To divide: The 28 storms into 4 subgroups.
To select: A random sample of 3 storms from each group.
To compute: The means for maximum wind speeds.
To compare: The means to the population

Explanation of Solution
Given info:
In the 2005 Atlantic hurricane season the maximum wind speed and classifications for different storms are given in the data.
Calculation:
First arrange the data according to the serial number,
Serial No. | Name | Max. wind | Classification |
1 | Arlene | 70 | Storm |
2 | Bret | 40 | S |
3 | Cindy | 75 | Hurricane |
4 | Dennis | 150 | H |
5 | Emily | 160 | H |
6 | Franklin | 70 | S |
7 | Gert | 45 | S |
8 | Harvey | 65 | S |
9 | Irene | 105 | H |
10 | Jose | 50 | S |
11 | Katrina | 175 | H |
12 | Lee | 40 | S |
13 | Maria | 115 | H |
14 | Nate | 90 | H |
15 | Ophelia | 85 | H |
16 | Philippe | 70 | H |
17 | Rita | 175 | H |
18 | Stan | 80 | H |
19 | Unnamed | 50 | S |
20 | Tammy | 50 | S |
21 | Vince | 75 | H |
22 | Wilma | 175 | H |
23 | Alpha | 50 | S |
24 | Beta | 115 | H |
25 | Gamma | 55 | S |
26 | Delta | 70 | S |
27 | Epsilon | 85 | H |
28 | Zeta | 65 | S |
Procedure for dividing the 28 storms into 4 subgroups:
Step1:
Divide the population into two groups. From the 28 storms, divide the observations according to classification- Storm and Hurricane. There are 15 Hurricanes and 13 Storms:
Group 1 (H) | Group 2 (S) | ||
Name | Max. wind | Name | Max. wind |
Cindy | 75 | Arlene | 70 |
Dennis | 150 | Bret | 40 |
Emily | 160 | Franklin | 70 |
Irene | 105 | Gert | 45 |
Katrina | 175 | Harvey | 65 |
Maria | 115 | Jose | 50 |
Nate | 90 | Lee | 40 |
Ophelia | 85 | Unnamed | 50 |
Philippe | 70 | Tammy | 50 |
Rita | 175 | Alpha | 50 |
Stan | 80 | Gamma | 55 |
Vince | 75 | Delta | 70 |
Wilma | 175 | Zeta | 65 |
Beta | 115 | ||
Epsilon | 85 |
Step2:
Divide each group into two subgroups, based on the
For Group 1 (H), the median value of max. wind is 105. Thus, the 1st subgroup will contain all storms with max. wind less than or equal to 105 and the 2nd subgroup will contain all storms with max. wind greater than 105.
For Group 2 (S), the median value of max. wind is 50. Thus, the 3rd subgroup will contain all storms with max. wind less than or equal to 50 and the 4th subgroup will contain all storms with max. wind greater than 50.
The subgroups are:
SNO | Subgroup1 | Subgroup2 | Subgroup3 | Subgroup4 |
1 | Cindy | Dennis | Bret | Arlene |
2 | Irene | Emily | Gert | Franklin |
3 | Nate | Katrina | Jose | Harvey |
4 | Ophelia | Maria | Lee | Gamma |
5 | Philippe | Rita | Unnamed | Delta |
6 | Stan | Wilma | Tammy | Zeta |
7 | Vince | Beta | Alpha | |
8 | Epsilon |
From the s select a random sample of 3 storms by using random numbers.
Procedure for selecting 3 random samples from subgroup 1:
- From the figure 14.1(Table of random numbers), select a starting point.
- Here, the selected starting point is ‘7’ which is present in 1st row and 1st column. There are 8 names of storms in subgroup 1. Hence, select the random numbers in the
range of ‘1’ to ‘8. Avoid repetition of numbers and 0. - The random numbers starting from ‘7’ are:
7, 2, 1.
Thus, the random numbers are and corresponding names of the wind are,
Serial No. | Name |
7 | Vince |
2 | Irene |
1 | Cindy |
The average maximum wind of above selected sample is calculated by using the following formula.
