Review of the role of uncertainties in room acoustics

Size: px
Start display at page:

Download "Review of the role of uncertainties in room acoustics"

Transcription

1 Review of the role of uncertainties in room acoustics Ralph T. Muehleisen, Ph.D. PE, FASA, INCE Board Certified Principal Building Scientist and BEDTR Technical Lead Division of Decision and Information Sciences Argonne National Laboratory BEDTR Better Decisions + Better Technology = Better Buildings Building Energy Decision and Technology Research Program

2 Outline What is Uncertainty Types of Uncertainties How to Get Started Steps of Calculating Uncertainty Characterizing Input Uncertainty Recent Applications of Uncertainty in Architectural Acoustics 2

3 What is Uncertainty? Uncertainty = Lack of Knowledge When modeling, uncertainty is reflected in Lack of knowledge of inputs to model Uncertainty in model parameters Lack of knowledge of knowledge of true model uncertainty in model itself When measuring, uncertainty is reflected in Interfering signals Background noises Measurement instrumentation Finite precision, equipment noise, drift, and offsets 3

4 Random and Systematic Uncertainties Random Uncertainties are the result of stochastic fluctuations in the system or in background interference. Not Reproducible Often Unclear Causes Results in Poor Precision Generally Uncorrelated With Each Other and True Value Cannot Always Be Reduced Systematic uncertainties are associated with the nature of the measurement apparatus, choice of model used, assumptions made by modeler or experimenter Reproducible Definite Causes Results in Poor Accuracy Generally Correlated Measurement to Measurement Can Usually Be Reduced 4

5 Understanding Random and Systematic Uncertainty Large Random Uncertainty Large Systematic Uncertainty Large Random and Systematic Uncertainty Small Random and Systematic Uncertainty 5

6 A Few Uncertainties in Room Acoustic Modeling Simplified models make analysis and prediction tractable but create uncertainty Ignore diffraction, refraction Assume pure diffuse or specular reflection Ignore sound structure interaction Use simplified geometry 6

7 Parametric Sweeps Uncertainty Analysis The most common form of uncertainty analysis is parametric sweeps, where inputs are varied over some range and the output range is determined I have only one thing to say JUST DON T DO IT If you are going to go through the effort of varying parameters and doing multiple computations, do a proper uncertainty analysis because then you will know you did it right 7

8 How Can I Get Started in Uncertainty Analysis? Use the GUM Luke! JCGM 100:2008, Guide to the Expression of Uncertainty In Measurements (GUM), is an ISO standard methodology for estimating measurement uncertainties and propagating uncertainties through formulae The supplemental guides are very important! They discuss more advanced topics like strong non-linearities, large parameter uncertainty and mutually dependent (correlated) uncertainty between variables The GUM is the basis of uncertainty estimation for many measurement standards 8

9 How Can I Include Uncertainty in My Analysis? 1. Decide what uncertainty is important and what is not Include uncertainty for parameters with high influence and high uncertainty, perhaps ignore others 2. Characterize the uncertainty of the selected parameters or the model itself 3. Propagate uncertainty through the model Analytic methods if model is very simple and uncertainty is small Numerical methods for other cases 4. Statistically analyze results to make predictions Generate empirical probability and cumulative density functions (PDF and CDF) Get standard statistical measures (mean, median, standard deviation, skew) 9

10 1. Deciding What is Important Sensitivity Analysis should be performed that combines both the size of the uncertainty in parameters with the influence that the parameter has on output For analytic models with little interaction of input parameters we can use partial derivatives to estimate the parameter influence and define the local sensitivity as S local 2 i = σ y xi x i xi =x i The most robust way to decide what is important is to do a global sensitivity analysis that includes the entire parameter space and nonlinear interactions This works for linear and non-linear models with either small or large uncertainties in individual parameters and with strong parameter interaction The first order sensitivity index, S i, and total sensitivity, S ti, are given by S i = V E y x i V y S ti = 1 V E y x i V y where E and V are the mean and variance operators and E[y x i ] is the mean of y given variation in x i and E[y x i ] is the mean of y given variation in all parameters but x i 10

11 3. Propagation of Uncertainty For models with analytic equations and small independent random uncertainty one can use the analytic equation for propagation of uncertainties u(x i ) and covariances u(x i, x j ) (if inputs are correlated) y = f x 1, x 2, x n with known covariances u(x i, x j ) u 2 y = n i=1 n j=1 f f x i x j u 2 x i, x j This method is only accurate if the u(x i, x j ) are small and a simple variance characterizes the uncertainty well The distribution of uncertainty in y is assumed to be Gaussian with a mean of y = f x 1, x 2, x n and variance u(y) 11

12 3. Propagation of Uncertainty For other cases one will usually use numerical methods to propagate uncertainty (Monte Carlo, Important Sampling) x 1 x 2 x n f x 1, x 2, x n y This method requires one to define uncertainty probability distribution functions (PDF) for the model inputs The propagation can be very computationally intensive for many inputs and hard to compute models 12

13 Implementing Monte Carlo: It s All in the Details Careful choice of input uncertainty sampling can make all the difference between fast and slow convergence. Use Latin Hypercube Sampling or Quasirandom numbers whenever practical they almost always converge much faster These methods break CDF into equal probability regions and choose samples from each region rather than completely randomly Example of PDF generated from sampling a Triangle Distribution 300 times 13

