Discrimination Statistics Research Articles

Analysis of extrema of heartbeat time series in exercise test

The heartbeat time series of the electrocardiogram recorded during exercise test clearly reflects the physiological control mechanism of the autonomic nervous system on heart rate. This series shows both decreasing and increasing trends and variability of the variance. We analyse the series of intervals between two consecutive extrema, i.e. the durations of accelerations or decelerations of heart rate. We compute the distribution of the length of these intervals and their mean in a model of stationary independent variables, where they are independent of the variables' distribution. We use the mean length as discriminant statistics to compare stress and recovery phases. Data analysis performed over the heartbeat series of 14 healthy subjects shows significant difference between stress and recovery.

Validation of Default Probabilities

Well performing default predictions show good discrimination and calibration. Discrimination is the ability to separate defaulters from non-defaulters. Calibration is the ability to make unbiased forecasts. We derive novel discrimination and calibration statistics to verify forecasts expressed in terms of probability under dependent observations. The test statistics' asymptotic distributions can be derived in analytic form. Not accounting for cross correlation can result in the rejection of actually well performing predictions as shown in an empirical application. We demonstrate that forecasting errors must be serially uncorrelated. As a consequence, our multi-period tests are statistically consistent.

Morphometrics ofManipora(Tabulata; Upper Ordovician; southern Manitoba, Canada)

Multivariate morphometric analysis was applied for differentiation of closely related species and evaluation of intra- and interspecific variation inManiporafrom the Selkirk Member, Red River Formation, in southern Manitoba. Seven morphological characters were quantified in transverse thin sections of 46 coralla and statistically tested for selecting effective characters in discriminating species. Cluster analysis was performed on a raw data matrix coordinated with 46 coralla by three selected characters. Two major clusters on the resulting dendrogram were regarded as morphospecies, following comparative examination of the coralla using serial sections. Cluster analyses were also conducted on principal component score matrices obtained from the raw data set coordinated with 46 coralla by all seven characters, and from an experimental data set including the 46 coralla plus two replicates of each and six of the characters. the results agree closely with the first cluster analysis, but discrimination of morphospecies was slightly degraded. the validity of two morphospecies recognized in the first cluster analysis was verified by discriminant analyses, descriptive statistics, and bivariate plots. the results show that tabularium area is the most meaningful character for distinguishing these morphospecies; ranges of variations of the other six characters overlap between morphospecies.Another cluster analysis like the first was performed, but with the addition of 11 type specimens and reference coralla ofManiporaspecies from the Upper Ordovician of southern and northern Manitoba and Texas. Based on this analysis, together with comparative examination of thin sections, the two morphospecies are identified as valid species:M. amicarumSinclair, 1955 andM. manitoba(Sokolov, 1955).Manipora magnaFlower, 1961 is considered to be a synonym ofM. amicarum, whileM. trapezoidalisFlower, 1961 andM. garsonensisCaramanica, 1992 are considered to be synonyms ofM. manitoba, and the hypotypes ofM. amicarumof Nelson (1963) are assigned toM. manitoba.

Polarimetric Characterization of Ultrawideband Propagation Channels

The polarization characteristics of the indoor ultrawideband channel are investigated using dual-polar 3.1-10.6 GHz channel measurements. Under the generalized elliptical polarization framework, the channel cross-polar discrimination (XPD) statistics are evaluated. Lognormal and triangular distributions are shown to well model the XPD and ellipticity angle. Considerable spectral and small-scale spatial variability is observed in the XPD. Asymptotic convergence of XPD to its mean with increasing bandwidth is established. An analysis of the variation of tap XPD with excess delay indicates that the XPD is highest for the initial paths. It is shown that increased scattering leads to greater depolarization. The dependence of XPD on the channel's rms delay spread is modelled using a linear regression with -0.5 dB/ns slope. This characterization will aid the analysis of polarization-dependent loss and the design of polarized multiple-antenna systems.

Performance of the QRISK cardiovascular risk prediction algorithm in an independent UK sample of patients from general practice: a validation study

Aim:To assess the performance of the QRISK score for predicting cardiovascular disease (CVD) in an independent UK sample from general practice and compare with the Framingham score.Design:Prospective open cohort studySetting:UK...