Thus, the sample mean for subgroup 1 is 85.
Procedure for selecting 3 random samples from subgroup 2:
- From the figure 14.1(Table of random numbers), select a starting point.
- Here, the selected starting point is ‘4’ which is present in 1st row and 2nd column. There are 7 names of storms in subgroup 2. Hence, select the random numbers in the range of ‘1’ to ‘7’. Avoid repetition of numbers and 0.
- The random numbers starting from ‘4’ are:
4, 5, 1.
Thus, the random numbers are and corresponding names of the wind are,
Serial No. | Name |
4 | Maria |
5 | Rita |
1 | Dennis |
The average maximum wind of above selected sample is calculated by using the following formula.
Thus, the sample mean for subgroup 2 is 146.67.
Procedure for selecting 3 random samples from subgroup 3:
- From the figure 14.1(Table of random numbers), select a starting point.
- Here, the selected starting point is ‘7’ which is present in 5th row and 13th column. There are 7 names of storms in subgroup 3. Hence, select the random numbers in the range of ‘1’ to ‘7’. Avoid repetition of numbers and 0.
- The random numbers starting from ‘7’ are:
7, 4, 2.
Thus, the random numbers are and corresponding names of the wind are,
Serial No. | Name |
4 | Alpha |
5 | Lee |
1 | Gret |
The average maximum wind of above selected sample is calculated by using the following formula.
Thus, the sample mean for subgroup 3 is 45.
Procedure for selecting 3 random samples from subgroup 4:
- From the figure 14.1(Table of random numbers), select a starting point.
- Here, the selected starting point is ‘5’ which is present in 6th row and 9th column. There are 6 names of storms in subgroup 4. Hence, select the random numbers in the range of ‘1’ to ‘6’. Avoid repetition of numbers and 0.
- The random numbers starting from ‘5’ are:
5, 2, 6.
Thus, the random numbers are and corresponding names of the wind are,
Serial No. | Name |
5 | Delta |
2 | Franklin |
6 | Zeta |
The average maximum wind of above selected sample is calculated by using the following formula.
Thus, the sample mean for subgroup 4 is 68.3.
The population mean of maximum wind is,
Thus, the population mean is 87.5.
Comparison of means:
The sample mean for subgroup 1 is 85 and the population mean of maximum wind speed is 87.5.
The sample mean for subgroup 2 is 146.67 and the population mean of maximum wind speed is 87.5.
The sample mean for subgroup 3 is 45 and the population mean of maximum wind speed is 87.5.
The sample mean for subgroup 4 is 68.3 and the population mean of maximum wind speed is 87.5.
That implies that the sample means are smaller than the population mean for subgroup 3 an 4 whereas the sample mean is greater than the population mean for subgroup 2. But, for subgroup 1 sample mean is slightly smaller than population mean.
It is clear that there is some difference between the sample mean and the population mean.
Want to see more full solutions like this?
