7 views

Original Title: HW1 Stat JeanPaul statistics

Uploaded by yohanize

- Structural Reliability
- Multiple Choice Review
- The Way We Work in Class
- statsc
- R Tutorial on Normal Distributions
- Lecture 6
- Probability Theory and Stochastic Processes
- Sila Bus
- PROBLEM SET-3 Discrete Probability
- class03_7
- 11_stoch
- ecostat ps4
- UniMasr.com_2578f4ebc770211534702a193d581362
- Week 5
- Blog Brilliant Org
- Eee251 Obe
- jenree.pptx
- Chapter 2
- Chapter2.ppt
- basic statistic and probability theory in civil engineering system

You are on page 1of 9

for IT Managers 1. a)

Looking at the Histogram of volume, we can see that the distribution is positively skewed. Looking at the Box plot of volume, we can see that there is an outlier (Row 2: volume = 31415.9). b) Descriptive Statistics: Volume

Variable Volume N 30 N* 0 Mean 11735 SE Mean 1340 StDev 7340 Minimum 1616 Q1 7245 Median 9027 Q3 16811 Maximum 31416

Mean = 11735 Median = 9027 Standard deviation = 7340 Variance = the square of the standard deviation = 73402 = 53875600 Range = maximum minimum = 31416 1616 = 29800 Interquartile range = Q3 Q1 = 16811 7245 = 9566

Based on these statistics, the hypothesis stated that the distribution is positively skewed is confirmed because the mean > median (11735 > 9027). c) Diameters of first six trees: 7, 11, 12, 16, 18, 20 - Mean = (7+11+12+16+18+20) / 6 = 84 /6 = 14 - Median = (12+16) /2 = 14 - Standard deviation: Deviations: -7, -3, -2, 2, 4, 6 Squared deviations: 49, 9, 4, 4, 16, 36 Variance: S2 = (49+9+4+4+16+36) / (6-1) = 118/5 = 23.6 Standard deviation: S = - Range = 20-7 = 13 2. Conditional probability and Bayes rule We are given the following probabilities: P(use drugs) = 0.03 this means that P(dont use drugs) = 0.97 P(positive | uses drugs) = 0.95 this means that P(negative | uses drugs) = 0.05 P(positive | doesnt use drugs) = 0.2 this means that P(negative | doesnt use drugs) = 0.8

23.6

= 4.86

P(positive | uses drugs) P(use drugs) P(positive | uses drugs) P(use drugs) + P(positive | doesn' t drugs) P(don' t use drugs)

b)

P(uses

drugs

negative)

P(negative | uses drugs) P(use drugs) P(negative | uses drugs) P(use drugs) + P(negative | doesn' t drugs) P(don' t use drugs)

c) P(uses drug | A and B are positive) = P(uses drug | A is positive) * P(uses drug | B is positive)

P(A is positive | uses drugs) P(use drugs) P(A is positive | uses drugs) P(use drugs) + P(A is positive | doesn' t drugs) P(don' t use drugs) P(B is positive | uses drugs) P(use drugs) P(B is positive | uses drugs) P(use drugs) + P(B is positive | doesn' t drugs) P(don' t use drugs)

0.95 * 0.03 0.95 * 0.03 * = 0.128090* 0.128090= 0.0164070481 0.95 * 0.03 + 0.2 * 0.97 0.95 * 0.03 + 0.2 * 0.97

d) P(B is positive | A is positive) = P(B is positive | use drugs) P(use drugs | A is positive) + P(B is positive | dont use drug) P (dont use drug | A is positive) =

P( don' t use drugs | B is positive) P(B is positive) P( don' t use drugs | B is positive) P(B is positive) + P(don' t use drugs | B is negative) P(B is negative)

* = 0.128090+

P( uses drugs | B is positive) P(B is positive) P( uses drugs | B is positive) P(B is positive) + P(uses drugs | B is negative) P(B is negative)