A New Resource-Constrained Triage Method Applied to Victims of Penetrating Injury

Resource-constrained triage occurs when the number of trauma patients exceeds the capacity for simultaneous transport and treatment. The objective of this article is to apply a new resource-constrained triage method (denoted Sacco triage method [STM]) to victims of penetrating trauma and compare it with existing methods. STM is a mathematical model of resource-constrained triage. Its objective is to maximize expected survivors given constraints on the timing and availability of resources. The model incorporates estimates of time-dependent victim survival probabilities based on initial assessments and expected deteriorations. For application to penetrating trauma, an "RPM" score based on respiratory rate, pulse rate, and best motor response was used to predict survivability. Logistic function-generated survival probability estimates for scene values of RPM were determined from 7,274 penetrating injury patients from the Pennsylvania Trauma Outcome Study. The Delphi Method provided expert consensus on victim deterioration rates, and the model was solved using linear programming. The accuracy of predicting survivability was assessed using calibration and discrimination statistics. STM was compared with START (Simple Triage and Rapid Treatment)-like triage methods with respect to process and outcomes (assessed by expected number of survivors in simulated resource-constrained casualty incidents). RPM was shown to be an accurate predictor of survival probability for penetrating trauma, equivalent to the Revised Trauma Score and exceeding that of the Injury Severity Score, as measured by calibration and discrimination statistics. In the simulations, STM had substantially more expected survivors than did current triage methods. Resource-constrained triage is modeled as an evidence-based, outcome-driven method (STM) that maximizes expected survivors in consideration of resources. STM offers lifesaving and operational advantages over current methods.

The appraisal of mathematics teachers in Ghana

This study examined the nature and existing methods of teacher appraisal in Ghana. 441 secondary mathematics teachers participated, of whom 193 teach the subject at the junior secondary level and 248 teach it at the senior secondary level. In addition, 44 Ghana Education Service Officials and 6 Heads of secondary schools who appraise mathematics teachers were sampled. Methods used included questionnaires, interviews and observation of appraisers at work. Chi-squarex2 and discriminant analysis statistics were used. Highly significant relationships were found between mathematics teachers' perceived professional support and appraisal experience, mathematics teaching experience and professional status at the senior secondary level; and between perceived support and appraisal experience at the junior secondary level. The results indicated inefficiencies in the appraisal system employed by the Ghana Education Service (GES) in supporting mathematics teachers to improve their work. African Journal of Educational Studies in Mathematics and Sciences Vol. 1, 2001: 81-102

Validated Prediction Model for the Development of Primary Open-Angle Glaucoma in Individuals with Ocular Hypertension

To test the validity and generalizability of the Ocular Hypertension Treatment Study (OHTS) prediction model for the development of primary open-angle glaucoma (POAG) in a large independent sample of untreated ocular hypertensive individuals and to develop a quantitative calculator to estimate the 5-year risk that an individual with ocular hypertension will develop POAG. A prediction model was developed from the observation group of the OHTS and then tested on the placebo group of the European Glaucoma Prevention Study (EGPS) using a z statistic to compare hazard ratios, a c statistic for discrimination, and a calibration chi2 for systematic overestimation/underestimation of predicted risk. The 2 study samples were pooled to increase precision and generalizability of a 5-year predictive model for developing POAG. The OHTS observation group (n = 819; 6.6 years' median follow-up) and EGPS placebo group (n = 500; 4.8 years' median follow-up). Data were collected on demographic characteristics, medical history, ocular examination visual fields (VFs), and optic disc photographs. Development of reproducible VF abnormality or optic disc progression as determined by masked readers and attributed to POAG by a masked end point committee. The same predictors for the development of POAG were identified independently in both the OHTS observation group and the EGPS placebo group-baseline age, intraocular pressure, central corneal thickness, vertical cup-to-disc ratio, and Humphrey VF pattern standard deviation. The pooled multivariate model for the development of POAG had good discrimination (c statistic, 0.74) and accurate estimation of POAG risk (calibration chi2, 7.05). The OHTS prediction model was validated in the EGPS placebo group. A calculator to estimate the 5-year risk of developing POAG, based on the pooled OHTS-EGPS predictive model, has high precision and will be useful for clinicians and patients in deciding the frequency of tests and examinations during follow-up and advisability of initiating preventive treatment.

Validation of the SWAP-200 for Diagnosing Psychostructural Organization in Personality Disorders

Background: The aim of the study was to investigate the validity of the prototype-matching, empirically based 200-item Shedler-Westen Assessment Procedure (SWAP-200) and its clinical utility for describing underlying dimensions of psychostructural organization and functioning. Sampling and Methods: Patients (n = 306) from two psychoanalytic out-patient departments were included. Replicatory and exploratory factor analysis, correlation and discriminant validity statistics, and canonical correlation analysis were performed. Results: Replicatory factor analysis failed to reproduce the identical original factorial structure. Standard factor analysis revealed an eight-factor solution displaying a dimensional description of psychostructural personality organization (high functioning – neurotic/inhibited – borderline/emotionally dysregulated – psychotic/dissocial). Discriminant validity exists across the sample owing to high/poor psychological functioning. Canonical correlation analysis does not support the replacement of the Structured Clinical Interview for DSM-IV, but provides relevant implications for refining DSM-IV axis II. Conclusions: Support is given for the SWAP instrument in describing dimensional higher-order personality organization and psychostructural functioning.

