same factor pattern was confirmed in a separate factor analysis on another sample in which the order of administration of the tests was reversed. Implications are pointed out for future psychomotor test development.Perceptual and Motor Skills Research Laboratory, Lackland Air Force Base, San Antonio, Texas. The opinions or conclusions contained in this report are those of the author. They are not to be construed as reflecting the views or indorsement of the Department of the Air Force.     

Incentive learning and the motivational control of instrumental performance

Hungry rats were trained to press a lever and pull a chain concurrently, with one action being reinforced with a sucrose solution and the other with food pellets. In addition, in the first two experiments all animals experienced non-contingent presentations of the two incentives in the absence of the operant manipulanda while either thirsty or hungry and either before (Experiment 1A) or after (Experiment 1B) the instrumental training. When lever pressing was assessed subsequently in extinction under thirst, the animals pressed at a relatively high rate only if (1) this action had been reinforced with the sucrose solution rather than the food pellets during training and (2) they had received the non-contingent presentations of the sucrose solution and food pellets on days on which they were thirsty rather than hungry. A third experiment demonstrated that non-contingent exposure to the sucrose solution alone, but not to water under thirst was sufficient to bring about this type of motivational control of instrumental performance.     

AGSuite: Software to conduct feature analysis of artificial grammar learning performance

To simplify the problem of studying how people learn natural language, researchers use the artificial grammar learning (AGL) task. In this task, participants study letter strings constructed according to the rules of an artificial grammar and subsequently attempt to discriminate grammatical from ungrammatical test strings. Although the data from these experiments are usually analyzed by comparing the mean discrimination performance between experimental conditions, this practice discards information about the individual items and participants that could otherwise help uncover the particular features of strings associated with grammaticality judgments. However, feature analysis is tedious to compute, often complicated, and ill-defined in the literature. Moreover, the data violate the assumption of independence underlying standard linear regression models, leading to Type I error inflation. To solve these problems, we present AGSuite, a free Shiny application for researchers studying AGL. The suite’s intuitive Web-based user interface allows researchers to generate strings from a database of published grammars, compute feature measures (e.g., Levenshtein distance) for each letter string, and conduct a feature analysis on the strings using linear mixed effects (LME) analyses. The LME analysis solves the inflation of Type I errors that afflicts more common methods of repeated measures regression analysis. Finally, the software can generate a number of graphical representations of the data to support an accurate interpretation of results. We hope the ease and availability of these tools will encourage researchers to take full advantage of item-level variance in their datasets in the study of AGL. We moreover discuss the broader applicability of the tools for researchers looking to conduct feature analysis in any field.