Chapter 10 Solutions: Section 10.1: 1.) x = length of metacarpal y = height of person Heigth of Person (cm) Height verse Metacarpal Length 190 180 170 160 150 0 10 20 30 40 Length of Metacarpal (cm) 50 60 ŷ = 1.719x + 93.709 x = 44 cm ŷ = 1.719 ( 44 ) + 93.709 = 169.3 cm x = 55 cm ŷ = 1.719 ( 55 ) + 93.709 = 188.3 cm Life Expectancy vs Fertility Rate Life Expectancy 2.) 3.) The height for the 44 cm is probably closer to the true height than the one for 55 cm because it is interpolation, while the one for 55 cm is extrapolation. x = fertility rate of a country y = life expectancy of a country 100 80 60 40 20 0 0 2 4 Fertility Rate 6 8 ŷ = -4.706x + 84.873 x = 2.7 ŷ = -4.706 ( 2.7 ) + 84.873 = 72.17 x = 8.1 ŷ = -4.706 ( 8.1) + 84.873 = 46.75 The life expectancy for an x of 2.7 is probably closer to the true value than the one for 8.1 because it is interpolation, while the one for 8.1 is extrapolation. 4.) 5.) x = height (inches) y = weight (pounds) Weight (pounds) Weight vs Height 300 250 200 150 100 50 0 68 70 72 74 76 Height (inches) 78 80 ŷ = 5.85883x - 230.94 x = 75 inches ŷ = 5.85883 ( 75 ) - 230.94 » 208.5 pounds x = 68 inches ŷ = 5.85883 ( 68 ) - 230.94 » 167.5 pounds 6.) 7.) The weight from the height of 75 inches is probably closer to the true value since it is interpolation. The weight from the height of 68 inches is extrapolation. x = amount of calories in beef hotdogs y = amount of sodium (mg) in beef hotdogs Sodium vs Calories 700 Sodium (mg) 600 500 400 300 200 100 0 0 50 100 Calories 150 200 ŷ = 4.01327x - 228.33 x = 170 ŷ = 4.01327 (170 ) - 228.33 » 453.9 mg x = 120 ŷ = 4.01327 (120 ) - 228.33 » 253.3 mg 8.) 9.) The sodium for 170 calories is probably closer to the true value since it is interpolation. The sodium for 120 calories is extrapolation. x = number of cigarette sales (per capita) y = number of deaths per one hundred thousands from bladder cancer Number of Bladder Cancer Deaths (per 100 Thousand) Bladder Cancer Deaths vs Cigarette Sales 8 6 4 2 0 0 10 20 30 40 Number of Cigarette Sales (per Capita) 50 ŷ = 0.121821x +1.0861 x = 20 ŷ = 0.121821( 20 ) +1.0861 = 3.52 hundred thousand x = 6 ŷ = 0.121821( 6 ) +1.0861 = 1.82 hundred thousand 10.) The number of bladder cancer deaths for 20 cigarette sales per capita is probably closer to the true value since it is interpolation. The number of bladder cancer deaths for 6 cigarette sales per capita is extrapolation. - Section 10.2: 1.) 2.) 3.) 4.) 5.) 6.) 7.) x = length of metacarpal y = height of person correlation coefficient: r » 0.8578 , which is a strong, positive correlation coefficient of determination: r 2 » 0.7357 , 73.8% of the variability in the height of a person is accounted for by the length of the metacarpal x = fertility rate of a country y = life expectancy of a country correlation coefficient: r » -0.9313 , which is a strong, negative correlation coefficient of determination: r 2 » 0.8674 , 86.7% of the variability in the life expectancy of a country is accounted for by the fertility rate of the country x = height (inches) y = weight (pounds) correlation coefficient: r » 0.6605 , moderate, positive correlation coefficient of determination: r 2 » 0.4362 , 43.6% of the variability in the weight of a baseball player is accounted for by the height of the player x = amount of calories in beef hotdogs y = amount of sodium (mg) in beef hotdogs correlation coefficient: r » 0.8871, strong, positive correlation 8.) 9.) 10.) 11.) 12.) 13.) 14.) coefficient of determination: r 2 » 0.7869 , 78.7% of the variability in the amount of sodium in beef hotdogs is accounted for by the number of calories x = number of cigarette sales (per capita) y = number of deaths per one hundred thousands from bladder cancer correlation coefficient: r » 0.7036 , moderate, positive correlation coefficient of determination: r 2 » 0.4951, 49.5% of the variability in the number of deaths per one hundred thousands from bladder cancer is accounted for by the number of cigarette sales per capita No, just because there is a correlation between police expenditure and crime rate, doesn’t mean that one caused the other. Both could be changed because the area was more affluent, so it could spend more on police and there was less crime because people were better off. No, a positive correlation just means that the two go up at the same time, but that does not mean that higher temperatures cause women to die from breast cancer. These two seem completely unrelated, and probably are just a coincidence. - Section 10.3: 1.) x = length of metacarpal y = height of person a.) 1. State the null and alternative hypotheses and the level of significance Ho : r = 0 H1 : r > 0 a = 0.01 2. State and check the assumptions for the hypothesis test a. A random sample of length of metacarpal bone and height of a person was taken. This is not stated, so it is not sure if this is true. b. The distribution for each height of a person value is normally distributed for every length of metacarpal bone. i. Look at the scatter plot of length of metacarpal bone versus height of a person. It looks fairly linear. ii. There are no points that appear to be outliers. iii. The residual plot for height versus length appears to be fairly random. It appears that there is a normal distribution. Residuals 10 5 0 30 35 40 45 50 55 -5 3. Find the test statistic and p-value Test statistic: t » 4.087 p-value: 2.) 