Sexual differences in Turkish dentition

Sexual variation in the human skeleton and dentition is of great concern for both anthropologists and odontologists. Assessment of variation in dental size gives a clue about the behavior of a population, and also differences between the sexes. This study deals with sexual differences in a Turkish sample of individuals ranging in age from 20 to 29 years. The sample is composed of 28 buccolingual (BL) and mesiodistal (MD) dimensions of upper and lower dentition (I1 through M2). Dental casts of 50 males and 50 females were analyzed using discriminant function statistics. The results indicated that 8 of the upper and 7 of the lower dimensions were significantly greater in males. Many of the differences were located in the anterior teeth of both jaws. In a stepwise function applied to both arches, the lower and upper canine BL, lower canine and P1 MD, and lower I2 BL were used as the most discriminating variables. When the front teeth (i.e., I1, I2, and C) are used in separate functions, only the canine BL of the lower jaw and I2 and C BL of the upper jaw were found to have the discriminating variables. Classification accuracy was 81% for the total sample, 76% for upper front and 81% for lower front teeth. In conclusion, dentition in Turkish people seems to be less sexually dimorphic than the populations with which they were compared (Jordanians, Swedish and South Africans) as was determined by the percent of accuracy obtained. In comparison with other populations, as anticipated, Turkish dental size is closest to the Jordanian sample and farthest from the South African whites.

Discriminative Game-Related Statistics between Basketball Starters and Nonstarters When Related to Team Quality and Game Outcome

The aim of the present paper was to examine the differences in game-related statistics between basketball players who are selected for the starting five of the team (starters) and those who are not (nonstarters) when related to game outcome (winning and losing) and team quality (best teams, teams classified for the playoffs; and worst teams, teams who miss playoff classification). Archival data were gathered for all 2002-2003 regular season games from the Portuguese Professional League (N = 156). Discriminant analysis was used to identify the game-related statistics that differentiate between starters and nonstarters and interpreted by the examination of the structure coefficients (SC). When the best teams won the games, results described differences between starters and nonstarters with an emphasis on defensive rebounds (SC = .32), assists (SC = .32) and committed fouls (SC = -.68). When the worst teams won the games, results described differences between starters and nonstarters with an emphasis on 2-point field goals successful (SC = .47) and unsuccessful (SC = .48), defensive rebounds (SC =.39), successful free throws (SC =.32), and committed fouls (SC = -.55). An also important finding was that, in best teams, the nonstarters' performance was worse in the games that the team lost, whereas in worst teams, it was the starters' performance that was worse in the games that the team lost.

Use of Diagonal Teeth Measurements in Predicting Gender in a Turkish Population*

Mesiodistal and buccolingual measurements, commonly used as a means of sex determination from teeth, can sometimes cause difficulties. The aim of this study is to test whether diagonal measurements can make it possible to take more accurate measurements. The results of diagonal measurements of dental casts taken from 30 males and 30 females have been evaluated by discriminant function statistics. Intra- and interobserver error tests did not indicate any statistically significant differences between the findings of two observers. Seven of the 14 measurements on the maxilla and 10 of the 14 measurements on the mandible have been found to be significantly greater in males. According to the results of the stepwise discriminant function statistics, the most contributory measurements to the function were upper first incisor mesiobuccal-distolingual (MBDL) and distobuccal-mesiolingual, lower second incisor MBDL, and lower canine MBDL. The highest reliability was obtained in MBDL measurements. It was realized that diagonal measurements of teeth, especially of canines, revealed clear dimorphic differences. Classification accuracy was found to be 83.3% for total sample, 78.3 for upper jaw, and 85.0% for the lower jaw. Accuracy rate was higher in the lower teeth. Commonly seen orthodontic anomalies, such as tooth rotations, crowding, attritions, deep dentin-enamel junction defects, and certain types of fillings, could make it difficult to correctly take width measurements or could cause other mistakes to occur. This explains the reason why this research has been considered to be of some use in diagonal measurements, which is an accurate method, particularly when employed for the front teeth.

