AUC Optimization vs. Error Rate Minimization

Size: px
Start display at page:

Download "AUC Optimization vs. Error Rate Minimization"

Transcription

1 AUC Optiization vs. Error Rate Miniization Corinna Cortes and Mehryar Mohri AT&T Labs Research 180 Park Avenue, Florha Park, NJ 0793, USA {corinna, Abstract The area under an ROC curve (AUC is a criterion used in any applications to easure the quality of a classification algorith. However, the objective function optiized in ost of these algoriths is the error rate and not the AUC value. We give a detailed statistical analysis of the relationship between the AUC and the error rate, including the first eact epression of the epected value and the variance of the AUC for a fied error rate. Our results show that the average AUC is onotonically increasing as a function of the classification accuracy, but that the standard deviation for uneven distributions and higher error rates is noticeable. Thus, algoriths designed to iniize the error rate ay not lead to the best possible AUC values. We show that, under certain conditions, the global function optiized by the RankBoost algorith is eactly the AUC. We report the results of our eperients with RankBoost in several datasets deonstrating the benefits of an algorith specifically designed to globally optiize the AUC over other eisting algoriths optiizing an approiation of the AUC or only locally optiizing the AUC. 1 Motivation In any applications, the overall classification error rate is not the ost pertinent perforance easure, criteria such as ordering or ranking see ore appropriate. Consider for eaple the list of relevant docuents returned by a search engine for a specific query. That list ay contain several thousand docuents, but, in practice, only the top fifty or so are eained by the user. Thus, a search engine s ranking of the docuents is ore critical than the accuracy of its classification of all docuents as relevant or not. More generally, for a binary classifier assigning a real-valued score to each object, a better correlation between output scores and the probability of correct classification is highly desirable. A natural criterion or suary statistic often used to easure the ranking quality of a classifier is the area under an ROC curve (AUC [8]. 1 However, the objective function optiized by ost classification algoriths is the error rate and not the AUC. Recently, several algoriths have been proposed for aiizing the AUC value locally [4] or aiizing soe approiations of the global AUC value [9, 15], but, in general, these algoriths do not obtain AUC values significantly better than those obtained by an algorith designed to iniize the error rates. Thus, it is iportant to deterine the relationship between the AUC values and the error rate. This author s new address is: Google Labs, 1440 Broadway, New York, NY 10018, corinna@google.co. 1 The AUC value is equivalent to the Wilcoon-Mann-Whitney statistic [8] and closely related to the Gini inde [1]. It has been re-invented under the nae of L-easure by [11], as already pointed out by [], and slightly odified under the nae of Linear Ranking by [13, 14].

2 True positive rate ROC Curve. AUC0.718 (1,1 (0,0 False positive rate True positive rate False positive rate correctly classified positive total positive incorrectly classified negative total negative Figure 1: An eaple of ROC curve. The line connecting (0, 0 and (1, 1, corresponding to rando classification, is drawn for reference. The true positive (negative rate is soeties referred to as the sensitivity (resp. specificity in this contet. In the following sections, we give a detailed statistical analysis of the relationship between the AUC and the error rate, including the first eact epression of the epected value and the variance of the AUC for a fied error rate. We show that, under certain conditions, the global function optiized by the RankBoost algorith is eactly the AUC. We report the results of our eperients with RankBoost in several datasets and deonstrate the benefits of an algorith specifically designed to globally optiize the AUC over other eisting algoriths optiizing an approiation of the AUC or only locally optiizing the AUC. Definition and properties of the AUC The Receiver Operating Characteristics (ROC curves were originally developed in signal detection theory [3] in connection with radio signals, and have been used since then in any other applications, in particular for edical decision-aking. Over the last few years, they have found increased interest in the achine learning and data ining counities for odel evaluation and selection [1, 10, 4, 9, 15, ]. The ROC curve for a binary classification proble plots the true positive rate as a function of the false positive rate. The points of the curve are obtained by sweeping the classification threshold fro the ost positive classification value to the ost negative. For a fully rando classification, the ROC curve is a straight line connecting the origin to (1, 1. Any iproveent over rando classification results in an ROC curve at least partially above this straight line. Fig. (1 shows an eaple of ROC curve. The AUC is defined as the area under the ROC curve and is closely related to the ranking quality of the classification as shown ore forally by Lea 1 below. Consider a binary classification task with positive eaples and n negative eaples. We will assue that a classifier outputs a strictly ordered list for these eaples and will denote by 1 X the indicator function of a set X. Lea 1 ([8] Let c be a fied classifier. Let 1,..., be the output of c on the positive eaples and y 1,..., y n its output on the negative eaples. Then, the AUC, A, associated to c is given by: A n i1 j1 1 i>y j n that is the value of the Wilcoon-Mann-Whitney statistic [8]. (1 Proof. The proof is based on the observation that the AUC value is eactly the probability P(X > Y where X is the rando variable corresponding to the distribution of the outputs for the positive eaples and Y the one corresponding to the negative eaples [7]. The Wilcoon-Mann-Whitney statistic is clearly the epression of that probability in the discrete case, which proves the lea [8]. Thus, the AUC can be viewed as a easure based on pairwise coparisons between classifications of the two classes. With a perfect ranking, all positive eaples are ranked higher than the negative ones and A 1. Any deviation fro this ranking decreases the AUC. An attept in that direction was ade by [15], but, unfortunately, the authors analysis and the result are both wrong.

3 Threshold θ k Positive eaples n Negative eaples Negative eaples (k Positive eaples Figure : For a fied nuber of errors k, there ay be,0 k, false negative eaples. 3 The Epected Value of the AUC In this section, we copute eactly the epected value of the AUC over all classifications with a fied nuber of errors and copare that to the error rate. Different classifiers ay have the sae error rate but different AUC values. Indeed, for a given classification threshold θ, an arbitrary reordering of the eaples with outputs ore than θ clearly does not affect the error rate but leads to different AUC values. Siilarly, one ay reorder the eaples with output less than θ without changing the error rate. Assue that the nuber of errors k is fied. We wish to copute the average value of the AUC over all classifications with k errors. Our odel is based on the siple assuption that all classifications or rankings with k errors are equiprobable. One could perhaps argue that errors are not necessarily evenly distributed, e.g., eaples with very high or very low ranks are less likely to be errors, but we cannot justify such biases in general. For a given classification, there ay be, 0 k, false positive eaples. Since the nuber of errors is fied, there are k false negative eaples. Figure 3 shows the corresponding configuration. The two regions of eaples with classification outputs above and below the threshold are separated by a vertical line. For a given, the coputation of the AUC, A, as given by Eq. (1 can be divided into the following three parts: A A 1 + A + A 3, with ( n A 1 the su over all pairs ( i, y j with i and y j in distinct regions; A the su over all pairs ( i, y j with i and y j in the region above the threshold; A 3 the su over all pairs ( i, y j with i and y j in the region below the threshold. The first ter, A 1, is easy to copute. Since there are ( (k positive eaples above the threshold and n negative eaples below the threshold, A 1 is given by: A 1 ( (k (n (3 To copute A, we can assign to each negative eaple above the threshold a position based on its classification rank. Let position one be the first position above the threshold and let α 1 <... < α denote the positions in increasing order of the negative eaples in the region above the threshold. The total nuber of eaples classified as positive is N (k +. Thus, by definition of A, A (N α i ( i (4 i1 where the first ter N α i represents the nuber of eaples ranked higher than the ith eaple and the second ter i discounts the nuber of negative eaples incorrectly ranked higher than the ith eaple. Siilarly, let α 1 <... < α k denote the positions of the k positive eaples below the threshold, counting positions in reverse by starting fro the threshold. Then, A 3 is given by: A 3 (N α j ( j (5 j1 with N n + (k and k. Cobining the epressions of A 1, A, and A 3 leads to: A A 1 + A + A 3 n 1 + (k + k n ( i1 α i + j1 α j n (6

