
Concept explainers
To find: The value of joint distribution, marginal distribution and the conditional distribution for the first and second scenario.

Answer to Problem 21E
Solution: Joint Distribution for first scenario is:
Time Period | |||
Design | More than a minute | Less than a minute | Total |
Design1 | 24.00% | 26.00% | 50.00% |
Design2 | 10.00% | 40.00% | 50.00% |
Total | 34.00% | 66.00% | 100.00% |
The conditional distribution is:
Design | More than a minute | Less than a minute |
Design1 | 70.58% | 39.4% |
Design2 | 29.42% | 60.6% |
Total | 100.00% | 100.00% |
And,
Time Period | |||
Design | More than a minute | Less than a minute | Total |
Design1 | 48.00% | 52.00% | 100.00% |
Design2 | 20.00% | 80.00% | 100.00% |
Now, joint distribution for second scenario is:
Response | |||
Student Type | Yes | No | Total |
1st year | 14.60% | 47.40% | 62.00% |
4th year | 20.10% | 17.90% | 38.00% |
Total | 34.70% | 65.30% | 100.00% |
The conditional distribution is,
Student Type | More than a minute | Less than a minute |
1st year | 42.00% | 72.60% |
4th year | 58.00% | 27.40% |
Total | 100.00% | 100.00% |
And,
Response | |||
Student Type | Yes | No | Total |
1st year | 23.50% | 76.45% | 100.00% |
4th year | 53.00% | 47.00% | 100.00% |
Explanation of Solution
Given: In the study, for the first scenario, there are 12 students who look at the 1st design for more than a minute and 5 students who look at the 2nd design for the same time period. But, there are 13 students, who look at 1st design for less than a minute and 20 students who look at 2nd design for less than a minute.
The 2 x 2 table for first scenario is as follows:
Time Period | |||
Design | More than a minute | Less than a minute | Total |
Design1 | 12 | 13 | 25 |
Design2 | 5 | 20 | 25 |
Total | 17 | 33 | 50 |
For the second scenario, there are two types of student, one in the 1st year and other in the 4th year and their responses to the newly proposed core curriculum. Among the 361, 1st year students, 85 respond yes and 276 respond no. While, among the 221, 4th year students, 117 responded yes and 104 responded no.
The 2 x 2 table for the second scenario is as follows:
Response | |||
Student Type | Yes | No | Total |
1st year | 85 | 276 | 361 |
2nd year | 117 | 104 | 221 |
Total | 202 | 380 | 582 |
Calculations:
In the study, for the first scenario, the Joint distribution is computed by dividing the cell element by the total observation. The obtained joint distribution is shown below:
Time Period | |||
Design | More than a minute | Less than a minute | Total |
Design1 | |||
Design2 | |||
Total |
Now, the marginal distribution is computed by dividing the row or column totals by the overall total. Marginal distributions provide information about the individual variables but not about the relationship between two variables.
Thus, the marginal distribution of designs is shown below:
Design | Marginal Distribution |
Design1 | |
Design2 |
And the marginal distribution of time duration is shown below:
Time Period | ||
More than a minute | Less than a minute | |
Marginal probability |
Conditional distribution is obtained by dividing the row or column elements by the sum of the observations in the corresponding row or column. The conditional distribution of Time Period by Design is shown below:
Time Period | |||
Design | More than a minute | Less than a minute | Total |
Design1 | |||
Design2 |
The conditional distribution of Design by Time Period is shown below:
Design | More than a minute | Less than a minute |
Design1 | ||
Design2 | ||
Total |
For the second scenario, the calculations are as follows:
In the study, Joint distribution is computed by dividing the cell element by the total observation. The obtained joint distribution is shown below:
Response | |||
Student Type | Yes | No | Total |
1st year | |||
2nd year | |||
Total |
Now, the marginal distribution is computed by dividing the row or column totals by the overall total. Marginal distributions provide information about the individual variables but not about the relationship between two variables. Thus, the marginal distribution for the types of students is shown below:
Student Type | Marginal Distribution |
1st year | |
2nd year |
Whereas, the marginal distribution of responses is shown below:
Response | ||
Yes | No | |
Marginal Probability |
Conditional distribution is obtained by dividing the row or column elements by the sum of the observations in the corresponding row or column.
The conditional distribution of Responses by Student Type is shown below:
Response | |||
Student Type | Yes | No | Total |
1st year | |||
4th year |
The conditional distribution of Student Type by Responses is shown below:
Student Type | More than a minute | Less than a minute |
1st year | ||
4th year | ||
Total |
Interpretation: The above 2x2 tables for the first scenario show different percentage values for joint, marginal and conditional distributions. The percentage of looking at the 2nd design for more than a minute is 10% and the percentage of looking at the 2nd design for less than a minute is 40%. The value of the marginal distribution for more than a minute is 34% and for less than a minute is 66%. The conditional distributional for the percentage of Time Period by Design for looking at the 1st design for more than a minute is 48%, the percentage of looking at the 2nd design for the same is 20%.
Also, for the second scenario, the percentage of 4th year students responding yes and no for the new curriculum are 20.1% and 17.9% respectively. The marginal distribution for the responding yes and no are 34.7% and 65.3% respectively. The conditional probability of responding no by the 1st year student is 76.45%.
Want to see more full solutions like this?