A statistical test to determine the quality of accelerometer data

Accelerometer data quality can be inadequate due to data corruption or to non-compliance of the subject with regard to study protocols. We propose a simple statistical test to determine if accelerometer data are of good quality and can be used for analysis or if the data are of poor quality and should be discarded. We tested several data evaluation methods using a group of 105 subjects who wore Motionlogger actigraphs (Ambulatory Monitoring, Inc.) over a 15 day period to assess sleep quality in a study of health outcomes associated with stress among police officers. Using leave-one-out cross-validation and calibration-testing methods of discrimination statistics, error rates for the methods ranged from 0.0167 to 0.4046. We found that the best method was to use the overall average distance between consecutive time points and the overall average mean amplitude of consecutive time points. These values gave us a classification error rate of 0.0167. The average distance between points is a measure of smoothness in the data, and the average mean amplitude between points gave an average reading. Both of these values were then normed to determine a final statistic, K, which was then compared to a cut-off value, KC, to determine data quality.

Successful Use of a Competency Step Exam in a Perfusion Education Program

The perfusion education program at The Ohio State University uses a step exam to rank students and identify incompetent students in regard to the program learning objectives. The step exam determines student progress from the didactic to the clinical phase. Each student must pass the competency step exam to gain entry to the clinical rotations. The development, use, and results of the step exam are reported. The design and knowledge matrix establish the content validity of the exam. Single test question discrimination and difficulty statistics identify valid exam items. Examples of the exam’s predictive ability are presented. The step exam is a 200-question exam using multiple choice items. The exam is modeled after several health-related national certification exam processes. The exam has content validity based on the published, written objectives for the education program. Each item on the exam has a history of use and meets criteria for difficulty, discrimination, and distraction. The use of a high-stake competency exam in clinical science and medical education programs is controversial and technically challenging. A step exam to have high-stake consequences must be reliable, meet requirements for content validity, and hopefully exhibit predictive validity.

Characterization of the volatile fraction of young wines from the Denomination of Origin “Vinos de Madrid” (Spain)

Twenty-five volatile compounds of 71 white, 53 rose and 70 red commercial young wines, representative for the young wines commercialized under the Denomination of Origin (DO) “Vinos de Madrid” (Spain) were analyzed by gas chromatography-flame ionization detector (GC-FID) and gas chromatography-mass spectrometry (GC-MS). Odor activity values (OAV) of 21 of them were calculated, also. Twenty-four of the 25 determined odor compounds were found in the three types of wines, which means that the differences between white, rose and red wines are essentially quantitative, rather than qualitative. 4-Vinyl-guayacol was typical only for the white wines. Thirteen of the 21 odor compounds with determined OAVs had significant relevance to the global aroma of the white and rose and 12 of the red wines. Among them (in diminishing order of odor importance) ethyl octanoate, ethyl hexanoate, isoamyl acetate and isovaleric acid were the most determinant for the aroma of the white and rose wines, whereas, ethyl octanoate, isovaleric acid, isoamyl acetate and ethyl hexanoate were for the red wines. Discriminant statistic analysis showed that the isoamylic alcohols, higher major alcohols, ethyl hexanoate, acetates, ethyl octanoate, 4-vinyl-guaiacol and decanoic acid were the most significant compounds in the differentiation between the white, rose and red young wines. The same analysis showed correct classification of 96.6% of the wines (92.1% cross-validation), according to their type (white, rose or red).

Precise Formulation and Evidence‐based Application of Resource‐constrained Triage

To develop a precise mathematical formulation of resource-constrained triage, denoted the Sacco triage method (STM), to develop an evidence-based application to blunt trauma, and to compare the STM with the simple triage and rapid treatment (START) method. Resource-constrained triage is modeled mathematically as a classic resource allocation problem. The objective is to maximize expected survivors given constraints on the timing and availability of resources. The model incorporates estimates of time-dependent victim survival probabilities based on an initial assessment and expected deterioration. For application to blunt trauma, an "RPM" score, based on respiratory rate, pulse rate, and motor response, was used to predict survivability. Logistic function-generated survival probability estimates for scene values of RPM were determined from 76,459 blunt-injured patients from the Pennsylvania Trauma Outcome Study (PTOS). The Delphi method provided expert consensus on victim deterioration rates, and the model was solved using linear programming. STM was compared with START across various criteria of process and outcome. Outcome was measured by expected number of survivors in simulated resource-constrained casualty incidents. In this mathematical simulation, RPM was a more accurate predictor of survivability from blunt trauma than the Injury Severity Score and the Revised Trauma Score, as measured by calibration and discrimination statistics. STM resulted in greater expected survivorship than START in all simulations. Resource-constrained triage is modeled precisely as an evidence-based, outcome-driven method that maximizes expected survivors in consideration of resources. The lifesaving potential and operational advantages over current methods warrant scrutiny and further research.

