Modern Methods of Data Analysis - WS 07/08

Similar documents
Modern Methods of Data Analysis - WS 07/08

Physics 1140 Fall 2013 Introduction to Experimental Physics

PHYSICS 2150 LABORATORY

Uncertainty and Bias UIUC, 403 Advanced Physics Laboratory, Fall 2014

Statistics. Lent Term 2015 Prof. Mark Thomson. 2: The Gaussian Limit

PHYSICS 2150 LABORATORY

Measurements of a Table

PHY 123 Lab 1 - Error and Uncertainty and the Simple Pendulum

Data and Error analysis

Normal Distributions Rejection of Data + RLC Circuits. Lecture 4 Physics 2CL Summer 2011

Errors: What they are, and how to deal with them

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

Measurement and Uncertainty

LAB INFORMATION TFYA76 Mekanik

Physics 509: Propagating Systematic Uncertainties. Scott Oser Lecture #12

Averaging, Errors and Uncertainty

Physics 403. Segev BenZvi. Propagation of Uncertainties. Department of Physics and Astronomy University of Rochester

Lecture 2: Reporting, Using, and Calculating Uncertainties 2. v = 6050 ± 30 m/s. v = 6047 ± 3 m/s

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

Error analysis for IPhO contestants

PHYSICS 2150 EXPERIMENTAL MODERN PHYSICS. Lecture 3 Rejection of Data; Weighted Averages

Lab 1: Measurement, Uncertainty, and Uncertainty Propagation

Uncertainty, Measurement, and Models Overview Exp #1. Lecture # 2 Physics 2BL Summer Session I 2015

Statistics and Data Analysis

Data and Error Analysis

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

STATISTICS OF OBSERVATIONS & SAMPLING THEORY. Parent Distributions

Appendix C: Accuracy, Precision, and Uncertainty

Course Project. Physics I with Lab

Intermediate Lab PHYS 3870

Electromagnetism lab project

Uncertainty, Error, and Precision in Quantitative Measurements an Introduction 4.4 cm Experimental error

1 Measurement Uncertainties

Statistical Methods in Particle Physics

PHYS 352. On Measurement, Systematic and Statistical Errors. Errors in Measurement

Experiment 2: Projectile motion and conservation of energy

Measurements and Data Analysis

Error analysis for the physical sciences A course reader for phys 1140 Scott Pinegar and Markus Raschke Department of Physics, University of Colorado

The SuperBall Lab. Objective. Instructions

Lecture 10. Lidar Simulation and Error Analysis Overview (2)

Appendix B: Accuracy, Precision and Uncertainty

Introduction to the General Physics Laboratories

EM Waves in Media. What happens when an EM wave travels through our model material?

Physics 115 Experiment 1. Introduction to Measurement and Error Analysis (PHY 115 and 117)

University of Massachusetts Boston - Chemistry Department Physical Chemistry Laboratory Introduction to Maximum Probable Error

Error Analysis. V. Lorenz L. Yang, M. Grosse Perdekamp, D. Hertzog, R. Clegg PHYS403 Spring 2016

Electricity Designing a Voltmeter c 2 testing Review. Lecture # 7 Physics 2BL Summer 2011

Instrumentation & Measurement AAiT. Chapter 2. Measurement Error Analysis

Introduction to Data Analysis

Physics: Uncertainties - Student Material (AH) 1

Modern Methods of Data Analysis - WS 07/08

Typing Equations in MS Word 2010

ERRORS AND THE TREATMENT OF DATA

Lecture 5. G. Cowan Lectures on Statistical Data Analysis Lecture 5 page 1

Uncertainty, Measurement, and Models. Lecture 2 Physics 2CL Summer Session 2011

Appendix II Calculation of Uncertainties

Experiment 2. Reaction Time. Make a series of measurements of your reaction time. Use statistics to analyze your reaction time.

1 Measurement Uncertainties

BRIEF SURVEY OF UNCERTAINITY IN PHYSICS LABS

Introduction to 1118 Labs

Conservation of Momentum

Introduction to Statistics and Error Analysis

Advanced Statistical Methods. Lecture 6

EXPERIMENT: REACTION TIME

Statistical Methods in Particle Physics Lecture 1: Bayesian methods

PHYS 2211L - Principles of Physics Laboratory I Propagation of Errors Supplement

Name: Section #: Date: The Pendulum

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?

PHY 101L - Experiments in Mechanics

Lab 0 Appendix C L0-1 APPENDIX C ACCURACY OF MEASUREMENTS AND TREATMENT OF EXPERIMENTAL UNCERTAINTY

MEASUREMENTS AND ERRORS (OR EXPERIMENTAL UNCERTAINTIES)

BRIEF SURVEY OF UNCERTAINITY IN PHYSICS LABS

Introduction to Measurement

Experiment 1 Simple Measurements and Error Estimation

California State Science Fair

Physics 1140 Lecture 6: Gaussian Distributions

Experiment 2 Random Error and Basic Statistics

5 Error Propagation We start from eq , which shows the explicit dependence of g on the measured variables t and h. Thus.

Introduction to Measurements & Error Analysis

Uncertainties in AH Physics

Probability Density Functions

Introduction to Experiment: Part 1

More Probability and Error Analysis

Measurement: The Basics

Introduction to Statistical Methods for High Energy Physics

Modern Navigation. Thomas Herring

Statistical Methods in Particle Physics

Error Analysis How Do We Deal With Uncertainty In Science.