14 P(x) F(X) 4. Analyzing the Results Once we have the PDF, P x, we can do a lot of other things including: Calculate the Cumulative Density Function, F X, from the PDF, P x X F x = P X dx x= Get simple statistics (mean, standard deviation, median, mode, etc) x = xp x dx, σ 2 = x x 2 P(x)dx median = F 0.5, mode = max P x Determine confidence intervals for true risk analysis The 5% 95% interval is X 1 to X 2 where F X 1 = 0.05 and F X 2 =

15 2. Characterizing Uncertainty This is often the most difficult part of the whole process. How do we estimate the uncertainty of a parameter? Expert Judgment Most common method but subject to wide variations, individual biases, mistakes Analysis of many independent measurements of the same quantity Results of interlab material testing Uncertainty bounds on measurement standards Check the measurement standard see what info it gives about uncertainty and repeatability Physical Limitations Mother nature has thankfully limited many quantities. Use fundamental physics (conservation of mass and energy) to help you put bounds on some quantities Information Theory Use methods like Maximum Entropy to develop conservative input PDFs from minimal information 15

16 Some Recent Applications Of Uncertainty Vorlander investigated the effect of audience and wall absorption uncertainty on RT, G, and C80 Predictions He ran only 20 Monte Carlo runs so the sampling from the input PDF and resulting output PDFs are fairly ragged Note: Use of Latin Hypercube sampling probably would have improved convergence Vorlander, 2013, JASA 133 (3),

17 More Recent Applications Reynders utilized maximum entropy method to determine PDF for loss factors used in Transmission Loss predictions I think this is a very important new technique for acoustics Input PDF for Block Walls Loss Factor Output PDF for Block Wall TL Reynders, 2014, JASA 135 (4),

18 So Who Do You Wanna Be? Mr. Slick? Midband RT of 0.8 seconds and STI of 0.8. I Guarantee It! Ms. Thoughtful? Midband RT between 0.9 and 0.95 seconds, STI between 0.65 and 0.9 with 95% certainty. BEDTR: Better Decisions + Better Technology = Better Buildings 18

19 Thank you. Questions? Ralph Muehleisen

Guide to the Expression of Uncertainty in Measurement (GUM) and its supplemental guides

Guide to the Expression of Uncertainty in Measurement (GUM) and its supplemental guides National Physical Laboratory Guide to the Expression of Uncertainty in Measurement (GUM) and its supplemental guides Maurice Cox National Physical Laboratory, UK maurice.cox@npl.co.uk http://www.npl.co.uk/ssfm/index.html

More information

Science. Approaches to measurement uncertainty evaluation. Introduction. for a safer world 28/05/2017. S L R Ellison LGC Limited, Teddington, UK

Science. Approaches to measurement uncertainty evaluation. Introduction. for a safer world 28/05/2017. S L R Ellison LGC Limited, Teddington, UK Approaches to measurement uncertainty evaluation S L R Ellison LGC Limited, Teddington, UK Science for a safer world 1 Introduction Basic principles a reminder Uncertainty from a measurement equation Gradient

More information

Part I. Experimental Error

Part I. Experimental Error Part I. Experimental Error 1 Types of Experimental Error. There are always blunders, mistakes, and screwups; such as: using the wrong material or concentration, transposing digits in recording scale readings,

More information

Monte Carlo Integration. Computer Graphics CMU /15-662, Fall 2016

Monte Carlo Integration. Computer Graphics CMU /15-662, Fall 2016 Monte Carlo Integration Computer Graphics CMU 15-462/15-662, Fall 2016 Talk Announcement Jovan Popovic, Senior Principal Scientist at Adobe Research will be giving a seminar on Character Animator -- Monday

More information

Estimation of uncertainties using the Guide to the expression of uncertainty (GUM)

Estimation of uncertainties using the Guide to the expression of uncertainty (GUM) Estimation of uncertainties using the Guide to the expression of uncertainty (GUM) Alexandr Malusek Division of Radiological Sciences Department of Medical and Health Sciences Linköping University 2014-04-15

More information

If we want to analyze experimental or simulated data we might encounter the following tasks:

If we want to analyze experimental or simulated data we might encounter the following tasks: Chapter 1 Introduction If we want to analyze experimental or simulated data we might encounter the following tasks: Characterization of the source of the signal and diagnosis Studying dependencies Prediction

More information

Fourier and Stats / Astro Stats and Measurement : Stats Notes

Fourier and Stats / Astro Stats and Measurement : Stats Notes Fourier and Stats / Astro Stats and Measurement : Stats Notes Andy Lawrence, University of Edinburgh Autumn 2013 1 Probabilities, distributions, and errors Laplace once said Probability theory is nothing

More information

Probability theory. References:

Probability theory. References: Reasoning Under Uncertainty References: Probability theory Mathematical methods in artificial intelligence, Bender, Chapter 7. Expert systems: Principles and programming, g, Giarratano and Riley, pag.

