CHAPTER VI Statistical Analysis of Experimental Data

Similar documents
Chapter 5 Properties of a Random Sample

Continuous Distributions

Lecture Notes Types of economic variables

Lecture 3. Sampling, sampling distributions, and parameter estimation

Summary of the lecture in Biostatistics

X ε ) = 0, or equivalently, lim

= 1. UCLA STAT 13 Introduction to Statistical Methods for the Life and Health Sciences. Parameters and Statistics. Measures of Centrality

ENGI 4421 Joint Probability Distributions Page Joint Probability Distributions [Navidi sections 2.5 and 2.6; Devore sections

2.28 The Wall Street Journal is probably referring to the average number of cubes used per glass measured for some population that they have chosen.

Functions of Random Variables

Module 7. Lecture 7: Statistical parameter estimation

MEASURES OF DISPERSION

Median as a Weighted Arithmetic Mean of All Sample Observations

UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS

best estimate (mean) for X uncertainty or error in the measurement (systematic, random or statistical) best

Lecture 3 Probability review (cont d)

Lecture 1 Review of Fundamental Statistical Concepts

Estimation of Stress- Strength Reliability model using finite mixture of exponential distributions

Module 7: Probability and Statistics

Chapter -2 Simple Random Sampling

22 Nonparametric Methods.

Point Estimation: definition of estimators

Simulation Output Analysis

Mean is only appropriate for interval or ratio scales, not ordinal or nominal.

f f... f 1 n n (ii) Median : It is the value of the middle-most observation(s).

Chapter -2 Simple Random Sampling

LECTURE - 4 SIMPLE RANDOM SAMPLING DR. SHALABH DEPARTMENT OF MATHEMATICS AND STATISTICS INDIAN INSTITUTE OF TECHNOLOGY KANPUR

Chapter 4 Multiple Random Variables

A Study of the Reproducibility of Measurements with HUR Leg Extension/Curl Research Line

UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS

Econometric Methods. Review of Estimation

Utts and Heckard. Why Study Statistics? Why Study Statistics? American Heritage College Dictionary, 3rd Ed.

LINEAR REGRESSION ANALYSIS

Introduction to local (nonparametric) density estimation. methods

Chapter 14 Logistic Regression Models

is the score of the 1 st student, x

GOALS The Samples Why Sample the Population? What is a Probability Sample? Four Most Commonly Used Probability Sampling Methods

Special Instructions / Useful Data

STATISTICAL PROPERTIES OF LEAST SQUARES ESTIMATORS. x, where. = y - ˆ " 1

STA 105-M BASIC STATISTICS (This is a multiple choice paper.)

Class 13,14 June 17, 19, 2015

( ) = ( ) ( ) Chapter 13 Asymptotic Theory and Stochastic Regressors. Stochastic regressors model

Statistics Descriptive and Inferential Statistics. Instructor: Daisuke Nagakura

X X X E[ ] E X E X. is the ()m n where the ( i,)th. j element is the mean of the ( i,)th., then

Outline. Point Pattern Analysis Part I. Revisit IRP/CSR

Chapter 4 Multiple Random Variables

STK4011 and STK9011 Autumn 2016

Lesson 3. Group and individual indexes. Design and Data Analysis in Psychology I English group (A) School of Psychology Dpt. Experimental Psychology

ρ < 1 be five real numbers. The

CHAPTER 3 POSTERIOR DISTRIBUTIONS

Arithmetic Mean Suppose there is only a finite number N of items in the system of interest. Then the population arithmetic mean is

Analysis of Variance with Weibull Data

A New Family of Transformations for Lifetime Data

{ }{ ( )} (, ) = ( ) ( ) ( ) Chapter 14 Exercises in Sampling Theory. Exercise 1 (Simple random sampling): Solution:

Chapter 8. Inferences about More Than Two Population Central Values

Handout #1. Title: Foundations of Econometrics. POPULATION vs. SAMPLE

PTAS for Bin-Packing

Random Variables and Probability Distributions

Parameter, Statistic and Random Samples

12.2 Estimating Model parameters Assumptions: ox and y are related according to the simple linear regression model

Lecture 7. Confidence Intervals and Hypothesis Tests in the Simple CLR Model

Measures of Dispersion


Lecture 1: Introduction to Regression

CODING & MODULATION Prof. Ing. Anton Čižmár, PhD.