Chapter 9 Solutions
Introduction to the Practice of Statistics: w/CrunchIt/EESEE Access Card
- In a survey of a group of men, the heights in the 20-29 age group were normally distributed, with a mean of 69.6 inches and a standard deviation of 4.0 inches. A study participant is randomly selected. Complete parts (a) through (d) below. (a) Find the probability that a study participant has a height that is less than 68 inches. The probability that the study participant selected at random is less than 68 inches tall is 0.4. (Round to four decimal places as needed.) 20 2arrow_forwardPEER REPLY 1: Choose a classmate's Main Post and review their decision making process. 1. Choose a risk level for each of the states of nature (assign a probability value to each). 2. Explain why each risk level is chosen. 3. Which alternative do you believe would be the best based on the maximum EMV? 4. Do you feel determining the expected value with perfect information (EVWPI) is worthwhile in this situation? Why or why not?arrow_forwardQuestions An insurance company's cumulative incurred claims for the last 5 accident years are given in the following table: Development Year Accident Year 0 2018 1 2 3 4 245 267 274 289 292 2019 255 276 288 294 2020 265 283 292 2021 263 278 2022 271 It can be assumed that claims are fully run off after 4 years. The premiums received for each year are: Accident Year Premium 2018 306 2019 312 2020 318 2021 326 2022 330 You do not need to make any allowance for inflation. 1. (a) Calculate the reserve at the end of 2022 using the basic chain ladder method. (b) Calculate the reserve at the end of 2022 using the Bornhuetter-Ferguson method. 2. Comment on the differences in the reserves produced by the methods in Part 1.arrow_forward
- You are provided with data that includes all 50 states of the United States. Your task is to draw a sample of: o 20 States using Random Sampling (2 points: 1 for random number generation; 1 for random sample) o 10 States using Systematic Sampling (4 points: 1 for random numbers generation; 1 for random sample different from the previous answer; 1 for correct K value calculation table; 1 for correct sample drawn by using systematic sampling) (For systematic sampling, do not use the original data directly. Instead, first randomize the data, and then use the randomized dataset to draw your sample. Furthermore, do not use the random list previously generated, instead, generate a new random sample for this part. For more details, please see the snapshot provided at the end.) Upload a Microsoft Excel file with two separate sheets. One sheet provides random sampling while the other provides systematic sampling. Excel snapshots that can help you in organizing columns are provided on the next…arrow_forwardThe population mean and standard deviation are given below. Find the required probability and determine whether the given sample mean would be considered unusual. For a sample of n = 65, find the probability of a sample mean being greater than 225 if μ = 224 and σ = 3.5. For a sample of n = 65, the probability of a sample mean being greater than 225 if μ=224 and σ = 3.5 is 0.0102 (Round to four decimal places as needed.)arrow_forward***Please do not just simply copy and paste the other solution for this problem posted on bartleby as that solution does not have all of the parts completed for this problem. Please answer this I will leave a like on the problem. The data needed to answer this question is given in the following link (file is on view only so if you would like to make a copy to make it easier for yourself feel free to do so) https://docs.google.com/spreadsheets/d/1aV5rsxdNjHnkeTkm5VqHzBXZgW-Ptbs3vqwk0SYiQPo/edit?usp=sharingarrow_forward
- The data needed to answer this question is given in the following link (file is on view only so if you would like to make a copy to make it easier for yourself feel free to do so) https://docs.google.com/spreadsheets/d/1aV5rsxdNjHnkeTkm5VqHzBXZgW-Ptbs3vqwk0SYiQPo/edit?usp=sharingarrow_forwardThe following relates to Problems 4 and 5. Christchurch, New Zealand experienced a major earthquake on February 22, 2011. It destroyed 100,000 homes. Data were collected on a sample of 300 damaged homes. These data are saved in the file called CIEG315 Homework 4 data.xlsx, which is available on Canvas under Files. A subset of the data is shown in the accompanying table. Two of the variables are qualitative in nature: Wall construction and roof construction. Two of the variables are quantitative: (1) Peak ground acceleration (PGA), a measure of the intensity of ground shaking that the home experienced in the earthquake (in units of acceleration of gravity, g); (2) Damage, which indicates the amount of damage experienced in the earthquake in New Zealand dollars; and (3) Building value, the pre-earthquake value of the home in New Zealand dollars. PGA (g) Damage (NZ$) Building Value (NZ$) Wall Construction Roof Construction Property ID 1 0.645 2 0.101 141,416 2,826 253,000 B 305,000 B T 3…arrow_forwardRose Par posted Apr 5, 2025 9:01 PM Subscribe To: Store Owner From: Rose Par, Manager Subject: Decision About Selling Custom Flower Bouquets Date: April 5, 2025 Our shop, which prides itself on selling handmade gifts and cultural items, has recently received inquiries from customers about the availability of fresh flower bouquets for special occasions. This has prompted me to consider whether we should introduce custom flower bouquets in our shop. We need to decide whether to start offering this new product. There are three options: provide a complete selection of custom bouquets for events like birthdays and anniversaries, start small with just a few ready-made flower arrangements, or do not add flowers. There are also three possible outcomes. First, we might see high demand, and the bouquets could sell quickly. Second, we might have medium demand, with a few sold each week. Third, there might be low demand, and the flowers may not sell well, possibly going to waste. These outcomes…arrow_forward
- Consider the state space model X₁ = §Xt−1 + Wt, Yt = AX+Vt, where Xt Є R4 and Y E R². Suppose we know the covariance matrices for Wt and Vt. How many unknown parameters are there in the model?arrow_forwardBusiness Discussarrow_forwardYou 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_forward
- Big Ideas Math A Bridge To Success Algebra 1: Stu...AlgebraISBN:9781680331141Author:HOUGHTON MIFFLIN HARCOURTPublisher:Houghton Mifflin HarcourtGlencoe Algebra 1, Student Edition, 9780079039897...AlgebraISBN:9780079039897Author:CarterPublisher:McGraw Hill