More information

Uncertainty due to Finite Resolution Measurements

Uncertainty due to Finite Resolution Measurements Uncertainty due to Finite Resolution Measurements S.D. Phillips, B. Tolman, T.W. Estler National Institute of Standards and Technology Gaithersburg, MD 899 Steven.Phillips@NIST.gov Abstract We investigate

More information

Statistics and Data Analysis

Statistics and Data Analysis Statistics and Data Analysis The Crash Course Physics 226, Fall 2013 "There are three kinds of lies: lies, damned lies, and statistics. Mark Twain, allegedly after Benjamin Disraeli Statistics and Data

More information

Basics of Uncertainty Analysis

Basics of Uncertainty Analysis Basics of Uncertainty Analysis Chapter Six Basics of Uncertainty Analysis 6.1 Introduction As shown in Fig. 6.1, analysis models are used to predict the performances or behaviors of a product under design.

More information

Introduction to Statistics and Error Analysis

Introduction to Statistics and Error Analysis Introduction to Statistics and Error Analysis Physics116C, 4/3/06 D. Pellett References: Data Reduction and Error Analysis for the Physical Sciences by Bevington and Robinson Particle Data Group notes

More information

* Tuesday 17 January :30-16:30 (2 hours) Recored on ESSE3 General introduction to the course.

* Tuesday 17 January :30-16:30 (2 hours) Recored on ESSE3 General introduction to the course. Name of the course Statistical methods and data analysis Audience The course is intended for students of the first or second year of the Graduate School in Materials Engineering. The aim of the course

More information

Monte Carlo uncertainty estimation for wavelength calibration Abstract

Monte Carlo uncertainty estimation for wavelength calibration Abstract Monte Carlo uncertainty estimation for wavelength calibration *Thang H.L., Nguyen D.D., Dung.D.N. Vietnam metrology institute 8 Hoang Quoc Viet street, Cau Giay district, Hanoi city, Vietnam * thanglh@vmi.gov.vn

More information

Physics 509: Error Propagation, and the Meaning of Error Bars. Scott Oser Lecture #10

Physics 509: Error Propagation, and the Meaning of Error Bars. Scott Oser Lecture #10 Physics 509: Error Propagation, and the Meaning of Error Bars Scott Oser Lecture #10 1 What is an error bar? Someone hands you a plot like this. What do the error bars indicate? Answer: you can never be

More information

F denotes cumulative density. denotes probability density function; (.)

F denotes cumulative density. denotes probability density function; (.) BAYESIAN ANALYSIS: FOREWORDS Notation. System means the real thing and a model is an assumed mathematical form for the system.. he probability model class M contains the set of the all admissible models

More information

Measurement And Uncertainty

Measurement And Uncertainty Measurement And Uncertainty Based on Guidelines for Evaluating and Expressing the Uncertainty of NIST Measurement Results, NIST Technical Note 1297, 1994 Edition PHYS 407 1 Measurement approximates or

More information

Bayes Decision Theory

Bayes Decision Theory Bayes Decision Theory Minimum-Error-Rate Classification Classifiers, Discriminant Functions and Decision Surfaces The Normal Density 0 Minimum-Error-Rate Classification Actions are decisions on classes

More information

Logistic Regression Review Fall 2012 Recitation. September 25, 2012 TA: Selen Uguroglu

Logistic Regression Review Fall 2012 Recitation. September 25, 2012 TA: Selen Uguroglu Logistic Regression Review 10-601 Fall 2012 Recitation September 25, 2012 TA: Selen Uguroglu!1 Outline Decision Theory Logistic regression Goal Loss function Inference Gradient Descent!2 Training Data

More information

Modeling Uncertainty in the Earth Sciences Jef Caers Stanford University

Modeling Uncertainty in the Earth Sciences Jef Caers Stanford University Probability theory and statistical analysis: a review Modeling Uncertainty in the Earth Sciences Jef Caers Stanford University Concepts assumed known Histograms, mean, median, spread, quantiles Probability,

More information

Unsupervised Learning Methods

Unsupervised Learning Methods Structural Health Monitoring Using Statistical Pattern Recognition Unsupervised Learning Methods Keith Worden and Graeme Manson Presented by Keith Worden The Structural Health Monitoring Process 1. Operational

More information

BRIDGE CIRCUITS EXPERIMENT 5: DC AND AC BRIDGE CIRCUITS 10/2/13

BRIDGE CIRCUITS EXPERIMENT 5: DC AND AC BRIDGE CIRCUITS 10/2/13 EXPERIMENT 5: DC AND AC BRIDGE CIRCUITS 0//3 This experiment demonstrates the use of the Wheatstone Bridge for precise resistance measurements and the use of error propagation to determine the uncertainty

More information

Physics 509: Bootstrap and Robust Parameter Estimation

Physics 509: Bootstrap and Robust Parameter Estimation Physics 509: Bootstrap and Robust Parameter Estimation Scott Oser Lecture #20 Physics 509 1 Nonparametric parameter estimation Question: what error estimate should you assign to the slope and intercept

More information

Know Your Uncertainty

Know Your Uncertainty April 2000 METROLOGY Know Your Uncertainty Understanding and documenting measurement uncertainty is key to gage calibration. By Henrik S. Nielsen, Ph.D. The process of developing uncertainty budgets requires

More information

Bayesian analysis in nuclear physics

Bayesian analysis in nuclear physics Bayesian analysis in nuclear physics Ken Hanson T-16, Nuclear Physics; Theoretical Division Los Alamos National Laboratory Tutorials presented at LANSCE Los Alamos Neutron Scattering Center July 25 August

More information

However, reliability analysis is not limited to calculation of the probability of failure.

