Averaging of TNTC Counts

Size: px
Start display at page:

Download "Averaging of TNTC Counts"

Transcription

1 APPLIED AND ENVIRONMENTAL MICROBIOL-OGY. Aug p /88/082)069-04$02.00/0 Copyright O 1988, American Society for Microbiology Vol. 54. No. 8 Averaging of TNTC Counts CHARLES N. HAAS* AND BARBARA HELLER Illiniois Itistitite of Technology, Chi ago, Illitiois Received 10 March 1988/Accepted 23 May 1988 When plate count methods are used for microbial enumeration, if too-numerous-to-count results occur, they are commonly discarded. In this paper, a method for consideration of such results in computation of an average microbial density is developed, and its use is illustrated by example. In the determination of microorganisms by a technique in which individual viable units are determined, such as by plate count assay of bacteria or by plaque count assay of viruses, with insufficiently diluted samples an overgrowth or dense formation of colonies is noted which is conventionally reported as TNTC (too numerous to count). For example, q,. x Nj and plates with TNTC (TNTCi). It is convenient to maximize the log likelihood function (natural log of the joint probabilities) rather than the likelihood itself. If there are a total of q plates with scorable counts (less than T colonies) and r plates with counts greater than T, then the log likelihood function can be written: Y = In (L) = E [-AVj + Nj In (AkV1) -In (Nj!)] + In E exp [(-AVk)] (AVk)'..lin! J-I- IIIJW the membrane filter method for heterotrophic plate count of waters (1) specified that only samples with counts of 20 to 200 colonies per filter be scored. However, the omission of plates in which TNTC counts are present in the estimation of the average number of microorganisms present in a sample may lead to a misestimation of their numbers. In this paper, a statistically based method for quantitative use of TNTC information in the construction of an average-density estimate for a sample is presented. THEORETICAL DERIVATION The fundamental procedure for statistical estimation is the maximum likelihood theory (2, 4, 6). For a single plate on which a sample of volume YV has been plated, if the Poisson distribution is assumed, equation 1 gives the probability that Nj colonies will arise. P(Nj) = exp[(-avj)(avj)ni/n1j! (1) In equation 1, A is the mean concentration (number/volume) of microorganisms in the water from which the sample was taken. If T is the minimum number of colonies which is regarded as TNTC (e.g., 200 colonies in the case of the heterotrophic plate count), then the probability that a sample of water Vj will plate out with TNTC colonies is given by a summation of Poisson terms as in equation 2. The summation in equation 2 is taken over all colonies in excess of the maximum countable number (T).,~~~ P(TNTC1) = E exp[(-avj) (AIj)k]/k! (2) The maximum likelihood estimator of the unknown mean concentration is obtained as the value of Ak which maximizes the probability of having obtained the series of colony counts * Corresponding author. Given a set of experimental observations (Njs and TNTCs at various sample volumes), equation 3 can be maximized to determine the maximum likelihood estimator of the mean concentration from which the samples were taken. The value of A that maximizes equation 3 can be determined in two basic ways, either by searching for the maximum directly or by differentiating, equating the derivative in A to zero, and solving the resulting nonlinear equation for A. In this work, the first approach of direct search is used with the algorithm of Nelder and Mead (5) for nonlinear optimization. The calculation is performed using a BASIC program for a personal computer. A listing suitable for use with standard interpreted BASICs is given in Fig. 1. To use this program, the ordinary user need only modify the statements from lines 1070 on. The first DATA statement contains the number of countable plates, the number of TNTC plates, and the maximum number of countable colonies on a plate (T). The following DATA statements are one line for each countable plate with the volume plated and the number of colonies on that plate, followed by one line for each TNTC plate with the volume plated on each TNTC plate. Note that the number of colonies on a countable plate must not exceed the TNTC threshold. If more than 20 plates are counted, the dimension statements in lines 20 and 30 for the arrays VOLSCORE, VOLTNTC, and YOBS must be increased accordingly. Compilation of the program for execution on a machine with a math coprocessor will dramatically improve execution times. The tolerance criterion of in line 70 has been found to be generally acceptable; however, the user can lower this for a greater degree of precision. COMPUTATIONAL EXAMPLE The use of equation 3 for the particular case of two plates at volumes of 1 and 10 is illustrated. It is assumed that a countable number of colonies (including 0) occurs on the low-volume plate but that TNTC occurs on the higher- (3) Downloaded from on April 20, 2018 by guest 2069

2 2070 HAAS AND HELLER APPL. ENVIRON. MICROBIOL. - - "; 10 REM PROGRAM TO COMPUTE MAXIMUM LIKELIHOOD ESTIMATORS DIM SET(20,20),CENTROID(20),EXPAND(20),CONTR(20),X(20),FVAL(20),REFLECT(20) 30 DIM VOLSCORE(20),VOLTNTC(20),LNFACTOR(300),BEST(20),YOBS(20) 40 RESTORE:READ NSCORABLE,NTNTC,TNTCCOUNT:LNFACTOR(0)-0 50 FOR I-1 TO TNTCCOUNT:LNFACTOR(I)-LNFACTOR(I-1)+LOG(I):NEXT I 60 NVAR-1 : REM - number of parameters 70 TOL REM - convergence criterion 80 MAXITER - 50 REM - maximum iterations 90 A -.1 : REM - polygon side for initial guess 100 AM-1:BB-.5:GG-2: REM - parameters for simplex (do not change) 110 REM -g----get data FOR I-1 TO NSCORABLE:READ VOLSCORE(I),YOBS(I):NEXT I 130 FOR J-1 TO NTNTC:READ VOLTNTC(J):NEXT J 140 REM Compute Initial Guess By Neglecting TNTC's SUMCOL-0:SUMVOLO0 160 FOR I1 TO NSCORABLE:SUMCOL-SUMCOL+YOBS(I):SUMVOL-SUMVOL+VOLSCORE(I):NEXT I 170 ITER-0:PRINT:PRINT 'Working 180 SET(l,l)-(SUMCOL+.5)/SUMVOL : REM Initial Guess 190 Q-A 200 FOR I-2 TO NVAR FOR J-1 TO NVAR 220 IF I-1<>J THEN SET(I,J)-SET(1,J)*(1-Q) 230 IF I-1-J THEN SET(I,J)-SET(1,J)*(l+A) 240 CENTROID(J)-CENTROID(J)+SET(I,J)/(NVAR+l) 250 NEXT J 260 NEXT I 270 REM get values at polygon vertices FOR I-1 TO NVAR FOR J-1 TO NVAR:X(J)-SET(I,J):NEXT J 300 GOSUB FVAL(I)-F 320 NEXT I 330 REM find worst point and best point 340 BEST-1:WORST FOR I-2 TO NVAR IF FVAL(I)<FVAL(BEST) THEN BEST-I 370 IF FVAL(I)>FVAL(WORST) THEN WORST-I 380 NEXT I 390 FOR I-1 TO NVAR:BEST(I)-SET(BEST,I);NEXT I 400 IF ITER>MAXITER THEN DELTA-ABS(FVAL(BEST)-FVAL(WORST)):PRINT "+ ";:IF DELTA>TOL THEN PRINT:PRINT " PRINT :PRINT:PRINT "The Estimated Mean Density - ";SET(BEST,1) ;"colonies/unit volume" 440 PRINT:PRINT:PRINT "- ln(likelihood) -";FVAL(BEST) 450 END: 460 REM ****************** SIMPLEX ALGORITHM *************************** 470 REM **************************************************************** 480 ITER-ITER FOR I1 TO NVAR:CENTROID(I)-0:NEXT I 500 FOR I-1 TO NVAR FOR J-1 TO NVAR 520 IF I-WORST THEN CENTROID(J)-CENTROID(J)+SET(I,J)/(NVAR) 540 NEXT J 550 NEXT I 560 FOR I-1 TO NVAR:REFLECT(I)-CENTROID(I)+M*(CENTROID(I)-SET(WORST,I) ):NEXT I 570 FOR I-1 TO NVAR:X(I)-REFLECT(I):NEXT I 580 GOSUB 870 :FREFLECT-F