0.87191

0.87191 * 0.19 0.128090 * 0.19 * 0.128090 + *0.87191 0.87191 * 0.19 + 0.8 * 0.81 0.128090 * 0.19 + 0.05 * 0.81

= 0.2036 * 0.128090 + 0.3754 * 0.87191 = 0.3534 3. Discrete and continuous random variables a) Manager 1: We have the interval [$5,000, $35,000] Mean: = ($5,000 + $ 35,000) / 2 = $ 20,000 Standard deviation Manager 2: The mean and the standard deviation of his groups monthly expenses are the same as those estimated. Mean: = $21,000 Standard deviation: Manager 3: Mean: =

= ($35,000 - $ 5,000) /

12 = $8660.2540

=$2,000

p ( x)

2 = ( x )

p( x)

= ((-6500)2 0.2 + (-1500)2 0.4 + (3500)2 0.3 + (8500)2 0.1)) = $20250000 Standard deviation:

2 = 20250000 = $4500

b) Using Minitab, we can calculate these probabilities. The steps are: Select Calc > Probability Distributions > Normal Select Cumulative Probability Fill-in the values in the dialog box (mean, standard deviation and the input constant) Click OK Manager 1:

i) From Minitab,

Cumulative Distribution Function

Normal with mean = 20000 and standard deviation = 8660.25 x 17000 P( X <= x ) 0.364517 and x 24000 P( X <= x ) 0.677916

The probability that is between $17,000 and $24,000 is 0.677916 0.364517 = 0.313399 ii) From Minitab we can calculate the probability that is less than $22,000 and the probability that it is greater than $22,000 will be 1- P(is less than $22,000)

Cumulative Distribution Function

Normal with mean = 20000 and standard deviation = 8660.25

Thus the probability that is greater than $22,000 will be 1- 0.591319 = 0.408681 iii) Cumulative Distribution Function

Normal with mean = 20000 and standard deviation = 8660.25 x 18000 P( X <= x ) 0.408681

iv) Because this is a single value, (random variable) the probability will be zero (P(x=$25,000 = 0) Manager 2: i) From Minitab,

Cumulative Distribution Function

Normal with mean = 21000 and standard deviation = 2000 x 17000 P( X <= x ) 0.0227501 and x 24000 P( X <= x ) 0.933193

The probability that is between $17,000 and $24,000 is 0.933193 0.0227501 = 0.910443 ii) From Minitab we can calculate the probability that is less than $22,000 and the probability that it is greater than $22,000 will be 1- P(is less than $22,000)

Cumulative Distribution Function

Normal with mean = 21000 and standard deviation = 2000

P( X <= x )

22000

Thus the probability that is greater than $22,000 will be 1- 0.691462 = 0.308538 iii) Cumulative Distribution Function

Normal with mean = 21000 and standard deviation = 2000 x 18000 P( X <= x ) 0.0668072

iv) Because this is a single value, (random variable) the probability will be zero (P(x=$25,000 = 0) Manager 3: i) From Minitab,

Cumulative Distribution Function

Normal with mean = 21500 and standard deviation = 4500 x 17000 P( X <= x ) 0.158655 and x 24000 P( X <= x ) 0.710743

The probability that is between $17,000 and $24,000 is 0.710743 0.158655 = 0.552088 ii) From Minitab we can calculate the probability that is less than $22,000 and the probability that it is greater than $22,000 will be 1- P(is less than $22,000)

Cumulative Distribution Function

Normal with mean = 21500 and standard deviation = 4500 x P( X <= x ) 22000 0.544236 (less than $22,000)

Thus the probability that is greater than $22,000 will be 1- 0.544236 = 0.455764 iii) Cumulative Distribution Function

Normal with mean = 21500 and standard deviation = 4500 x 18000 P( X <= x ) 0.218350

iv) Because this is a single value, (random variable) the probability will be zero (P(x=$25,000 = 0) c) This is an inverse problem. With Minitab we can calculate this value using the Inverse Normal Cumulative Probability. The steps are the following: Select Calc > Probability Distributions > Normal Select Inverse cumulative probability

