Estimating Single Variance or Stand Dev Worksheet Answers 1. Let 𝑥 = age in years of a rural Quebec woman at the time of her first marriage. IN the year 1941, the population variance of 𝑥 was approximately 𝜎 2 = 5.1. Suppose a recent study of age at first marriage for a random sample of 41 women in rural Quebec gave a sample variance of 𝑠 2 = 3.3. Use a 5% level of significance to test the claim that the current variance is less than 5.1. Find a 90% confidence interval for the population variance and population standard deviation. 𝐻0 ∶ 𝜎 2 = 5.1 𝑥2 = (𝑛−1)𝑠 2 𝜎2 𝐻1 ∶ 𝜎 2 < 5.1 = (41−1)(3.3) (5.1) = (40)(3.3) 5.1 𝛼 = 0.05 = 25.89 𝑑. 𝑓. = 𝑛 − 1 = 41 − 1 = 40 𝑃 − 𝑣𝑎𝑙𝑢𝑒 ( left – tailed ) between 0.975 and 0.950 1 − 0.975 < 𝑃 − 𝑣𝑎𝑙𝑢𝑒 < 1 − 0.950 0.025 < 𝑃 − 𝑣𝑎𝑙𝑢𝑒 < 0.050 Conclude the test Since 𝑃 − 𝑣𝑎𝑙𝑢𝑒 < 0.05, reject null Confidence interval ( 𝜎 2 ) 𝑥𝑈2 = 1−𝑐 𝑥𝐿2 = 1+𝑐 2 2 (𝑛−1)𝑠 2 2 𝑥𝑈 (40)(3.3) 55.76 = = 1−0.90 2 1+0.90 2 < 𝜎2 < < 𝜎2 < = = 0.10 2 1.90 2 = 0.05 with d.f. = 40 𝑥𝑈2 = 55.76 ( from table ) = 0.95 with d.f. = 40 𝑥𝐿2 = 26.51 ( from table ) (𝑛−1)𝑠 2 𝑥𝐿2 (40)(3.3) 26.51 Confidence interval (𝜎) √2.37 < 𝜎 < √5.00 1.54 < 𝜎 < 2.24 2.37 < 𝜎 2 < 5.00 2. Let 𝑥 represent the number of mountain climbers killed each year. The long – term variance of 𝑥 is approximately 𝜎 2 = 136.2. Suppose that for the past 8 years, the variance has been 𝑠 2 = 115.1 . Use a 1% level of significance to test the claim that the recent variance for number of mountain climber deaths is less than 136.2. Find a 90% confidence interval for the population variance and population standard deviation. 𝐻0 ∶ 𝜎 2 = 136.2 𝑥2 = (𝑛−1)𝑠 2 (8−1)(115.1) = 𝜎2 𝐻1 ∶ 𝜎 2 < 136.2 136.2 = (7)(115.1) 136.2 𝛼 = 0.01 = 5.92 𝑑. 𝑓. = 𝑛 − 1 = 8 − 1 = 7 𝑃 − 𝑣𝑎𝑙𝑢𝑒 ( left – tailed ) between 0.100 and 0.900 1 − 0.900 < 𝑃 − 𝑣𝑎𝑙𝑢𝑒 < 1 − 0.100 0.100 < 𝑃 − 𝑣𝑎𝑙𝑢𝑒 < 0.900 Conclude the test Since 𝑃 − 𝑣𝑎𝑙𝑢𝑒 > 0.01, we do not reject null hypothesis Confidence interval ( 𝜎 2 ) 𝑥𝑈2 = 1−𝑐 𝑥𝐿2 = 1+𝑐 2 (𝑛−1)𝑠 2 2 𝑥𝑈 2 = 1−0.90 2 1+0.90 2 < 𝜎2 < (7)(115.1) 14.07 = 0.10 = = 2 1.90 2 = 0.05 with d.f. = 7 𝑥𝑈2 = 14.07 ( from table ) = 0.95 with d.f. = 7 𝑥𝐿2 = 2.17 ( from table ) (𝑛−1)𝑠 2 < 𝜎2 < 𝑥𝐿2 (7)(115.1) 2.17 Confidence interval (𝜎) √57.26 < 𝜎 < √371.29 7.57 < 𝜎 < 19.27 57.26 < 𝜎 2 < 371.29 3. A set of solar batteries is used in a research satellite. The satellite can run on only one battery, but it runs best if more than one battery is used. The variance 𝜎 2 of lifetimes of these batteries affects the useful lifetime of the satellite before it goes dead. Engineers have determined that a variance of 𝜎 2 = 23 months is most desirable for these batteries. A random sample of 22 batteries gave a sample variance of 14.3 months. Using a 0.05 level of significance, test the claim that 𝜎 2 = 23 against the claim that 𝜎 2 is different from 23. Find a 90% confidence interval for both the population variance and population standard deviation. 𝐻0 : 𝜎 2 = 23 𝑥2 = (𝑛−1)𝑠 2 𝜎2 𝐻1 ∶ 𝜎 2 ≠ 23 = (22−1)(14.3) 23 = (21)(14.3) 23 𝛼 = 0.05 = 13.06 𝑑. 𝑓. = 𝑛 − 1 = 22 − 1 = 21 𝑃 − 𝑣𝑎𝑙𝑢𝑒 is between 0.950 and 0.900 ( two – tailed ) 1 − 0.950 < 0.050 < 𝑃−𝑣𝑎𝑙𝑢𝑒 2 𝑃−𝑣𝑎𝑙𝑢𝑒 2 < 1 − 0.900 < 0.100 0.100 < 𝑃 − 𝑣𝑎𝑙𝑢𝑒 < 0.200 Conclude the test Since 𝑃 − 𝑣𝑎𝑙𝑢𝑒 > 0.05, we do not reject null Confidence interval ( 𝜎 2 ) 𝑥𝑈2 = 1−𝑐 𝑥𝐿2 = 1+𝑐 2 2 (𝑛−1)𝑠 2 2 𝑥𝑈 = 1−0.90 2 1+0.90 2 < 𝜎2 < (21)(14.3) 32.67 = = = 0.10 2 1.90 2 = 0.05 with d.f. = 21 𝑥𝑈2 = 32.67 ( from table ) = 0.95 with d.f. = 21 𝑥𝐿2 = 11.59 ( from table ) (𝑛−1)𝑠 2 < 𝜎2 < 𝑥𝐿2 (21)(14.3) 11.59 Confidence interval (𝜎) √9.19 < 𝜎 < √25.91 3.03 < 𝜎 < 5.09 9.19 < 𝜎 2 < 25.91