Richard Cutler - Academia.edu (original) (raw)

Papers by Richard Cutler

Breeding Science, 2009

Our goal was to determine whether the genomic groups of perennial species Triticeae having solita... more Our goal was to determine whether the genomic groups of perennial species Triticeae having solitary spikelets could be identified morphologically and, if so, to construct identification keys that could be used for this purpose. If so, it would strengthen the argument for recognizing such groups as genera. We conducted Discriminant and Random Forest ® analyses of 61 characters scored on 218 herbarium specimens representing 13 genomic groups. In addition, we closely examined some additional characters that came to our attention, evaluating our findings on specimens not scored for the two kinds of analysis. Random Forest ® analysis was almost always more successful in distinguishing the genomic groups, whether separating all 13 groups or a subset of the 13. The results suggest that it is usually possible to identify the genomic group to which a specimen of perennial Triticeae with solitary spikelets belongs on the basis of its morphology but that doing so will require examination of characters that have not been considered particularly important in the past. Among these are the length of the middle inflorescence internodes, the width of the palea tip, and the morphology of the glumes. Generic descriptions and keys have been posted to the web (see http://herbarium.usu.edu/ triticeae). They include all the genera that we recognize in the tribe, not just those included in the analyses, and will be improved as additional information becomes available.

Diversity and Distributions, Nov 26, 2011

... The coqui's extremely loud mating calls (80–90 dB at 0.5 m) has been determined to negat... more ... The coqui's extremely loud mating calls (80–90 dB at 0.5 m) has been determined to negatively impact real estate values (Kaiser & Burnett, 2006) and ... In this study, we compare CT, RF and SVM models for their ability to predict the invasive frog habitat in the island of Hawaii. ...

Communications in Statistics, 2000

We compare minimum Hellinger distance and minimum Hellinger disparity estimates for U-shaped beta... more We compare minimum Hellinger distance and minimum Hellinger disparity estimates for U-shaped beta distributions. Given suitable density estimates, both methods are known to be asymptotically efficient when the data come from the assumed model family, and robust to ...

Financial Services Review, Apr 1, 2005

We analyzed survey data from examinees of six administrations of the CFP® Certification Examinati... more We analyzed survey data from examinees of six administrations of the CFP® Certification Examination between November 1999 and November 2001. We observed increases in the proportions of examinees that work in insurance and as attorneys, and in the proportion of persons whose highest degree is a baccalaureate. We updated earlier work on factors associated with success on the examination. One new result is that exam preparation, in hours per week, is positively associated with performance on the examination. The five variables that are most predictive of performance on the examination are exam retake (yes, no), primary business activity, registered program, SAT score, and holding a CPA license. © 2005 Academy of Financial Services. All rights reserved.

Financial Services Review, Jul 1, 2003

Abstract We surveyed examinees from three administrations of the CFP(R) Certification Examination... more Abstract We surveyed examinees from three administrations of the CFP(R) Certification Examination. Factors that are statistically significantly associated with passing the exam include primary business activity; highest degree earned; undergraduate GPA; the CPA, Enrolled Agent, and securities licenses or designations; and being a personal financial planning practitioner. Other studies have identified associations between CPA exam success and both highest degree earned and undergraduate GPA. We are not aware of other studies that have established a relationship between experience in the field and success on the related professional exam. Interestingly, employer incentives for candidates, including bonuses, raises, and promotions, do not have a significant impact on pass rates. (C) 2003 Academy of Financial Services. All rights reserved. 1. Introduction Certified Financial Planner Board of Standards, Inc. is a professional regulatory organization that fosters professional standards in personal financial planning so that the public values, has access to, and benefits from competent financial planning. To fulfill initial certification requirements to use the CFP(R), Certified Financial Planner(TM), and certification marks, individuals must satisfy educational, examination, work experience, and ethical requirements. In 1991, CFP Board introduced a single comprehensive examination to test the candidates' integration and application of the knowledge important to providing financial advice to clients. The CFP(R) Certification Examination is designed to assess a candidate's ability to apply financial planning knowledge to real-life financial planning situations. In 1999, CFP Board's Board of Examiners, working in conjunction with CFP Board's Board of Governors and the staff of Certified Financial Planner Board of Standards, embarked on a new project. The goal of that project was to identify factors that are associated with success on the CFP(R) Certification Examination and, wherever applicable, to share that information with individuals selecting a CFP Board-Registered Program, candidates preparing for the CFP(R) Certification Examination, and CFP Board-Registered Programs evaluating their educational training. 2. Literature review This project marked the first attempt to collect data from CFP(R) Certification Examination testers to identify factors that are associated with successful performance on this exam, so no literature specifically related to the CFP(R) Certification Examination exists. However, much can be learned from studies of factors related to success on other licensing and certification exams, especially those in allied fields. In a review of the literature concerning success on the CPA examination, several factors emerged. Using data from the Uniform Statistical Information Questionnaire (USIQ) completed by candidates taking the November 1965 and May 1966 CPA examinations in Illinois and Kansas, Reilly and Stettler (1972) identified scholastic record in college and inherent academic ability, as measured by scores on the SAT College Entrance Exam, as being positively associated with success on the CPA exam. They found that the number of hours taken in accounting and graduate study was not statistically associated with success, and they received inconclusive results on several other variables studied. Using the USIQ completed by candidates in 49 states for the May 1970 examination, Leathers (1972) also found a positive correlation between SAT scores and success on the CPA examination. In a second study using May 1970 USIQ data, Sanders (1972) reported that candidates with higher degrees performed better than those with lower degrees, but the hours taken in accounting did not correlate with exam success. He also found that students who took classroom courses rather than correspondence courses had a higher pass rate, but work experience did not contribute to success on the CPA examination. …