However, reliability analysis is not limited to calculation of the probability of failure. Probabilistic Analysis probabilistic analysis methods, including the first and second-order reliability methods, Monte Carlo simulation, Importance sampling, Latin Hypercube sampling, and stochastic expansions

More information

Markov chain Monte Carlo methods in atmospheric remote sensing

Markov chain Monte Carlo methods in atmospheric remote sensing 1 / 45 Markov chain Monte Carlo methods in atmospheric remote sensing Johanna Tamminen johanna.tamminen@fmi.fi ESA Summer School on Earth System Monitoring and Modeling July 3 Aug 11, 212, Frascati July,

More information

Guide to the Expression of Uncertainty in Measurement Supplement 1 Numerical Methods for the Propagation of Distributions

Guide to the Expression of Uncertainty in Measurement Supplement 1 Numerical Methods for the Propagation of Distributions Guide to the Expression of Uncertainty in Measurement Supplement 1 Numerical Methods for the Propagation of Distributions This version is intended for circulation to the member organizations of the JCGM

More information

Inferring from data. Theory of estimators

Inferring from data. Theory of estimators Inferring from data Theory of estimators 1 Estimators Estimator is any function of the data e(x) used to provide an estimate ( a measurement ) of an unknown parameter. Because estimators are functions

More information

Lab 1: Measurement, Uncertainty, and Uncertainty Propagation

Lab 1: Measurement, Uncertainty, and Uncertainty Propagation Lab 1: Measurement, Uncertainty, and Uncertainty Propagation 17 ame Date Partners TA Section Lab 1: Measurement, Uncertainty, and Uncertainty Propagation The first principle is that you must not fool yourself

More information

Unit 4. Statistics, Detection Limits and Uncertainty. Experts Teaching from Practical Experience

Unit 4. Statistics, Detection Limits and Uncertainty. Experts Teaching from Practical Experience Unit 4 Statistics, Detection Limits and Uncertainty Experts Teaching from Practical Experience Unit 4 Topics Statistical Analysis Detection Limits Decision thresholds & detection levels Instrument Detection

More information

BAYESIAN DECISION THEORY

BAYESIAN DECISION THEORY Last updated: September 17, 2012 BAYESIAN DECISION THEORY Problems 2 The following problems from the textbook are relevant: 2.1 2.9, 2.11, 2.17 For this week, please at least solve Problem 2.3. We will

More information

Monte Carlo Simulations

Monte Carlo Simulations Monte Carlo Simulations What are Monte Carlo Simulations and why ones them? Pseudo Random Number generators Creating a realization of a general PDF The Bootstrap approach A real life example: LOFAR simulations

More information

Supervised Learning: Non-parametric Estimation

Supervised Learning: Non-parametric Estimation Supervised Learning: Non-parametric Estimation Edmondo Trentin March 18, 2018 Non-parametric Estimates No assumptions are made on the form of the pdfs 1. There are 3 major instances of non-parametric estimates:

More information

A Probability Primer. A random walk down a probabilistic path leading to some stochastic thoughts on chance events and uncertain outcomes.

A Probability Primer. A random walk down a probabilistic path leading to some stochastic thoughts on chance events and uncertain outcomes. A Probability Primer A random walk down a probabilistic path leading to some stochastic thoughts on chance events and uncertain outcomes. Are you holding all the cards?? Random Events A random event, E,

More information

Treatment of Error in Experimental Measurements

Treatment of Error in Experimental Measurements in Experimental Measurements All measurements contain error. An experiment is truly incomplete without an evaluation of the amount of error in the results. In this course, you will learn to use some common

More information

Combining Interval and Probabilistic Uncertainty in Engineering Applications

Combining Interval and Probabilistic Uncertainty in Engineering Applications Combining Interval and Probabilistic Uncertainty in Engineering Applications Andrew Pownuk Computational Science Program University of Texas at El Paso El Paso, Texas 79968, USA ampownuk@utep.edu Page

More information

16 : Markov Chain Monte Carlo (MCMC)

16 : Markov Chain Monte Carlo (MCMC) 10-708: Probabilistic Graphical Models 10-708, Spring 2014 16 : Markov Chain Monte Carlo MCMC Lecturer: Matthew Gormley Scribes: Yining Wang, Renato Negrinho 1 Sampling from low-dimensional distributions

More information

Suggestions for Making Useful the Uncertainty Quantification Results from CFD Applications

Suggestions for Making Useful the Uncertainty Quantification Results from CFD Applications Suggestions for Making Useful the Uncertainty Quantification Results from CFD Applications Thomas A. Zang tzandmands@wildblue.net Aug. 8, 2012 CFD Futures Conference: Zang 1 Context The focus of this presentation

