William P Dunlap
Biographic Data
| ID | 1659559 |
|---|---|
| NAME | William P Dunlap |
| GIVEN NAMES | William P |
| FAMILY NAME | Dunlap |
| SIGNATURE | DUNLAP W P |
| AFFILIATIONS | Tulane University |
| VERIFIED | No |
| TOTAL WORKS | 35 |
| TOTAL CITATIONS | 42 |
| AUTHOR COUNT | 35 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 1970 |
| LATEST PUBLICATION YEAR | 2003 |
| H-INDEX | 3 |
A Monte Carlo Evaluation of the Tetrachoric Correlation Coefficient
The tetrachoric correlation coefficient ( r tet), computed from a phi coefficient, approximates what the bivariate normal correlation would have been had the dichotomous variables been analyzed in their continuous form with underlying normal distributions. Although often used by early researchers to adjust phi when marginal distributions had extreme proportions, r tet, more commonly, has been regarded with suspicion. The purpose of these Monte Ca…
Some Thoughts Regarding the Sensitivity of t to Error in Estimated Within-Group Variance
A. J. Riopelle (2003) has eloquently demonstrated that the null hypothesis assessed by the t test involves not only mean differences but also error in the estimation of the within-group standard deviation, s. He is correct in his conclusion that the precision of the interpretation of a significant t and the null hypothesis tested is complex, particularly when sample sizes are small. In this article, the author expands on Riopelle's thoughts by co…
Estimating Interrater Agreement with the Average Deviation Index: A User’s Guide
The authors present guidelines for establishing a useful range for interrater agreement and a cutoff for acceptable interrater agreement when using Burke, Finkelstein, and Dusig’s average deviation (AD) index as well as critical values for tests of statistical significance with the AD index. Under the assumption that judges respond randomly to an item or set of items in a measure, the authors show that a criterion for acceptable interrater agreem…
Canonical Correlation and Chi-Square: Relationships and Interpretation
A 2 x 2 chi-square can be computed from a phi coefficient, which is the Pearson correlation between two binomial variables. Similarly, chi-square for larger contingency tables can be computed from canonical correlation coefficients. The authors address the following series of issues involving this relationship: (a) how to represent a contingency table in terms of a correlation matrix involving r - 1 row and c - 1 column dummy predictors; (b) how …
Averaging Correlations: Expected Values and Bias in Combined Pearson r s and Fisher's z Transformations
R. A. Fisher's z (z'; 1958) essentially normalizes the sampling distribution of Pearson r and can thus be used to obtain an average correlation that is less affected by sampling distribution skew, suggesting a less biased statistic. Analytical formulae, however, indicate less expected bias in average r than in average z' back-converted to average rz' . In large part because of this fact, J. E. Hunter and F. L. Schmidt (1990) have argued that aver…
Interpretations of Multiple Regression Borrowed From Factor Analysis and Canonical Correlation
Because multiple regression (MR) is a simplified case of canonical correlation, the authors present an alternative interpretation of MR in which loadings, in addition to weights, may be computed for predictors. The loadings, computed by both canonical correlation and factor analysis, represent the correlations of each predictor with the predicted criterion score. The authors concluded that in some situations, researchers should examine those valu…
The Accuracy of Different Methods for Estimating the Standard Error of Correlations Corrected for Range Restriction
A Monte Carlo study was conducted to compare the accuracy of different estimates of the standard error of correlations corrected for restriction in range. It was found that the procedure suggested by P. Bobko and A. Rieck, also derived by N. S. Raju and colleagues, generated the most accurate estimates of the standard error compared to other existing procedures. The study also repeated previous findings that Pearson correlations corrected for res…
The Spurious Correlation of Ratios that Have Common Variables: A Monte Carlo Examination of Pearson's Formula
Pearson (1897) investigated correlations of ratios of bone measurements and found that although the correlations among the original measures were low, the correlations among ratios with common measures were about .5. To understand this result, he developed an approximate equation for the correlations of ratios. In the present study, Monte Carlo methods were used to show that Pearson's equation is fairly accurate and that correlations among ratios…
Meta-analysis of experiments with matched groups or repeated measures designs.