4 Lea For a fied, the average value of the AUC A is given by: Proof. < A > 1 n + k The proof is based on the coputation of the average values of i1 α i and j1 α j for a given. We start by coputing the average value < α i > for a given i, 1 i. Consider all the possible positions for α 1... α i 1 and α i+1... α, when the value of α i is fied at say α i l. We have i l N ( i since there need to be at least i 1 positions before α i and N ( i above. There are l 1 possible positions for α 1... α i 1 and N l possible positions for α i+1... α. Since the total nuber of ways of choosing the positions for α 1... α out of N is, the average value < αi > is: N ( i li l ( ( l 1 N l i 1 i < α i > (8 Thus, < N ( i i1 li l ( ( l 1 N l N i 1 i l1 α i > l i1 i 1 i (9 i1 i1 ( l 1 l Using the classical identity: ( u ( v ( p 1+p p p 1 p u+v p, we can write: N l1 < α i > l( ( N 1 N 1 1 N(N (N + 1 Siilarly, we have: < α j > (N + 1 j1 Replacing < i1 α i > and < j1 α j > in Eq. (6 by the epressions given by Eq. (10 and Eq. (11 leads to: < A > 1 + (k + k (N + 1 (N n which ends the proof of the lea. n + k Note that Eq. (7 shows that the average AUC value for a given is siply one inus the average of the accuracy rates for the positive and negative classes. Proposition 1 Assue that a binary classification task with positive eaples and n negative eaples is given. Then, the epected value of the AUC A over all classifications with k errors is given by: < A > 1 k + n (n ( + n + 1 4n ( k + n k 1 ( +n 0 k 0 ( +n+1 Proof. Lea gives the average value of the AUC for a fied value of. To copute the average over all possible values of, we need to weight the epression of Eq. (7 with the total nuber of possible classifications for a given. There are possible ways of choosing the positions of the isclassified negative eaples, and siilarly ( N possible ways of choosing the positions of the k isclassified positive eaples. Thus, in view of Lea, the average AUC is given by: < A > N ( (1 k 0 k 0 n + k (7 (10 (11 (1 (13 (14

5 Mean value of the AUC r0.05 r0.01 r0.1 r0.5 r Error rate Relative standard deviation r0.01 r0.05 r0.1 r Error rate r0.5 Figure 3: Mean (left and relative standard deviation (right of the AUC as a function of the error rate. Each curve corresponds to a fied ratio of r n/(n +. The average AUC value onotonically increases with the accuracy. For n, as for the top curve in the left plot, the average AUC coincides with the accuracy. The standard deviation decreases with the accuracy, and the lowest curve corresponds to n. This epression can be siplified into Eq. (13 3 using the following novel identities:!!! kx N N kx n !!! kx N N kx (k ( n + k n (15 (16 that we obtained by using Zeilberger s algorith 4 and nuerous cobinatorial tricks. Fro the epression of Eq. (13, it is clear that the average AUC value is identical to the accuracy of the classifier only for even distributions (n. For n, the epected value of the AUC is a onotonic function of the accuracy, see Fig. (3(left. For a fied ratio of n/(n +, the curves are obtained by increasing the accuracy fro n/(n + to 1. The average AUC varies onotonically in the range of accuracy between 0.5 and 1.0. In other words, on average, there sees nothing to be gained in designing specific learning algoriths for aiizing the AUC: a classification algorith iniizing the error rate also optiizes the AUC. However, this only holds for the average AUC. Indeed, we will show in the net section that the variance of the AUC value is not null for any ratio n/(n + when k 0. 4 The Variance of the AUC Let D n + (k +k, a i1 α i, a j1 α j, and α a + a. Then, by Eq. (6, na D α. Thus, the variance of the AUC, σ (A, is given by: (n σ (A < (D α (< D > < α > > (17 < D > < D > + < α > < α > (< αd > < α >< D > As before, to copute the average of a ter X over all classifications, we can first deterine its average < X > for a fied, and then use the function F defined by: k N 0 F(Y ( Y k N (18 0 ( and < X > F(< X >. A crucial step in coputing the eact value of the variance of the AUC is to deterine the value of the ters of the type < a > < ( i1 α i >. 3 An essential difference between Eq. (14 and the epression given by [15] is the weighting by the nuber of configurations. The authors analysis leads the to the conclusion that the average AUC is identical to the accuracy for all ratios n/(n +, which is false. 4 We thank Neil Sloane for having pointed us to Zeilberger s algorith and Maple package.

6 Lea 3 For a fied, the average of ( i1 α i is given by: < a (N + 1 > (3N + + N (19 1 Proof. By definition of a, < a > b + c with: b < α i > c < i1 1 i<j Reasoning as in the proof of Lea, we can obtain: N ( i i1 li l ( ( l 1 N l N 1 i 1 i b l 1 l1 α i α j > (0 (N + 1(N To copute c, we start by coputing the average value of < α i α j >, for a given pair (i, j with i < j. As in the proof of Lea, consider all the possible positions of α 1... α i 1, α i+1...α j 1, and α j+1... α when α i is fied at α i l, and α j is fied at α j l. There are l 1 possible positions for the α 1... α i 1, l l 1 possible positions for α i+1...α j 1, and N l possible positions for α j+1... α. Thus, we have: i l<l < α i α j > N ( j ll ( ( l 1 l ( l 1 N l i 1 j i 1 j ( (1 and c ( l 1 ( l ( l<l ll l 1 N l ( N (3 3 Using the identity ( l 1 ( l ( l 1 N l ( N, we obtain: (N + 1(3N + ( 1 c 4 Cobining Eq. (1 and Eq. (4 leads to Eq. (19. Proposition Assue that a binary classification task with positive eaples and n negative eaples is given. Then, the variance of the AUC A over all classifications with k errors is given by: σ (A F((1 n + k F((1 n + k (4 + (5 F( + n(k + (( n(n + 1(k (k ( + n n Proof. Eq. (18 can be developed and epressed in ters of F, D, a, and a : (n σ (A F([D < a + a > ] F(D < a + a > + F(< a > < a > + F(< a > < a > (6 The epressions for < a > and < a > were given in the proof of Lea, and that of < a > by Lea 3. The following forula can be obtained in a siilar way: < a > (N +1 1 (3N + + N. Replacing these epressions in Eq. (6 and further siplifications give eactly Eq. (5 and prove the proposition. The epression of the variance is illustrated by Fig. (3(right which shows the value of one standard deviation of the AUC divided by the corresponding ean value of the AUC. This figure is parallel to the one showing the ean of the AUC (Fig. (3(left. Each line is obtained by fiing the ratio n/(n + and varying the nuber of errors fro 1 to the size of the sallest class. The ore uneven class distributions have the highest variance, the variance increases with the nuber of errors. These observations contradict the ineact clai of [15] that the variance is zero for all error rates with even distributions n. In Fig. (3(right, the even distribution n corresponds to the lowest dashed line.