More information

Modeling Measurement Uncertainty in Room Acoustics P. Dietrich

Modeling Measurement Uncertainty in Room Acoustics P. Dietrich Modeling Measurement Uncertainty in Room Acoustics P. Dietrich This paper investigates a way of determining and modeling uncertainty contributions in measurements of room acoustic parameters, which are

More information

Application Note AN37. Noise Histogram Analysis. by John Lis

Application Note AN37. Noise Histogram Analysis. by John Lis AN37 Application Note Noise Histogram Analysis by John Lis NOISELESS, IDEAL CONVERTER OFFSET ERROR σ RMS NOISE HISTOGRAM OF SAMPLES PROBABILITY DISTRIBUTION FUNCTION X PEAK-TO-PEAK NOISE Crystal Semiconductor

More information

Practical Statistics for the Analytical Scientist Table of Contents

Practical Statistics for the Analytical Scientist Table of Contents Practical Statistics for the Analytical Scientist Table of Contents Chapter 1 Introduction - Choosing the Correct Statistics 1.1 Introduction 1.2 Choosing the Right Statistical Procedures 1.2.1 Planning

More information

Statistics for Data Analysis. Niklaus Berger. PSI Practical Course Physics Institute, University of Heidelberg

Statistics for Data Analysis. Niklaus Berger. PSI Practical Course Physics Institute, University of Heidelberg Statistics for Data Analysis PSI Practical Course 2014 Niklaus Berger Physics Institute, University of Heidelberg Overview You are going to perform a data analysis: Compare measured distributions to theoretical

More information

Why is the field of statistics still an active one?

Why is the field of statistics still an active one? Why is the field of statistics still an active one? It s obvious that one needs statistics: to describe experimental data in a compact way, to compare datasets, to ask whether data are consistent with

More information

Determination of Uncertainties for Correlated Input Quantities by the Monte Carlo Method

Determination of Uncertainties for Correlated Input Quantities by the Monte Carlo Method Determination of Uncertainties for Correlated Input Quantities by the Monte Carlo Method Marcel Goliaš 1, Rudolf Palenčár 1 1 Department of Automation, Measurement and Applied Informatics, Faculty of Mechanical

More information

AE2160 Introduction to Experimental Methods in Aerospace

AE2160 Introduction to Experimental Methods in Aerospace AE160 Introduction to Experimental Methods in Aerospace Uncertainty Analysis C.V. Di Leo (Adapted from slides by J.M. Seitzman, J.J. Rimoli) 1 Accuracy and Precision Accuracy is defined as the difference

More information

Introduction to Error Analysis

Introduction to Error Analysis Introduction to Error Analysis Part 1: the Basics Andrei Gritsan based on lectures by Petar Maksimović February 1, 2010 Overview Definitions Reporting results and rounding Accuracy vs precision systematic

More information

Brandon C. Kelly (Harvard Smithsonian Center for Astrophysics)

Brandon C. Kelly (Harvard Smithsonian Center for Astrophysics) Brandon C. Kelly (Harvard Smithsonian Center for Astrophysics) Probability quantifies randomness and uncertainty How do I estimate the normalization and logarithmic slope of a X ray continuum, assuming

More information

Statistics, Probability Distributions & Error Propagation. James R. Graham

Statistics, Probability Distributions & Error Propagation. James R. Graham Statistics, Probability Distributions & Error Propagation James R. Graham Sample & Parent Populations Make measurements x x In general do not expect x = x But as you take more and more measurements a pattern

More information

Multivariate Distributions

Multivariate Distributions Copyright Cosma Rohilla Shalizi; do not distribute without permission updates at http://www.stat.cmu.edu/~cshalizi/adafaepov/ Appendix E Multivariate Distributions E.1 Review of Definitions Let s review

More information

What is measurement uncertainty?

What is measurement uncertainty? What is measurement uncertainty? What is measurement uncertainty? Introduction Whenever a measurement is made, the result obtained is only an estimate of the true value of the property being measured.

More information

Statistical Methods for Astronomy

Statistical Methods for Astronomy Statistical Methods for Astronomy Probability (Lecture 1) Statistics (Lecture 2) Why do we need statistics? Useful Statistics Definitions Error Analysis Probability distributions Error Propagation Binomial

More information

Monte Carlo Studies. The response in a Monte Carlo study is a random variable.

Monte Carlo Studies. The response in a Monte Carlo study is a random variable. Monte Carlo Studies The response in a Monte Carlo study is a random variable. The response in a Monte Carlo study has a variance that comes from the variance of the stochastic elements in the data-generating

More information

The Monte Carlo method what and how?

