Statistical Reasoning Preview Assignment 12.C Preview Assignment 12.C Preparing for the next class In the next lesson, you will need to find normal distribution probabilities using a table of areas under the standard normal curve and interpret the meaning of z-scores. Find the two-page table of probabilities at the end of this preview and have it ready to use for this assignment. Also be sure to bring the table to class for your next lesson. Suppose a variable has a normal distribution. To find the probability of an observation having a z-score of less than 1.23, think about the normal distribution as follows: Write 1.23 as 1.2 + 0.03 and locate 1.2 on the left side of the table as shown. The Charles A. Dana Center at The University of Texas at Austin 1 Version 2.0 Statistical Reasoning Preview Assignment 12.C Next, locate 0.03 at the top of the table and read the table as illustrated below. There is a 0.891 probability of having a z-score less than 1.23, which can be written as P(z < 1.23) = 0.891. Note that a positive z-score is to the right of the mean, and the probability is more than 0.5. (Look at the shaded curve at the beginning of this assignment.) 1) Use the table above to determine the probability of z < 1.14. 2) Use Table 1 at the end of this preview to determine the probability of z < .36. 3) Use Table 2 at the end of this preview to determine the probability of z < –1.63. The Charles A. Dana Center at The University of Texas at Austin 2 Version 2.0 Statistical Reasoning Preview Assignment 12.C Using Table 1 or Table 2 at the end of this preview, determine the following probabilities. 4) P(z < 1.19) = 5) P(z < –1.19) = 6) P(z < 3.02) = 7) P(z < –3.02) = 8) Without looking at the table, do you expect the probability of z < –0.4 to be: a) Less than 0 b) Between 0 and 0.5 c) Between 0.5 and 1 d) More than 1 The Charles A. Dana Center at The University of Texas at Austin 3 Version 2.0 Statistical Reasoning Preview Assignment 12.C Monitoring your readiness 9) To effectively plan and use your time wisely, it helps to think about what you know and do not know. For each of the following, rate how confident you are that you can successfully do that skill. Use the following descriptions to rate yourself: 5—I am extremely confident I can do this task. 4—I am somewhat confident I can do this task. 3—I am not sure how confident I am. 2—I am not very confident I can do this task. 1—I am definitely not confident I can do this task. Skills needed for Lesson 12, Part C Skill or Concept: I can . . . Questions to check your understanding Find normal distribution probabilities using tables. Rating from 1 to 5 1–7 Interpret the meaning of z-scores. 8 Now use the ratings to get ready for your next lesson. If your rating is a 3 or below, you should get help with the material before class. Remember, your instructor is going to assume that you are confident with the material and will not take class time to answer questions about it. 10) What are some ways to get help? The Charles A. Dana Center at The University of Texas at Austin 4 Version 2.0 Statistical Reasoning Preview Assignment 12.C Table 1: The Charles A. Dana Center at The University of Texas at Austin 5 Version 2.0 Statistical Reasoning Preview Assignment 12.C Table 2: The Charles A. Dana Center at The University of Texas at Austin 6 Version 2.0 Statistical Reasoning Student Pages 12.C, Probability and critical values Lesson 12, Part C Probability and Critical Values You are part of a design team working for an American auto company that is attempting to make the most fuel-efficient car on the market. 1) What are some features of a car that might affect fuel efficiency? Credit: ©iStock.com Objectives for the lesson You will understand: o The z-score as it relates to the standard normal curve. You will be able to: o Calculate probabilities using the normal curve. In designing the car, you will need to be sure that most people will be comfortable. Begin by analyzing the heights of adult American females. (You will analyze male heights in the homework). Women’s heights are normally distributed with a mean of 64 inches and a standard deviation of 2.8 inches. 2) Because of the design of the interior, women who are less than 60 inches tall will not be comfortable in the car. Part A: Draw a sketch of the normal distribution of female heights. Shade the area under the curve that represents the probability that a woman is less than 60 inches tall. Part B: Determine the probability that a randomly selected adult American female is less than 60 inches tall. The Charles A. Dana Center at The University of Texas at Austin 7 Version 2.0 Statistical Reasoning Student Pages 12.C, Probability and critical values 3) Women who are over 70 inches tall will also be uncomfortable in the car. Part A: Shade the area under the curve that corresponds to adult American females who are less than 70 inches tall. Part B: Determine the probability that a randomly selected adult American female is less than 70 inches tall. 4) Now focus on the women who will be comfortable. Part A: Shade the area under the curve that corresponds to adult American females who are between 60 inches tall and 70 inches tall. Part B: Determine the probability that a randomly