Statistics for Business Assignment - Covariance, Correlation, Exponential Distribution, Hypothesis Test
Verified
Added on 2023/06/04
|13
|1672
|354
AI Summary
This assignment covers topics such as covariance, correlation, exponential distribution, and hypothesis testing. It includes computations and interpretations of results.
Contribute Materials
Your contribution can guide someone’s learning journey. Share your
documents today.
Statistics for Business Assignment Student’s Name Course Code Student’s Number Institution Affiliation
Secure Best Marks with AI Grader
Need help grading? Try our AI Grader for instant feedback on your assignments.
Question One Data:Years of Experience (x)and Salary (y) Table1 x53792468 y2023151127211714 a.Covariance and It interpretation According toHahs-Vaughn& Lomax (2013), the covariance betweenX∧Yis given by the formula; Cov(X,Y)= ∑ i n (Xi−X)(Yi−Y) n−1, whereX∧YaresamplemeansofX∧Yrespectively,nisthesample¿¿ To work out the covariance between X and Y, all the items in the above formula will be computed and presented in table:
Table2 StatisticXYX−XY−Y(X−X)(Y−Y) 520-0.51.5-0.75 323-2.54.5-11.25 7151.5-3.5-5.25 9113.5-7.5-26.25 227-3.58.5-29.75 421-1.52.5-3.75 6170.5-1.5-0.75 8142.5-4.5-11.25 ∑ i n (Xi−X)(Yi−Y)=−89n(sample size)88 Sum44148 Mean∑X n=44 8=5.5∑X n=148 8=18.5 Therefore, Cov(X,Y)= ∑ i n (Xi−X)(Yi−Y) n−1=−89 8−1 ¿−12.7143 Interpretation: The covariance explains the relationship between two variables, say X and Y (Hassett &Stewart 2006). According toHassett &Stewart (2006), a negative covariance between two variables, indicates a negative relationship, that two are negatively associated. Therefore, since the
covariance between X and Y, -12.71, is negative,Years of Experience (x)and Salary (y) are said to be negatively related. This implies that a change in one influence the other in opposite direction. b.Reason for the Negativity of the covariance between X and Y inaabove. The covariance between X and Y is negative, since small values of X (year of experience) are associated withlarge values of Y (salary) and vice versa. This is an indicator of negative relationship. c.Coefficient of correlation and its Interpretation According toHassett &Stewart (2006), coefficient of correlation is computed using the formula Corr(X,Y)=Cov(X,Y) √Var(X)∗Var(Y) The data from table 2 will be borrowed to work out Variance(X) and Variance(Y) Var(X)=∑(Xi−X)2 n−1,∧Var(Y)=∑(Yi−Y)2 n−1 StatisticsXY(Xi−X)(Yi−Y)(Xi−X)2 (Yi−Y)2 520-0.51.50.252.25 323-2.54.56.2520.25 7151.5-3.52.2512.25 9113.5-7.512.2556.25
Paraphrase This Document
Need a fresh take? Get an instant paraphrase of this document with our AI Paraphraser
227-3.58.512.2572.25 421-1.52.52.256.25 6170.5-1.50.252.25 8142.5-4.56.2520.25 n(sample size) 88 Sum4414842192 Mean5.518.5 Therefore, Var(X)=∑(Xi−X)2 n−1=42 7=6 Var(Y)=∑(Yi−Y)2 n−1=192 7=27.43 Then use the two variances and the covariance obtained in part a to find the coefficient of correlation. Corr(X,Y)=Cov(X,Y) √Var(X)∗Var(Y)=−12.7143 √6∗27.43 ¿−12.7143 12.8285=−0.991098 Hence, the correlation coefficient is -0.9911, which is very close to -1. This implies X (years of experience) and Y (salary) are highly negatively related. Just like the covariance, it shows that X and Y are negatively associated. d.Reason for negative correlation coefficient.
The covariance between X and Y was negative, which influence the sign of correlation level between the two variables. Question Two Data: meanof an exponential distribution is 3 minute The probability density function (pdf) of an exponential distribution is; f(t)=λe−λt,fort≥0 Given this pdf, the mean (T) is given by1 λ.Also the cumulative probability function (Cdf) is given by1−e−λt a.The valueofλ,parameter for the exponential distribution Mean(T)=3=1 λ,3λ=1,therrfore,λ=1 3 b.The proportion of customers who will hold for more than 1.5 minutes. This will be given by the probability of waiting for more than 1.5 minutes. This will be computed by integrating the pdf of exponential distribution between 1.5 and infinity.