The Monte Carlo method what and how? A top down approach in measurement uncertainty estimation the Monte Carlo simulation By Yeoh Guan Huah GLP Consulting, Singapore (http://consultglp.com) Introduction The Joint Committee for Guides in Metrology

More information

2D Image Processing (Extended) Kalman and particle filter

2D Image Processing (Extended) Kalman and particle filter 2D Image Processing (Extended) Kalman and particle filter Prof. Didier Stricker Dr. Gabriele Bleser Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz

More information

Stochastic Subgradient Methods

Stochastic Subgradient Methods Stochastic Subgradient Methods Stephen Boyd and Almir Mutapcic Notes for EE364b, Stanford University, Winter 26-7 April 13, 28 1 Noisy unbiased subgradient Suppose f : R n R is a convex function. We say

More information

Probability & Statistics: Introduction. Robert Leishman Mark Colton ME 363 Spring 2011

Probability & Statistics: Introduction. Robert Leishman Mark Colton ME 363 Spring 2011 Probability & Statistics: Introduction Robert Leishman Mark Colton ME 363 Spring 2011 Why do we care? Why do we care about probability and statistics in an instrumentation class? Example Measure the strength

More information

The Gaussian distribution

The Gaussian distribution The Gaussian distribution Probability density function: A continuous probability density function, px), satisfies the following properties:. The probability that x is between two points a and b b P a

More information

Data Analysis I. Dr Martin Hendry, Dept of Physics and Astronomy University of Glasgow, UK. 10 lectures, beginning October 2006

Data Analysis I. Dr Martin Hendry, Dept of Physics and Astronomy University of Glasgow, UK. 10 lectures, beginning October 2006 Astronomical p( y x, I) p( x, I) p ( x y, I) = p( y, I) Data Analysis I Dr Martin Hendry, Dept of Physics and Astronomy University of Glasgow, UK 10 lectures, beginning October 2006 4. Monte Carlo Methods

More information

Systematic bias in pro rata allocation schemes

Systematic bias in pro rata allocation schemes Systematic bias in pro rata allocation schemes Armin Pobitzer Ranveig Nygaard Bjørk Astrid Marie Skålvik Christian Michelsen Research AS, Bergen, Norway ABSTRACT Misallocation due to allocation uncertainty

More information

Load-Strength Interference

Load-Strength Interference Load-Strength Interference Loads vary, strengths vary, and reliability usually declines for mechanical systems, electronic systems, and electrical systems. The cause of failures is a load-strength interference

More information

Robert Collins CSE586, PSU Intro to Sampling Methods

Robert Collins CSE586, PSU Intro to Sampling Methods Intro to Sampling Methods CSE586 Computer Vision II Penn State Univ Topics to be Covered Monte Carlo Integration Sampling and Expected Values Inverse Transform Sampling (CDF) Ancestral Sampling Rejection

More information

Basic Probability Reference Sheet

Basic Probability Reference Sheet February 27, 2001 Basic Probability Reference Sheet 17.846, 2001 This is intended to be used in addition to, not as a substitute for, a textbook. X is a random variable. This means that X is a variable

More information

Sensor Tasking and Control

Sensor Tasking and Control Sensor Tasking and Control Sensing Networking Leonidas Guibas Stanford University Computation CS428 Sensor systems are about sensing, after all... System State Continuous and Discrete Variables The quantities

More information

CHAPTER 9: TREATING EXPERIMENTAL DATA: ERRORS, MISTAKES AND SIGNIFICANCE (Written by Dr. Robert Bretz)

CHAPTER 9: TREATING EXPERIMENTAL DATA: ERRORS, MISTAKES AND SIGNIFICANCE (Written by Dr. Robert Bretz) CHAPTER 9: TREATING EXPERIMENTAL DATA: ERRORS, MISTAKES AND SIGNIFICANCE (Written by Dr. Robert Bretz) In taking physical measurements, the true value is never known with certainty; the value obtained

More information

Assume that you have made n different measurements of a quantity x. Usually the results of these measurements will vary; call them x 1

Assume that you have made n different measurements of a quantity x. Usually the results of these measurements will vary; call them x 1 #1 $ http://www.physics.fsu.edu/users/ng/courses/phy2048c/lab/appendixi/app1.htm Appendix I: Estimates for the Reliability of Measurements In any measurement there is always some error or uncertainty in

More information

Asymptotic distribution of the sample average value-at-risk

Asymptotic distribution of the sample average value-at-risk Asymptotic distribution of the sample average value-at-risk Stoyan V. Stoyanov Svetlozar T. Rachev September 3, 7 Abstract In this paper, we prove a result for the asymptotic distribution of the sample

More information

Introduction to Statistical Methods for High Energy Physics

Introduction to Statistical Methods for High Energy Physics Introduction to Statistical Methods for High Energy Physics 2011 CERN Summer Student Lectures Glen Cowan Physics Department Royal Holloway, University of London g.cowan@rhul.ac.uk www.pp.rhul.ac.uk/~cowan

More information

Introduction to Systems Analysis and Decision Making Prepared by: Jakub Tomczak

Introduction to Systems Analysis and Decision Making Prepared by: Jakub Tomczak Introduction to Systems Analysis and Decision Making Prepared by: Jakub Tomczak 1 Introduction. Random variables During the course we are interested in reasoning about considered phenomenon. In other words,

More information

Independent Component Analysis for Redundant Sensor Validation

Independent Component Analysis for Redundant Sensor Validation Independent Component Analysis for Redundant Sensor Validation Jun Ding, J. Wesley Hines, Brandon Rasmussen The University of Tennessee Nuclear Engineering Department Knoxville, TN 37996-2300 E-mail: hines2@utk.edu

More information

Inverse problems and uncertainty quantification in remote sensing

Inverse problems and uncertainty quantification in remote sensing 1 / 38 Inverse problems and uncertainty quantification in remote sensing Johanna Tamminen Finnish Meterological Institute johanna.tamminen@fmi.fi ESA Earth Observation Summer School on Earth System Monitoring

More information

Lecture 32. Lidar Error and Sensitivity Analysis

Lecture 32. Lidar Error and Sensitivity Analysis Lecture 3. Lidar Error and Sensitivity Analysis Introduction Accuracy in lidar measurements Precision in lidar measurements Error analysis for Na Doppler lidar Sensitivity analysis Summary 1 Errors vs.