selected adult American female is between 60 inches tall and 70 inches tall. 5) If the prototype comfortably accommodates adult females between 60 inches tall and 70 inches tall, what proportion of adult American women will be comfortable in the car? 6) What proportion of adult American females are too tall to fit in the prototype comfortably? The Charles A. Dana Center at The University of Texas at Austin 8 Version 2.0 Statistical Reasoning Suggested Instructor Notes 12.C, Probability and critical values Lesson 12, Part C Probability and Critical Values Overview and student objectives Lesson Length: 25 minutes Overview Prior Lesson: Lesson 12, Part B, “z-Scores and Normal Distributions” In this lesson, students will analyze normally distributed heights of women in order to make automobile design recommendations. In Preview Assignment 12.C, students computed probabilities using z-tables; they will apply that skill in this lesson to compute the probabilities of women meeting certain height requirements using the normal curve. The practice assignment repeats these concepts for men. Next Lesson: Lesson 12, Part D, “Probability and Critical Values (continued)” (25 minutes) Objectives Outcomes: PS2, PS3 Students will understand: Goals: Communication and Problem Solving • The z-score as it relates to the standard normal curve. Students will be able to: • Constructive Perseverance Level: 2 Related Foundations Outcome: N8 Calculate probabilities using the normal curve. Suggested resources and preparation Materials and technology • Computer, projector, document camera • Preview Assignment 12.C • Student Pages for Lesson 12, Part C • Practice Assignment 12.C Prerequisite assumptions Before beginning this lesson, students should be able to find probabilities using z-tables. Making connections This lesson: • Connects back to computing z-scores. • Connects forward to sampling distributions and the Central Limit Theorem. The Charles A. Dana Center at The University of Texas at Austin 9 Version 2.0 Statistical Reasoning Suggested Instructor Notes 12.C, Probability and critical values Background context The students used a standard normal table in the preview and were asked to bring it to class. Suggested instructional plan Frame the lesson (6 minutes) Student Pages Literacy Support • Debrief the preview assignment to ensure student understanding. Ask students to refer to the z-table provided in the preview. (They were asked to bring the table to class.) • Choose a positive z-score and a negative z-score example to write on the board. Ask students to determine the probability of a z-score less than those given. • Look for students who do not understand how to use a table to find probabilities and provide assistance before moving on. • Take responses to question 1. • “How do car companies make decisions about the interior design of an automobile?” • “What is a ‘prototype’?” Have students share what prototype means and reach consensus on the definition before moving on. • “Why do you think it’s important to design an automobile that meets the needs of most people?” • Allow discussion before transitioning to the lesson. • Transition to the lesson activities by briefly discussing the Objectives for the lesson. Lesson activities (15 minutes) Questions 2–3 Guiding Question • Note: Consider having half of the class complete problem 2 and the other half of the class complete problem 3. Use the results from each group to answer question 4. • “How could we label the x-axis to help us visualize standard deviations?” • Assist students with drawing the normal distribution. Ensure that students are labeling appropriately. The Charles A. Dana Center at The University of Texas at Austin 10 Version 2.0 Statistical Reasoning Suggested Instructor Notes 12.C, Probability and critical values • Assist students, as needed, in locating and plotting 60 on their graph. • “Where is 60 on the x-axis?” • “What information do you need in order to determine the shaded area?” [Answer: The z-score for 60.] • Facilitate question 3 in a similar manner. Question 4 • This question may be a bit more difficult for students because it involves visualizing two different areas and subtracting. • Have the two groups share the results and compare the areas. o “How can I use both areas to find the area in between?” o “In terms of area, what information does the table provide?” o “How can I use both z-scores to help me find the answer?” • Remind students that the table only provides the area to the left of a z-score and guide them to understand that subtraction is the key. You may want display a student’s graph, point to the area in question, and guide students to understand how to subtract areas in order to arrive at the answer. • If students used shading and double-shading on a single graph, consider drawing separate curves on the board, with the graph for question 3 aligned beneath the curve for question 2. Label the areas on each curve. Draw a third graph underneath with vertical lines at 60 and 70, then shade in between the lines. Question 5 • This question promotes discussion of the relationship between proportions and probabilities. For example, the probability that a woman is less than 60 inches tall follows directly