7 n Dataset Size # of n+ AUCsplit[4] RankBoost Attr. (% Accuracy (% AUC (% Accuracy (% AUC (% Breast-Wpbc ± ± ± ± 8.0 Credit ± ±.9 Ionosphere ± ± ± ± 3.3 Pia ± ± ± ± 6.5 SPECTF Page-blocks ± ± ± ± 1.5 Yeast (CYT ± ± ± ± 3.0 Table 1: Accuracy and AUC values for several datasets fro the UC Irvine repository. The values for RankBoost are obtained by 10-fold cross-validation. The values for AUCsplit are fro [4]. 5 Eperiental Results Proposition above deonstrates that, for uneven distributions, classifiers with the sae fied (low accuracy ehibit noticeably different AUC values. This otivates the use of algoriths directly optiizing the AUC rather than doing so indirectly via iniizing the error rate. Under certain conditions, RankBoost [5] can be viewed eactly as an algorith optiizing the AUC. In this section, we ake the connection between RankBoost and AUC optiization, and copare the perforance of RankBoost to two recent algoriths proposed for optiizing an approiation [15] or locally optiizing the AUC [4]. The objective of RankBoost is to produce a ranking that iniizes the nuber of incorrectly ordered pairs of eaples, possibly with different costs assigned to the is-rankings. When the eaples to be ranked are siply two disjoint sets, the objective function iniized by RankBoost is n 1 1 rloss n 1 i y j (7 i1 j1 which is eactly one inus the Wilcoon-Mann-Whitney statistic. Thus, by Lea 1, the objective function aiized by RankBoost coincides with the AUC. RankBoost s optiization is based on cobining a nuber of weak rankings. For our eperients, we chose as weak rankings threshold rankers with the range {0, 1}, siilar to the boosted stups often used by AdaBoost [6]. We used the so-called Third Method of RankBoost for selecting the best weak ranker. According to this ethod, at each step, the weak threshold ranker is selected so as to aiize the AUC of the weighted distribution. Thus, with this ethod, the global objective of obtaining the best AUC is obtained by selecting the weak ranking with the best AUC at each step. Furtherore, the RankBoost algorith aintains a perfect 50-50% distribution of the weights on the positive and negative eaples. By Proposition 1, for even distributions, the ean of the AUC is identical to the classification accuracy. For threshold rankers like step functions, or stups, there is no variance of the AUC, so the ean of the AUC is equal to the observed AUC. That is, instead of viewing RankBoost as selecting the weak ranker with the best weighted AUC value, one can view it as selecting the weak ranker with the lowest weighted error rate. This is siilar to the choice of the best weak learner for boosted stups in AdaBoost. So, for stups, AdaBoost and RankBoost differ only in the updating schee of the weights: RankBoost updates the positive eaples differently fro the negative ones, while AdaBoost uses one coon schee for the two groups. Our eperiental results corroborate the observation that RankBoost is an algorith optiizing the AUC. RankBoost based on boosted stups obtains AUC values that are substantially better than those reported in the literature for algoriths designed to locally or approiately optiize the AUC. Table 1 copares the results of RankBoost on a nuber of datasets fro the UC Irvine repository to the results reported by [4]. The results for RankBoost are obtained by 10-fold cross-validation. For RankBoost, the accuracy and the best AUC values reported on each line of the table correspond to the sae boosting step. RankBoost consistently outperfors AUCsplit in a coparison based on AUC values, even for the datasets such as Breast-Wpbc and Pia where the two algoriths obtain siilar accuracies. The table also lists results for the UC Irvine Credit Approval and SPECTF heart dataset, for which the authors of [15] report results corresponding to their AUC optiization algoriths. The AUC values reported by [15] are no better than 9.5% for the Credit

8 Approval dataset and only 87.5% for the SPECTF dataset, which is substantially lower. Fro the table, it is also clear that RankBoost is not an error rate iniization algorith. The accuracy for the Yeast (CYT dataset is as low as 45%. 6 Conclusion A statistical analysis of the relationship between the AUC value and the error rate was given, including the first eact epression of the epected value and standard deviation of the AUC for a fied error rate. The results offer a better understanding of the effect on the AUC value of algoriths designed for error rate iniization. For uneven distributions and relatively high error rates, the standard deviation of the AUC suggests that algoriths designed to optiize the AUC value ay lead to substantially better AUC values. Our eperiental results using RankBoost corroborate this clai. In separate eperients we have observed that AdaBoost achieves significantly better error rates than RankBoost (as epected but that it also leads to AUC values close to those achieved by RankBoost. It is a topic for further study to eplain and understand this property of AdaBoost. A partial eplanation could be that, just like RankBoost, AdaBoost aintains at each boosting round an equal distribution of the weights for positive and negative eaples. References [1] L. Breian, J. H. Friedan, R. A. Olshen, and C. J. Stone. Classification and Regression Trees. Wadsworth International, Belont, CA, [] J-H. Chauchat, R. Rakotoalala, M. Carloz, and C. Pelletier. Targeting custoer groups using gain and cost atri; a arketing application. Technical report, ERIC Laboratory - University of Lyon, 001. [3] J. P. Egan. Signal Detection Theory and ROC Analysis. Acadeic Press, [4] C. Ferri, P. Flach, and J. Hernández-Orallo. Learning decision trees using the area under the ROC curve. In ICML-00. Morgan Kaufann, 00. [5] Y. Freund, R. Iyer, R. E. Schapire, and Y. Singer. An efficient boosting algorith for cobining preferences. In ICML-98. Morgan Kaufann, San Francisco, US, [6] Yoav Freund and Robert E. Schapire. A decision theoretical generalization of online learning and an application to boosting. In Proceedings of the Second European Conference on Coputational Learning Theory, volue, [7] D. M. Green and J. A Swets. Signal detection theory and psychophysics. New York: Wiley, [8] J. A. Hanley and B. J. McNeil. The eaning and use of the area under a receiver operating characteristic (ROC curve. Radiology, 198. [9] M. C. Mozer, R. Dodier, M. D. Colagrosso, C. Guerra-Salcedo, and R. Wolniewicz. Prodding the ROC curve. In NIPS-00. MIT Press, 00. [10] C. Perlich, F. Provost, and J. Sionoff. Tree induction vs. logistic regression: A learning curve analysis. Journal of Machine Learning Research, 003. [11] G. Piatetsky-Shapiro and S. Steingold. Measuring lift quality in database arketing. In SIGKDD Eplorations. ACM SIGKDD, 000. [1] F. Provost and T. Fawcett. Analysis and visualization of classifier perforance: Coparison under iprecise class and cost distribution. In KDD-97. AAAI, [13] S. Rosset. Ranking-ethods for fleible evaluation and efficient coparison of - class odels. Master s thesis, Tel-Aviv University, [14] S. Rosset, E. Neuann, U. Eick, N. Vatnik, and I. Idan. Evaluation of prediction odels for arketing capaigns. In KDD-001. ACM Press, 001. [15] L. Yan, R. Dodier, M. C. Mozer, and R. Wolniewicz. Optiizing Classifier Perforance Via the Wilcoon-Mann-Whitney Statistics. In ICML-003, 003.