Lab 1: Measurement and Uncertainty

SPH3U UNIVERSITY PHYSICS

26, 24, 26, 28, 23, 23, 25, 24, 26, 25

arxiv:hep-ex/ v1 2 Jun 2000

THE COMPTON EFFECT Last Revised: January 5, 2007

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

Error Analysis and Graph Drawing

Methods and Tools of Physics

 ± σ A ± t A ˆB ± σ B ± t B. (1)

Conservation of Momentum

Experiment 2 Random Error and Basic Statistics

Physics 121, Spring 2008 Mechanics. Physics 121, Spring What are we going to talk about today? Physics 121, Spring Goal of the course.

Transcription:

Modern Methods of Data Analysis Lecture VIa (19.11.07) Contents: Uncertainties (II): Re: error propagation Correlated uncertainties Systematic uncertainties

Re: Error Propagation (I) x = Vi,j and µi known y(x) is function of first order Taylor expansion...

Re: Error Propagation (II)

Re: Gaussian error propagation Error estimates for functions of several correlated variables : Additional terms accounting Normal errors for correlations for uncorrelated variables Special case, uncorrelated variables: This is called Gaussian error propagation, however has nothing to do with Gaussian distributions Modern Methods of Data Analysis - WS 07/08

And the same in more dimensions (A is Jacobi matrix)

Be aware... The approximation using Taylor expansion breaks down if the function is significantly not linear in the region ± 1σ around the mean value. Example: momentum estimate in B field; p ~ 1/κ 10 % momentum bias!

2. Order Taylor Expansion

Example Systematic Error Measurements are taken with a steel ruler, the ruler was calibrated at 15C, but the measurements were carried out at 22C. This is a systematic mistake (bias) and not a systematic uncertainty! To neglect this effect is a systematic mistake. Effects can be corrected for! If the temperature coefficient and lab temperature is known (exactly), then there is no systematic uncertainty. If we correct for effect, but corrections are not known exactly, then we have to introduce a systematic uncertainty. In practice (unfortunately): often not corrected for such effects, but then just included in sys. errors.

Systematic Error Definition: A systematic error denotes the uncertainty in effects caused by systematic mistakes and caused by neglecting systematic mistakes A systematic mistake is not a systematic error. Comments on systematic errors: sys. error do NOT decrease with 1/ N statistical and systematic errors can in general be added in quadrature (if uncorrelated; else include correlations) need to quote them separately in the results, they are often correlated among experiments: m(b0) = 5279.63 ± 0.53 (stat) ± 0.33 (sys)

Combing Errors (I) Suppose you have two measurements, with a random (statistical) uncertainties and a common systematic error S. How to make the covariance matrix?

Combining Errors (II) Consider and as sum of three random variables: assign according uncertainties More extended case, three measurements with one common systematic uncertainty S, and one systematic uncertainty T common for two of the measurements

Example: Pendulum Measure length of bar by measuring period of pendelum. Take two time measurements at different temperature. Compute the difference in length: and associated uncertainties. Given statistical uncertainties on the time measurements, additional common systematic uncertainty on the time measurement ( )and common systematic uncertainty on g ( ).

Evaluating Systematic Errors (I) Distinguish systematic errors from known and from unsuspected sources known sources error on factors in the analysis, energy calibration, tracking efficiencies, corrections,... error on external input: theory error, error on branching ratios, masses, fragmentation evaluate systematic uncertainties from known sources s(i) on result R. take several typical assumptions on s(i), compute R for each of them. Compute standard deviation of R take two extreme assumptions, compute R. Take difference of results divided by 12

Evaluating Systematic Errors (II) Errors from unsuspected sources need first to be identified repeat the analysis in different form helps to find systematic effects vary the range of data used for extraction of the result, use subset of data change cuts, change histogram binning change parameterizations, change fit techniques look for impossibilities It is clearly wrong to add in quadrature resulting deviations from the check list as systematic error this is misconception Moreover, the more careful you are doing more checks, the bigger should your systematic be??? - No! Modern Methods of Data Analysis - WS 07/08

Evaluating Systematic Errors (III) define before the consistency checks a pass/fail criteria. Remember with 20 checks you expect on average one 2σ deviation. However uncertainties are highly correlated! if you do not expect a systematic effect a priori and if the deviation is not significant, then do not add this in the systematic error if there is a deviation, try to understand, where the mistake is in the analysis and fix it! only as a last resort include discrepancy in systematic error

Evaluating Systematic Errors (IV) Conservative estimate of uncertainties.. Physicists tend to overestimate their systematics: If we estimate them conservatively, we are save in case we have forgotten to evaluate one source. How can we be sure that this identified source is covered by the conservative uncertainties??!! This is (commonly used) non-sense.