3 VOL. 54, 1988 AVERAGING OF TNTC COUNTS IF FREFLECT<FVAL(BEST) THEN 750 : REM reflected point is best 600 IF FREFLECT>FVAL(WORST) THEN IF FREFLECT<-FVAL(WORST) THEN FOR I11 TO NVAR:CONTR(I)-CENTROID(I)-BB*(CENTROID(I)-SET(WORST,I)):NEXT I 630 GOTO FOR I-1 TO NVAR:CONTR(I)-CENTROID(I)-BB*(CENTROID(I)-REFLECT(I)):NEXT I 650 FOR I11 TO NVAR:X(I)-CONTR(I):NEXT I 660 GOSUB CONTR-F 680 IF CONTR>FVAL(WORST) THEN FOR I-1 TO NVAR : REM contracted point is an improvement 700 SET(WORST,I)-CONTR(I) 710 NEXT I 720 FVAL(W0RST)-CONTR:GOTO FOR J-1 TO NVAR:FOR I'1 TO NVAR+1:SET(I,J)-(SET(I,J)+BEST(J))/2:NEXT I:NEXT J 740 GOTO FOR I-1 TO NVAR:EXPAND(I)-CENTROID(I)+GG*(REFLECT(I)-CENTROID(I)):NEXT I 760 FOR I-1 TO NVAR:X(I)-EXPAND(I):NEXT I 770 GOSUB 870:FEXPANDF:IF FEXPAND > FREFLECT THEN FOR I-1 TO NVAR:SET(WORST,I)-EXPAND(I):NEXT I 790 FVAL(WORST)-FEXPAND 800 GOTO FOR I-1 TO NVAR:SET(WORST,I)-REFLECT(I):NEXT I 820 FVAL(WORST)-FREFLECT 830 GOTO REM******************************************************************** 850 REM * FUNCTION COMPUTATION ***************************** 860 REM **********SUM LIKELIHOOD FUNCTION FOR ALL POINTS******************** 870 IF X(1)<-0 TEEN F E+24:RETURN :REM No Negative Densities 880 F# FOR JJJ-1 TO NSCORABLE 900 TEMPf--X(1)*VOLSCORE(JJJ)+YOBS(JJJ)*LOG(X(1)*VOLSCORE(JJJ) )-LNFACTOR(YOBS(JJJ)) 910 F#-F#-TEMP# 920 NEXT JJJ 930 FOR JJJ-1 TO NTNTC 940 LOGTTERMD--(X(1)*VOLTNTC(JJJ) )+TNTCCOUNT*LOG(X(1)*VOLTNTC( JJJ) ) -LNFACTOR(TNTCCOUNT) 950 SUM?'0:IF LOGTTERMI-60 TEEN SUM#.EXP(LOGTTERM#) 960 KKK-TNTCCOUNT MULT#-LOG(X(1)*VOLTNTC(JJJ) /KIXK) :LOGTTERM#ILOGTTERM#+MULT# 980 IF LOGTTERMI>-60 THEN SUM-SUMI+EXP(LOGTTERMI) 990 KKK-KKK+1:IF KKK>500 TEEN PRINT "KKK TOO LARGE": STOP 1000 IF SUM#0 THEN GOTO LOGRATIOPLOGTTERk*-LOG(SUM#):IF MULT#>0 OR LOGRATIO#>LOG(TOL) TEEN GOTO IF SUMI>1 THEN SUtM F#-F#-LOG(SUM ) :F-F# 1040 NEXT JJJ 1050 RETURN 1060 REM ************************* DATA STATEMENTS *************************** 1070 DATA 5,3,80 :REM # Scorables, # TNTC Observations, TNTC Cutoff 1080 DATA 1,10 :REM scorable data -- volume, colonies 1090 DATA 1, DATA 1, DATA 5, DATA 5, DATA DATA 10 :REM TNTC data -- volume of sample with TNTC 1150 DATA 10 FIG. 1. BASIC program listing.