from the proportion of the population of women who are less than 60 inches tall. Question 6 • This question requires students to subtract from 1 to find the area above a z-score. Ask: o “What is the total area under the curve?” [Answer: 1] o “If I know the area below, how can I find the area above?” • If students are struggling, refer them back to the curve and shading for question 3. Again, if the students used shading and doubleshading, refer them to the individual graphs on the board. Guiding Questions The Charles A. Dana Center at The University of Texas at Austin 11 Version 2.0 Statistical Reasoning Suggested Instructor Notes 12.C, Probability and critical values Wrap-up/transition (4 minutes) Wrap-up Transition • Remind students that the normal distribution occurs much more often than uniform distributions. Explain that the normal distribution will also play a role as they move into the idea of inference and sampling. • Remind students that this study focused only on women. Men will be analyzed in their homework. • Have students refer back to the Objectives for the lesson and check the ones they recognize from the activity. Alternatively, they may check the objectives throughout the lesson. • “Management sends a memo: The car must be comfortable for all but the tallest 2.5% of American women. What should we do?” Suggested assessment, assignments, and reflections • Give Practice Assignment 12.C. • Give the Preview Assignments, if any, for the lesson activities you plan to complete in the next class meeting. The Charles A. Dana Center at The University of Texas at Austin 12 Version 2.0 Statistical Reasoning Practice Assignment 12.C Practice Assignment 12.C 1) The heights of adult American males are approximately normally distributed with a mean of 69 inches and a standard deviation of 2.5 inches. Part A: What is the probability that a randomly selected adult American male is less than 63 inches tall? Round your answer to the nearest thousandth. Part B: What is the probability that a randomly selected adult American male is less than 76 inches tall? Round your answer to the nearest thousandth. Part C: What is the probability that a randomly selected adult American male is more than 76 inches tall? Round your answer to the nearest thousandth. Part D: What is the probability that a randomly selected adult American male is between 63 and 76 inches tall? Round your answer to the nearest thousandth. 13 Version 2.0 Statistical Reasoning Practice Assignment 12.C 2) Is there a difference between the following two questions? Explain. What is the probability that a randomly selected adult American male is more than 76 inches tall? What proportion of adult American males are more than 76 inches tall? 3) The time students take to complete a statistics test is approximately normally distributed with a mean of 74 minutes and a standard deviation of 8 minutes. Part A: What is the probability that a student took more than 1 hour to complete the test? Part B: What is the probability that a student took less than 84 minutes to complete the test? Part C: What is the probability that a student took between 60 and 84 minutes to complete the test? 14 Version 2.0 Statistical Reasoning Practice Assignment 12.C 4) A company regularly chooses 100 people to survey through random selection. They want to ensure that their survey groups are reasonably representative of the U.S. population. 17% of the U.S. population is Hispanic. If the company truly used simple random sampling of the U.S. population, the number of Hispanics in the survey groups would follow the probability distribution shown below. These data look roughly normal, so we can approximate this with a normal distribution with the same mean and standard deviation. Assuming the number of Hispanics in the survey groups followed this continuous distribution, answer following the questions. Part A: What percentage of the survey groups have fewer than 20 Hispanics? 15 Version 2.0 Statistical Reasoning Practice Assignment 12.C Part B: What percentage of survey groups have more than 18 Hispanics? Part C: What percentage of survey groups have between 15 and 25 Hispanics? Part D: What percentage of survey groups have fewer than 6 Hispanics? What might you suspect if most of the company's survey groups actually had fewer than 6 Hispanics? 16 Version 2.0 Statistical Reasoning Practice Assignment 12.C 5) For each of the following situations: o Sketch a normal curve and shade a region that represents the probability. o Calculate the probability. The first problem has been done as an example. Example: If µ = 25 and σ = 3, the probability that x > 20. Answer: P(x > 20) = 0.9522 Part A: If µ = 413 and σ = 63, the probability that x < 400. 17 Version 2.0 Statistical Reasoning Practice Assignment 12.C Part B: If µ = –40 and σ = 5, the probability that x > –37. Part C: If µ = 0.16 and σ = 0.0132, the probability that 0.16 < x < 0.17. 