Tucker, L. R, & Lewis, C. (1973). A reliability coefficient for maximum likelihood factor

Tucker, L. R, & Lewis, C. (1973). A reliability coefficient for maximum likelihood factor T&L article, version of 6/7/016, p. 1 Tucker, L. R, & Lewis, C. (1973). A reliability coefficient for axiu likelihood factor analysis. Psychoetrika, 38, 1-10 (4094 citations according to Google Scholar

More information

A scored AUC Metric for Classifier Evaluation and Selection

A scored AUC Metric for Classifier Evaluation and Selection A scored AUC Metric for Classifier Evaluation and Selection Shaomin Wu SHAOMIN.WU@READING.AC.UK School of Construction Management and Engineering, The University of Reading, Reading RG6 6AW, UK Peter Flach

More information

Predicting Time Spent with Physician

Predicting Time Spent with Physician Ji Zheng jizheng@stanford.edu Stanford University, Coputer Science Dept., 353 Serra Mall, Stanford, CA 94305 USA Ioannis (Yannis) Petousis petousis@stanford.edu Stanford University, Electrical Engineering

More information

The sensitivity analysis of hypergame equilibrium

The sensitivity analysis of hypergame equilibrium 3rd International Conference on Manageent, Education, Inforation and Control (MEICI 015) The sensitivity analysis of hypergae equilibriu Zhongfu Qin 1,a Xianrong Wei 1,b Jingping Li 1,c 1 College of Civil

More information

A Learning Method of Directly Optimizing Classifier Performance at Local Operating Range

A Learning Method of Directly Optimizing Classifier Performance at Local Operating Range A Learning Method of Directly Optimizing Classifier Performance at Local Operating Range Lae-Jeong Park and Jung-Ho Moon Department of Electrical Engineering, Kangnung National University Kangnung, Gangwon-Do,

More information

Optical coherence tomography (OCT) is a noninvasive

Optical coherence tomography (OCT) is a noninvasive Coparison of Optical Coherence Toography in Diabetic Macular Edea, with and without Reading Center Manual Grading fro a Clinical Trials Perspective Ada R. Glassan, 1 Roy W. Beck, 1 David J. Browning, 2

More information

Efficient AUC Optimization for Information Ranking Applications

Efficient AUC Optimization for Information Ranking Applications Efficient AUC Optimization for Information Ranking Applications Sean J. Welleck IBM, USA swelleck@us.ibm.com Abstract. Adequate evaluation of an information retrieval system to estimate future performance

More information

Bivariate Quantitative Trait Linkage Analysis: Pleiotropy Versus Co-incident Linkages

Bivariate Quantitative Trait Linkage Analysis: Pleiotropy Versus Co-incident Linkages Genetic Epideiology 14:953!958 (1997) Bivariate Quantitative Trait Linkage Analysis: Pleiotropy Versus Co-incident Linkages Laura Alasy, Thoas D. Dyer, and John Blangero Departent of Genetics, Southwest

More information

Fuzzy Analytical Hierarchy Process for Ecological Risk Assessment

Fuzzy Analytical Hierarchy Process for Ecological Risk Assessment Inforation Technology and Manageent Science Fuzzy Analytical Hierarchy Process for Ecological Risk Assessent Andres Radionovs 1 Oļegs Užga-Rebrovs 2 1 2 Rezekne Acadey of Technologies ISSN 2255-9094 (online)

More information

Learning the topology of the genome from protein-dna interactions

Learning the topology of the genome from protein-dna interactions Learning the topology of the genoe fro protein-dna interactions Suhas S.P. Rao, SUnet ID: suhasrao Stanford University I. Introduction A central proble in genetics is how the genoe (which easures 2 eters

More information

Challenges and Implications of Missing Data on the Validity of Inferences and Options for Choosing the Right Strategy in Handling Them

Challenges and Implications of Missing Data on the Validity of Inferences and Options for Choosing the Right Strategy in Handling Them International Journal of Statistical Distributions and Applications 2017; 3(4): 87-94 http://www.sciencepublishinggroup.co/j/ijsda doi: 10.11648/j.ijsd.20170304.15 ISSN: 2472-3487 (Print); ISSN: 2472-3509

More information

Hierarchical Cellular Automata for Visual Saliency

Hierarchical Cellular Automata for Visual Saliency https://doi.org/.7/s263-7-62-2 Hierarchical Cellular Autoata for Visual Saliency Yao Qin Mengyang Feng 2 Huchuan Lu 2 Garrison W. Cottrell Received: 2 May 27 / Accepted: 26 Deceber 27 Springer Science+Business

More information

Performance Measurement Parameter Selection of PHM System for Armored Vehicles Based on Entropy Weight Ideal Point. Yuanhong Liu

Performance Measurement Parameter Selection of PHM System for Armored Vehicles Based on Entropy Weight Ideal Point. Yuanhong Liu nd International Conference on Coputer Engineering, Inforation Science & Application Technology (ICCIA 17) Perforance Measureent Paraeter Selection of PHM Syste for Arored Vehicles Based on Entropy Weight

More information

Results Univariable analyses showed that heterogeneity variances were, on average, increased among trials at

Results Univariable analyses showed that heterogeneity variances were, on average, increased among trials at Between-trial heterogeneity in eta-analyses ay be partially explained by reported design characteristics KM Rhodes 1, RM Turner 1,, J Savović 3,4, E Jones 3, D Mawdsley 5, JPT iggins 3 1 MRC Biostatistics

More information

Keywords: meta-epidemiology; randomised trials; heterogeneity; Bayesian methods; Cochrane

Keywords: meta-epidemiology; randomised trials; heterogeneity; Bayesian methods; Cochrane Label-invariant odels for the analysis of eta-epideiological data KM Rhodes 1, D Mawdsley, RM Turner 1,3, HE Jones 4, J Savović 4,5, JPT Higgins 4 1 MRC Biostatistics Unit, School of Clinical Medicine,

More information

A Comparison of Poisson Model and Modified Poisson Model in Modelling Relative Risk of Childhood Diabetes in Kenya

A Comparison of Poisson Model and Modified Poisson Model in Modelling Relative Risk of Childhood Diabetes in Kenya Aerican Journal of Theoretical and Applied Statistics 2018; 7(5): 193-199 http://www.sciencepublishinggroup.co/j/ajtas doi: 10.11648/j.ajtas.20180705.15 ISSN: 2326-8999 (Print); ISSN: 2326-9006 (Online)

More information

CHAPTER 7 THE HIV TRANSMISSION DYNAMICS MODEL FOR FIVE MAJOR RISK GROUPS

CHAPTER 7 THE HIV TRANSMISSION DYNAMICS MODEL FOR FIVE MAJOR RISK GROUPS CHAPTER 7 THE HIV TRANSMISSION DYNAMICS MODEL FOR FIVE MAJOR RISK GROUPS Chapters 2 and 3 have focused on odeling the transission dynaics of HIV and the progression to AIDS for hoosexual en. That odel

More information

Matching Methods for High-Dimensional Data with Applications to Text

Matching Methods for High-Dimensional Data with Applications to Text Matching Methods for High-Diensional Data with Applications to Text Margaret E. Roberts, Brandon M. Stewart, and Richard Nielsen This draft: October 6, 2015 We thank the following for helpful coents and

More information

UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Midterm, 2016

UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Midterm, 2016 UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Midterm, 2016 Exam policy: This exam allows one one-page, two-sided cheat sheet; No other materials. Time: 80 minutes. Be sure to write your name and

More information

Winner s Report: KDD CUP Breast Cancer Identification

Winner s Report: KDD CUP Breast Cancer Identification Winner s Report: KDD CUP Breast Cancer Identification ABSTRACT Claudia Perlich, Prem Melville, Yan Liu, Grzegorz Świrszcz, Richard Lawrence IBM T.J. Watson Research Center Yorktown Heights, NY 10598 {perlich,pmelvil,liuya}@us.ibm.com

More information

Data Mining Techniques for Performance Evaluation of Diagnosis in

Data Mining Techniques for Performance Evaluation of Diagnosis in ISSN: 2347-3215 Volue 2 Nuber 1 (October-214) pp. 91-98 www.ijcrar.co Data Mining Techniques for Perforance Evaluation of Diagnosis in Gestational Diabetes Srideivanai Nagarajan 1*, R.M.Chandrasekaran