4 2072 HAAS AND HELLER APPL. ENVIRON. MICROBIOL..) c a0) L ID -0 4-,- E 0 U i Counts on low volume plote FIG. 2. Estimated average densities per unit volume for a single observation at 1 and 10 volume units with TNTC at 10 units. Numbers in the graph are the assumed lower bounds for TNTC. volume plate. The threshold of TNTC is varied from 80 to 300 colonies, illustrating the effect in the range of practical interest. From application of maximum likelihood, the estimated mean density is reported as a function of the counts read on the low-volume plate and the threshold for reporting as TNTC on the high-volume plate. Figure 2 summarizes the results of these calculations. At low counts on the low-volume plate (less than those given by the TNTC threshold divided by the dilution factor, e.g., 8 colonies when 80 is the threshold), the estimated mean density is much greater than that given by the direct use of only the countable plate. In other words, the exclusion of TNTC results tends to bias the estimated density below that given from the use of the maximum likelihood equation (equation 3). As the number of colonies on the low-volume plate increases, however, there is greater agreement between the estimate that would be obtained from the exclusion of the TNTC results and that obtained from its inclusion in the maximum likelihood estimator. Execution of the program shown in Fig. 1 leads to a solution for a problem in which there are 8 plates taken and the maximum countable number is 80 colonies. On a 1-ml sample, counts for three replicate plates are 10, 12, and 23. On a 5-mi sample, counts are 40, 63, and TNTC, and on a 10-ml sample, duplicate counts are TNTC. The maximum likelihood estimated count is 13.28/ml, with a -log(likelihood) of Note that, if the TNTC results were ignored in this case and an average (total colonies per volume in countable plates) were taken, one would obtain a density of 11.9/ml, underestimating the density by about 10%. DISCUSSION Conventional practice generally discards TNTC data obtained at large volumes and retains only data in countable ranges. As shown, however, particularly when the counts in the countable ranges are low, this may lead to an underestimate of the microbial concentration from the sample. It is proposed that the procedure based on equation 3 be used for the evaluation of data. In conclusion, it is noted that the maximum likelihood approach assumes intrinsic Poisson replication errors. The authors have discussed tests of this assumption elsewhere (3). If the Poisson distribution does not characterize the distribution of microbial counts between samples, then the proposed procedure should be modified accordingly. ACKNOWLEDGMENT We thank Christine Moe of the University of North Carolina for posing this problem. LITERATURE CITED 1. American Public Health Association Standard methods for the examination of water and wastewater, 16th ed. American Public Health Association, Washington, D.C. 2. Finney, D. J Statistical method in biological assay, 2nd ed. Hafner Press, New York. 3. Haas, C. N., and B. Heller Statistics of enumerating total coliforms in water samples by membrane filter techniques. Water Res. 20: Maul, A., J. C. Block, and A. H. El-Shaarawi Statistical approach for comparison between methods of bacterial enumeration in drinking water. J. Microbiol. Methods 4: Nelder, J. A., and R. Mead A simplex method for function minimization. Computer J. 7: Rohatgi, V. K Statistical inference. John Wiley & Sons, Inc., New York.

5 ERRATUM Averaging of TNTC Counts CHARLES N. HAAS AND BARBARA HELLER Illinois Institute of Technology, Chicago, Illinois Volume 54, no. 8, p. 2069, equation 1: the equation should read "P(Nj) = exp[(-avj)](avj)nj/n1!'' Page 2069, equation 2: the equation should read "P(TNTCj) = k=r exp[(-avj)](avj)/k!" 2884

Estimating MU for microbiological plate count using intermediate reproducibility duplicates method

Estimating MU for microbiological plate count using intermediate reproducibility duplicates method Estimating MU for microbiological plate count using intermediate reproducibility duplicates method Before looking into the calculation aspect of this subject, let s get a few important definitions in right

More information

Introduction to Scientific Computing

Introduction to Scientific Computing Introduction to Scientific Computing Benson Muite benson.muite@ut.ee http://kodu.ut.ee/ benson https://courses.cs.ut.ee/2018/isc/spring 26 March 2018 [Public Domain,https://commons.wikimedia.org/wiki/File1

More information

Relationship Between Atmospheric Temperature

Relationship Between Atmospheric Temperature APPLIED MICROBIOLOGY, Feb. 1970, p. 245-249 Copyright ( 1970 American Society for Microbiology Vol. 19, No. 2 Printed in U.S.A. Relationship Between Atmospheric Temperature and Survival of Airborne Bacteria

More information

Investigating Models with Two or Three Categories

Investigating Models with Two or Three Categories Ronald H. Heck and Lynn N. Tabata 1 Investigating Models with Two or Three Categories For the past few weeks we have been working with discriminant analysis. Let s now see what the same sort of model might

More information

Estimating terminal half life by non-compartmental methods with some data below the limit of quantification

Estimating terminal half life by non-compartmental methods with some data below the limit of quantification Paper SP08 Estimating terminal half life by non-compartmental methods with some data below the limit of quantification Jochen Müller-Cohrs, CSL Behring, Marburg, Germany ABSTRACT In pharmacokinetic studies

More information

Thermal Injury and Recovery of Salmonella typhimurium and Its Effect on

Thermal Injury and Recovery of Salmonella typhimurium and Its Effect on APPLIED MICROBIOLOGY, Sept. 1969, p. 332-336 Copyright @ 1969 American Society for Microbiology Vol. 18, No. 3 Printed in U.S.A. Thermal Injury and Recovery of Salmonella typhimurium and Its Effect on

More information

Interpretation Guide. Aerobic Count Plate

Interpretation Guide. Aerobic Count Plate Interpretation Guide The 3M Petrifilm is a ready-made culture medium system that contains modified Standard Methods nutrients, a cold-water-soluble gelling agent and an indicator that facilitates colony

More information

Experiences with the Coulter Counter in Bacteriology1

Experiences with the Coulter Counter in Bacteriology1 Experiences with the Coulter Counter in Bacteriology1 ELLEN M. SWANTON, WILLIAM A. CTJRBY, AND HOWARD E. LIND Sias Laboratories, Brooks Hospital, Brookline, Massachusetts Received for publication May 24,

More information

Analytical Report

Analytical Report Analytical Report 386228 for Natural Soap Formulas Project Manager: Wanda Baligad Formula 206 Natural Soap Formulas 20-AUG-10 3231 NW 7th Avenue, Boca Raton, FL 33431 Ph:(561) 447-7373 Fax:(561) 447-6136

More information

Statistical Study of the Spot-Plate Technique for Viable-Cell Counts

Statistical Study of the Spot-Plate Technique for Viable-Cell Counts Statistical Study of the Spot-Plate Technique for Viable-Cell Counts A. F. GAUDY, JR., F. ABU-NIAAJ,' AND E. T. GAUDY 0 Bio-engineering Laboratories, School of Civil Engineering, and Microbiology Department,

More information

SPSS, University of Texas at Arlington. Topics in Machine Learning-EE 5359 Neural Networks

SPSS, University of Texas at Arlington. Topics in Machine Learning-EE 5359 Neural Networks Topics in Machine Learning-EE 5359 Neural Networks 1 The Perceptron Output: A perceptron is a function that maps D-dimensional vectors to real numbers. For notational convenience, we add a zero-th dimension

More information

434 CHAP. 8 NUMERICAL OPTIMIZATION. Powell's Method. Powell s Method

434 CHAP. 8 NUMERICAL OPTIMIZATION. Powell's Method. Powell s Method 434 CHAP. 8 NUMERICAL OPTIMIZATION Powell's Method Powell s Method Let X be an initial guess at the location of the minimum of the function z = f (x, x 2,...,x N ). Assume that the partial derivatives

More information

Convenor: Colin Fricker Co-convenor: Olivier Molinier Objective of the revisionof ISO 13843

