ST259F23L3_Solns_Combined

pdf

School

Wilfrid Laurier University *

*We aren’t endorsed by this school

Course

259

Subject

Industrial Engineering

Date

Dec 6, 2023

Type

pdf

Pages

6

Uploaded by mamba6800

Report
ST259 Lab 3 - Fall 2023 1. [12 marks ] Benford°s law states that in many naturally occurring numbers that the leading signi±cant digit tends to be °small° (e.g. stock prices, city populations). In these scenarios, the leading digit is a discrete random variable X with probability mass function p X ( x ) = log k ° 1 + 1 x ± where k is dependent on the number system in use (e.g. binary, decimal, etc.) : For the remainder of this question, suppose that x 2 f 1 ; 2 ; 3 ; 4 ; 5 g (i.e. the senary number system is being used). (a) Using properties of logarithms, determine the exact value of k: 5 X x =1 p X ( x ) = 1 ) log k (2) + log k ° 3 2 ± + log k ° 4 3 ± + log k ° 5 4 ± + log k ° 6 5 ± = 1 ) log k ° 2 ° 3 2 ° 4 3 ° 5 4 ° 6 5 ± = 1 ) log k 6 = 1 ) k = 6 (b) Rounding to 2 decimals where necessary, state: i. The p.m.f. of X as a table. x = 1 2 3 4 5 p X ( x ) = log 6 2 ± 0 : 39 log 6 3 2 ± 0 : 23 log 6 4 3 ± 0 : 16 log 6 5 4 ± 0 : 12 log 6 6 5 ± 0 : 10 ii. The c.d.f. of X as a table. [Note: Use interval notation for x: ] x 2 ( ²1 ; 1) [1 ; 2) [2 ; 3) [3 ; 4) [4 ; 5) [5 ; 1 ) F X ( x ) = 0 0 : 39 0 : 39 + 0 : 23 = 0 : 62 0 : 62 + 0 : 16 = 0 : 78 0 : 78 + 0 : 12 = 0 : 90 0 : 90 + 0 : 10 = 1 (c) To 2 decimal places, calculate (use correct notation and show your work) P (2 ³ X ³ 4) using: i. The p.m.f. from part (b)(i). P (2 ³ X ³ 4) = p X (2) + p X (3) + p X (4) = 0 : 23 + 0 : 16 + 0 : 12 = 0 : 51 ii. The c.d.f. from part (b)(ii). P (2 ³ X ³ 4) = F X (4) ² F X (2 ° ) = 0 : 90 ² 0 : 39 = 0 : 51 (d) Showing your work, determine the expected value (or mean) of X . Be sure to use proper notation and round result to 2 decimal places. ° X = E [ X ] = 5 X i =1 x i f ( x i ) = 1 (0 : 39) + 2(0 : 23) + 3 (0 : 16) + 4(0 : 12) + 5 (0 : 10) = 2 : 31 (e) Showing your work, determine the standard deviation (to 3 decimal places) in X . Be sure to use proper notation and round result to 2 decimal places. ± X = p E [ X 2 ] ² ° 2 = v u u t 5 X i =1 x 2 i f ( x i ) ² ° 2 = p 1 (0 : 39) + 4(0 : 23) + 9 (0 : 16) + 16(0 : 12) + 25 (0 : 10) ² 2 : 31 2 = 1 : 35
2. [5 marks ] Recall the Roulette question from Labs 1 and 2 where: Event A : f ball lands in the "3rd twelve" g = f 25 ; 26 ; :::; 35 ; 36 g with P ( A ) = 6 19 Event B : f ball lands on a "red" number g with P ( B ) = 9 19 Also, consider event C = f ball lands on "1st street" g = f 1 ; 2 ; 3 g with P ( C ) = 3 38 : Suppose that you have decided to try your luck at the game and have $25 to gamble on a single spin. Important Note : If a bet pays N to 1 odds on a wager of $ Z then the bettor°s winnings/pro±t is $ ( N ´ Z ) if they win and ² $ Z if they lose. (a) Suppose you bet the entire $25 on the ball landing on a "red" number (which, if successful, pays 1 to 1 odds). Showing your calculation, determine your expected winnings, E [ W 1 ] ; to the closest cent. E [ W 1 ] = (1 ´ 25) ° 9 19 ± ² 25 ° 1 ² 9 19 ± = (1 ´ 25) ° 9 19 ± ² 25 ° 10 19 ± : = ² $1 : 32 (b) Suppose you bet the entire $25 on the ball landing in the "3rd twelve" (which, if successful, pays 2 to 1 odds). Showing your calculation, determine your expected winnings, E [ W 2 ] ; to the closest cent. E [ W 2 ] = (2 ´ 25) ° 6 19 ± ² 25 ° 13 19 ± : = ² $1 : 32 (c) Suppose you bet the entire $25 on the ball landing on "1st street" (which, if successful, pays 11 to 1 odds). Showing your calculation, determine