Approximating Pearson Product-Moment Correlations from Kendall's Tau and Spearman's Rho
This article used Monte Carlo methods to investigate the accuracy of formulas presented by Kendall for estimating Pearson's r from X and by Pearson for estimating Pearson's r from rs. Results indicated that the formula for approximating r from r is somewhat more accurate than the formula for approximating r from rs. However, both formulas were found to be quite accurate. The largest asymptotic difference between a converted and actual r was -.005…
A Monte-Carlo Study of Type I Error Rates and Power for Tukey's Pocket Test
Tukey's pocket test (1959) is a two-group test of mean differences for which the calculations do not require a calculator or a book of tables. The critical values for the test were derived mathematically by Tukey, and the Type I errors and power of the test when n = 20 and n = 40 for normal and bimodal distributions were studied by Neave and Granger (1968). As an extension of the findings of Neave and Granger, a Monte-Carlo simulation to study Ty…
Effects of Relative Area on Matching Heterochromatic Stimuli for Saturation
Participants adjusted the saturation of one rectangular color stimulus so that it appeared to match the saturation of another rectangular color stimulus for stimulus pairs of different relative areas. In Experiment 1, in which stimuli of complementary colors were used, higher saturation stimuli were consistently chosen for large areas to match lower saturation stimuli in smaller areas. In Experiment 2, better saturation matches were obtained if p…
The Effect of Skew on the Magnitude of Product-Moment Correlations
The effect of transforming actual skewed variables toward symmetry on the intercorrelations among the transformed variables was examined. The results showed that average correlations increased in all 20 cases studied, even though the transformations to correct skew produced slightly greater nonlinear relationships in some cases. Because the F and t tests for the significance of r are directly proportional to the size of r, correcting skew increas…
Factor Analysis of Ipsative Measures
lpsative measures are multiple measures, where the data are collected, or are modified, in such a way that all subject totals across the measures are equal. Much has been written about factor analysis with such data, however, no clear consensus has been reached regarding the suitability of ipsative measures for factor analysis. The purpose of the present article is to show analytically the fundamental problems that ipsative measures impose for fa…
Generalizing the common language effect size indicator to bivariate normal correlations
Generalizing the common language effect size indicator to bivariate normal correlations
Sequential Anovas and Type I Error Rates
Monte Carlo simulations were used to examine three different cases of using analysis of variance sequentially. The first case dealt with adding additional data to original data that were not significant and then reanalyzing. Alpha levels reached a high of .086 in this case. In the second case, data were added only when the F-ratio was not significant but exceeded 1.00; in this case, the alpha level reached a high of .16. The third case added data…
Dealing with Nonnormal Data: Parametric Analysis of Transformed Data vs Nonparametric Analysis
Researchers have typically employed parametric analysis of raw data to test experimental data for statistical significance. When the data are not normally distributed, data transformation or nonparametric analysis are often recommended. The present study compares parametric analysis of raw data to parametric analysis of transformed data and to nonparametric analysis when the tests are carried out under population nonnormality. The results of a Mo…
Factor Analysis of the 1985 Revision of Kolb's Learning Style Inventory
Kolb's earlier (1976) Learning Style Inventory (LSI) has been criticized for its poor reliability and validity. Even after revisions (1985) were made and a new instrument was developed, the test-retest reliability remained low. Although construct validity of the original instrument has been often investigated, little work has been done on the revised version. In this study, the responses of 317 subjects who completed the LSI-1985 were factor anal…
Differences in Color Balance Depending upon Mode of Comparison
Previous research on color balance has shown that small areas of high-chroma (saturation) colors appear balanced when paired with larger areas of low-chroma colors, a finding that is consistent with Munsell's (1905) ideas on color harmony. In these previous experiments, subjects were asked to adjust the relative areas of color pairs that had fixed chromas until the stimuli appeared balanced. In the present study, subjects were additionally asked …