Convenor: Colin Fricker Co-convenor: Olivier Molinier Objective of the revisionof ISO 13843 VALIDATION OF MICROBIOLOGICAL METHODS FOR WATER AND ENVIRONMENT REVISION OF ISO 13843 Eurachem Workshop Gent 2016 Method Validation in Analytical Science Current Practices and Future Challenges Olivier

More information

Model Estimation Example

Model Estimation Example Ronald H. Heck 1 EDEP 606: Multivariate Methods (S2013) April 7, 2013 Model Estimation Example As we have moved through the course this semester, we have encountered the concept of model estimation. Discussions

More information

Model Based Statistics in Biology. Part V. The Generalized Linear Model. Chapter 16 Introduction

Model Based Statistics in Biology. Part V. The Generalized Linear Model. Chapter 16 Introduction Model Based Statistics in Biology. Part V. The Generalized Linear Model. Chapter 16 Introduction ReCap. Parts I IV. The General Linear Model Part V. The Generalized Linear Model 16 Introduction 16.1 Analysis

More information

DISPLAYING THE POISSON REGRESSION ANALYSIS

DISPLAYING THE POISSON REGRESSION ANALYSIS Chapter 17 Poisson Regression Chapter Table of Contents DISPLAYING THE POISSON REGRESSION ANALYSIS...264 ModelInformation...269 SummaryofFit...269 AnalysisofDeviance...269 TypeIII(Wald)Tests...269 MODIFYING

More information

School of Mathematical and Physical Sciences, University of Newcastle, Newcastle, NSW 2308, Australia 2

School of Mathematical and Physical Sciences, University of Newcastle, Newcastle, NSW 2308, Australia 2 International Scholarly Research Network ISRN Computational Mathematics Volume 22, Article ID 39683, 8 pages doi:.542/22/39683 Research Article A Computational Study Assessing Maximum Likelihood and Noniterative

More information

Estimation of Microbial Concentration in Food Products from Qualitative Microbiological Test Data with the MPN Technique

Estimation of Microbial Concentration in Food Products from Qualitative Microbiological Test Data with the MPN Technique 173 Original Paper Estimation of Microbial Concentration in Food Products from Qualitative Microbiological Test Data with the MPN Technique Hiroshi Fujikawa* Faculty of Agriculture, Tokyo University of

More information

The Poisson Distribution

The Poisson Distribution The Poisson Distribution Mary Lindstrom (Adapted from notes provided by Professor Bret Larget) February 5, 2004 Statistics 371 Last modified: February 4, 2004 The Poisson Distribution The Poisson distribution

More information

(Jennison, 1937). This lack of agreement may be overcome, at

(Jennison, 1937). This lack of agreement may be overcome, at EVALUATION OF THE ERRORS INVOLVED IN ESTIMATING BACTERIAL NUMBERS BY THE PLATING METHOD' MARSHALL W. JENNISON AND GEORGE P. WADSWORTH Department of Biology and Public Health, and Department of Mathematics,

More information

A Model for Computer Identification of Micro-organisms

A Model for Computer Identification of Micro-organisms J. gen, Microbial. (1965), 39, 401405 Printed.in Great Britain 401 A Model for Computer Identification of Micro-organisms BY H. G. GYLLENBERG Department of Microbiology, Ulziversity of Helsinki, Finland

More information

The nltm Package. July 24, 2006

The nltm Package. July 24, 2006 The nltm Package July 24, 2006 Version 1.2 Date 2006-07-17 Title Non-linear Transformation Models Author Gilda Garibotti, Alexander Tsodikov Maintainer Gilda Garibotti Depends

More information

(16 µm). Then transferred to a 250 ml flask with culture medium without nitrate, and left in

(16 µm). Then transferred to a 250 ml flask with culture medium without nitrate, and left in Oikos OIK-04046 Barreiro, A., Roy, S. and Vasconcelos, V. M. 2017. Allelopathy prevents competitive exclusion and promotes phytoplankton biodiversity. Oikos doi: 10.1111/oik.04046 Appendix 1 Parameterization

More information

D-optimal Designs for Factorial Experiments under Generalized Linear Models

D-optimal Designs for Factorial Experiments under Generalized Linear Models D-optimal Designs for Factorial Experiments under Generalized Linear Models Jie Yang Department of Mathematics, Statistics, and Computer Science University of Illinois at Chicago Joint research with Abhyuday

More information

CISC 889 Bioinformatics (Spring 2004) Hidden Markov Models (II)

CISC 889 Bioinformatics (Spring 2004) Hidden Markov Models (II) CISC 889 Bioinformatics (Spring 24) Hidden Markov Models (II) a. Likelihood: forward algorithm b. Decoding: Viterbi algorithm c. Model building: Baum-Welch algorithm Viterbi training Hidden Markov models

More information

Parametric Techniques

Parametric Techniques Parametric Techniques Jason J. Corso SUNY at Buffalo J. Corso (SUNY at Buffalo) Parametric Techniques 1 / 39 Introduction When covering Bayesian Decision Theory, we assumed the full probabilistic structure

More information

Tineke Jones Agriculture and Agri-Food Canada Lacombe Research Centre Lacombe, Alberta

Tineke Jones Agriculture and Agri-Food Canada Lacombe Research Centre Lacombe, Alberta Growth of Escherichia Coli at Chiller Temperatures Tineke Jones Agriculture and Agri-Food Canada Lacombe Research Centre Lacombe, Alberta \ Introduction The responses of mesophilic microorganisms to chiller

More information

Neural Networks. CSE 6363 Machine Learning Vassilis Athitsos Computer Science and Engineering Department University of Texas at Arlington

Neural Networks. CSE 6363 Machine Learning Vassilis Athitsos Computer Science and Engineering Department University of Texas at Arlington Neural Networks CSE 6363 Machine Learning Vassilis Athitsos Computer Science and Engineering Department University of Texas at Arlington 1 Perceptrons x 0 = 1 x 1 x 2 z = h w T x Output: z x D A perceptron

More information

Why ZMPE When You Can MUPE?

Why ZMPE When You Can MUPE? T E C O L O T E R ESE ARC H, I NC. Bridging Engineering and Economics Since 1973 Why ZMPE When You Can MUPE? 6 th Joint ISPA/SCEA Conference Dr. Shu-Ping Hu and Alfred Smith 12-15 June 2007 Los Angeles

More information

Colorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science.

Colorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science. rofessor William Hoff Dept of Electrical Engineering &Computer Science http://inside.mines.edu/~whoff/ 1 Review of robability For additional review material, see http://eecs.mines.edu/courses/csci507/schedule/

More information

THE JOURNAL OF AGRICULTURE

THE JOURNAL OF AGRICULTURE THE JOURNAL OF AGRICULTURE OF THE UNIVERSITY OF PUERTO RICO Issued quarterly by the Agricultural Expenment Station of the University of Puerto Rico, Mayaguez Campus, for the publication of articles and

More information

Exploring Microbes in the Sea. Alma Parada Postdoctoral Scholar Stanford University

Exploring Microbes in the Sea. Alma Parada Postdoctoral Scholar Stanford University Exploring Microbes in the Sea Alma Parada Postdoctoral Scholar Stanford University Cruising the ocean to get us some microbes It s all about the Microbe! Microbes = microorganisms an organism that requires

More information

Count data page 1. Count data. 1. Estimating, testing proportions

Count data page 1. Count data. 1. Estimating, testing proportions Count data page 1 Count data 1. Estimating, testing proportions 100 seeds, 45 germinate. We estimate probability p that a plant will germinate to be 0.45 for this population. Is a 50% germination rate

More information

Sequential Procedure for Testing Hypothesis about Mean of Latent Gaussian Process

Sequential Procedure for Testing Hypothesis about Mean of Latent Gaussian Process Applied Mathematical Sciences, Vol. 4, 2010, no. 62, 3083-3093 Sequential Procedure for Testing Hypothesis about Mean of Latent Gaussian Process Julia Bondarenko Helmut-Schmidt University Hamburg University

More information

Protein Complex Identification by Supervised Graph Clustering

Protein Complex Identification by Supervised Graph Clustering Protein Complex Identification by Supervised Graph Clustering Yanjun Qi 1, Fernanda Balem 2, Christos Faloutsos 1, Judith Klein- Seetharaman 1,2, Ziv Bar-Joseph 1 1 School of Computer Science, Carnegie

More information

Enumeration and generation of all constitutional alkane isomers of methane to icosane using recursive generation and a modified Morgan s algorithm

Enumeration and generation of all constitutional alkane isomers of methane to icosane using recursive generation and a modified Morgan s algorithm The C n H 2n+2 challenge Zürich, November 21st 2015 Enumeration and generation of all constitutional alkane isomers of methane to icosane using recursive generation and a modified Morgan s algorithm Andreas

More information

Mapping Microbial Biodiversity

Mapping Microbial Biodiversity APPLIED AND ENVIRONMENTAL MICROBIOLOGY, Sept. 2001, p. 4324 4328 Vol. 67, No. 9 0099-2240/01/$04.00 0 DOI: 10.1128/AEM.67.9.4324 4328.2001 Copyright 2001, American Society for Microbiology. All Rights

More information

Numerical Optimization: Basic Concepts and Algorithms

Numerical Optimization: Basic Concepts and Algorithms May 27th 2015 Numerical Optimization: Basic Concepts and Algorithms R. Duvigneau R. Duvigneau - Numerical Optimization: Basic Concepts and Algorithms 1 Outline Some basic concepts in optimization Some

More information

Productivity. Technician. Maximized. Interpretation Guide

Productivity. Technician. Maximized. Interpretation Guide 3M Food Safety 3M Petrifilm Aqua Enterobacteriaceae Count Plate 3M Petrifilm Aqua Yeast and Mold Count Plate Technician Productivity Maximized Interpretation Guide Introducing 3M Petrifilm Aqua Plates

More information

Bacterial Aerosol Samplers

Bacterial Aerosol Samplers 1959] BACTERIAL AEROSOL SAMPLERS. II 349 II. Bacterial Aerosol Samplers RETTGER, L. F. 1910 A new and improved method of enumerating air bacteria. J. Med. Research, 22, 461-468. ROSEBURY, T. 1947 Experimental

More information

Introduction to Maximum Likelihood Estimation

Introduction to Maximum Likelihood Estimation Introduction to Maximum Likelihood Estimation Eric Zivot July 26, 2012 The Likelihood Function Let 1 be an iid sample with pdf ( ; ) where is a ( 1) vector of parameters that characterize ( ; ) Example:

More information

Error analysis in biology

Error analysis in biology Error analysis in biology Marek Gierliński Division of Computational Biology Hand-outs available at http://is.gd/statlec Oxford Latin dictionary 2 Previously on Errors Random variable: numerical outcome

More information

PROBABILITY AND STOCHASTIC PROCESSES A Friendly Introduction for Electrical and Computer Engineers

PROBABILITY AND STOCHASTIC PROCESSES A Friendly Introduction for Electrical and Computer Engineers PROBABILITY AND STOCHASTIC PROCESSES A Friendly Introduction for Electrical and Computer Engineers Roy D. Yates Rutgers, The State University ofnew Jersey David J. Goodman Rutgers, The State University

More information

Rapid Aerobic Count. Interpretation Guide. 3M Food Safety 3M Petrifilm Rapid Aerobic Count Plate

Rapid Aerobic Count. Interpretation Guide. 3M Food Safety 3M Petrifilm Rapid Aerobic Count Plate 3M Food Safety 3M Petrifilm Rapid Aerobic Count Plate Rapid Aerobic Count Interpretation Guide The 3M Petrifilm Rapid Aerobic Count Plate is a sample-ready culture medium system which contains nutrients,

More information

Tentative Identification of Methanogenic Bacteria by Fluorescence Microscopy

Tentative Identification of Methanogenic Bacteria by Fluorescence Microscopy APPLIED AND ENVIRONMENTAL MICROBIOLOGY, Mar. 1977, p. 713-717 Copyright (C 1977 American Society for Microbiology Vol. 33, No. 3 Printed in U.S.A. Tentative Identification of Methanogenic Bacteria by Fluorescence

More information

3M Petrifilm Lactic Acid Bacteria Count Plate Reminders for Use

3M Petrifilm Lactic Acid Bacteria Count Plate Reminders for Use Petrifilm Lactic Acid Bacteria 3M Petrifilm Lactic Acid Bacteria Count Plate Reminders for Use Storage Petrifilm Lactic Acid Bacteria -20 to 8 C Store the unopened 3M Petrifilm Lactic Acid Bacteria Count

More information

Parametric Techniques Lecture 3

Parametric Techniques Lecture 3 Parametric Techniques Lecture 3 Jason Corso SUNY at Buffalo 22 January 2009 J. Corso (SUNY at Buffalo) Parametric Techniques Lecture 3 22 January 2009 1 / 39 Introduction In Lecture 2, we learned how to

More information

Chapter 5. Introduction to Path Analysis. Overview. Correlation and causation. Specification of path models. Types of path models

Chapter 5. Introduction to Path Analysis. Overview. Correlation and causation. Specification of path models. Types of path models Chapter 5 Introduction to Path Analysis Put simply, the basic dilemma in all sciences is that of how much to oversimplify reality. Overview H. M. Blalock Correlation and causation Specification of path

More information

Statistical Experiment A statistical experiment is any process by which measurements are obtained.