Chapter 14 Solutions
Bluman, Elementary Statistics: A Step By Step Approach, © 2015, 9e, Student Edition (reinforced Binding) (a/p Statistics)
- You want to obtain a sample to estimate the proportion of a population that possess a particular genetic marker. Based on previous evidence, you believe approximately p∗=11% of the population have the genetic marker. You would like to be 90% confident that your estimate is within 0.5% of the true population proportion. How large of a sample size is required?n = (Wrong: 10,603) Do not round mid-calculation. However, you may use a critical value accurate to three decimal places.arrow_forward2. [20] Let {X1,..., Xn} be a random sample from Ber(p), where p = (0, 1). Consider two estimators of the parameter p: 1 p=X_and_p= n+2 (x+1). For each of p and p, find the bias and MSE.arrow_forward1. [20] The joint PDF of RVs X and Y is given by xe-(z+y), r>0, y > 0, fx,y(x, y) = 0, otherwise. (a) Find P(0X≤1, 1arrow_forward4. [20] Let {X1,..., X} be a random sample from a continuous distribution with PDF f(x; 0) = { Axe 5 0, x > 0, otherwise. where > 0 is an unknown parameter. Let {x1,...,xn} be an observed sample. (a) Find the value of c in the PDF. (b) Find the likelihood function of 0. (c) Find the MLE, Ô, of 0. (d) Find the bias and MSE of 0.arrow_forward3. [20] Let {X1,..., Xn} be a random sample from a binomial distribution Bin(30, p), where p (0, 1) is unknown. Let {x1,...,xn} be an observed sample. (a) Find the likelihood function of p. (b) Find the MLE, p, of p. (c) Find the bias and MSE of p.arrow_forwardGiven the sample space: ΩΞ = {a,b,c,d,e,f} and events: {a,b,e,f} A = {a, b, c, d}, B = {c, d, e, f}, and C = {a, b, e, f} For parts a-c: determine the outcomes in each of the provided sets. Use proper set notation. a. (ACB) C (AN (BUC) C) U (AN (BUC)) AC UBC UCC b. C. d. If the outcomes in 2 are equally likely, calculate P(AN BNC).arrow_forwardSuppose a sample of O-rings was obtained and the wall thickness (in inches) of each was recorded. Use a normal probability plot to assess whether the sample data could have come from a population that is normally distributed. Click here to view the table of critical values for normal probability plots. Click here to view page 1 of the standard normal distribution table. Click here to view page 2 of the standard normal distribution table. 0.191 0.186 0.201 0.2005 0.203 0.210 0.234 0.248 0.260 0.273 0.281 0.290 0.305 0.310 0.308 0.311 Using the correlation coefficient of the normal probability plot, is it reasonable to conclude that the population is normally distributed? Select the correct choice below and fill in the answer boxes within your choice. (Round to three decimal places as needed.) ○ A. Yes. The correlation between the expected z-scores and the observed data, , exceeds the critical value, . Therefore, it is reasonable to conclude that the data come from a normal population. ○…arrow_forwardding question ypothesis at a=0.01 and at a = 37. Consider the following hypotheses: 20 Ho: μ=12 HA: μ12 Find the p-value for this hypothesis test based on the following sample information. a. x=11; s= 3.2; n = 36 b. x = 13; s=3.2; n = 36 C. c. d. x = 11; s= 2.8; n=36 x = 11; s= 2.8; n = 49arrow_forward13. A pharmaceutical company has developed a new drug for depression. There is a concern, however, that the drug also raises the blood pressure of its users. A researcher wants to conduct a test to validate this claim. Would the manager of the pharmaceutical company be more concerned about a Type I error or a Type II error? Explain.arrow_forwardFind the z score that corresponds to the given area 30% below z.arrow_forwardFind the following probability P(z<-.24)arrow_forward3. Explain why the following statements are not correct. a. "With my methodological approach, I can reduce the Type I error with the given sample information without changing the Type II error." b. "I have already decided how much of the Type I error I am going to allow. A bigger sample will not change either the Type I or Type II error." C. "I can reduce the Type II error by making it difficult to reject the null hypothesis." d. "By making it easy to reject the null hypothesis, I am reducing the Type I error."arrow_forwardarrow_back_iosSEE MORE QUESTIONSarrow_forward_ios
- MATLAB: An Introduction with ApplicationsStatisticsISBN:9781119256830Author:Amos GilatPublisher:John Wiley & Sons IncProbability and Statistics for Engineering and th...StatisticsISBN:9781305251809Author:Jay L. DevorePublisher:Cengage LearningStatistics for The Behavioral Sciences (MindTap C...StatisticsISBN:9781305504912Author:Frederick J Gravetter, Larry B. WallnauPublisher:Cengage Learning
- Elementary Statistics: Picturing the World (7th E...StatisticsISBN:9780134683416Author:Ron Larson, Betsy FarberPublisher:PEARSONThe Basic Practice of StatisticsStatisticsISBN:9781319042578Author:David S. Moore, William I. Notz, Michael A. FlignerPublisher:W. H. FreemanIntroduction to the Practice of StatisticsStatisticsISBN:9781319013387Author:David S. Moore, George P. McCabe, Bruce A. CraigPublisher:W. H. Freeman