your expected winnings, E [ W 3 ] ; to the closest cent. E [ W 3 ] = (11 ´ 25) ° 3 38 ± ² 25 ° 35 38 ± : = ² $1 : 32 (d) Suppose you change up your strategy and bet $15 on event A , $8 on event B , and $2 on event C for one spin of the wheel. Showing your calculation, determine your expected winnings, E [ W 4 ] ; to the closest cent. E [ W 4 ] = ² (1 ´ 8) ° 9 19 ± ² 8 ° 10 19 ±³ + ² (2 ´ 15) ° 6 19 ± ² 15 ° 13 19 ±³ + ² (11 ´ 2) ° 3 38 ± ² 2 ° 35 38 ±³ = ² 0 : 42105 ² 0 : 78947 ² 0 : 10526 = ² $1 : 32 3. [5 marks ] Suppose that random variable X represents the outcome when an n -sided fair die is rolled (i.e. each outcome is equally likely to occur). The p.m.f. of X is then p X ( x i ) = 1 n where x i = i for 1 ³ i ³ n: (a) Determine E [ X ] (the expected value of X ) in a simpli±ed form. [Hint: n X i =1 i = n ( n + 1) 2 ] E [ X ] = n X i =1 x i p X ( x i ) = n X i =1 x i ° 1 n ± = 1 n n X i =1 i = 1 n ² n ( n + 1) 2 ³ = n + 1 2 (b) Determine V ( X ) (the variance in X ) in a simpli±ed form. [Hint: n X i =1 i 2 = n ( n + 1)(2 n + 1) 6 ] E ´ X 2 µ = n X i =1 x 2 i ° 1 n ± = 1 n n X i =1 i 2 = 1 n ° n ( n + 1)(2 n + 1) 6 ± = 2 n 2 + 3 n + 1 6 ) V ( X ) = E ´ X 2 µ ² ( E [ X ]) 2 = 2 n 2 + 3 n + 1 6 ² ° n + 1 2 ± 2 = 2(2 n 2 + 3 n + 1) ² 3( n 2 + 2 n + 1) 12 = n 2 ² 1 12
4. [12 marks ] In a folder that you can easily ±nd on your computer, save the ±les named: µ Hog.csv (found under "Weekly Lab Information" on the lab MyLS page) which contains daily closing stock prices (in US dollars) for Harley Davidson (HOG on the Nasdaq) in 2022 and µ ST259F23L3.Rmd (found under "Lab Assignment" on the lab MyLS page) [Note: Parts (a) to (e) in Question #4 will be completed using RStudio. You are not required to record any of the results on your answer sheet. Just complete the following exercises in the ±le and then I will explain how to submit the .Rmd ±le as a .R ±le to Gradescope at the end of the question. For grading purposes, you must name variables the same as I have suggested below. Parts (f) and (g) are to be completed on your written answer sheet.] (a) Open the ST259F23L3.Rmd in RStudio. Then: i. On the toolbar, go to Session I Set Working Directory I Choose Directory... and select the folder where you saved both of the ±les. ii. Import the Hog.csv data set into R (name it HOG ) and then display its ±rst few rows. (b) Calculate i) the expected value of and ii) the variance in the Hog stock prices ( P _ USD ) using US dollars. Call the results ExpP_USD and VarP_USD , respectively. (c) To convert the closing stock prices from US dollars ( P _ USD ) to Canadian dollars ( P _ CAD ) the formula P _ CAD = 1 : 37 P _ USD can be used. De±ne a new column (i.e. variable) called P_CAD in the HOG data set using the command HOG$P_CAD=1.37*HOG$P_USD . Then use the random variable P _ CAD to calculate i) the expected value of and ii) the variance in the Hog stock prices using Canadian dollars. Call the results ExpP_CAD and VarP_CAD , respectively.. [Note: To see that the variable was indeed added to the data set, type head(HOG) to see the data set.] (d) Suppose that there is a $6.95 (in US dollars) brokerage fee to trade the stock. De±ne a new column (i.e. variable) called V_USD in the HOG data set that represents the true stock values in US dollars ( V _ USD = P _ USD ² 6 : 95) . Then use the random variable V _ USD to calculate i) the expected value of and ii) the variance in the true HOG stock values using US dollars. Call the results ExpV_USD and VarV_USD , respectively. (e) De±ne a new column (i.e. variable) called V_CAD in the HOG