More information

Predicting Breast Cancer Survival Using Treatment and Patient Factors

Predicting Breast Cancer Survival Using Treatment and Patient Factors Predicting Breast Cancer Survival Using Treatment and Patient Factors William Chen wchen808@stanford.edu Henry Wang hwang9@stanford.edu 1. Introduction Breast cancer is the leading type of cancer in women

More information

Research Article Association Patterns of Ontological Features Signify Electronic Health Records in Liver Cancer

Research Article Association Patterns of Ontological Features Signify Electronic Health Records in Liver Cancer Hindawi Journal of Healthcare Engineering Volue 2017, Article ID 6493016, 9 pages https://doi.org/10.1155/2017/6493016 Research Article Association Patterns of Ontological Features Signify Electronic Health

More information

1 Introduction. st0020. The Stata Journal (2002) 2, Number 3, pp

1 Introduction. st0020. The Stata Journal (2002) 2, Number 3, pp The Stata Journal (22) 2, Number 3, pp. 28 289 Comparative assessment of three common algorithms for estimating the variance of the area under the nonparametric receiver operating characteristic curve

More information

Toll Pricing. Computational Tests for Capturing Heterogeneity of User Preferences. Lan Jiang and Hani S. Mahmassani

Toll Pricing. Computational Tests for Capturing Heterogeneity of User Preferences. Lan Jiang and Hani S. Mahmassani Toll Pricing Coputational Tests for Capturing Heterogeneity of User Preferences Lan Jiang and Hani S. Mahassani Because of the increasing interest in ipleentation and exploration of a wider range of pricing

More information

Adaptive visual attention model

Adaptive visual attention model H. Hügli, A. Bur, Adaptive Visual Attention Model, Proceedings of Iage and Vision Coputing New Zealand 2007, pp. 233 237, Hailton, New Zealand, Deceber 2007. Adaptive visual attention odel H. Hügli and

More information

arxiv: v1 [cs.lg] 28 Nov 2017

arxiv: v1 [cs.lg] 28 Nov 2017 Snorkel: Rapid Training Data Creation with Weak Supervision Alexander Ratner Stephen H. Bach Henry Ehrenberg Jason Fries Sen Wu Christopher Ré Stanford University Stanford, CA, USA {ajratner, bach, henryre,

More information

How Should Blood Glucose Meter System Analytical Performance Be Assessed?

How Should Blood Glucose Meter System Analytical Performance Be Assessed? 598599DSTXXX1.1177/1932296815598599Journal of Diabetes Science and TechnologySions research-article215 Coentary How Should Blood Glucose Meter Syste Analytical Perforance Be Assessed? Journal of Diabetes

More information

Beating by hitting: Group Competition and Punishment

Beating by hitting: Group Competition and Punishment Beating by hitting: Group Copetition and Punishent Eva van den Broek *, Martijn Egas **, Laurens Goes **, Arno Riedl *** This version: February, 2008 Abstract Both group copetition and altruistic punishent

More information

Follicle Detection in Digital Ultrasound Images using Bidimensional Empirical Mode Decomposition and Fuzzy C-means Clustering Algorithm

Follicle Detection in Digital Ultrasound Images using Bidimensional Empirical Mode Decomposition and Fuzzy C-means Clustering Algorithm Follicle Detection in Digital Ultrasound Iages using Bidiensional Epirical Mode Decoposition and Fuzzy C-eans Clustering Algorith M.Jayanthi Rao @, Dr.R.Kiran Kuar # @ Research Scholar, Departent of CS,

More information

Dendritic Inhibition Enhances Neural Coding Properties

Dendritic Inhibition Enhances Neural Coding Properties Dendritic Inhibition Enhances Neural Coding Properties M.W. Spratling and M.H. Johnson Centre for Brain and Cognitive Developent, Birkbeck College, London, UK The presence of a large nuber of inhibitory

More information

A new approach for epileptic seizure detection: sample entropy based feature extraction and extreme learning machine

A new approach for epileptic seizure detection: sample entropy based feature extraction and extreme learning machine J. Bioedical Science and Engineering, 2010, 3, 556-567 doi:10.4236/jbise.2010.36078 Published Online June 2010 (http://www.scirp.org/journal/jbise/). A new approach for epileptic seizure detection: saple

More information

FAST ACQUISITION OF OTOACOUSTIC EMISSIONS BY MEANS OF PRINCIPAL COMPONENT ANALYSIS

FAST ACQUISITION OF OTOACOUSTIC EMISSIONS BY MEANS OF PRINCIPAL COMPONENT ANALYSIS FAST ACQUISITION OF OTOACOUSTIC EMISSIONS BY MEANS OF PRINCIPAL COMPONENT ANALYSIS P. Ravazzani 1, G. Tognola 1, M. Parazzini 1,2, F. Grandori 1 1 Centro di Ingegneria Bioedica CNR, Milan, Italy 2 Dipartiento

More information

4. Model evaluation & selection

4. Model evaluation & selection Foundations of Machine Learning CentraleSupélec Fall 2017 4. Model evaluation & selection Chloé-Agathe Azencot Centre for Computational Biology, Mines ParisTech chloe-agathe.azencott@mines-paristech.fr

More information

Fig.1. Block Diagram of ECG classification. 2013, IJARCSSE All Rights Reserved Page 205

Fig.1. Block Diagram of ECG classification. 2013, IJARCSSE All Rights Reserved Page 205 Volue 3, Issue 9, Septeber 2013 ISSN: 2277 128X International Journal of Advanced Research in Coputer Science and Software Engineering Research Paper Available online at: www.ijarcsse.co Autoatic Classification

More information

Bayesian Networks Modeling for Crop Diseases

Bayesian Networks Modeling for Crop Diseases Bayesian Networs Modeling for Crop Diseases Chunguang Bi and Guifen Chen College of nforation & Technology, Jilin gricultural University, Changchun, China Bi_chunguan@126.co, guifchen@163.co bstract. Severe

More information

Sudden Noise Reduction Based on GMM with Noise Power Estimation

Sudden Noise Reduction Based on GMM with Noise Power Estimation J. Software Engineering & Applications, 010, 3: 341-346 doi:10.436/jsea.010.339 Pulished Online April 010 (http://www.scirp.org/journal/jsea) 341 Sudden Noise Reduction Based on GMM with Noise Power Estiation

More information

Evolution of Indirect Reciprocity by Social Information: The Role of

Evolution of Indirect Reciprocity by Social Information: The Role of 1 Title: Evolution of indirect reciprocity by social inforation: the role of Trust and reputation in evolution of altruis Author Affiliation: Mojdeh Mohtashei* and Lik Mui* *Laboratory for Coputer Science,

More information

Implications of ASHRAE s Guidance On Ventilation for Smoking-Permitted Areas

Implications of ASHRAE s Guidance On Ventilation for Smoking-Permitted Areas Copyright 24, Aerican Society of Heating, Refrigerating and Air-Conditioning Engineers, Inc. This posting is by perission fro ASHRAE Journal. This article ay not be copied nor distributed in either paper

More information

Learning Decision Trees Using the Area Under the ROC Curve

Learning Decision Trees Using the Area Under the ROC Curve Learning Decision rees Using the Area Under the ROC Curve Cèsar erri, Peter lach 2, José Hernández-Orallo Dep. de Sist. Informàtics i Computació, Universitat Politècnica de València, Spain 2 Department

More information

Speech Enhancement Using Temporal Masking in the FFT Domain

Speech Enhancement Using Temporal Masking in the FFT Domain PAGE 8 Speech Enhanceent Using Teporal Masking in the FFT Doain Yao Wang, Jiong An, Teddy Surya Gunawan, and Eliathaby Abikairajah School of Electrical Engineering and Telecounications The University of

More information

A novel technique for stress recognition using ECG signal pattern.