18 Version 2.0 Statistical Reasoning Preview Assignment 12.D Preview Assignment 12.D Preparing for the next class In the next lesson, you will need to use a normal probability table to find the z-score associated with a certain probability, read and understand a probability table, and solve equations. In the last lesson, you used z-scores to find a probability. Now you will read the table “from the inside out,” starting from a probability and finding the z-score. To determine the z-score associated with probability = 0.936, begin by finding 0.936 in the body of the table. Then look left and up to determine the z-score associated with the probability. See below: Probability = 0.936 is associated with the z-score 1.52. The Charles A. Dana Center at The University of Texas at Austin 19 Version 2.0 Statistical Reasoning Preview Assignment 12.D 1) Find the z-score that is associated with a probability of 0.841 in the table. 2) Which of the statements is true? a) The probability that z > 1.00 is 0.841. b) The probability that z < 1.00 is 0.841. c) The probability z = 1.00 is 0.841. 3) Find the z-score that is associated with a probability = 0.053 in Table 2 at the end of this preview. 4) Which of the following is true: a) The probability that z > –1.62 is 0.053. b) The probability that z < –1.62 is 0.053. c) The probability z = –1.62 is 0.053. Solve the following equations: 5) Solve –3.4 = x – 8. The Charles A. Dana Center at The University of Texas at Austin 20 Version 2.0 Statistical Reasoning Preview Assignment 12.D x . 7 6) Solve 2.5 = 7) Solve 5 = 8) Solve 33.4 = x−2 . 3 x−23.2 . ! 5 Monitoring your readiness 9) To effectively plan and use your time wisely, it helps to think about what you know and do not know. For each of the following, rate how confident you are that you can successfully do that skill. Use the following descriptions to rate yourself: 5—I am extremely confident I can do this task. 4—I am somewhat confident I can do this task. 3—I am not sure how confident I am. 2—I am not very confident I can do this task. 1—I am definitely not confident I can do this task. The Charles A. Dana Center at The University of Texas at Austin 21 Version 2.0 Statistical Reasoning Preview Assignment 12.D Skills needed for Lesson 12, Part D Skill or Concept: I can . . . Questions to check your understanding Use a normal probability table to find the z-score associated with a certain probability. 1, 3 Read and understand a probability table. 2, 4 Solve equations. 5–8 Rating from 1 to 5 Now use the ratings to get ready for your next lesson. If your rating is a 3 or below, you should get help with the material before class. Remember, your instructor is going to assume that you are confident with the material and will not take class time to answer questions about it. 10) What are some ways to get help? The Charles A. Dana Center at The University of Texas at Austin 22 Version 2.0 Statistical Reasoning Preview Assignment 12.D Table 1: The Charles A. Dana Center at The University of Texas at Austin 23 Version 2.0 Statistical Reasoning Preview Assignment 12.D Table 2: The Charles A. Dana Center at The University of Texas at Austin 24 Version 2.0 Statistical Reasoning Student Pages 12.D, Probability and critical values (continued) Lesson 12, Part D 1) Probability and Critical Values (continued) The manufacturer wants the design team to make the car comfortable for all but the tallest 2.5% of American women. Is it possible to determine the height limit that would meet this requirement? Explain. Credit: @iStock.com Objectives for the lesson You will understand: o The z-score as it relates to the standard normal curve. You will be able to: o Calculate probabilities using the normal curve. o Find critical values using the normal curve. Recall that the heights of American women are approximately normally distributed with a mean of 64 inches and a standard deviation of 2.8 inches. 2) How can you use a normal curve to represent the tallest 2.5% of adult American females? How would you use this information in the probability table? 3) Recall that z = 4) Suppose the design team also decides to make the car comfortable for all but the shortest 2.5% of females. Sketch the graph of the normal distribution and shade the area needed to find the z-score. 5) What is the cutoff height for the shortest 2.5% of women? x−µ . What is the cutoff height for the tallest 2.5% of women? σ The Charles A. Dana Center at The University of Texas at Austin 25 Version 2.0 Statistical Reasoning Student Pages 12.D, Probability and critical values (continued) 6) If the car is comfortable for all women who have heights between your answers from questions 3 and 5, what proportion of American women fit comfortably in the car? The Charles A. Dana Center at The University of Texas at Austin 26 Version 2.0 Statistical Reasoning Suggested Instructor Notes 12.D, Probability and critical values (continued) Lesson 12, Part D Probability and Critical Values (continued) Overview and student objectives Lesson Length: 25 minutes Overview In this lesson, students analyze normally distributed heights of American women. Constraints are introduced that require that the car being designed accommodate only the middle 95% of consumers. Students work backward from a given probability to find the upper and the lower cutoff heights for women. Students may need additional support in this lesson. In particular, working backward with the z-score formula may require some direct instruction. Objectives Next Lesson: Lesson 13, Part A, “Sampling Variability” (25 