A Fortran IV Program for Testing the Significance of Correlation Matrices
A FORTRAN IV program is presented which computes the Brien, Venables, James, and Mayo (1984) procedure for testing the hypothesis that the observed correlation matrix significantly differs from the identity matrix
A Monte Carlo Study of Testing the Significance of Correlation Matrices
A Monte Carlo simulation was conducted to examine the Type I error rates and power of the tests by Bartlett; Brien, Venables, James, and Mayo; Kullback; and Steiger of the null hypothesis that a correlation matrix equals the identity matrix. Such tests are often recommended as preliminary procedures before performing factor analysis or evaluating the hypothesis of equal correlations. The Brien et al. procedure was found to be the most powerful te…
Baddeley's Grammatical Reasoning Test: Active versus passive processing differences re-examined
In Baddeley's grammatical reasoning test it is assumed that passive voice takes longer to process than active and that negative sentences take longer than posi tive ; however, such differences are confounded with sentence length. The present study equated sentence length to examine these issues. A factorial design was used with: (1) two methods of presentation (computer vs. paper and pencil); (2) using the words 'leads' vs. 'precedes'; (3) variab…
Reaction Time Measures of Backward Masking
We employed both simple and choice reaction time (RT) paradigms in which the subjects were required to respond to 3.0 cycles per degree (c/d) square-wave gratings presented to one eye, while checkerboard masks were presented at various stimulus-onset asynchronies to the other eye. No masking was evident using the simple RT paradigm, but with the choice RT task, checkerboard masks presented to the contralateral eye of three subjects resulted in su…
Averaging correlation coefficients: Should Fisher's z transformation be used?
Failure to detect moderating effects: Is multicollinearity the problem
Averaging Correlations: Expected Values and Bias in Combined Pearson r s and Fisher's z Transformations
R. A. Fisher's z (z'; 1958) essentially normalizes the sampling distribution of Pearson r and can thus be used to obtain an average correlation that is less affected by sampling distribution skew, suggesting a less biased statistic. Analytical formulae, however, indicate less expected bias in average r than in average z' back-converted to average rz' . In large part because of this fact, J. E. Hunter and F. L. Schmidt (1990) have argued that aver…
The Effect of Skew on the Magnitude of Product-Moment Correlations
The effect of transforming actual skewed variables toward symmetry on the intercorrelations among the transformed variables was examined. The results showed that average correlations increased in all 20 cases studied, even though the transformations to correct skew produced slightly greater nonlinear relationships in some cases. Because the F and t tests for the significance of r are directly proportional to the size of r, correcting skew increas…
Interpretations of Multiple Regression Borrowed From Factor Analysis and Canonical Correlation
Because multiple regression (MR) is a simplified case of canonical correlation, the authors present an alternative interpretation of MR in which loadings, in addition to weights, may be computed for predictors. The loadings, computed by both canonical correlation and factor analysis, represent the correlations of each predictor with the predicted criterion score. The authors concluded that in some situations, researchers should examine those valu…
Generalizing the common language effect size indicator to bivariate normal correlations
Canonical Correlation and Chi-Square: Relationships and Interpretation
A 2 x 2 chi-square can be computed from a phi coefficient, which is the Pearson correlation between two binomial variables. Similarly, chi-square for larger contingency tables can be computed from canonical correlation coefficients. The authors address the following series of issues involving this relationship: (a) how to represent a contingency table in terms of a correlation matrix involving r - 1 row and c - 1 column dummy predictors; (b) how …
The Spurious Correlation of Ratios that Have Common Variables: A Monte Carlo Examination of Pearson's Formula
Pearson (1897) investigated correlations of ratios of bone measurements and found that although the correlations among the original measures were low, the correlations among ratios with common measures were about .5. To understand this result, he developed an approximate equation for the correlations of ratios. In the present study, Monte Carlo methods were used to show that Pearson's equation is fairly accurate and that correlations among ratios…