∫ 1.5 ∞ 1 3e −t 3dt ¿−3∗1 3{∞ 1.5e −t 3=−1(0−e −1.5 3) ¿e −1.5 3=0.6065 ¿60.65% c.Waiting time at which 10% of the customer will continue to hold. This the probability thatT=t, which can computed from the Cdf of the exponential distribution. Therefore, 0.1=1−e−λt Since,λ=1 3then,−0.9=−e −t 3 0.9=e −t 3 ln(0.9)=−1 3t 0.10536=1 3t t=0.31608 t=0.316minutes d.Probability a randomly selected customer is placed on hold for 3 to 6 minutes. This will be given byP(T=6)−P(T=3)
Secure Best Marks with AI Grader
Need help grading? Try our AI Grader for instant feedback on your assignments.
P(T=6)=1−e −6 3=1−e−2 ¿1−0.1353 ¿0.8647 P(T=3)=1−e −3 3=1−e−1=1−0.3679=0.6321 Therefore,P(T=6)−P(T=3)=0.8647−0.6321 ¿0.2326 Question Three Data: H0: = 950 hours vs. H1: 950 hours,n¿ Standarddeviation(σ)=200hours a.Computation ofβthe probability of a Type II error whenμ= 1000 andα= 0.10. Below hypothesis will be considered; H0:μ=950 H1:μ≠950 First, the critical value of sample mean will be computed. According toGoos & Meintrup (2016), critical value of mean is given by c=μ0±Zα∗σ √n
s √n=200 √25=200 5=40 μ0=950Zα=0.1=±1.645 Zα∗σ √n=1.645∗40=65.8 Therefore,c=950±65.8 ¿884.2≤c≤1015.8 β=Prob¿ This given by Prob¿ ¿Prob(z≤1015.8−1000 40)−Prob(z<884.2−1000 40) ¿Prob(z≤0.395)−Prob(−2.895)=0.6554−0.0019=0.6535 Thus,β=0.6535 b.Calculate the power of the test whenμ= 1000 andα= 0.10. The power of the test is given by
ptest=1−β=1−0.6535=0.3465 c.Interpretation of power of the test Ptest=0.3465, is the probability of correctly rejecting the null hypothesis thatμ=950. d.Effects of increasing the sample size. To explain this, we shall assume that the sample size of the population in question was changed from 25 to 36. Then compute the newβ c=μ0±Zα∗σ √n σ √n=200 √36=33.33 c=950±1.645∗33.33=950±54.83 ¿895.17≤c≤1004.8 β=Prob¿ This given by Prob¿ ¿Prob(z≤1004−1000 33.33)−Prob(z<895.17−1000 33.33)
Paraphrase This Document
Need a fresh take? Get an instant paraphrase of this document with our AI Paraphraser
¿Prob(z≤0.12)−Prob(−3.15)=0.5478−0.00082 ¿0.54698≈0.547 Thus,Newβ=0.547, which is less than initialβ=0.6535. This clear show that the when sample size is increasedβ,probability of a Type II error will decrease. On the other hands, the power of test will increase as it depends on the value ofβ, a smallerβresults to a bigger power of test. Question Four Data: Production Filling Operations Standarddeviation(σ)=6,Meanweightforproductionprocess(μ)=47ounces Sample¿36,samplemean(x)=48.6 Hypothesis test at 5% significance level H0:μ=47 H0:μ>47 Since the population mean and standard deviation are known, the hypothesis test will be based onz-score. According toGoos & Meintrup (2016, p.100),z-score is computed by the formula
z=x−μ σ √n ¿48.6−47 6/√36=1.6 Hence,z-score is 1.6 To decide the significance of the test, critical value ofz, will be determined from tables at 5% significance level. Since, the above test single tailed (right), the criticalzwill be 1.645, which is greater thancomputed−z, 1.6. Interpretation: Sincez−computedcomputed is less than criticalz, then null hypothesis will not be rejected (Goos & Meintrup 2016).This implies that the population mean is not greater than 47 at 5% significance level
References Hahs-Vaughn, D.L. and Lomax, R.G., 2013.An introduction to statistical concepts. Routledge. Hassett, M.J. and Stewart, D., 2006.Probability for risk management. Actex Publications. Goos, P. and Meintrup, D., 2016.Statistics with JMP: Hypothesis Tests, ANOVA and Regression. John Wiley & Sons.