minutes) Constructive Perseverance Level: 3 Outcomes: PS2, PS3 Goals: Communication and Problem Solving Related Foundations Outcomes: N8, A3 Students will understand: • Prior Lesson: Lesson 12, Part C, “Probability and Critical Values” The z-score as it relates to the standard normal curve. Students will be able to: • Calculate probabilities using the normal curve. • Find critical values using the normal curve. Suggested resources and preparation Materials and technology • Computer, projector, document camera • Preview Assignment 12.D • Student Pages for Lesson 12, Part D • Practice Assignment 12.D • Students should have their z-table from Preview Assignment 12.C. You may wish to have a few extra copies available. Prerequisite assumptions Before beginning this lesson, students should be able to: • Find probabilities using z-tables. • Manipulate algebraic equations to solve for unknowns. The Charles A. Dana Center at The University of Texas at Austin 27 Version 2.0 Statistical Reasoning Suggested Instructor Notes 12.D, Probability and critical values (continued) Making connections This lesson: • Connects back to computing z-scores. • Connects forward to sampling distributions and the Central Limit Theorem. Background context None. Suggested instructional plan Frame the lesson (6 minutes) Question 1 Motivating Questions Literacy Support • “Is it possible to build a car that accommodates all people?” • “Is it realistic for car companies to build cars that will accommodate all people, or do they target certain people?” • “What are some reasons that it’s difficult for car companies to build a car that accommodates all people?” • Encourage class discussion. Explain to students that car companies may place constraints on car designs because of expectations of fuel efficiency, cost of materials, and assembly line limitations. • “What is a ‘constraint’?” • Have students discuss the definition and reach a consensus on the definition before moving on. Connect constraints to the upper and lower cutoff scores that students will be finding in this lesson. • Transition to the lesson activities by briefly discussing the Objectives for the lesson. Lesson activities (15 minutes) Question 2 Group Work • Encourage students often to turn to a quick, shaded, normal curve when they are unsure how to begin a problem. • Stress, whenever possible, the connection between the percentage of a population, the proportion of a population, and the probability of selecting a particular value from a population data set. The Charles A. Dana Center at The University of Texas at Austin 28 Version 2.0 Statistical Reasoning Suggested Instructor Notes 12.D, Probability and critical values (continued) Guiding Questions • “What does this normal curve represent?” [Answer: The population of adult American women.] • “Where in the curve would the tallest 2.5% of women be?” [Answer: In the right tail.] • “Estimate where the boundary would be and mark with a z. Shade that area of the curve. What is the probability that a randomly selected American woman has a z-score larger than that?” [Answer: 0.025.] One valid strategy would be to look up 0.025 in the table, get z = –1.96, and use the symmetry of the table to state that the z-score should be +1.96. • Alternatively, facilitate the following strategy: o “What is the probability that a randomly selected American woman has a z-score smaller than this z?” [Answer: 1 – 0.025 or 0.975.] o “What is that z-score?” [Answer from the table: z = 1.96.] Question 3 • Students may struggle a bit more because this question involves using z-score formula to solve for the height. The preview assignment contained two basic equation-solving tasks. • Encourage students to always write down the symbolic formula x−µ before substituting in any values. Encourage them to think z= σ through the connection in words as well. • “If we knew a specific height, where does it go in the formula?” [Answer: In place of x.] • “In this case. we are looking for a cutoff height. Which variable represents height?” [Answer: The x-variable represents height.] • “Of the variables in the equation, which are known and which are unknown?” [Answer: We know the mean and the standard deviation. We also have the target proportion so we can use the table to determine the z-score.] • “What do you need to do in order to isolate x?” [Answer: Multiply both sides of the equation by the standard deviation, then add the mean to both sides.] Question 4 • Students should be able to work independently on this question. • You might want to pause the lesson at this point and have students describe the step-by-step process they just went through. Have a student write the list on the board for students to refer to. The Charles A. Dana Center at The University of Texas at Austin 29 Version 2.0 Statistical Reasoning Suggested Instructor Notes 12.D, Probability and critical values (continued) • For example, the list on the board could look like this: o Step 1: Shade the appropriate area. (The table values refer to the area to the left of the associated z-score.) o Step 2: Find the probability in the body of the table and determine the corresponding z-score. o Step 3: Use the formula to solve for x. Question 5 • Students have already