3.) p » 0.0032 4. Conclusion Reject H o since the p-value is less than 0.01. 5. Interpretation There is enough evidence to show that there is a positive correlation between length of metacarpal bone one and height of a person. b.) se » 4.559 c.) x = 44 cm. y = 169.351 cm ± 18.0349 cm or 151.3161 cm < y < 187.3859 cm x = fertility rate of a country y = life expectancy of a country a.) 1. State the null and alternative hypotheses and the level of significance Ho : r = 0 H1 : r < 0 a = 0.01 2. State and check the assumptions for the hypothesis test a. A random sample of fertility rate and life expectancy was taken. This is stated, so it is safe to assume this. b. The distribution for each life expectance value is normally distributed for every fertility rate. i. Look at the scatter plot of fertility rate versus life expectancy. It looks fairly linear. ii. There are no points that appear to be outliers. iii. The residual plot for fertility rate versus life expectancy appears to be fairly random. It appears that there is a normal distribution. Residuals 8 6 4 2 0 -2 0 -4 -6 -8 2 4 6 8 3. Find the test statistic and p-value Test statistic: t » -12 p-value: 4.) 5.) p < 0.0001 4. Conclusion Reject H o since the p-value is less than 0.01. 5. Interpretation There is enough evidence to show that there is a negative correlation between fertility rate and life expectancy. b.) se » 3.133 c.) x = 2.7%. y = 72.168 years ± 9.223 years or 62.945 years < y < 81.391 years x = height (inches) y = weight (pounds) a.) 1. State the null and alternative hypotheses and the level of significance Ho : r = 0 H1 : r > 0 a = 0.05 2. State and check the assumptions for the hypothesis test a. A random sample of height and weight of baseball players was taken. This is not stated, so it is not sure if this is true. b. The distribution for each weight of a baseball players value is normally distributed for every height. i. Look at the scatter plot of weight versus height of a baseball player. It looks fairly linear. ii. There are no points that appear to be outliers. iii. The residual plot for weight versus height appears to be fairly random. It appears that there is a normal distribution. Residuals 30 20 10 0 -10 68 70 72 74 76 78 80 -20 -30 -40 3. Find the test statistic and p-value Test statistic: t » 4.218 p-value: 6.) 7.) p » 0.00016 4. Conclusion Reject H o since the p-value is less than 0.05. 5. Interpretation There is enough evidence to show that there is a positive correlation between height and weight of baseball players. b.) se » 15.331 c.) x = 75 inches. y = 208.47 inches ± 32.45 inches or 176.02 inches < y < 240.92 inches x = amount of calories in beef hotdogs y = amount of sodium (mg) in beef hotdogs a.) 1. State the null and alternative hypotheses and the level of significance Ho : r = 0 H1 : r ¹ 0 a = 0.05 2. State and check the assumptions for the hypothesis test a. A random sample of amount of calories and amount of sodium was taken. This is not stated, so it is not sure if this is true. b. The distribution for each amount of sodium value is normally distributed for every amount of calories. i. Look at the scatter plot of amount of calories versus amount of sodium for a beef hotdog. It looks fairly linear. ii. iii. There are no points that appear to be outliers. The residual plot for scatter plot of amount of calories versus amount of sodium for a beef hotdog appears to be fairly random. It appears that there is a normal distribution. Residuals 150 100 50 0 -50 0 50 100 150 200 -100 3. Find the test statistic and p-value Test statistic: t » 8.153 p-value: 8.) 9.) p < 0.0001 4. Conclusion Reject H o since the p-value is less than 0.05. 5. Interpretation There is enough evidence to show that there is a correlation between amount of calories and amount of sodium. b.) se » 48.580 c.) x = 170 calories. y = 453.92 mg ± 105.46 mg or 348.46 mg < y < 559.38 mg x = number of cigarette sales (per capita) y = number of deaths per one hundred thousands from bladder cancer a.) 1. State the null and alternative hypotheses and the level of significance Ho : r = 0 H1 : r > 0 a = 0.01 2. State and check the assumptions for the hypothesis test a. A random sample of number of deaths per one hundred thousand from bladder cancer and the number of cigarettes sold per capita was taken. This is not stated, so it is not sure if this is true. b. The distribution for each number of deaths per one hundred thousand from bladder cancer is normally distributed for every number of cigarettes sold per capita. i. Look at the scatter plot of number of deaths per one hundred thousand from bladder cancer versus number of cigarettes sold per capita. It looks fairly linear. ii. There are no points that appear to be outliers. iii. The residual plot for number of deaths per one hundred thousand from bladder cancer versus number of cigarettes sold per capita appears to be fairly random. It appears that there is a normal distribution. Residuals 2 1.5 1 0.5 0 -0.5 0 10 20 30 40 50 -1 -1.5 3. Find the test statistic and p-value Test statistic: t » 6.417 p-value: 10.) p < 0.0001 4. Conclusion Reject H o since the p-value is less than 0.01. 5. Interpretation There is enough evidence to show that there is a positive correlation between cigarette smoking and deaths of bladder cancer. b.) se » 0.6857 c.) x = 20 sales. y = 3.523 hundred thousand ± 1.910 hundred thousand or 1.613 hundred thousand < y < 5.433 hundred thousand -