data set that represents the true stock values in Canadian dollars ( V _ CAD = 1 : 37( P _ USD ² 6 : 95) = 1 : 37 P _ USD ² 9 : 5215) . Then use the random variable V _ CAD to calculate i) the expected value of and ii) the variance in the true HOG stock values using Canadian dollars. Call the results ExpV_CAD and VarV_CAD , respectively. (f) On your written answer sheet, evaluate the linear transformations in parts (c), (d), and (e) using the E [ P _ USD ] from part (b) and compare the results to the E [ P _ CAD ] ; E [ V _ USD ] ; and E [ V _ CAD ] . If a; b 2 R and X is a discrete random variable, what do these observations suggest about the relationship between E [ X ] and E [ aX + b ]? From part (c): 1 : 37 E [ P _ USD ] = 1 : 37(38 : 56669) ± 52 : 836 = E [ P _ CAD ] From part (d): E [ P _ USD ] ² 6 : 95 = 38 : 56669 ² 6 : 95 ± 31 : 617 = E [ V _ USD ] From part (e): 1 : 37 E [ P _ USD ] ² 9 : 5215 = 1 : 37(38 : 56669) ² 9 : 5215 ± 43 : 315 = E [ V _ CAD ] This all suggests that E [ aX + b ] = aE [ X ] + b: (g) On your written answer sheet, how does the V ar ( P _ USD ) compare to the V ar ( P _ CAD ) ? V ar ( V _ USD ) ? V ar ( V _ CAD )? If a; b 2 R and X is a discrete random variable, what do these observations suggest about the relationship between V ar ( X ) and V ar ( aX + b )? V ar ( P _ USD ) = V ar ( V _ USD ) (i.e. b does not a/ect variance), and (1 : 37) 2 V ar ( P _ USD ) = (1 : 37) 2 (17 : 8938) ± 33 : 585 = V ar ( P _ CAD ) = V ar ( V _ CAD ) : This suggests that V ( aX + b ) = a 2 V ( X ) :
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
Run the °nal line of code [i.e. knitr::purl("ST259F23L3.Rmd") in the °le] to convert the .RMD °le to a .R °le. It will be saved in the same folder that you originally saved the .RMD °le. Submit the newly created ST259F23L3.R °le to Gradescope via the website link found on the lab MyLS page. ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² ² Once you have completed the problems (or your time is up), be sure that you have submitted the PDF for the R code/output in Question #4(a)-(e) to Gradescope via the website link on the lab MyLS lab page. Hand all other written work in to your IA/TA (be sure your name and student ID are clearly written). It will be uploaded separately to Gradescope for you. Grade: 34
You should have worked through the pre-lab worksheet before attending the lab. If not, you will need to go investigate the Lab2 Pre-Lab file under “Weekly Lab Information” for a description of the functions and commands required below. QUESTION #4) ON LAB ASSIGNMENT #Part a) HOG = read.csv( "Hog.csv" ) #HOG #Displays data set #Part b) ExpP_USD = mean(HOG$P_USD) ExpP_USD #Displays result ## [1] 38.56669 VarP_USD = sd(HOG$P_USD)ˆ 2 VarP_USD #Displays result ## [1] 17.8938 #Part c) HOG$P_CAD = 1.37 *HOG$P_USD ExpP_CAD = mean(HOG$P_CAD) ExpP_CAD ## [1] 52.83637 VarP_CAD = sd(HOG$P_CAD)ˆ 2 VarP_CAD ## [1] 33.58488 #Part d) HOG$V_USD = HOG$P_USD -6.95 ExpV_USD = mean(HOG$V_USD) ExpV_USD ## [1] 31.61669 VarV_USD = sd(HOG$V_USD)ˆ 2 VarV_USD ## [1] 17.8938 #Part e) HOG$V_CAD = 1.37 *HOG$P_USD -9.5215 ExpV_CAD = mean(HOG$V_CAD) ExpV_CAD ## [1] 43.31487 1
VarV_CAD = sd(HOG$V_CAD)ˆ 2 VarV_CAD ## [1] 33.58488 View(HOG) DO NOT CHANGE THE FOLLOWING LINE OF CODE. WHEN YOU RUN IT, THE CODE WILL CONVERT THIS .RMD FILE INTO A .R FILE FOR SUBMISSION TO GRADESCOPE. TO ENSURE YOUR RESULTS ARE GRADED PROPERLY, MAKE SURE THE NAMES OF YOUR VARIABLES ARE AS INDICATED ON THE ASSIGNMENT. #knitr::purl("ST259F23L3.Rmd") 2
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help