A novel technique for stress recognition using ECG signal pattern. Curr Pediatr Res 2017; 21 (4): 674-679 ISSN 0971-9032 www.currentpediatrics.co A novel technique for stress recognition using ECG signal pattern. Supriya Goel, Gurjit Kau, Pradeep Toa Gauta Buddha University,

More information

Direct in situ measurement of specific capacitance, monolayer tension, and bilayer tension in a droplet interface bilayer

Direct in situ measurement of specific capacitance, monolayer tension, and bilayer tension in a droplet interface bilayer Electronic Suppleentary Material (ESI) for Soft Matter. This journal is The Royal Society of Cheistry 2015 Taylor et al. Electronic Supporting Inforation Direct in situ easureent of specific capacitance,

More information

Parameter Identification using δ Decisions for Hybrid Systems in Biology

Parameter Identification using δ Decisions for Hybrid Systems in Biology CMACS/AVACS Worshop Paraeter Identification using δ Decisions for Hbrid Sstes in Biolog Bing Liu Joint wor with Soonho Kong, Sean Gao, Ed Clare Biological Sste Bolins et al. SIGGRAPH, 26 2 Coputational

More information

Using AUC and Accuracy in Evaluating Learning Algorithms

Using AUC and Accuracy in Evaluating Learning Algorithms 1 Using AUC and Accuracy in Evaluating Learning Algorithms Jin Huang Charles X. Ling Department of Computer Science The University of Western Ontario London, Ontario, Canada N6A 5B7 fjhuang, clingg@csd.uwo.ca

More information

Biomedical Research 2016; Special Issue: S178-S185 ISSN X

Biomedical Research 2016; Special Issue: S178-S185 ISSN X Bioedical Research 2016; Special Issue: S178-S185 ISSN 0970-938X www.bioedres.info A novel autoatic stepwise signal processing based coputer aided diagnosis syste for epilepsy-seizure detection and classification

More information

Learning with Rare Cases and Small Disjuncts

Learning with Rare Cases and Small Disjuncts Appears in Proceedings of the 12 th International Conference on Machine Learning, Morgan Kaufmann, 1995, 558-565. Learning with Rare Cases and Small Disjuncts Gary M. Weiss Rutgers University/AT&T Bell

More information

Selection and Combination of Markers for Prediction

Selection and Combination of Markers for Prediction Selection and Combination of Markers for Prediction NACC Data and Methods Meeting September, 2010 Baojiang Chen, PhD Sarah Monsell, MS Xiao-Hua Andrew Zhou, PhD Overview 1. Research motivation 2. Describe

More information

The Roles of Beliefs, Information, and Convenience. in the American Diet

The Roles of Beliefs, Information, and Convenience. in the American Diet The Roles of Beliefs, Inforation, and Convenience in the Aerican Diet Selected Paper Presented at the AAEA Annual Meeting 2002 Long Beach, July 28 th -31 st Lisa Mancino PhD Candidate University of Minnesota

More information

Assessment of Human Random Number Generation for Biometric Verification ABSTRACT

Assessment of Human Random Number Generation for Biometric Verification ABSTRACT Original Article www.jss.ui.ac.ir Assessent of Huan Rando Nuber Generation for Bioetric Verification Elha Jokar, Mohaad Mikaili Departent of Engineering, Shahed University, Tehran, Iran Subission: 07-01-2012

More information

Classical Psychophysical Methods (cont.)

Classical Psychophysical Methods (cont.) Classical Psychophysical Methods (cont.) 1 Outline Method of Adjustment Method of Limits Method of Constant Stimuli Probit Analysis 2 Method of Constant Stimuli A set of equally spaced levels of the stimulus

More information

Investigation of Binaural Interference in Normal-Hearing and Hearing-Impaired Adults

Investigation of Binaural Interference in Normal-Hearing and Hearing-Impaired Adults J A Acad Audiol 11 : 494-500 (2000) Investigation of Binaural Interference in Noral-Hearing and Hearing-Ipaired Adults Rose L. Allen* Brady M. Schwab* Jerry L. Cranford* Michael D. Carpenter* Abstract

More information

METHODS FOR DETECTING CERVICAL CANCER

METHODS FOR DETECTING CERVICAL CANCER Chapter III METHODS FOR DETECTING CERVICAL CANCER 3.1 INTRODUCTION The successful detection of cervical cancer in a variety of tissues has been reported by many researchers and baseline figures for the

More information

Identification of Consumer Adverse Drug Reaction Messages on Social Media

Identification of Consumer Adverse Drug Reaction Messages on Social Media Association for Inforation Systes AIS Electronic Library (AISeL) PACIS 2013 Proceedings Pacific Asia Conference on Inforation Systes (PACIS) 6-18-2013 Identification of Consuer Adverse Drug Reaction Messages

More information

Survival and Probability of Cure Without and With Operation in Complete Atrioventricular Canal

Survival and Probability of Cure Without and With Operation in Complete Atrioventricular Canal ORIGINAL ARTICLES Survival and Probability of Cure Without and With Operation in Coplete Atrioventricular Canal Thoas J. Berger, M.D., Eugene H. Blackstone, M.D., John W. Kirklin, M.D., L. M. Bargeron,

More information

An Empirical and Formal Analysis of Decision Trees for Ranking

An Empirical and Formal Analysis of Decision Trees for Ranking An Empirical and Formal Analysis of Decision Trees for Ranking Eyke Hüllermeier Department of Mathematics and Computer Science Marburg University 35032 Marburg, Germany eyke@mathematik.uni-marburg.de Stijn

More information

Did Modeling Overestimate the Transmission Potential of Pandemic (H1N1-2009)? Sample Size Estimation for Post-Epidemic Seroepidemiological Studies

Did Modeling Overestimate the Transmission Potential of Pandemic (H1N1-2009)? Sample Size Estimation for Post-Epidemic Seroepidemiological Studies Georgia State University ScholarWorks @ Georgia State University Public Health Faculty Publications School of Public Health 2011 Did Modeling Overestiate the Transission Potential of Pandeic (H1N1-2009)?

More information

Longevity Clubs. Ulla Lehmijoki University of Helsinki and HECER. Discussion Paper No. 234 September 2008 ISSN

Longevity Clubs. Ulla Lehmijoki University of Helsinki and HECER. Discussion Paper No. 234 September 2008 ISSN ömföäflsäafaäsflassflassflas ffffffffffffffffffffffffffffffffffff Discussion Papers Longevity Clubs Ulla Lehijoki University of Helsinki and HECER Discussion Paper No. 234 Septeber 2008 ISSN 1795 0562

More information

DIET QUALITY AND CALORIES CONSUMED: THE IMPACT OF BEING HUNGRIER, BUSIER AND EATING OUT

DIET QUALITY AND CALORIES CONSUMED: THE IMPACT OF BEING HUNGRIER, BUSIER AND EATING OUT Working Paper 04-02 The Food Industry Center University of Minnesota Printed Copy $25.50 DIET QUALITY AND CALORIES CONSUMED: THE IMPACT OF BEING HUNGRIER, BUSIER AND EATING OUT Lisa Mancino and Jean Kinsey

More information

Introduction. We can make a prediction about Y i based on X i by setting a threshold value T, and predicting Y i = 1 when X i > T.