Statistical Experiment A statistical experiment is any process by which measurements are obtained. (التوزيعات الا حتمالية ( Distributions Probability Statistical Experiment A statistical experiment is any process by which measurements are obtained. Examples of Statistical Experiments Counting the number

More information

Control Charts for Monitoring the Zero-Inflated Generalized Poisson Processes

Control Charts for Monitoring the Zero-Inflated Generalized Poisson Processes Thai Journal of Mathematics Volume 11 (2013) Number 1 : 237 249 http://thaijmath.in.cmu.ac.th ISSN 1686-0209 Control Charts for Monitoring the Zero-Inflated Generalized Poisson Processes Narunchara Katemee

More information

Development and Calibration of an Item Response Model. that Incorporates Response Time

Development and Calibration of an Item Response Model. that Incorporates Response Time Development and Calibration of an Item Response Model that Incorporates Response Time Tianyou Wang and Bradley A. Hanson ACT, Inc. Send correspondence to: Tianyou Wang ACT, Inc P.O. Box 168 Iowa City,

More information

Modeling Data with Linear Combinations of Basis Functions. Read Chapter 3 in the text by Bishop

Modeling Data with Linear Combinations of Basis Functions. Read Chapter 3 in the text by Bishop Modeling Data with Linear Combinations of Basis Functions Read Chapter 3 in the text by Bishop A Type of Supervised Learning Problem We want to model data (x 1, t 1 ),..., (x N, t N ), where x i is a vector

More information

Numerical Study of Some Iterative Methods for Solving Nonlinear Equations

Numerical Study of Some Iterative Methods for Solving Nonlinear Equations International Journal of Engineering Science Invention ISSN (Online): 2319 6734, ISSN (Print): 2319 6726 Volume 5 Issue 2 February 2016 PP.0110 Numerical Study of Some Iterative Methods for Solving Nonlinear

More information

Pairwise Parameter Estimation in Rasch Models

Pairwise Parameter Estimation in Rasch Models Pairwise Parameter Estimation in Rasch Models Aeilko H. Zwinderman University of Leiden Rasch model item parameters can be estimated consistently with a pseudo-likelihood method based on comparing responses

More information

A Universal Turing Machine

A Universal Turing Machine A Universal Turing Machine A limitation of Turing Machines: Turing Machines are hardwired they execute only one program Real Computers are re-programmable Solution: Universal Turing Machine Attributes:

More information

ABSTRACT. even billions per gram or square centimeter, occur on or in poultry, fish, meats, vegetables,

ABSTRACT. even billions per gram or square centimeter, occur on or in poultry, fish, meats, vegetables, APPLIED MICROBIOLOGY, Jan., 1966 Vol. 14, No. 1 Copyright 1966 American Society for Microbiology Printed in U.S.A. Quantitative Ecology of Psychrophilic Microorganisms J. L STOKES AND MARY L. REDMOND Department

More information

H-LIKELIHOOD ESTIMATION METHOOD FOR VARYING CLUSTERED BINARY MIXED EFFECTS MODEL

H-LIKELIHOOD ESTIMATION METHOOD FOR VARYING CLUSTERED BINARY MIXED EFFECTS MODEL H-LIKELIHOOD ESTIMATION METHOOD FOR VARYING CLUSTERED BINARY MIXED EFFECTS MODEL Intesar N. El-Saeiti Department of Statistics, Faculty of Science, University of Bengahzi-Libya. entesar.el-saeiti@uob.edu.ly

More information

Number of analysis cases (objects) n n w Weighted number of analysis cases: matrix, with wi

Number of analysis cases (objects) n n w Weighted number of analysis cases: matrix, with wi CATREG Notation CATREG (Categorical regression with optimal scaling using alternating least squares) quantifies categorical variables using optimal scaling, resulting in an optimal linear regression equation

More information

3M Petrifilm Lactic Acid Bacteria Count Plate

3M Petrifilm Lactic Acid Bacteria Count Plate 3M Petrifilm Lactic Acid Bacteria Count Plate The 3M Petrifilm Lactic Acid Bacteria Count Plate is a self-contained, sampleready-culture-medium system which contains nutrients, selective agents, a cold-water-soluble

More information

...(iii), x 2 Example 7: Geetha Perfume Company produces both perfumes and body spray from two flower extracts F 1. The following data is provided:

...(iii), x 2 Example 7: Geetha Perfume Company produces both perfumes and body spray from two flower extracts F 1. The following data is provided: The LP formulation is Linear Programming: Graphical Method Maximize, Z = 2x + 7x 2 Subject to constraints, 2x + x 2 200...(i) x 75...(ii) x 2 00...(iii) where x, x 2 ³ 0 Example 7: Geetha Perfume Company

More information

Variations of Logistic Regression with Stochastic Gradient Descent

Variations of Logistic Regression with Stochastic Gradient Descent Variations of Logistic Regression with Stochastic Gradient Descent Panqu Wang(pawang@ucsd.edu) Phuc Xuan Nguyen(pxn002@ucsd.edu) January 26, 2012 Abstract In this paper, we extend the traditional logistic

More information

Approximation of Average Run Length of Moving Sum Algorithms Using Multivariate Probabilities

Approximation of Average Run Length of Moving Sum Algorithms Using Multivariate Probabilities Syracuse University SURFACE Electrical Engineering and Computer Science College of Engineering and Computer Science 3-1-2010 Approximation of Average Run Length of Moving Sum Algorithms Using Multivariate

More information

Data Mining 2018 Bayesian Networks (1)

Data Mining 2018 Bayesian Networks (1) Data Mining 2018 Bayesian Networks (1) Ad Feelders Universiteit Utrecht Ad Feelders ( Universiteit Utrecht ) Data Mining 1 / 49 Do you like noodles? Do you like noodles? Race Gender Yes No Black Male 10

More information

Maximum Likelihood Estimation. only training data is available to design a classifier

Maximum Likelihood Estimation. only training data is available to design a classifier Introduction to Pattern Recognition [ Part 5 ] Mahdi Vasighi Introduction Bayesian Decision Theory shows that we could design an optimal classifier if we knew: P( i ) : priors p(x i ) : class-conditional

More information

Since the publication of the ISO Guide to the Expression

Since the publication of the ISO Guide to the Expression DE SILVA: JOURNAL OF AOAC INTERNATIONAL VOL. 86, NO. 5, 003 1077 SPECIAL GUEST EDITOR SECTION Uncertainty of Analytical Determinations GALAPPATTI M.S. DE SILVA 4, PB Alwis Perera Mawatha, Katubedda, Sri