Fill-in the values in the dialog box (mean, standard deviation and the input constant) Click OK The input constant will be 20% = 0.2

For manager 1:

Inverse Cumulative Distribution Function

Normal with mean = 20000 and standard deviation = 8660.25 P( X <= x ) 0.2 x 12711.3

Thus the company should budget $12,711 for manager 1. For manager 2:

Inverse Cumulative Distribution Function

Normal with mean = 21000 and standard deviation = 2000 P( X <= x ) 0.2 x 19316.8

Thus the company should budget $19,317 for manager 2. For manager 3:

Inverse Cumulative Distribution Function

Normal with mean = 21500 and standard deviation = 4500 P( X <= x ) 0.2 x 17712.7

d) We will use the same approach as the above (on c) but the input constant will be 0.02 For manager 1:

Inverse Cumulative Distribution Function

Normal with mean = 20000 and standard deviation = 8660.25 P( X <= x ) 0.02 x 2214.01

Thus the company should budget $2214 for manager 1. For manager 2:

Normal with mean = 21000 and standard deviation = 2000 P( X <= x ) 0.02 x 16892.5

Thus the company should budget $16,893 for manager 2. For manager 3:

Inverse Cumulative Distribution Function

Normal with mean = 21500 and standard deviation = 4500 P( X <= x ) 0.02 x 12258.1

4. a) n (number of trials) = 1000 p (probability of success i.e no defective) = 1-0.01 = 0.99 q(probability of failure i.e defective) = 1% = 0.01 Mean of defective chips: = nq = 1000 * 0.01 = 100 Standard deviation:

npq

= 9.9

b) Total cost: 1000 * $200= $200,000 Total sell: 1000 * $1000 = $1,000,000 Profit if no defective: $1,000,000 - $200,000 = $800,000 p(800,000) = 0.98 and p(-200,000) = 0.02 The manufacturers expected profit will be: 0.98($800,000) + 0.02($-200,000) = $780,000 c) In this case the profit will be 1($800,000) = $800,000 since there would be no defective The implementation of this technology will increase the manufacturers expected profit to $800,000 - $780,000 = $20,000

- Structural ReliabilityUploaded byShredBetty
- Multiple Choice ReviewUploaded byJia Yi S
- The Way We Work in ClassUploaded byKairatTM
- statscUploaded byreezman
- R Tutorial on Normal DistributionsUploaded byactistic
- Lecture 6Uploaded bygobigupta
- Probability Theory and Stochastic ProcessesUploaded byToaster97
- Sila BusUploaded byMiljan Kovacevic
- PROBLEM SET-3 Discrete ProbabilityUploaded bymaxentiuss
- class03_7Uploaded byDr. Ir. R. Didin Kusdian, MT.
- 11_stochUploaded byManoj Gupta
- ecostat ps4Uploaded byDivyanshu Dvh
- UniMasr.com_2578f4ebc770211534702a193d581362Uploaded byyolo master
- Week 5Uploaded byJingwen Shi
- Blog Brilliant OrgUploaded byJuang Bhakti Hastyadi
- Eee251 ObeUploaded byChaudry Arshad Mehmood
- jenree.pptxUploaded by김태태
- Chapter 2Uploaded byLugabaluga
- Chapter2.pptUploaded byLugabaluga
- basic statistic and probability theory in civil engineering systemUploaded byTiti Sari
- C Siruri de Asteptare QueuingUploaded byLorand Becsek
- Lecture_10_ch7_222_w05_s4Uploaded byRa Yaj
- fajardo micaela lauren r week3 reflective learning journalUploaded byapi-351776914
- 1 November 1-4, 2016 OkUploaded byjun del rosario
- c1-Review of ProbabilityUploaded byhermas67
- bbaldi_ips_chapter05Uploaded bycrutili
- Chapter 6Uploaded byOng Siaow Chien
- Meaning of Normalization in Probability ContextUploaded byAbraham Jyothimon
- Chapter 2Uploaded byAman Malik
- A new reliability analysis method for uncertain structures with random and interval variablesUploaded byYoun Seok Choi