More information

Introduction to Design of Experiments

Introduction to Design of Experiments Introduction to Design of Experiments Jean-Marc Vincent and Arnaud Legrand Laboratory ID-IMAG MESCAL Project Universities of Grenoble {Jean-Marc.Vincent,Arnaud.Legrand}@imag.fr November 20, 2011 J.-M.

More information

Statistical Methods in Particle Physics

Statistical Methods in Particle Physics Statistical Methods in Particle Physics Lecture 11 January 7, 2013 Silvia Masciocchi, GSI Darmstadt s.masciocchi@gsi.de Winter Semester 2012 / 13 Outline How to communicate the statistical uncertainty

More information

Joint Probability Distributions and Random Samples (Devore Chapter Five)

Joint Probability Distributions and Random Samples (Devore Chapter Five) Joint Probability Distributions and Random Samples (Devore Chapter Five) 1016-345-01: Probability and Statistics for Engineers Spring 2013 Contents 1 Joint Probability Distributions 2 1.1 Two Discrete

More information

Structural Reliability

Structural Reliability Structural Reliability Thuong Van DANG May 28, 2018 1 / 41 2 / 41 Introduction to Structural Reliability Concept of Limit State and Reliability Review of Probability Theory First Order Second Moment Method

More information

SHIFTED UP COSINE FUNCTION AS MODEL OF PROBABILITY DISTRIBUTION

SHIFTED UP COSINE FUNCTION AS MODEL OF PROBABILITY DISTRIBUTION IMEKO World Congress Fundamental and Applied Metrology September 6 11, 009, Lisbon, Portugal SHIFTED UP COSINE FUNCTION AS MODEL OF PROBABILITY DISTRIBUTION Zygmunt Lech Warsza 1, Marian Jerzy Korczynski,

More information

Jerry Gilfoyle The Hydrogen Optical Spectrum 1 / 15

Jerry Gilfoyle The Hydrogen Optical Spectrum 1 / 15 Jerry Gilfoyle The Hydrogen Optical Spectrum 1 / 15 What holds atoms together? Jerry Gilfoyle The Hydrogen Optical Spectrum 1 / 15 What holds atoms together? How do we know? Jerry Gilfoyle The Hydrogen

More information

Semester , Example Exam 1

Semester , Example Exam 1 Semester 1 2017, Example Exam 1 1 of 10 Instructions The exam consists of 4 questions, 1-4. Each question has four items, a-d. Within each question: Item (a) carries a weight of 8 marks. Item (b) carries

More information

Measurements and Errors

Measurements and Errors 1 Measurements and Errors If you are asked to measure the same object two different times, there is always a possibility that the two measurements may not be exactly the same. Then the difference between

More information

Gaussian processes. Chuong B. Do (updated by Honglak Lee) November 22, 2008

Gaussian processes. Chuong B. Do (updated by Honglak Lee) November 22, 2008 Gaussian processes Chuong B Do (updated by Honglak Lee) November 22, 2008 Many of the classical machine learning algorithms that we talked about during the first half of this course fit the following pattern:

More information

A suggested method to be used to measure scattering coefficients of full scale samples.

A suggested method to be used to measure scattering coefficients of full scale samples. A suggested method to be used to measure scattering coefficients of full scale samples. Ronald Sauro a Michael Vargas b NWAA Labs, Inc 25132 Rye Canyon Loop Santa Clarita, CA 91355 USA ABSTRACT In attempting

More information

Basic Statistical Tools

Basic Statistical Tools Structural Health Monitoring Using Statistical Pattern Recognition Basic Statistical Tools Presented by Charles R. Farrar, Ph.D., P.E. Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants

More information

A Polynomial Chaos Approach to Robust Multiobjective Optimization

A Polynomial Chaos Approach to Robust Multiobjective Optimization A Polynomial Chaos Approach to Robust Multiobjective Optimization Silvia Poles 1, Alberto Lovison 2 1 EnginSoft S.p.A., Optimization Consulting Via Giambellino, 7 35129 Padova, Italy s.poles@enginsoft.it

More information

Why Correlation Matters in Cost Estimating

Why Correlation Matters in Cost Estimating Why Correlation Matters in Cost Estimating Stephen A. Book The Aerospace Corporation P.O. Box 92957 Los Angeles, CA 90009-29597 (310) 336-8655 stephen.a.book@aero.org 32nd Annual DoD Cost Analysis Symposium

More information

DEEP LEARNING CHAPTER 3 PROBABILITY & INFORMATION THEORY

DEEP LEARNING CHAPTER 3 PROBABILITY & INFORMATION THEORY DEEP LEARNING CHAPTER 3 PROBABILITY & INFORMATION THEORY OUTLINE 3.1 Why Probability? 3.2 Random Variables 3.3 Probability Distributions 3.4 Marginal Probability 3.5 Conditional Probability 3.6 The Chain