More information

Morphology and Ultrastructure of Staphylococcal L Colonies: Light, Scanning,

Morphology and Ultrastructure of Staphylococcal L Colonies: Light, Scanning, JOURNAL OF BACTERIOLOGY, Feb. 1973, p. 1049-1053 Copyright ( 1973 American Society for Microbiology Vol. 113, No. 2 Printed in U.S.A. Morphology and Ultrastructure of Staphylococcal L Colonies: Light,

More information

Generalized Linear Models (1/29/13)

Generalized Linear Models (1/29/13) STA613/CBB540: Statistical methods in computational biology Generalized Linear Models (1/29/13) Lecturer: Barbara Engelhardt Scribe: Yangxiaolu Cao When processing discrete data, two commonly used probability

More information

Stat 5101 Lecture Notes

Stat 5101 Lecture Notes Stat 5101 Lecture Notes Charles J. Geyer Copyright 1998, 1999, 2000, 2001 by Charles J. Geyer May 7, 2001 ii Stat 5101 (Geyer) Course Notes Contents 1 Random Variables and Change of Variables 1 1.1 Random

More information

MBOONI WEST SUB - COUNTY JOINT EVALUATION TEST

MBOONI WEST SUB - COUNTY JOINT EVALUATION TEST NAME.... DATE INDEX NO........ SIGNATURE.... 233/3 CHEMISTRY PRACTICAL PAPER 3 JULY/AUGUST, 2014 TIME: 2¼ HOURS. MBOONI WEST SUB - COUNTY JOINT EVALUATION TEST Kenya Certificate of Secondary Education.

More information

O 3 O 4 O 5. q 3. q 4. Transition

O 3 O 4 O 5. q 3. q 4. Transition Hidden Markov Models Hidden Markov models (HMM) were developed in the early part of the 1970 s and at that time mostly applied in the area of computerized speech recognition. They are first described in

More information

of the work reported here was to define the point in the developmental process at which the curing salts act to prevent outgrowth.

of the work reported here was to define the point in the developmental process at which the curing salts act to prevent outgrowth. APPLIED MICROBIOLOGY, Feb. 1968, p. 406-411 Copyright 1968 American Society for Microbiology Vol. 16, No. 2 Printed in U.S.A. Effect of Sodium Nitrite, Sodium Chloride, and Sodium Nitrate on Germination

More information

ANALYSIS OF DEFECT MAPS OF LARGE AREA VLSI IC's

ANALYSIS OF DEFECT MAPS OF LARGE AREA VLSI IC's ANALYSIS OF DEFECT MAPS OF LARGE AREA VLSI IC's Israel Koren, Zahava Karen*, and Charles H. Stapper** Department of Electrical and Computer Engineering *Department of Industrial Engineering and Operations

More information

SPATIAL-TEMPORAL TECHNIQUES FOR PREDICTION AND COMPRESSION OF SOIL FERTILITY DATA

SPATIAL-TEMPORAL TECHNIQUES FOR PREDICTION AND COMPRESSION OF SOIL FERTILITY DATA SPATIAL-TEMPORAL TECHNIQUES FOR PREDICTION AND COMPRESSION OF SOIL FERTILITY DATA D. Pokrajac Center for Information Science and Technology Temple University Philadelphia, Pennsylvania A. Lazarevic Computer

More information

BAYESIAN ANALYSIS OF DOSE-RESPONSE CALIBRATION CURVES

BAYESIAN ANALYSIS OF DOSE-RESPONSE CALIBRATION CURVES Libraries Annual Conference on Applied Statistics in Agriculture 2005-17th Annual Conference Proceedings BAYESIAN ANALYSIS OF DOSE-RESPONSE CALIBRATION CURVES William J. Price Bahman Shafii Follow this

More information

Removal of Escherichia coli in Wastewater by Activated Sludge

Removal of Escherichia coli in Wastewater by Activated Sludge APPLIED AND ENVIRONMENTAL MICROBIOLOGY, Sept. 1977, p. 315-319 Copyright C 1977 American Society for Microbiology Vol. 34, No. 3 Printed in U.S.A. Removal of Escherichia coli in Wastewater by Activated

More information

A Cautionary Note on the Use of LISREL s Automatic Start Values in Confirmatory Factor Analysis Studies R. L. Brown University of Wisconsin

A Cautionary Note on the Use of LISREL s Automatic Start Values in Confirmatory Factor Analysis Studies R. L. Brown University of Wisconsin A Cautionary Note on the Use of LISREL s Automatic Start Values in Confirmatory Factor Analysis Studies R. L. Brown University of Wisconsin The accuracy of parameter estimates provided by the major computer

More information

USING PEARSON TYPE IV AND OTHER CINDERELLA DISTRIBUTIONS IN SIMULATION. Russell Cheng

USING PEARSON TYPE IV AND OTHER CINDERELLA DISTRIBUTIONS IN SIMULATION. Russell Cheng Proceedings of the Winter Simulation Conference S. Jain, R.R. Creasey, J. Himmelspach, K.P. White, and M. Fu, eds. USING PEARSON TYPE IV AND OTHER CINDERELLA DISTRIBUTIONS IN SIMULATION Russell Cheng University

More information

Number of cases (objects) Number of variables Number of dimensions. n-vector with categorical observations

Number of cases (objects) Number of variables Number of dimensions. n-vector with categorical observations PRINCALS Notation The PRINCALS algorithm was first described in Van Rickevorsel and De Leeuw (1979) and De Leeuw and Van Rickevorsel (1980); also see Gifi (1981, 1985). Characteristic features of PRINCALS

More information

CELL DIFFERENTIATION & GROWTH OF ORGANISMS BIOLOGY TEAM

CELL DIFFERENTIATION & GROWTH OF ORGANISMS BIOLOGY TEAM CELL DIFFERENTIATION & GROWTH OF ORGANISMS BIOLOGY TEAM Agricultural Technology Faculty Brawijaya University 2013 OVERVIEW Growth Definition & Terminology Differentiation & Growth of Unicellular Organisms

More information

Researchers often record several characters in their research experiments where each character has a special significance to the experimenter.