- Jean Paul ResumeUploaded byyohanize
- HCI HW1 JeanPaul NizeyimanaUploaded byyohanize
- Quiz exam 1Uploaded byyohanize
- jnizeyim_critique1Uploaded byyohanize
- ICTPolicy-HW1-JeanPaulUploaded byyohanize
- UsabilityEvalReport_JeanPaulUploaded byyohanize
- Final Jean Paul ICTPolicy-HW2Uploaded byyohanize
- Assignment of Knowledge Based SystemUploaded byyohanize
- Cv Leoncie for hotelUploaded byyohanize
- Paper Review questionsUploaded byyohanize
- Lab 0_Jean PaulUploaded byyohanize
- CAT_1 PhysicsUploaded byyohanize
- Chapter 2&3 e-bankingUploaded byyohanize
- ASSIGN1_17Uploaded byyohanize
- Project Scope StatementUploaded byyohanize
- Project Scope StatementUploaded byyohanize
- fiancial analysisUploaded byyohanize
- Intern as Hip Anabelle Version FinaleUploaded byyohanize
- HW1_JeanPaulUploaded byyohanize
- HW1_JeanPaulUploaded byyohanize
- HW4 JeanPaul CorrectedUploaded byyohanize
- jnizeyim_critique5Uploaded byyohanize
- HW6_JeanPaul.docUploaded byyohanize
- Rwanda Education Sector Plan 2006 2010Uploaded byyohanize

- asset-v1_ColumbiaX+CSMM.102x+3T2018+type@asset+block@ML_lecture3.pdfUploaded bySalvo Nice
- Maths Nov_Dec 2010Uploaded byJenitha Rajadurai
- 1-edaUploaded byminakirolos
- Bestglm Using RUploaded bySankarsanaSahoo
- intUploaded bySpica Dim
- Hardy WeinbergUploaded byGabi Molina
- Entropy Rates of a Stochastic ProcessUploaded bymaxbmen
- Information TheoryUploaded byamirali55
- Results of Final Year Research Project-FYP 2017 of BIMS-Arid Agriculture University, Rawalpindi.Uploaded bydaniyal
- Statistics confidence intervalsUploaded byCollegestudent
- 20121214-hcwangUploaded bymissinu
- Dmaic ToolkitUploaded byS M Arif Hussain
- Probit AnalysisUploaded byYaronBaba
- Spring 2006 Test 1 SolutionUploaded byAndrew Zeller
- Study of Correlation Times Using 2D Ising LatticeUploaded byt_sairam
- Stochastic ModelsUploaded byclassic_777
- The Binomial, Poisson, And Normal DistributionsUploaded byVinit Shah
- 10 ErrorUploaded byprogressksb
- Bacher Wenzig Vogler Spss TwostepUploaded byLuis Guillen
- Logistic Regression sample size calculationUploaded byAmado Saavedra
- Bootstrap Efron FulltextUploaded byEfemena Doroh
- chapter 17Uploaded byapi-232613595
- Students Tutorial Answers Week5Uploaded byHeoHamHố
- 1202.3665v4.Emcee.the MCMC HammerUploaded byMobashar Ahmad
- Review 12AUploaded byAmalAbdlFattah
- MQM100_MultipleChoice_Chapter7Uploaded byNakin K
- 15W M1 Sample problemsUploaded bysheiji_ro
- Quality ControlUploaded byDivina Melorra Macaraig Reyes
- F17_10601_HW3Uploaded bySushant Mehta
- 08Chap7Uploaded byVothe Dung