Chapter 3 Sampling For Proportions and Percentages

Third handout: On the Gini Index

PROPERTIES OF GOOD ESTIMATORS

Multivariate Transformation of Variables and Maximum Likelihood Estimation

Chapter 8: Statistical Analysis of Simulated Data

Simple Linear Regression

Lecture 2 - What are component and system reliability and how it can be improved?

Statistics Descriptive

Chapter Two. An Introduction to Regression ( )

BIOREPS Problem Set #11 The Evolution of DNA Strands

1 Onto functions and bijections Applications to Counting

Evaluation of uncertainty in measurements

Homework 1: Solutions Sid Banerjee Problem 1: (Practice with Asymptotic Notation) ORIE 4520: Stochastics at Scale Fall 2015

Descriptive Statistics

Introduction to Probability

Chapter Business Statistics: A First Course Fifth Edition. Learning Objectives. Correlation vs. Regression. In this chapter, you learn:

Chapter 5 Elementary Statistics, Empirical Probability Distributions, and More on Simulation

THE ROYAL STATISTICAL SOCIETY GRADUATE DIPLOMA

The Mathematical Appendix

STK3100 and STK4100 Autumn 2018

1. The weight of six Golden Retrievers is 66, 61, 70, 67, 92 and 66 pounds. The weight of six Labrador Retrievers is 54, 60, 72, 78, 84 and 67.

Lecture 8: Linear Regression

Bootstrap Method for Testing of Equality of Several Coefficients of Variation

Chapter 13, Part A Analysis of Variance and Experimental Design. Introduction to Analysis of Variance. Introduction to Analysis of Variance

Section l h l Stem=Tens. 8l Leaf=Ones. 8h l 03. 9h 58

A Combination of Adaptive and Line Intercept Sampling Applicable in Agricultural and Environmental Studies

Simple Linear Regression

Discrete Mathematics and Probability Theory Fall 2016 Seshia and Walrand DIS 10b

Bayesian Classification. CS690L Data Mining: Classification(2) Bayesian Theorem: Basics. Bayesian Theorem. Training dataset. Naïve Bayes Classifier

Some Notes on the Probability Space of Statistical Surveys

STK3100 and STK4100 Autumn 2017

Chapter Statistics Background of Regression Analysis

Summary tables and charts

Lecture 1. (Part II) The number of ways of partitioning n distinct objects into k distinct groups containing n 1,

Chapter 4: Elements of Statistics

Transcription:

Chapter VI Statstcal Aalyss of Expermetal Data CHAPTER VI Statstcal Aalyss of Expermetal Data Measuremets do ot lead to a uque value. Ths s a result of the multtude of errors (maly radom errors) that ca affect them. It s therefore essetal to take to accout these varabltes to use statstcal methods to terpret the results obtaed through a expermet. 6.. Itroducto A example of the use of statstcal aalyss of expermetal data s to use a represetato uder the form of a hstogram. Let us cosder the followg data represetg the measuremet of a temperature. umber of readgs Temperature ( C) 089 09 094 4 095 8 098 9 00 04 4 05 5 07 5 08 4 0 3 5 The data are frst arraged to groups called bs. Here the sze of a b s 5 C. The bs have to satsfy a couple of codtos: - The bs usually have the same sze ad cover the etre rage of the data wthout overlap. Fgure 6.. Hstogram. Istrumetato ad Measuremets \ LK\ 009 47

Chapter VI Statstcal Aalyss of Expermetal Data The above bell shaped curve of the hstogram s typcal of expermetal data (although ths s ot a rule, see fgure 6. for other types of hstograms). Fgure 6.. Dfferet dstrbutos of data. a) symmetrc; b) skewed; c) j-shaped; d) bmodale; e) uform. - Dscrete ad radom varables: Cotuous radom varables: It s a varable that ca take ay real value a certa doma. Dscrete varables: It a varable that ca take a lmted umber of values. 6.. Geeral cocepts ad deftos Populato: The populato comprses the etre collecto of objects, measuremets, observatos, ad so o whose propertes are uder cosderato ad about whch some geeralzatos are to be made. Sample: A sample s a represetatve subset of a populato o whch a expermet s performed ad umercal data are obtaed. Istrumetato ad Measuremets \ LK\ 009 48