Estimation of stature and determination of sex from radial and ulnar bone lengths in a Turkish corpse sample

Determination of sex and estimation of stature are important aspects of forensic identification of an unknown individual. In the absence of pelvis the sex is assessed from long bones and cranium as they both provide high accuracy in sexing. The present study is an attempt to assess sex and stature from long bones of the forearm using recently deceased forensic cases in Istanbul, Turkey. The sample is composed of 80 males and 47 females with an average age of 36 and 30 years, respectively. Length measurements from the radius and ulna were obtained by exposing the epiphyseal ends of the long bones in a fashion similar to dry long bones. Discriminant function statistics showed a sex determination accuracy as high as 96%. Regression analysis was used in stature estimation from these two bones. Ideally osteological remains are necessary to make standards for osteological identification. These materials are not always easy to obtain and those available seem to be less ideal when they do not represent a current population. Forensic anthropologists therefore should develop techniques that utilize autopsy remains.

A review of two journals found that articles using multivariable logistic regression frequently did not report commonly recommended assumptions

Background and Objective To examine if commonly recommended assumptions for multivariable logistic regression are addressed in two major epidemiological journals. Methods Ninety-nine articles from the Journal of Clinical Epidemiology and the American Journal of Epidemiology were surveyed for 10 criteria: six dealing with computation and four with reporting multivariable logistic regression results. Results Three of the 10 criteria were addressed in 50% or more of the articles. Statistical significance testing or confidence intervals were reported in all articles. Methods for selecting independent variables were described in 82%, and specific procedures used to generate the models were discussed in 65%. Fewer than 50% of the articles indicated if interactions were tested or met the recommended events per independent variable ratio of 10:1. Fewer than 20% of the articles described conformity to a linear gradient, examined collinearity, reported information on validation procedures, goodness-of-fit, discrimination statistics, or provided complete information on variable coding. There was no significant difference ( P > .05) in the proportion of articles meeting the criteria across the two journals. Conclusion Articles reviewed frequently did not report commonly recommended assumptions for using multivariable logistic regression.

Classical detection theory and the cryo-EM particle selection problem

Particle selection is an essential but tedious step in the determination of macromolecular structures by single particle reconstruction. This paper presents an automatic, multi-reference particle detection scheme that is based on the classical matched filter principle. It makes use of a pre-whitening filter to standardize the noise, a reduced representation of the references by means of principal component analysis, and a statistic for distinguishing particles from image artifacts. Standardizing the noise allows the noise-induced false-positive frequency to be estimated, and also allows the distribution of the discrimination statistic to be calculated a priori. The method is demonstrated with an annotated dataset of cryo-EM images.

Sexual variation in bucco-lingual dimensions in Turkish dentition

Sexual differences in the human skeleton have been well studied in many populations. Odontometric analysis of the human sexual variation has been less investigated and mostly derived from the dentition of extinct populations. Turkey is situated in a unique location where populations from different regions mixed with each other and created a rich gene pool. One might anticipate that modern Turkish population is composed of genes from the Balkans, Caucasus, Middle East, Iran and further as well as from ancient Romans, Byzantines, Arabs and Asiatic Turks. It is clear that contemporary Turks are a mixture of these extant and extinct people and ideal to consider it a representative study population. The purpose of this study is to analyze dental dimensions and sexual variation in living Turks and develop forensic techniques to identify human remains from the teeth when any other technique is not available or not reliable. The study is composed of Ankara University dental students (50 male and 50 female casts, average age of 21 years). Bucco-lingual breadths from 14 teeth (I1 through M2 of the maxilla and mandible) are taken from the left side and analyzed using the discriminant function statistics. An intraobserver error test did not indicate any statistically significant difference between any two measurements. Results of the study revealed that males exceeded females significantly ( P<0.001) in dimensions. Coefficient of variation was most obvious in I1s and I2s of both jaws in both sexes. Stepwise discriminant function statistics suggested that upper C, and lower C and M2 are the most contributory teeth to the function. Additional formulae were calculated for situation in which only one or a fragmented jaw is available for identification. Overall accuracy of sex diagnosis ranged from 73 to 77%. In conclusion this research supports earlier studies that sexual dimorphism is population specific. While dental difference between the sexes in several human populations has been found highly dimorphic, it was not found so in Turks and accuracy of classification remained low at about 77%. The difficulty or the lack of dimorphism comes from male subjects.