Differences in Color Balance Depending upon Mode of Comparison
Previous research on color balance has shown that small areas of high-chroma (saturation) colors appear balanced when paired with larger areas of low-chroma colors, a finding that is consistent with Munsell's (1905) ideas on color harmony. In these previous experiments, subjects were asked to adjust the relative areas of color pairs that had fixed chromas until the stimuli appeared balanced. In the present study, subjects were additionally asked …
Influence of Value on Spatial Balance of Color Pairs
The spatial balance of the component colors is an important element of color harmony in a design. Munsell (1905) suggested that the area of each color in a composition be inversely proportional to the product of the color's chroma and value. Moon and Spencer (1944) proposed that both chroma and value contribute to spatial balance, but the dominant factor is the contrast of a color with the background or with the adaptation point of the eye. The p…
Effects of Drive and Partial Reinforcement on Extinction Both between and within Daily Sessions
40 albino rats were assigned randomly to the cells of a 2 × 2 factorial design consisting of per cent reinforcement (50% and 100%) by deprivation (high and low). Speed measures were obtained from two segments of a straight-alley runway for 80 acquisition and 56 extinction trials with 4 trials given per day. Deprivation effects were found over the closely spaced trials within daily sessions for both acquisition and extinction. In extinction the in…
Frustration Effect and Extent of Instrumental Response
Goal-box activity of Ss run in a single alley was compared to activity of Ss placed directly into the goal box. Following nonreward significant increases in activity above rewarded activity levels were found for both Run and Placed groups. When these effects were compared to goal-box activity levels of never-rewarded control groups, however, only the activity increments in the Run group could be attributed to frustration produced by nonreward. Th…
Reversal of Partial Reinforcement Effects in Acquisition Goal Speed: An Artifact That Continues to Stimulate Theory
Power of the F test with skewed data: Should one transform or not
Power of the F test with skewed data: Should one transform or not
Data transformation, power, and skew: A rejoinder to Games
Data transformation, power, and skew: A rejoinder to Games
Averaging correlation coefficients: Should Fisher's z transformation be used?
A Monte Carlo Study of Using the First Eigenvalue for Averaging Intercorrelations
A procedure proposed by Kaiser (1968) for averaging correlation coefficients using the first eigenvalue of an intercorrelation matrix was studied via Monte Carlo methods. The Kaiser average if applied to sample intercorrelations was found to be markedly biased toward overestimation of the population correlation when the population correlation was small, and to show a slight negative bias similar to average r when the population correlation was la…
Influence of Value on Spatial Balance of Color Pairs
The spatial balance of the component colors is an important element of color harmony in a design. Munsell (1905) suggested that the area of each color in a composition be inversely proportional to the product of the color's chroma and value. Moon and Spencer (1944) proposed that both chroma and value contribute to spatial balance, but the dominant factor is the contrast of a color with the background or with the adaptation point of the eye. The p…
Failure to detect moderating effects: Is multicollinearity the problem
Reaction Time Measures of Backward Masking
We employed both simple and choice reaction time (RT) paradigms in which the subjects were required to respond to 3.0 cycles per degree (c/d) square-wave gratings presented to one eye, while checkerboard masks were presented at various stimulus-onset asynchronies to the other eye. No masking was evident using the simple RT paradigm, but with the choice RT task, checkerboard masks presented to the contralateral eye of three subjects resulted in su…
A Monte Carlo Study of Testing the Significance of Correlation Matrices
A Monte Carlo simulation was conducted to examine the Type I error rates and power of the tests by Bartlett; Brien, Venables, James, and Mayo; Kullback; and Steiger of the null hypothesis that a correlation matrix equals the identity matrix. Such tests are often recommended as preliminary procedures before performing factor analysis or evaluating the hypothesis of equal correlations. The Brien et al. procedure was found to be the most powerful te…
Baddeley's Grammatical Reasoning Test: Active versus passive processing differences re-examined
