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

Similar documents
1. a. Houston Chronicle, Des Moines Register, Chicago Tribune, Washington Post

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

MEASURES OF DISPERSION

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

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.

Descriptive Statistics

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

is the score of the 1 st student, x

Statistics Descriptive

STATISTICS 13. Lecture 5 Apr 7, 2010

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

CHAPTER 6. d. With success = observation greater than 10, x = # of successes = 4, and

Measures of Dispersion

CHAPTER VI Statistical Analysis of Experimental Data

Chapter 1: Overview and Descriptive Statistics CHAPTER 1. a. Houston Chronicle, Des Moines Register, Chicago Tribune, Washington Post

Summary tables and charts

Summary of the lecture in Biostatistics

Econometric Methods. Review of Estimation

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

Median as a Weighted Arithmetic Mean of All Sample Observations

Lecture Notes Types of economic variables

Measures of Central Tendency

Chapter 5 Properties of a Random Sample

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

THE ROYAL STATISTICAL SOCIETY HIGHER CERTIFICATE

Statistics: Unlocking the Power of Data Lock 5

Chapter 3 Sampling For Proportions and Percentages

Multiple Regression. More than 2 variables! Grade on Final. Multiple Regression 11/21/2012. Exam 2 Grades. Exam 2 Re-grades

Third handout: On the Gini Index

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.

Continuous Distributions

Module 7. Lecture 7: Statistical parameter estimation

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

PTAS for Bin-Packing

Class 13,14 June 17, 19, 2015

STA 108 Applied Linear Models: Regression Analysis Spring Solution for Homework #1

Laboratory I.10 It All Adds Up

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

Quantitative analysis requires : sound knowledge of chemistry : possibility of interferences WHY do we need to use STATISTICS in Anal. Chem.?

hp calculators HP 30S Statistics Averages and Standard Deviations Average and Standard Deviation Practice Finding Averages and Standard Deviations

STA302/1001-Fall 2008 Midterm Test October 21, 2008

UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS

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

Lecture 1 Review of Fundamental Statistical Concepts

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

Random Variate Generation ENM 307 SIMULATION. Anadolu Üniversitesi, Endüstri Mühendisliği Bölümü. Yrd. Doç. Dr. Gürkan ÖZTÜRK.

1 Onto functions and bijections Applications to Counting

Analysis of Variance with Weibull Data

b. There appears to be a positive relationship between X and Y; that is, as X increases, so does Y.

The expected value of a sum of random variables,, is the sum of the expected values:

Bounds on the expected entropy and KL-divergence of sampled multinomial distributions. Brandon C. Roy

Chapter 11 Systematic Sampling

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

Functions of Random Variables

UNIT 7 RANK CORRELATION

Chapter 14 Logistic Regression Models

Random Variables and Probability Distributions

2SLS Estimates ECON In this case, begin with the assumption that E[ i

Lecture 3. Sampling, sampling distributions, and parameter estimation

22 Nonparametric Methods.

Module 7: Probability and Statistics

UNIT 6 CORRELATION COEFFICIENT

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

UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS

A New Family of Transformations for Lifetime Data

Statistics Descriptive and Inferential Statistics. Instructor: Daisuke Nagakura

The variance and standard deviation from ungrouped data

Ideal multigrades with trigonometric coefficients

PROPERTIES OF GOOD ESTIMATORS

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

Ordinary Least Squares Regression. Simple Regression. Algebra and Assumptions.

STK3100 and STK4100 Autumn 2017

Comparison of Dual to Ratio-Cum-Product Estimators of Population Mean

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

Statistics MINITAB - Lab 5

ESS Line Fitting

Parameter, Statistic and Random Samples

CHAPTER 4 RADICAL EXPRESSIONS

Chapter 2. 1.what are the types of Data Sets

Lecture Notes Forecasting the process of estimating or predicting unknown situations

Lecture 3 Probability review (cont d)

Simulation Output Analysis

ENGI 4421 Propagation of Error Page 8-01

Chapter 4 (Part 1): Non-Parametric Classification (Sections ) Pattern Classification 4.3) Announcements

ε. Therefore, the estimate

Some Applications of the Resampling Methods in Computational Physics

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

STATISTICAL INFERENCE

ENGI 3423 Simple Linear Regression Page 12-01

The number of observed cases The number of parameters. ith case of the dichotomous dependent variable. the ith case of the jth parameter

The Mathematical Appendix

THE ROYAL STATISTICAL SOCIETY 2016 EXAMINATIONS SOLUTIONS HIGHER CERTIFICATE MODULE 5

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

UNIT 1 MEASURES OF CENTRAL TENDENCY

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

Lecture 9: Tolerant Testing

Regression. Linear Regression. A Simple Data Display. A Batch of Data. The Mean is 220. A Value of 474. STAT Handout Module 15 1 st of June 2009

