Paul R. Yarnold Optimal Data Analysis, LLC A method for computing the distance between an empirically-derived statistical classification model and a corresponding theoretically ideal classification model is described. Use of the distance index to identify and to compare globally optimal classification models, within and between descendent families, is illustrated with an example using ethnicity to … Continue reading Distance from a Theoretically Ideal Statistical Classification Model Defined as the Number of Additional Equivalent Effects Needed to Obtain Perfect Classification for the Sample

Paul R. Yarnold Optimal Data Analysis, LLC Research comparing the use of optimal versus legacy methods for analysis of data representing different experimental designs is on-going. This note discusses bivariate legacy statistical tools for which the alternative use of UniODA has already been demonstrated as an always valid, exact, maximum-accuracy statistical methodology. View journal article

Paul R. Yarnold Optimal Data Analysis, LLC An alphabetical roster of 211 articles using ODA statistical software and published in peer-reviewed journals in 2014 or earlier is presented. View journal article

Paul R. Yarnold & Fred B. Bryant Optimal Data Analysis, LLC The use of automated CTA software to obtain an enumerated optimal (maximum-accuracy) classification tree analysis (EO-CTA) model is demonstrated and the resulting model is compared with a HO-CTA model developed using the same data. View journal article

Paul R. Yarnold & Fred B. Bryant Optimal Data Analysis, LLC The use of UniODA software to obtain a hierarchically optimal (maximum-accuracy) classification tree analysis (HO-CTA) model is demonstrated. View journal article

Paul R. Yarnold Optimal Data Analysis, LLC Partial UniODA is a two-step procedure for: (a) identifying the exact statistical model that explicitly maximizes accuracy (normed against chance) achieved for the sample by using an attribute to classify observations’ actual class categories; while (b) simultaneously “controlling for” (eliminating) the effect of a confounding variable. Step One … Continue reading Evaluating Non-Confounded Association of an Attribute and a Class Variable Using Partial UniODA

Paul R. Yarnold Optimal Data Analysis, LLC Bowker’s test for symmetry is a generalization of McNemar's test for correlated proportions that is used for tables having more than two categories. The present study contrasts results achieved using Bowker’s test versus an iterative UniODA-based procedure. View journal article

Paul R. Yarnold Optimal Data Analysis, LLC McNemar's test is used to assess the significance of the difference between two correlated proportions. This methodology is compared with UniODA using an example involving a small sample. View journal article

Paul R. Yarnold Optimal Data Analysis, LLC McNemar's test is used to assess the significance of the difference between two correlated proportions: for example when the two proportions are based on the same sample of subjects or on matched-pair samples. This methodology is compared with UniODA using two examples in disease diagnosis before vs. after … Continue reading UniODA vs. McNemar’s Test for Correlated Proportions: Diagnosis of Disease Before vs. After Treatment

Paul R. Yarnold Optimal Data Analysis, LLC The inter-rater reliability of patient triage ratings made using the Emergency Severity Index is computed and compared for pooled data within and across studies versus separately for pairs of independent raters. Findings reveal that results for the pooled findings exhibit confounding attributable to Simpson’s Paradox. These findings raise … Continue reading Estimating Inter-Rater Reliability Using Pooled Data Induces Paradoxical Confounding: An Example Involving Emergency Severity Index Triage Ratings

Paul R. Yarnold Optimal Data Analysis, LLC An inherent limitation of ordinary least-squares regression models is that dependent measure values near the mean for the sample are predicted well, while values greater or less than the mean are predicted poorly. A UniODA-based methodology for circumventing this limitation and explicitly maximizing classification accuracy (ESS) has been … Continue reading Maximizing ESS of Regression Models in Applications with Dependent Measures with Domains Exceeding Ten Values

Paul R. Yarnold Optimal Data Analysis, LLC Two methods for specifying the minimum endpoint sample size for optimal (maximum-accuracy) classification tree analysis (CTA) models are noted. View journal article

Paul R. Yarnold & Fred B. Bryant Optimal Data Analysis, LLC This note contrasts the importance of the analysis of model residual values in assessing the invalidity of estimated Type I error rates for parametric methods, versus in determining ways of improving the validity of maximum-accuracy methods. View journal article

Paul R. Yarnold Optimal Data Analysis, LLC Compared to the Mann-Whitney U test, UniODA explicitly maximizes model accuracy for a specific sample and hypothesis; identifies the optimal threshold discriminating the groups; yields invariant findings over monotonic transformations of the data; indexes model effect strength on an absolute scale ranging from 0 (accuracy expected for the … Continue reading UniODA vs. Mann-Whitney U Test: Comparative Effectiveness of Laxatives

Paul R. Yarnold Optimal Data Analysis, LLC The Mann-Whitney U test is a nonparametric statistical test used to compare samples of scores obtained on an ordered variable between two independent groups. In contrast to U the use of UniODA in this application explicitly maximizes model accuracy for each specific sample and hypothesis; explicitly identifies the … Continue reading UniODA vs. Mann-Whitney U Test: Sunlight and Petal Width

It's a wrap! A link to the complete Volume 3 of Optimal Data Analysis is now available. View journal article

Paul R. Yarnold Optimal Data Analysis, LLC Kendall's coefficient of concordance W is a non-parametric statistic used to assess agreement in rankings of multiple stimuli made by multiple raters. A normalization of the test statistic for Friedman’s non-parametric alternative to ANOVA with repeated measures, W ranges from 0 (no agreement) to 1 (complete agreement). Problems … Continue reading UniODA vs. Kendall’s Coefficient of Concordance (W): Multiple Rankings of Multiple Movies

Paul R. Yarnold Optimal Data Analysis, LLC Receiver operator characteristic (ROC) analysis is sometimes used to assess the classification accuracy achieved using an ordered attribute to discriminate a dichotomous class variable, and in this context to identify an “optimal” discriminant cutpoint. In ROC analysis the optimal cutpoint corresponds to the threshold value at which distance … Continue reading UniODA vs. ROC Analysis: Computing the “Optimal” Cut-Point

Paul R. Yarnold Optimal Data Analysis, LLC The Bray-Curtis dissimilarity index is widely-used as an index of the magnitude of compositional dissimilarity in the count of different categories between two samples, yet it fails to address the statistical reliability of the dissimilarity, the precise nature of the dissimilarity, and the potential cross-generalizability of the findings. … Continue reading UniODA vs. Bray-Curtis Dissimilarity Index for Count Data

Paul R. Yarnold Optimal Data Analysis, LLC This study assesses agreement between number of lambs born to 227 ewes over two consecutive years. Polychoric correlation could not be validly used to assess agreement because underlying distributional assumptions were violated. Requiring no distributional assumptions, UniODA identified moderate, statistically significant agreement. View journal article