1. (21pts) These data represent the percent of adults with obesity in a random sample of U.S. States in 2020. This data set available in StatCrunch at this link Percent a) (1pt each) Find the following (Give 3 decimal places, where needed) Obese Mode n SamplesBe 35.3 * mean to 92 median 33.2 35.8 34 s SF-dev s' Variance Min Max 24.4 36.5 31.5 Range IQR 24.2 34 36.6 32.4 30.7 b) (1pt) Are the values above parameters or statistics? 36.4 24.3 c) (1pt) Lower Fence: LF 27.7 d) (1pt) Upper Fence: LF 34.3 e) (2pts) What is the shape of this distribution? Explain. 87 f) (2pts) Michigan had an obesity level in 2020 of 35.2 percent. What is Michigan's z-score? (Give 3 decimal places, show formula, substitution, and result) Z = (X-mean) st. dev g) (2pts) Based on the result above, does Michigan appear to have an unusual level of obesity? Explain. P.802. (13pts) The scatterplot shows the relationship between a U.S. State's annual alcohol consumption (in thousand gallons) and its annual drug overdose deaths for 2020. Simple linear regression results: Dependent Variable: Drug Overdose Deaths Independent Variable: Alcohol Consumption Drug Overdose = 325.70936 + 0.083661522 Alcohol Sample size: 51 R (correlation coefficient) = 0.88674094 R-sq = 0.78630949 Estimate of error standard deviation: 657.27338 Meshal Consumption X a) Michigan has a point on the graph at coordinates (19860, 2385). Explain what this meant for Michigan in 2020. Be specific and use context and units. In Zozo, people in Michigan b) What is the strength of the linear relationship between the two variables (Circle one)? Strong Positive Moderate Positive Weak Positive No Linear Relation P230 Strong Negative Moderate Negative Weak Negative Non-linear relation c) What is the regression equation (3 dec. places)? d) What is the slope of the linear regression equation? Interpret the slope in the context of the situation. (Include units!) e) What is the y-intercept of the linear regression equation? Explain why this does not make sense in the context of the situation.3. (20pts) The following table shows the type of health insurance coverage and race/ethnicity for a random group of people in the U.S., from the National Health Interview Survey in 2019. (Source) Private Medicaid Uninsured Total White 4712 1096 466 6274 Black 769 479 190 1438 Asian 449 104 44 597 Hispanic 933 581 231 1745 Total 6863 2260 931 10054 a) The column variable is health msurance b) The row variable is race / ethnicity c) Explain why researchers cannot conduct a designed experiment to obtain data on these variables and their relationship. requires random assignments wnethical to randomly give ) take away health insurance . d) What was the sample? e) What is the sample size? f) What is the population? all :) How many people that were surveyed were uninsured? h) Health insurance coverage is an example of a variable (Circle one) Qualitative Quantitative Discrete Quantitative Continuous i) Is it unusual to be uninsured in the U.S.? Use probability to explain. Gless than 5%= 0.05 j) Probabilities found from this table will be (Circle one) Classical Empirical Subjective#3 continued: You are going to select a single random person in the U.S. Using the two-way table, find the probability that: (Give 4 decimal places for all answers) k) They are insured by Medicaid fraction = # - decimal 10054 P 134 I) They are Asian 4135 m) That they do not have private insurance n) That they are Black and Uninsured 9 overlap o) That they are Black or Hispanic add (sobract?") p) To calculate the probability for part o) you had to assume that "Black" and "Hispanic" are: (Circle the best choice) Disjoint ( Cannot , Not Disjoint 57 Justadd ( hareboth) by add + subtract q) That they are Asian or on Medicaid ( can haveboth ! (9 add ( + subrack ? ) r) To calculate the probability for part q) you had to assume that "Asian" and "Medicaid" are: (Circle the best choice) Disjoint Not Disjoint