CHAPTER 2. = y ˆ β x (.1022) So we can write

Definition. Measures of Dispersion. Measures of Dispersion. Definition. The Range. Measures of Dispersion 3/24/2014

Overcoming Limitations of Sampling for Aggregation Queries

Transcription:

Secto.. 6l 34 6h 667899 7l 44 7h Stem=Tes 8l 344 Leaf=Oes 8h 5557899 9l 3 9h 58 Ths dsplay brgs out the gap the data: There are o scores the hgh 7's. 6. a. beams cylders 9 5 8 88533 6 6 98877643 7 488 7 8 3359 77 9 78 7 863 6 3 4 The data appears to be slghtly skewed to the rght, or postvely skewed. The value of 4. appears to be a outler. Three out of the twety, 3/ or.5 of the observatos eceed Mpa.

b. The majorty of observatos are betwee 5 ad 9 Mpa for both beams ad cylders, wth the modal class the 7 Mpa rage. The observatos for cylders are more varable, or spread out, ad the mamum value of the cylder observatos s hgher. c. Dot Plot... :.. :.:... :... -+---------+---------+---------+---------+---------+-----cylder 6. 7.5 9..5. 3.5 9. a. From ths frequecy dstrbuto, the proporto of wafers that cotaed at least oe partcle s (-)/ =.99, or 99%. Note that t s much easer to subtract (whch s the umber of wafers that cota partcles) from tha t would be to add all the frequeces for,, 3, partcles. I a smlar fasho, the proporto cotag at least 5 partcles s ( - --3-- )/ = 7/ =.7, or, 7%. b. The proporto cotag betwee 5 ad partcles s (5+8+++4+5)/ = 64/ =.64, or 64%. The proporto that cota strctly betwee 5 ad (meag strctly more tha 5 ad strctly less tha ) s (8+++4)/ = 44/ =.44, or 44%. c. The followg hstogram was costructed usg Mtab. The data was etered usg the same techque metoed the aswer to eercse 8(a). The hstogram s almost symmetrc ad umodal; however, t has a few relatve mama (.e., modes) ad has a very slght postve skew. Relatve frequecy... 5 Number of partcles 5

Desty 6. a. Yes: the proporto of sampled agles smaller tha 5 s.77 +.66 +.75 =.58. b. The proporto of sampled agles at least 3 s.78 +.44 +.3 =.5. c. The proporto of agles betwee ad 5 s roughly.75 +.36 + (..94)/ =.48. d. The dstrbuto of msoretato agles s heavly postvely skewed. Though agles ca rage from to 9, early 85% of all agles are less tha 3. Wthout more precse formato, we caot tell f the data cota outlers..4 Hstogram of Agle.3... 4 Agle 9

7. a. The edpots of the class tervals overlap. For eample, the value 5 falls both of the tervals 5 ad 5. b. Class Iterval Frequecy Relatve Frequecy - < 5 9.8 5 - < 9.38 - < 5. 5 - < 4.8 - < 5.4 5 - < 3.4 3 - < 35. 35 - < 4. >= 4. 5. 5 5 5 3 35 4 45 5 55 6 lfetme The dstrbuto s skewed to the rght, or postvely skewed. There s a gap the hstogram, ad what appears to be a outler the 5 55 terval.

c. Class Iterval Frequecy Relatve Frequecy.5 - <.75.4.75 - < 3.5.4 3.5 - < 3.75 3.6 3.75 - < 4.5 8.6 4.5 - < 4.75 8.36 4.75 - < 5.5. 5.5 - < 5.75 4.8 5.75 - < 6.5 3.6.5.75 3.5 3.75 4.5 4.75 5.5 5.75 6.5 l lfetme The dstrbuto of the atural logs of the orgal data s much more symmetrc tha the orgal. d. The proporto of lfetme observatos ths sample that are less tha s.8 +.38 =.56, ad the proporto that s at least s.4 +.4 +. +. +. =.4.

Cout of complat 9. Complat Frequecy Relatve Frequecy B 7.67 C 3.5 F 9.5 J.667 M 4.667 N 6. O.35 6. B C F J M N O complat Secto.3 35. a. The sample mea s = (.4/8) =.55. The sample sze ( = 8) s eve. Therefore, the sample meda s the average of the (/) ad (/) + values. By sortg the 8 values order, from smallest to largest: 8. 8.9.. 3. 4.5 5. 8., the forth ad ffth values are ad 3. The sample meda s (. + 3.)/ =.5. The.5% trmmed mea requres that we frst trm (.5)() or value from the eds of the ordered data set. The we average the remag 6 values. The.5% trmmed mea tr(.5) s 74.4/6 =.4.

