The nature of the data, or how to choose a correlation coefficient

Carroll, John B.

doi:10.1007/bf02289768

Cited by 319 publications

(169 citation statements)

References 22 publications

Supporting

Mentioning

165

Contrasting

Unclassified

Order By: Relevance

“…The score distributions of the RES, ASB and F/U scales are skewed, which can lead to an underestimation of the (true) correlation in the population (Carroll, 1961). Therefore, as a measure of control, all behavior variables were dichotomized, and polyserial correlations (Jiireskog & Sorbom, 1986) with the SCT were computed.…”

Section: Resultsmentioning

confidence: 99%

The star counting test: An attention test for children

Jong

Das-Smaal

1990

Personality and Individual Differences

View full text Add to dashboard Cite

Summary-The Star Counting Test (XT), an attention test for children, is presented. 'lhe test is suitable for groupwise administration. It was developed within a clear theoretical framework and focuses, in contrast to many current attention tests, on accuracy rather than speed. The test requires the control and alternation of two simple processes: forward and backward counting. In a prestudy, the reliability of the test appeared satisfactory. Substantial correlations were found with the Hyperactivity scale of the Conners Teacher Rating Scale and with grades for language and arithmetic. For the main study, a large scale assessment study of attentional deficits in Dutch elementary schools, three versions of the test were constructed. All versions of the test appeared reliable and substantial correlations were observed with the Attentional Behavior Scale of the Amsterdam Child Behavior Scale, a rating scale for teachers. Furthermore, the test was able to discriminate between various childhood disorders as rated by teachers. It was concluded that the SCT exhibits some essential characteristics that are needed for the measurement of individual differences in attention. The test can be used in large scale assessment studies and might be useful as a first screening device for attentional deficits.Attention is assumed to have a wide range of influence on many aspects of cognitive functioning. An efficient and successful course of the process of knowledge acquisition, for instance, is dependent on a proper functioning of attentional control processes like selectivity, flexibility, and planful behavior. Attention is a prerequisite for learning.In schools, children with attention deficits are of great concern. According to teachers in The Netherlands, an increasing number of children suffer from attentional problems (Das-Smaal, de Leeuw & Orlebeke, 1987), and large scale assessment studies in different countries indicate that the incidence of attentional problems among children aged 6-12 is considerable (Achenbach, Verhulst, Edelbrock, Baron & Akkerhuis, 1987;McGee, Williams & Silva, 1985; Taylor & Sandberg, 1944;Verhulst & Akkerhuis, 1986;Vikan, 1985). Cross-cultural and cross-temporal comparisons of prevalence rates are, however, problematic because most of these epidemiological studies have heavily relied on teacher ratings of behavior. Often the items in the rating scales that are used, are not tied to precise behaviors, but require a judgment about the appropriateness of a behavioral category, like for instance 'impulsiveness' (Taylor, 1987). Variations in teacher ratings might therefore reflect systematic differences in the behaviors that are considered relevant to a behavioral category. Another point of concern with respect to the comparison of teacher ratings are norm differences. Taylor (1987) suggests that the 20-fold difference in the prevalence rate of hyperactivity in the U.K. and U.S.A. might be the result of a discrepancy in the thresholds of tolerance towards the behaviors that form the problem. Because of ...

show abstract

Section: Resultsmentioning

confidence: 99%

The star counting test: An attention test for children

Jong

Das-Smaal

1990

Personality and Individual Differences

View full text Add to dashboard Cite

show abstract

“…We calculated the Spearman's rank correlation coefficients (17) between the aggressiveness features of the vehicle operation behaviors and the empirical aggressiveness scores. Features of aggressiveness for steering and acceleration behavior were calculated at time interval T , which was set to be from 5 to 55 seconds independently.…”

Section: Evaluation Of Features Used To Measure Aggressivenessmentioning

confidence: 99%

Evaluation Method for Aggressiveness of Driving Behavior Using Drive Recorders

Miyajima

Kitaoka

2015

IEEJ Journal IA

View full text Add to dashboard Cite

In this paper, we propose an automated method for measuring the aggressiveness of driving behavior by using driving signals from drive recorders. Currently, some risk consulting companies have experts review recorded driving behavior and then rate the drivers empirically. This approach is time-consuming and expensive, however, so an effective automated driver evaluation method is desired. We assumed that the aggressiveness of a driver's behavior can be determined by focusing on four types of vehicle operation behavior: steering, acceleration, deceleration, and alternation between acceleration and deceleration. Aggressiveness scores can be assigned to each of these behaviors, and a driver's overall aggressiveness score is then estimated by integrating these behaviors using multiple linear regression. We assessed the aggressiveness of 78 drivers and compared our assessments to the aggressiveness scores assigned empirically by the risk consulting experts. The proposed method achieved a rank correlation coefficient of 0.74 with the evaluations of the risk consulting experts.

show abstract

“…However, other problems can occur when tetrachorics are factor analyzed. Carroll (1945Carroll ( , 1961Carroll ( , 1983 has documented the problems involved in the factor analysis of tetrachoric correlation coefficients based on binary scored multiple-choice items where guessing is possible. In this context, failure to take guessing effects into account will again produce artifactual factors and misleading information as to the number of factors needed to account for the data.…”

Section: Item Score Modelmentioning

confidence: 99%