Androgen receptor (AR) gene CAG polymorphisms may be associated with body shape, and are associat... more Androgen receptor (AR) gene CAG polymorphisms may be associated with body shape, and are associated with certain breast and prostate cancers. In addition, body shape is associated with risk for a variety of diseases, including heart disease, diabetes, and certain forms of cancer. The CAG repeat in exon l of the AR gene was quantified using Perkin Elmer Applied Biosystems GeneScan analysis software in 96 and 59 healthy Caucasian men and women, respectively, who were over the age of 50 years. All participants had body measurements taken and donated a blood sample. Waist measurements included circumferences at the 1) umbilicus (wstumb), 2) top of the iliac crest (wstili), and 3) midpoint between the lowest rib and the iliac crest (wstwst). Waist-hip ratio (Wl-IR) was calculated using each corresponding waist measurement, respectively (WHRUMB, WHRILI, WHRWST). Mean repeat length was significantly different (p < 0.01) between men (22 ± 0.3 repeats) and women (23 ± 0.3 repeats). There ...

Springer eBooks, Nov 28, 2008

Cover-The survey and manage mitigation of the Northwest Forest Plan provides protection for taxon... more Cover-The survey and manage mitigation of the Northwest Forest Plan provides protection for taxonomically and structurally diverse species in eight taxa groups: amphibians, arthropods, bryophytes, fungi, lichens, mammals, mollusks, and vascular plants. Five species on the cover illustrate the diversity in form: (1) Bryoria tortuosa (photo courtesy of Stephen Sharnoff), (2) Allotropa virgata (photo courtesy of Dan Luoma), (3) Ramaria araiospora (photo by Dan Powell), (4) Plethodon vandykei (photo courtesy of William Leonard), and (5) Tetraphis geniculata (photo courtesy of Martin Hutten).

American Journal of Epidemiology, 2006

Communications in Statistics - Theory and Methods, 2000

Biological Invasions, 2011

The Puerto Rican coqui frog (Eleutherodactylus coqui) invaded Hawaii in the late 1980s. Because t... more The Puerto Rican coqui frog (Eleutherodactylus coqui) invaded Hawaii in the late 1980s. Because the coqui reaches high densities and consumes large quantities of invertebrates, it was hypothesized to change invertebrate communities where it invades. Previous research found that coquis can change invertebrate communities, but these studies used highly manipulative, small-scale experiments. The objective of this research was to determine whether coquis create community-level changes in invertebrate communities at the landscape scale. We collected leaf litter, flying, and foliage invertebrates on both sides of 15 coqui invasion fronts across the island of Hawaii. Multivariate analyses show that coquis are associated with changes in leaf-litter communities, primarily reductions in Acari, but are not associated with overall changes in flying or foliage communities. Across sites, coquis reduced the total number of leaflitter invertebrates by 27%, specifically by reducing Acari by 36%. Across sites, coquis increased flying Diptera by 19%. Changes were greater where coqui densities were higher. We suggest that coquis changed leaf-litter communities primarily through direct predation, but that they increased Diptera through the addition of frog carcasses and excrement. Results support previous studies conducted in more controlled settings, but add to our understanding of the invasion by showing that coqui effects on invertebrate communities are measurable at the landscape scale.

Ecology, 2007

Classification procedures are some of the most widely used statistical methods in ecology. Random... more Classification procedures are some of the most widely used statistical methods in ecology. Random forests (RF) is a new and powerful statistical classifier that is well established in other disciplines but is relatively unknown in ecology. Advantages of RF compared to other statistical classifiers include (1) very high classification accuracy; (2) a novel method of determining variable importance; (3) ability to model complex interactions among predictor variables; (4) flexibility to perform several types of statistical data analysis, including regression, classification, survival analysis, and unsupervised learning; and (5) an algorithm for imputing missing values. We compared the accuracies of RF and four other commonly used statistical classifiers using data on invasive plant species presence in Lava Beds National Monument, California, USA, rare lichen species presence in the Pacific Northwest, USA, and nest sites for cavity nesting birds in the Uinta Mountains, Utah, USA. We observed high classification accuracy in all applications as measured by cross-validation and, in the case of the lichen data, by independent test data, when comparing RF to other common classification methods. We also observed that the variables that RF identified as most important for classifying invasive plant species coincided with expectations based on the literature.