Introduction. We can make a prediction about Y i based on X i by setting a threshold value T, and predicting Y i = 1 when X i > T. Diagnostic Tests 1 Introduction Suppose we have a quantitative measurement X i on experimental or observed units i = 1,..., n, and a characteristic Y i = 0 or Y i = 1 (e.g. case/control status). The measurement

More information

Sodium Chloride Content in Ketchup by Precipitation Titration

Sodium Chloride Content in Ketchup by Precipitation Titration Background Sodiu Chloride Content in Ketchup by Precipitation Titration Sodiu chloride is one of the ost coon substances found in nature. Knowing the salt content in food products is iportant not only

More information

Receiver operating characteristic

Receiver operating characteristic Receiver operating characteristic From Wikipedia, the free encyclopedia In signal detection theory, a receiver operating characteristic (ROC), or simply ROC curve, is a graphical plot of the sensitivity,

More information

AIDS Epidemiology. Min Shim Math 164: Scientific Computing. April 30, 2004

AIDS Epidemiology. Min Shim Math 164: Scientific Computing. April 30, 2004 AIDS Epideiology Min Shi Math 64: Scientiic Coputing April 30, 004 Abstract Thopson s AIDS epideic odel, which is orulated in his article AIDS: The Misanageent o an Epideic, published in Great Britain,

More information

Modifying ROC Curves to Incorporate Predicted Probabilities

Modifying ROC Curves to Incorporate Predicted Probabilities Modifying ROC Curves to Incorporate Predicted Probabilities C. Ferri, P. Flach 2, J. Hernández-Orallo, A. Senad Departament de Sistemes Informàtics i Computació Universitat Politècnica de València Spain

More information

LONG-TERM PROGNOSIS OF SEIZURES WITH ONSET IN CHILDHOOD LONG-TERM PROGNOSIS OF SEIZURES WITH ONSET IN CHILDHOOD. Patients

LONG-TERM PROGNOSIS OF SEIZURES WITH ONSET IN CHILDHOOD LONG-TERM PROGNOSIS OF SEIZURES WITH ONSET IN CHILDHOOD. Patients LONG-TERM PROGNOSIS OF SEIZURES WITH ONSET IN CHILDHOOD LONG-TERM PROGNOSIS OF SEIZURES WITH ONSET IN CHILDHOOD MATTI SILLANPÄÄ, M.D., PH.D., MERJA JALAVA, M.D., PH.D., OLLI KALEVA, B.SC., AND SHLOMO SHINNAR,

More information

Estimation of Area under the ROC Curve Using Exponential and Weibull Distributions

Estimation of Area under the ROC Curve Using Exponential and Weibull Distributions XI Biennial Conference of the International Biometric Society (Indian Region) on Computational Statistics and Bio-Sciences, March 8-9, 22 43 Estimation of Area under the ROC Curve Using Exponential and

More information

THYROID SEGMENTATION IN ULTRASOUND IMAGES USING SUPPORT VECTOR MACHINE

THYROID SEGMENTATION IN ULTRASOUND IMAGES USING SUPPORT VECTOR MACHINE International Journal of Neural Networks and Applications, 4(1), 2011, pp. 7-12 THYROID SEGMENTATION IN ULTRASOUND IMAGES USING SUPPORT VECTOR MACHINE D. Selvathi 1 and V. S. Sharnitha 2 Mepco Schlenk

More information

Brain Computer Interface with Low Cost Commercial EEG Device

Brain Computer Interface with Low Cost Commercial EEG Device Brain Coputer Interface with Low Cost Coercial EEG Device 1 * Gürkan Küçükyıldız, Suat Karakaya, Hasan Ocak and 2 Öer Şayli 1 Faculty of Engineering, Departent of Mechatronics Engineering, Kocaeli University,

More information

HIGH-PRECISION BIDECADAL CALIBRATION OF THE RADIOCARBON TIME SCALE, BC

HIGH-PRECISION BIDECADAL CALIBRATION OF THE RADIOCARBON TIME SCALE, BC [RADIOCARBON, VOL. 35, No. 1, 1993, P. 25-33] HIGH-PRECISION BIDECADAL CALIBRATION OF THE RADIOCARBON TIME SCALE, 5-25 BC GORDON W. PEARSON Retired fro Palaeoecology Centre, The Queen's University of Belfast,

More information

A TWO-DIMENSIONAL THERMODYNAMIC MODEL TO PREDICT HEART THERMAL RESPONSE DURING OPEN CHEST PROCEDURES

A TWO-DIMENSIONAL THERMODYNAMIC MODEL TO PREDICT HEART THERMAL RESPONSE DURING OPEN CHEST PROCEDURES A TWO-DIMENSIONAL THERMODYNAMIC MODEL TO PREDICT HEART THERMAL RESPONSE DURING OPEN CHEST PROCEDURES F. G. Dias, J. V. C. Vargas, and M. L. Brioschi Universidade Federal do Paraná Departaento de Engenharia

More information

Application guide. High speed migration SYSTIMAX InstaPATCH 360 and SYSTIMAX Ultra-Low-Loss configuration guideline

Application guide. High speed migration SYSTIMAX InstaPATCH 360 and SYSTIMAX Ultra-Low-Loss configuration guideline Application guide High speed igration SYSTIMAX InstaPATCH 360 and SYSTIMAX Ultra-Low-Loss configuration guideline Contents Contents... 2 SYSTIMAX preterinated fiber-optic cabling systes configuration guide...

More information

TEACHING REGRESSION WITH SIMULATION. John H. Walker. Statistics Department California Polytechnic State University San Luis Obispo, CA 93407, U.S.A.

TEACHING REGRESSION WITH SIMULATION. John H. Walker. Statistics Department California Polytechnic State University San Luis Obispo, CA 93407, U.S.A. Proceedings of the 004 Winter Simulation Conference R G Ingalls, M D Rossetti, J S Smith, and B A Peters, eds TEACHING REGRESSION WITH SIMULATION John H Walker Statistics Department California Polytechnic

More information

Generalized additive model for disease risk prediction

Generalized additive model for disease risk prediction Generalized additive model for disease risk prediction Guodong Chen Chu Kochen Honors College, Zhejiang University Channing Division of Network Medicine, BWH & HMS Advised by: Prof. Yang-Yu Liu 1 Is it

More information

The Level of Participation in Deliberative Arenas

The Level of Participation in Deliberative Arenas The Level of Participation in Deliberative Arenas Autoria: Leonardo Secchi, Fabrizio Plebani Abstract This paper ais to contribute to the discussion on levels of participation in collective decision-aking

More information

An original approach to the diagnosis of scolineinduced

An original approach to the diagnosis of scolineinduced J. clin Path., 1972, 25, 422-426 An original approach to the diagnosis of scolineinduced apnoea A. FSHTAL, R. T. EVANS, AND C. N. CHAPMAN Fro the Departent ofpathology, Southead General Hospital, Bristol

More information

Evaluation of an In-Situ Output Probe-Microphone Method for Hearing Aid Fitting Verification*

Evaluation of an In-Situ Output Probe-Microphone Method for Hearing Aid Fitting Verification* 0196/0202/90/1101-003 1$02.00/0 EAR AND HEARNG Copyright 0 1990 by The Willias & Wilkins Co. Vol., No. Printed in U. S. A. AMPLFCATON AND AURAL REHABLTATON Evaluation of an n-situ Output Probe-Microphone

More information

An Improved Algorithm To Predict Recurrence Of Breast Cancer

An Improved Algorithm To Predict Recurrence Of Breast Cancer An Improved Algorithm To Predict Recurrence Of Breast Cancer Umang Agrawal 1, Ass. Prof. Ishan K Rajani 2 1 M.E Computer Engineer, Silver Oak College of Engineering & Technology, Gujarat, India. 2 Assistant