In Baddeley's grammatical reasoning test it is assumed that passive voice takes longer to process than active and that negative sentences take longer than posi tive ; however, such differences are confounded with sentence length. The present study equated sentence length to examine these issues. A factorial design was used with: (1) two methods of presentation (computer vs. paper and pencil); (2) using the words 'leads' vs. 'precedes'; (3) variab…
A Fortran IV Program for Testing the Significance of Correlation Matrices
A FORTRAN IV program is presented which computes the Brien, Venables, James, and Mayo (1984) procedure for testing the hypothesis that the observed correlation matrix significantly differs from the identity matrix
Dealing with Nonnormal Data: Parametric Analysis of Transformed Data vs Nonparametric Analysis
Researchers have typically employed parametric analysis of raw data to test experimental data for statistical significance. When the data are not normally distributed, data transformation or nonparametric analysis are often recommended. The present study compares parametric analysis of raw data to parametric analysis of transformed data and to nonparametric analysis when the tests are carried out under population nonnormality. The results of a Mo…
Factor Analysis of the 1985 Revision of Kolb's Learning Style Inventory
Kolb's earlier (1976) Learning Style Inventory (LSI) has been criticized for its poor reliability and validity. Even after revisions (1985) were made and a new instrument was developed, the test-retest reliability remained low. Although construct validity of the original instrument has been often investigated, little work has been done on the revised version. In this study, the responses of 317 subjects who completed the LSI-1985 were factor anal…
Differences in Color Balance Depending upon Mode of Comparison
Previous research on color balance has shown that small areas of high-chroma (saturation) colors appear balanced when paired with larger areas of low-chroma colors, a finding that is consistent with Munsell's (1905) ideas on color harmony. In these previous experiments, subjects were asked to adjust the relative areas of color pairs that had fixed chromas until the stimuli appeared balanced. In the present study, subjects were additionally asked …
Sequential Anovas and Type I Error Rates
Monte Carlo simulations were used to examine three different cases of using analysis of variance sequentially. The first case dealt with adding additional data to original data that were not significant and then reanalyzing. Alpha levels reached a high of .086 in this case. In the second case, data were added only when the F-ratio was not significant but exceeded 1.00; in this case, the alpha level reached a high of .16. The third case added data…
Factor Analysis of Ipsative Measures
lpsative measures are multiple measures, where the data are collected, or are modified, in such a way that all subject totals across the measures are equal. Much has been written about factor analysis with such data, however, no clear consensus has been reached regarding the suitability of ipsative measures for factor analysis. The purpose of the present article is to show analytically the fundamental problems that ipsative measures impose for fa…
Generalizing the common language effect size indicator to bivariate normal correlations
Generalizing the common language effect size indicator to bivariate normal correlations
Effects of Relative Area on Matching Heterochromatic Stimuli for Saturation
Participants adjusted the saturation of one rectangular color stimulus so that it appeared to match the saturation of another rectangular color stimulus for stimulus pairs of different relative areas. In Experiment 1, in which stimuli of complementary colors were used, higher saturation stimuli were consistently chosen for large areas to match lower saturation stimuli in smaller areas. In Experiment 2, better saturation matches were obtained if p…
The Effect of Skew on the Magnitude of Product-Moment Correlations
The effect of transforming actual skewed variables toward symmetry on the intercorrelations among the transformed variables was examined. The results showed that average correlations increased in all 20 cases studied, even though the transformations to correct skew produced slightly greater nonlinear relationships in some cases. Because the F and t tests for the significance of r are directly proportional to the size of r, correcting skew increas…
Meta-analysis of experiments with matched groups or repeated measures designs.
Mathematics (29 works) · Statistics (27 works) · Psychology (19 works) · Computer Science (15 works) · Econometrics (15 works) · Correlation (12 works) · Physics (12 works) · Advanced Statistical Methods and Models (10 works) · Monte Carlo method (8 works) · Geometry (7 works)