calculated the z-score to be –1.96 for 2.5%; x−µ to calculate the therefore, they just need to use the formula z = σ cutoff for the shortest height. Question 6 • This question synthesizes the results of the activity. If students struggle, suggest they draw a new curve and shade the area that represents the heights of the women who will fit in the car (the middle portion of the curve, rather than the two tails, as was done in the activity). Wrap-up/transition (4 minutes) Wrap-up • Close by asking students the following questions: o “Would a woman who is 72 inches tall fit comfortably in the car?” [Answer: No, the cutoff height was 69.49 inches, so she would be a little bit too tall. Her head may hit the roof.] o “Would a woman who is 56 inches tall fit comfortably in the car?” [Answer: No, the cutoff height was 58.51 inches, so she would be a little bit too short. Her feet might not reach the pedals.] o “Would you fit comfortably in the car? Why or why not?” • Take some time to compare and contrast the uniform distributions studied earlier to the normal distribution. Remind students about the importance of the normal distribution. Many things in real life have a normal distribution. • Highlight the idea of a business, in this case a car manufacturer, using statistics to make business decisions. • Have students refer back to the Objectives for the lesson and check the ones they recognize from the activity. Alternatively, they may check the objectives throughout the lesson. The Charles A. Dana Center at The University of Texas at Austin 30 Version 2.0 Statistical Reasoning Suggested Instructor Notes 12.D, Probability and critical values (continued) Suggested assessment, assignments, and reflections • Give Practice Assignment 12.D. • Give the Preview Assignments, if any, for the lesson activities you plan to complete in the next class meeting. The Charles A. Dana Center at The University of Texas at Austin 31 Version 2.0 Statistical Reasoning Suggested Instructor Notes 12.D, Probability and critical values (continued) The Charles A. Dana Center at The University of Texas at Austin 32 Version 2.0 Statistical Reasoning Practice Assignment 12.D Practice Assignment 12.D 1) The heights of American men are approximately normally distributed with a mean of 69 inches and a standard deviation of 2.5 inches. Part A: If the design team decides to make the car comfortable for all but the tallest 2.5% of males, what would be the cutoff height? Part B: If the design team also decides to make the car comfortable for all but the shortest 2.5% of males, what would be the cutoff height? Part C: What proportion of American men are more than 5 feet tall? Part D: What proportion of American men are more than 6 feet tall? 33 Version 2.0 Statistical Reasoning Practice Assignment 12.D Part E: What is the cutoff height for the tallest 10% of American men? Part F: What are the cutoff heights for the middle 70% of American men? 2) A random variable (X) has a continuous normal probability distribution with µ = 300 and σ = 40. Complete the table. The first row has been completed for you. x z P(X < x) P(X > x) 380 2.00 .977 .023 .691 .003 .767 .500 P(X < x) means "the probability that a given value of X is less than the value in the table." P(X > x) means "the probability that a given value of X is more than the value in the table." [continued on next page] 34 Version 2.0 Statistical Reasoning Practice Assignment 12.D 3) A random variable (X) has a continuous normal probability distribution with µ = 4.2 and σ = .89. Complete the table. The first row has been completed for you. x z P(X < x) P(X > x) 3.0 –1.35 .089 .911 .036 .184 .978 .022 .156 P(X < x) means "the probability that a given value of X is less than the value in the table." P(X > x) means "the probability that a given value of X is more than the value in the table." 4) A company regularly chooses 100 people to survey through random selection. They want to ensure that their survey groups are reasonably representative of the U.S. population. 17% of the U.S. population is Hispanic. If the company truly used simple random sampling of the U.S. population, the number of Hispanics in the survey groups would follow the probability distribution shown below. These data look roughly normal, so we can approximate this with a normal distribution with the same mean and standard deviation. 35 Version 2.0 Statistical Reasoning Practice Assignment 12.D Part A: An analyst wants to ensure that there are enough Hispanics in each survey group to be representative of the U.S. population. He suggests that if the number of Hispanics in a given survey group is in the bottom 5% of this distribution, then it's likely that there was bias in how the survey group was chosen. Therefore, the survey group should be discarded. Complete the following sentence. The analyst should discard survey groups that have fewer than ________ Hispanics. Part B: Another analyst suggests that too many Hispanics may also be a sign of bias. She would like to keep only the survey groups that are in the middle 95% of the distribution. Complete the following sentence. The analyst should discard survey groups that have fewer than ______ Hispanics and more than _____ Hispanics. 36 Version 2.0