More information

Various performance measures in Binary classification An Overview of ROC study

Various performance measures in Binary classification An Overview of ROC study Various performance measures in Binary classification An Overview of ROC study Suresh Babu. Nellore Department of Statistics, S.V. University, Tirupati, India E-mail: sureshbabu.nellore@gmail.com Abstract

More information

Physical Activity Training for

Physical Activity Training for Physical Activity Training for Functional Mobility in Older Persons To Hickey Fredric M. Wolf Lynne S. Robins University of Michigan Marilyn B. Wagner Cleveland State University Wafa Harik Case Western

More information

Week 2 Video 3. Diagnostic Metrics

Week 2 Video 3. Diagnostic Metrics Week 2 Video 3 Diagnostic Metrics Different Methods, Different Measures Today we ll continue our focus on classifiers Later this week we ll discuss regressors And other methods will get worked in later

More information

Policy Trap and Optimal Subsidization Policy under Limited Supply of Vaccines

Policy Trap and Optimal Subsidization Policy under Limited Supply of Vaccines olicy Trap and Optial Subsidization olicy under Liited Supply of Vaccines Ming Yi 1,2, Achla Marathe 1,3 * 1 Networ Dynaics and Siulation Science Laboratory, VBI, Virginia Tech, Blacsburg, Virginia, United

More information

Technical Specifications

Technical Specifications Technical Specifications In order to provide summary information across a set of exercises, all tests must employ some form of scoring models. The most familiar of these scoring models is the one typically

More information

Response to Mease and Wyner, Evidence Contrary to the Statistical View of Boosting, JMLR 9:1 26, 2008

Response to Mease and Wyner, Evidence Contrary to the Statistical View of Boosting, JMLR 9:1 26, 2008 Journal of Machine Learning Research 9 (2008) 59-64 Published 1/08 Response to Mease and Wyner, Evidence Contrary to the Statistical View of Boosting, JMLR 9:1 26, 2008 Jerome Friedman Trevor Hastie Robert

More information

Selective Averaging of Rapidly Presented Individual Trials Using fmri

Selective Averaging of Rapidly Presented Individual Trials Using fmri Huan Brain Mapping 5:329 340(1997) Selective Averaging of Rapidly Presented Individual Trials Using fmri Anders M. Dale* and Randy L. Buckner Massachusetts General Hospital Nuclear Magnetic Resonance Center

More information

Outcome measures in palliative care for advanced cancer patients: a review

Outcome measures in palliative care for advanced cancer patients: a review Journal of Public Health Medicine Vol. 19, No. 2, pp. 193-199 Printed in Great Britain Outcoe easures in for advanced cancer s: a review Julie Hearn and Irene J. Higginson Suary Inforation generated using

More information

changes in extracellular sodium or potassium concentration or in extracellular fluid volume could not account for these effects (1, 2).

changes in extracellular sodium or potassium concentration or in extracellular fluid volume could not account for these effects (1, 2). Journal of Clinical Investigation Vol. 46, No. 3, 1967 Studies on Auditory Thresholds in Noral Man and in Patients with Adrenal Cortical Insufficiency: The Role of Adrenal Cortical Steroids * ROBERT I.

More information

interactions (mechanism of folding/contact free energies/range of interactions/monte Carlo)

interactions (mechanism of folding/contact free energies/range of interactions/monte Carlo) Proc. Nat. Acad. Sci. USA Vol. 72, No. 1, pp. 382386, October 1975 Cheistry Model of protein folding: Inclusion of short, ediu, and longrange interactions (echanis of folding/contact free energies/range

More information

Detection Theory: Sensitivity and Response Bias

Detection Theory: Sensitivity and Response Bias Detection Theory: Sensitivity and Response Bias Lewis O. Harvey, Jr. Department of Psychology University of Colorado Boulder, Colorado The Brain (Observable) Stimulus System (Observable) Response System

More information

Noise Spectrum Estimation using Gaussian Mixture Model-based Speech Presence Probability for Robust Speech Recognition

Noise Spectrum Estimation using Gaussian Mixture Model-based Speech Presence Probability for Robust Speech Recognition Noise Spectru Estiation using Gaussian Mixture Model-bed Speech Presence Probability for Robust Speech Recognition M. J. Ala 2 P. Kenny P. Duouchel 2 D. O'Shaughnessy 3 CRIM Montreal Canada 2 ETS Montreal

More information

Behavioral Data Mining. Lecture 4 Measurement

Behavioral Data Mining. Lecture 4 Measurement Behavioral Data Mining Lecture 4 Measurement Outline Hypothesis testing Parametric statistical tests Non-parametric tests Precision-Recall plots ROC plots Hardware update Icluster machines are ready for

More information

Chapter 1. Relationship Bridge Building

Chapter 1. Relationship Bridge Building Chapter 1 An Introduction to Relationship Bridge Building a I know of no ore encouraging fact than the unquestionable ability of an to elevate his life by conscious endeavor. -Henry Thoreau The Road to

More information

Unit 1 Exploring and Understanding Data

Unit 1 Exploring and Understanding Data Unit 1 Exploring and Understanding Data Area Principle Bar Chart Boxplot Conditional Distribution Dotplot Empirical Rule Five Number Summary Frequency Distribution Frequency Polygon Histogram Interquartile

More information

Experimental Infection of the Skin in the Hamster Simulating Human Impetigo

Experimental Infection of the Skin in the Hamster Simulating Human Impetigo INFECTION AND IMMUNITY, June 1972, p. 942-946 Copyright 1972 Aerican Society for Microbiology Vol. 5, No. 6 Prinited in U.S.A. Experiental Infection of the Skin in the Haster Siulating Huan Ipetigo IV.

More information

Comparison of asynchronous versus synchronous arm crank ergometry

Comparison of asynchronous versus synchronous arm crank ergometry Spinal Cord (1999) 37, 569 ± 574 ã 1999 International Medical Society of Paraplegia All rights reserved 1362 ± 4393/99 $12.00 http://www.stockton-press.co.uk/sc Coparison of asynchronous versus synchronous

More information

International Journal of Advance Research in Computer Science and Management Studies

International Journal of Advance Research in Computer Science and Management Studies Volume 2, Issue 12, December 2014 ISSN: 2321 7782 (Online) International Journal of Advance Research in Computer Science and Management Studies Research Article / Survey Paper / Case Study Available online

More information

Derivative-Free Optimization for Hyper-Parameter Tuning in Machine Learning Problems

Derivative-Free Optimization for Hyper-Parameter Tuning in Machine Learning Problems Derivative-Free Optimization for Hyper-Parameter Tuning in Machine Learning Problems Hiva Ghanbari Jointed work with Prof. Katya Scheinberg Industrial and Systems Engineering Department Lehigh University

More information

IBM Research Report. Medical Data Mining: Insights from Winning Two Competitions

IBM Research Report. Medical Data Mining: Insights from Winning Two Competitions RC24758 (W0903-023) March 6, 2009 Computer Science IBM Research Report Medical Data Mining: Insights from Winning Two Competitions Saharon Rosset School of Mathematical Sciences Tel Aviv University Tel

More information

Review. Imagine the following table being obtained as a random. Decision Test Diseased Not Diseased Positive TP FP Negative FN TN

Review. Imagine the following table being obtained as a random. Decision Test Diseased Not Diseased Positive TP FP Negative FN TN Outline 1. Review sensitivity and specificity 2. Define an ROC curve 3. Define AUC 4. Non-parametric tests for whether or not the test is informative 5. Introduce the binormal ROC model 6. Discuss non-parametric

More information