The last 30 years has seen extraordinary development of new tools for the prediction of numerical... more The last 30 years has seen extraordinary development of new tools for the prediction of numerical and binary responses. Examples include the LASSO and elastic net for regularization in regression and variable selection, quantile regression for heteroscedastic data, and machine learning predictive method such as classification and regression trees (CART), multivariate adaptive regression splines (MARS), random forests, gradient boosting machines (GBM), and support vector machines (SVM). All these methods are implemented in SAS®, giving the user an amazing toolkit of predictive methods. In fact, the set of available methods is so rich it begs the question, “When should I use one or a subset of these methods instead of the other methods?” In this talk I hope to provide a partial answer to this question through the application of several of these methods in the analysis of several real datasets with numerical and binary response variables. INTRODUCTION Over the last 30 years there has b...

Mountain pine beetles are a pest indigenous to the pine forests of the western United States. Cap... more Mountain pine beetles are a pest indigenous to the pine forests of the western United States. Capable of exponential population growth, mo untain pine beetles can destroy thousands of acres of trees in a short period of time. Much research has been carried out on the mathematical modeling of mountain pine beetle phenology. The research reported here is part of a larger project to demonstrate the application of, and evaluate, differential equation models for mountain pine beetle progression through pine forests. The study area is the Sawtooth National Recreation area in Idaho. To provide input parameter to the mathematical models, and to measure the changes in the pine forest in the study area, IKONOS satellite imagery was used to classify the vegetation of the study area. Five classifiers-linear discriminant analysis, quadratic discriminant analysis, k-nearest neighbor discriminant analysis, classification trees and random forests-were applied to raw and transformed multispectral and panchromatic satellite imagery, with and without an elevation variable. Quadratic discriminant analysis and random forests proved to be the best classifiers as measured by cross-validated error estimates, with overall classification rates of about 12% without elevation, and about 5% when elevation was included. Redtops were relatively easy to identify, with misclassification rates of about 5%-6%, but green lodgepole pine and Douglas fir were relatively difficult to discriminate between and had much higher misclassification rates.

$Research paper thumbnail of Parity, VDR genotype, and risk of osteoporotic hipfracture in elderly women of Utah$

Remote Sensing of Environment, 1998

Landscapeand ecoregion-based conservation efforts constraints facing attempts to assess the accur... more Landscapeand ecoregion-based conservation efforts constraints facing attempts to assess the accuracy of large-area, remotely sensed cover maps. ©Elsevier Sci-increasingly use a spatial component to organize data for analysis and interpretation. A challenge particular to re-ence Inc., 1998 motely sensed cover maps generated from these efforts is how best to assess the accuracy of the cover maps, especially when they can exceed 1000 s/km 2 in size. Here we INTRODUCTION develop and describe a methodological approach for as-Conservation efforts are increasingly focused at the landsessing the accuracy of large-area cover maps, using as scape or ecoregion level rather than at localized sites. Ala test case the 21.9 million ha cover map developed for though the goals of these efforts vary, most use a spatial Utah Gap Analysis. As part of our design process, we component to organize data for analysis and interpretafirst reviewed the effect of intracluster correlation and a tion. One such effort, the National Biological Service's simple cost function on the relative efficiency of cluster (NBS) Gap Analysis Program (Edwards et al., 1993; Edsample designs to simple random designs. Our design ultiwards and Scott, 1995; Scott et al., 1993) uses land-cover mately combined clustered and subsampled field data land-use classes and terrestrial vertebrate species as indistratified by ecological modeling unit and accessibility cators of biological diversity and is designed to identify (hereafter a mixed design). We next outline estimation for-"gaps" in the protection of biological diversity. When mulas for simple map accuracy measures under our mixed identified, gaps can be filled through land acquisition or design and report results for eight major cover types and changes in existing land-use practices. the three ecoregions mapped as part of the Utah Gap Central to the goal of Gap Analysis is the creation Analysis. Overall accuracy of the map was 83.2% (SEϭ of a thematic map depicting land-cover/land-use cover 1.4). Within ecoregions, accuracy ranged from 78.9% to types. In general, cover types are derived by clustering 85.0%. Accuracy by cover type varied, ranging from a reflectance values from spatially explicit locations (pixels) low of 50.4% for barren to a high of 90.6% for man modobtained from satellite imagery (Richards, 1986) and asified. In addition, we examined gains in efficiency of our signing them to cover classes based on field observations, mixed design compared with a simple random sample apaerial photographs, and existing maps (Scott et al., 1993). proach. In regard to precision, our mixed design was Uses of these types of cover maps range from bioregional more precise than a simple random design, given fixed conservation planning (Merrill et al., in press) to more sample costs. We close with a discussion of the logistical finely focused management efforts aimed at specific species (Homer et al., 1993; Stoms et al., 1993). Because Gap Analysis data are organized by states and ecoregions,