Chapter VI Statstcal Aalyss of Expermetal Data Sample space: The set of all possble outcomes of a expermet s called the sample space. Is ca be a dscrete sample space of a cotuous sample space. Radom varable: It s a varable that wll chage o matter how you try to precsely repeat the expermet. A radom varable ca be dscrete or cotuous. Dstrbuto fucto: It s a mathematcal relatoshp used to represet the values of the radom varable. Parameter: It s a attrbute of the etre populato (exp. average, meda, ) Evet: It s the outcome of a radom expermet. Statstc: It s a attrbute of the sample (exp. average, meda, ) Probablty: It s the chace of occurrece of the evet a expermet. 6... Measures of cetral tedecy - Mea: x = = x x Ad for a fte umber of elemets: μ = = - Meda: t s the value at the ceter of a set, arraged ascedg or descedg order. If the sze of the set s eve, the meda represets the average of the two cetral peaks. - Mode: It represets the value of the varable that correspods to the peak value of the probablty of occurrece of a evet. 6..3. Measures of dsperso - devato: d = x x d - mea devato: d = = - stadard devato (for a populato wth a fte umber of elemets): ( x μ) σ = = - Sample stadard devato: Istrumetato ad Measuremets \ LK\ 009 49

Chapter VI Statstcal Aalyss of Expermetal Data devato. S = = ( x x) t s used to estmate the populato stadard - The varace: σ varace = S for populato for sample 6.3. Probablty Probablty s a umercal value expressg the lkelhood of occurrece of a evet relatve to all possbltes a sample space. The probablty of occurrece of a evet A s defed as the umber of successful occurreces (m) dvded by the total umber of possble outcomes () a sample space, evaluated for >>. probablt y of evet A = The evet ca be represeted by: ) a cotuous radom varable (the probablty s expressed as P(x)); ) a dscrete radom varable (the probablty s expressed as P(x )). Here are some propertes relatve to probablty: a- 0 P ( x or x ) b- If evet A s the complemet of evet A, the: P( = P( c- It the evets A ad B are mutually exclusve (A ad B ca ot occur smultaeously): P ( A + B) = P( + P( B) d- It the evets A ad B are depedet, the probablty that both A ad B wll occur tghter s: P ( AB) = P( P( B) e- The probablty of occurrece of A or B or both s: P( A B) = P( + P( B) P( AB) Example A dstrbutor clams that the chace that ay of the three major compoets of a computer (CPU, motor, ad keyboard) s defectve s 3%. Calculate the chace that all three wll be defectve a sgle computer? 6.3.. Probablty dstrbuto fuctos A mportat fucto of statstcs s to use formato from a sample to predct the behavor of a populato. For partcular stuatos, experece has show that the dstrbuto of the radom varable follow a certa mathematcal patter (fucto). The, f the parameters of ths fucto ca be determed usg the sample data, t wll be possble to predct the propertes of the paret populato. Such fuctos are called: probablty mass m Istrumetato ad Measuremets \ LK\ 009 50

Chapter VI Statstcal Aalyss of Expermetal Data fuctos for dscrete radom varables. For cotuous radom varables, these fuctos are called probablty desty fuctos. - Probablty mass fucto: = P( ) = ; x The mea of the populato for a dscrete radom varable (also called the expected value): μ = x P( ) = x The varace of the populato s gve by: σ = ( x μ) P( x ) - Probablty desty fucto: P ( x x x + dx) f ( x )dx = Ad the, to fd the probablty of x to occur betwee a ad b values: P = ( a x b) f ( x) + The mea of the populato s: μ x f ( x) b = = dx The varace of the populato s: σ ( x μ) f ( x) + a dx = dx Example Cosder the followg probablty dstrbuto fucto for a cotuous radom varable: 3x < x < 3 f ( x) = 35 0 elsewhere a- Show that ths fucto satsfes the requremets of a probablty dstrbuto fucto. b- Calculate the expected mea value of x. c- Calculate the varace ad the stadard devato of x. - Cumulatve dstrbuto fucto: Istrumetato ad Measuremets \ LK\ 009 5

Chapter VI Statstcal Aalyss of Expermetal Data Ths type of dstrbutos s used whe you wat to kow the probablty of evet to be lower that a certa value (x). x ( rv x) = F( x) = F f ( x) dx = P( rv x) For dscrete radom varable: F( rv x ) = P( x j j= Cumulatve dstrbuto fucto has the two followg propertes: P( a < x b) = F( b) F( a) P( x > a) = F( a) ) Istrumetato ad Measuremets \ LK\ 009 5