All three measures of ceter are smlar, dcatg lttle skewess to the data set. b. The smallest value (8.) could be creased to ay umber below. (a chage of less tha 4.) wthout affectg the value of the sample meda. c. The values obtaed part (a) ca be used drectly. For eample, the sample mea of.55 ps could be re-epressed as ks (.55 s) 5.7ks. ps. 36. a. A stem-ad leaf dsplay of ths data appears below: 3 55 stem: oes 33 49 leaf: teths 34 35 6699 36 34469 37 3345 38 9 39 347 4 3 4 4 4 The dsplay s reasoably symmetrc, so the mea ad meda wll be close. b. The sample mea s = 9638/6 = 37.7. The sample meda s ~ = (369+37)/ = 369.5. c. The largest value (curretly 44) could be creased by ay amout. Dog so wll ot chage the fact that the mddle two observatos are 369 ad 7, ad hece, the meda wll ot chage.

However, the value = 44 ca ot be chaged to a umber less tha 37 (a chage of 44-37 = 54) sce that wll lower the values(s) of the two mddle observatos. d. Epressed mutes, the mea s (37.7 sec)/(6 sec) = 6.8 m; the meda s 6.6 m. 4. a. 7. 7 b.. 7 = proporto of successes s c. 8 5. so s = (.8)(5) = total of successes 7 = 3 of the ew cars would have to be successes (57 79) 43. meda = 68., % trmmed mea = 66., 3% trmmed mea = 67.5. Secto.4 45. a. = = 577.9/5 = 5.58. Devatos from the mea: 6.4-5.58 =.8, 5.9-5.58 =.3, 4.6-5.58 = -.98, 5. - 5.58 = -.38, ad 5.8-5.58 =.. b. s = [(.8) + (.3) + (-.98) + (-.38) + (.) ]/(5-) =.98/4 =.48, so s =.694. c. = 66,795.6, so s = = [66,795.6 - (577.9) /5]/4 =.98/4 =.48. d. Subtractg from all values gves 5. 58, all devatos are the same as part b, ad the trasformed varace s detcal to that of part b.

5. a. 563 ad 368, 5, so [368,5 (563) /9] s 64.766 ad s 35. 564 8 c b. If y = tme mutes, the y = c where, so 6 64.766 35.564 s y c s.35 ad s y cs. 593 36 6 53. a. lower half:.34.43.6.74.74.75.78 3. 3.46 upper half: 3.46 3.56 3.65 3.85 3.88 3.93 4. 4.33 4.5 Thus the lower fourth s.74 ad the upper fourth s 3.88. b. f 3.88.74. 4 s c. f s would t chage, sce creasg the two largest values does ot affect the upper fourth. d. By at most.4 (that s, to aythg ot eceedg.74), sce the t wll ot chage the lower fourth. e. Sce s ow eve, the lower half cossts of the smallest 9 observatos ad the upper half cossts of the largest 9. Wth the lower fourth =.74 ad the upper fourth = 3.93, f. 9. s 59. a. ED: meda =.4 (the 4 th value the sorted lst of data). The lower quartle (meda of the lower half of the data, cludg the meda, sce s odd) s (.+. )/ =.. The upper quartle s (.7+.8)/ =.75. Therefore, IQR =.75 -. =.65. No-ED: meda = (.5+.7)/ =.6. The lower quartle (meda of the lower 5 observatos) s.3; the upper quartle (meda of the upper half of the data) s 7.9. Therefore, IQR = 7.9 -.3 = 7.6. b. ED: mld outlers are less tha. -.5(.65) = -3.875 or greater tha.75 +.5(.65) = 6.75. Etreme outlers are less tha. - 3(.65) = -7.85 or greater tha.75 + 3(.65) =.7. So, the two largest observatos (.7,.) are etreme outlers ad the et two largest values (8.9, 9.) are mld outlers. There are o outlers at the lower ed of the data. No-ED: mld outlers are less tha.3 -.5(7.6) = -. or greater tha 7.9 +.5(7.6) = 9.3. Note that there are o mld outlers the data, hece there ca ot be ay etreme outlers ether.

c. A comparatve boplot appears below. The outlers the ED data are clearly vsble. There s otceable postve skewess both samples; the No-Ed data has more varablty the the Ed data; the typcal values of the ED data ted to be smaller tha those for the No-ED data. No-ED ED Cocetrato (mg/l) 79. a. [ ( ), so ] b. s ( ) s ( ) ( ) ( ) ( ) Whe the epresso for from a s substtuted, the epresso braces smplfes to the followg, as desred: ( ( ) ) 5(.58).8.5 6 6 ( ) 4 (.8.58) s s.5. 45.38. 38 ( ) 5 (6) c.. 53 So the stadard devato s.38. 53.