More information

Math Review Sheet, Fall 2008

Math Review Sheet, Fall 2008 1 Descriptive Statistics Math 3070-5 Review Sheet, Fall 2008 First we need to know about the relationship among Population Samples Objects The distribution of the population can be given in one of the

More information

Lecture 23. Lidar Error and Sensitivity Analysis (2)

Lecture 23. Lidar Error and Sensitivity Analysis (2) Lecture 3. Lidar Error and Sensitivity Analysis ) q Derivation of Errors q Background vs. Noise q Sensitivity Analysis q Summary 1 Accuracy vs. Precision in Lidar Measurements q The precision errors caused

More information

Review of Probability Theory

Review of Probability Theory Review of Probability Theory Arian Maleki and Tom Do Stanford University Probability theory is the study of uncertainty Through this class, we will be relying on concepts from probability theory for deriving

More information

Gaussian Process Approximations of Stochastic Differential Equations

Gaussian Process Approximations of Stochastic Differential Equations Gaussian Process Approximations of Stochastic Differential Equations Cédric Archambeau Centre for Computational Statistics and Machine Learning University College London c.archambeau@cs.ucl.ac.uk CSML

More information

Introduction. Chapter 1

Introduction. Chapter 1 Chapter 1 Introduction In this book we will be concerned with supervised learning, which is the problem of learning input-output mappings from empirical data (the training dataset). Depending on the characteristics

More information

Pattern Recognition 2

Pattern Recognition 2 Pattern Recognition 2 KNN,, Dr. Terence Sim School of Computing National University of Singapore Outline 1 2 3 4 5 Outline 1 2 3 4 5 The Bayes Classifier is theoretically optimum. That is, prob. of error

More information

Introduction to statistics. Laurent Eyer Maria Suveges, Marie Heim-Vögtlin SNSF grant

Introduction to statistics. Laurent Eyer Maria Suveges, Marie Heim-Vögtlin SNSF grant Introduction to statistics Laurent Eyer Maria Suveges, Marie Heim-Vögtlin SNSF grant Recent history at the Observatory Request of something on statistics from PhD students, because of an impression of

More information

CSCI567 Machine Learning (Fall 2014)

CSCI567 Machine Learning (Fall 2014) CSCI567 Machine Learning (Fall 24) Drs. Sha & Liu {feisha,yanliu.cs}@usc.edu October 2, 24 Drs. Sha & Liu ({feisha,yanliu.cs}@usc.edu) CSCI567 Machine Learning (Fall 24) October 2, 24 / 24 Outline Review

More information

Keywords: Sonic boom analysis, Atmospheric uncertainties, Uncertainty quantification, Monte Carlo method, Polynomial chaos method.

Keywords: Sonic boom analysis, Atmospheric uncertainties, Uncertainty quantification, Monte Carlo method, Polynomial chaos method. Blucher Mechanical Engineering Proceedings May 2014, vol. 1, num. 1 www.proceedings.blucher.com.br/evento/10wccm SONIC BOOM ANALYSIS UNDER ATMOSPHERIC UNCERTAINTIES BY A NON-INTRUSIVE POLYNOMIAL CHAOS

More information

Take the measurement of a person's height as an example. Assuming that her height has been determined to be 5' 8", how accurate is our result?

Take the measurement of a person's height as an example. Assuming that her height has been determined to be 5' 8, how accurate is our result? Error Analysis Introduction The knowledge we have of the physical world is obtained by doing experiments and making measurements. It is important to understand how to express such data and how to analyze

More information

The Instability of Correlations: Measurement and the Implications for Market Risk

The Instability of Correlations: Measurement and the Implications for Market Risk The Instability of Correlations: Measurement and the Implications for Market Risk Prof. Massimo Guidolin 20254 Advanced Quantitative Methods for Asset Pricing and Structuring Winter/Spring 2018 Threshold

More information

Revision of the Guide to the expression of uncertainty in measurement impact on national metrology institutes and industry

Revision of the Guide to the expression of uncertainty in measurement impact on national metrology institutes and industry Revision of the Guide to the expression of uncertainty in measurement impact on national metrology institutes and industry Maurice Cox/Peter Harris National Physical Laboratory, Teddington, UK CCRI BIPM,

More information

ENSC327 Communications Systems 19: Random Processes. Jie Liang School of Engineering Science Simon Fraser University

ENSC327 Communications Systems 19: Random Processes. Jie Liang School of Engineering Science Simon Fraser University ENSC327 Communications Systems 19: Random Processes Jie Liang School of Engineering Science Simon Fraser University 1 Outline Random processes Stationary random processes Autocorrelation of random processes

More information

Robert Collins CSE586, PSU Intro to Sampling Methods

Robert Collins CSE586, PSU Intro to Sampling Methods Intro to Sampling Methods CSE586 Computer Vision II Penn State Univ Topics to be Covered Monte Carlo Integration Sampling and Expected Values Inverse Transform Sampling (CDF) Ancestral Sampling Rejection

More information