Researchers often record several characters in their research experiments where each character has a special significance to the experimenter. Dimension reduction in multivariate analysis using maximum entropy criterion B. K. Hooda Department of Mathematics and Statistics CCS Haryana Agricultural University Hisar 125 004 India D. S. Hooda Jaypee

More information

Testing Goodness Of Fit Of The Geometric Distribution: An Application To Human Fecundability Data

Testing Goodness Of Fit Of The Geometric Distribution: An Application To Human Fecundability Data Journal of Modern Applied Statistical Methods Volume 4 Issue Article 8 --5 Testing Goodness Of Fit Of The Geometric Distribution: An Application To Human Fecundability Data Sudhir R. Paul University of

More information

Microbial Grazers Lab

Microbial Grazers Lab Microbial Grazers Lab Objective: Measure the rate at which bacteria are consumed by predators. Overview Size based food webs Microbial loop concepts acterial predators Methods to assess microbial grazing

More information

Electrical Sensing Zone Particle Analyzer for Measuring Germination of Fungal Spores in the Presence of Other Particles'

Electrical Sensing Zone Particle Analyzer for Measuring Germination of Fungal Spores in the Presence of Other Particles' APPUED MicRoBImoLY, July 1967, p. 935-639 Vol. 15, No. 4 Copyright 1967 American Society for Microbiology Printed bi U.S.A. Electrical Sensing Zone Particle Analyzer for Measuring Germination of Fungal

More information

Genome 541! Unit 4, lecture 2! Transcription factor binding using functional genomics

Genome 541! Unit 4, lecture 2! Transcription factor binding using functional genomics Genome 541 Unit 4, lecture 2 Transcription factor binding using functional genomics Slides vs chalk talk: I m not sure why you chose a chalk talk over ppt. I prefer the latter no issues with readability

More information

Undirected Graphical Models

Undirected Graphical Models Outline Hong Chang Institute of Computing Technology, Chinese Academy of Sciences Machine Learning Methods (Fall 2012) Outline Outline I 1 Introduction 2 Properties Properties 3 Generative vs. Conditional

More information

A Cautionary Note on Estimating the Reliability of a Mastery Test with the Beta-Binomial Model

A Cautionary Note on Estimating the Reliability of a Mastery Test with the Beta-Binomial Model A Cautionary Note on Estimating the Reliability of a Mastery Test with the Beta-Binomial Model Rand R. Wilcox University of Southern California Based on recently published papers, it might be tempting

More information

Introduction to mtm: An R Package for Marginalized Transition Models

Introduction to mtm: An R Package for Marginalized Transition Models Introduction to mtm: An R Package for Marginalized Transition Models Bryan A. Comstock and Patrick J. Heagerty Department of Biostatistics University of Washington 1 Introduction Marginalized transition

More information

Automated determination of the uniformity of dosage in quinine sulfate tablets using a fiber optics autosampler

Automated determination of the uniformity of dosage in quinine sulfate tablets using a fiber optics autosampler Automated determination of the uniformity of dosage in quinine sulfate tablets using a fiber optics autosampler Application Note Author John Sanders. Agilent Technologies, Inc. Mulgrave, Victoria 3170,

More information

Counting Palindromes According to r-runs of Ones Using Generating Functions

Counting Palindromes According to r-runs of Ones Using Generating Functions 3 47 6 3 Journal of Integer Sequences, Vol. 7 (04), Article 4.6. Counting Palindromes According to r-runs of Ones Using Generating Functions Helmut Prodinger Department of Mathematics Stellenbosch University

More information

Unsupervised Learning

Unsupervised Learning 2018 EE448, Big Data Mining, Lecture 7 Unsupervised Learning Weinan Zhang Shanghai Jiao Tong University http://wnzhang.net http://wnzhang.net/teaching/ee448/index.html ML Problem Setting First build and

More information

Linear Discrimination Functions

Linear Discrimination Functions Laurea Magistrale in Informatica Nicola Fanizzi Dipartimento di Informatica Università degli Studi di Bari November 4, 2009 Outline Linear models Gradient descent Perceptron Minimum square error approach

More information

Artificial Neural Networks. MGS Lecture 2

Artificial Neural Networks. MGS Lecture 2 Artificial Neural Networks MGS 2018 - Lecture 2 OVERVIEW Biological Neural Networks Cell Topology: Input, Output, and Hidden Layers Functional description Cost functions Training ANNs Back-Propagation

More information

Mahdi karbasian* & Zoubi Ibrahim

Mahdi karbasian* & Zoubi Ibrahim International Journal of Industrial Engineering & Production Research (010) pp. 105-110 September 010, Volume 1, Number International Journal of Industrial Engineering & Production Research ISSN: 008-4889

More information

Techneau, 30. September Validation of the FISH-based detection and quantification of E.coli and coliform bacteria in water samples

Techneau, 30. September Validation of the FISH-based detection and quantification of E.coli and coliform bacteria in water samples Techneau, 30. September 2009 Validation of the FISH-based detection and quantification of E.coli and coliform bacteria in water samples Techneau, 30. September 2009 Validation of the FISH-based detection

More information

On the Power of Tests for Regime Switching

On the Power of Tests for Regime Switching On the Power of Tests for Regime Switching joint work with Drew Carter and Ben Hansen Douglas G. Steigerwald UC Santa Barbara May 2015 D. Steigerwald (UCSB) Regime Switching May 2015 1 / 42 Motivating

More information

Last lecture 1/35. General optimization problems Newton Raphson Fisher scoring Quasi Newton

Last lecture 1/35. General optimization problems Newton Raphson Fisher scoring Quasi Newton EM Algorithm Last lecture 1/35 General optimization problems Newton Raphson Fisher scoring Quasi Newton Nonlinear regression models Gauss-Newton Generalized linear models Iteratively reweighted least squares

More information

Generalized Linear Models

Generalized Linear Models Generalized Linear Models Advanced Methods for Data Analysis (36-402/36-608 Spring 2014 1 Generalized linear models 1.1 Introduction: two regressions So far we ve seen two canonical settings for regression.

More information

Clustering K-means. Clustering images. Machine Learning CSE546 Carlos Guestrin University of Washington. November 4, 2014.

Clustering K-means. Clustering images. Machine Learning CSE546 Carlos Guestrin University of Washington. November 4, 2014. Clustering K-means Machine Learning CSE546 Carlos Guestrin University of Washington November 4, 2014 1 Clustering images Set of Images [Goldberger et al.] 2 1 K-means Randomly initialize k centers µ (0)

More information

Week #16 - Differential Equations (Euler s Method) Section 11.3

Week #16 - Differential Equations (Euler s Method) Section 11.3 Week #16 - Differential Equations (Euler s Method) Section 11.3 From Calculus, Single Variable by Hughes-Hallett, Gleason, McCallum et. al. Copyright 2005 by John Wiley & Sons, Inc. This material is used

More information

Lecture 17: Numerical Optimization October 2014

Lecture 17: Numerical Optimization October 2014 Lecture 17: Numerical Optimization 36-350 22 October 2014 Agenda Basics of optimization Gradient descent Newton s method Curve-fitting R: optim, nls Reading: Recipes 13.1 and 13.2 in The R Cookbook Optional

More information