Survey
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Sampling Distribution and Confidence Interval 6-1 Sampling Distribution of Means Sampling Distribution Theoretical Probability Distribution of the Sample Statistic. If a random sample is taken from a normally distributed population that has a mean µ and a standard deviation σ , the sampling distribution of the sample means, x, is normal with µx = µ What is the Shape of this distribution? What are the values of the parameters such as mean and standard deviation? Samp.. D. - 1 Samp Central Tendency An Application Population Distribution σσ = 10 µx = µ Dispersion σ σ = n x µµ = 50 X Sampling Distribution n=4 σσ X = 5 Waiting times at a certain type of clinic are normally distribution with µ = 8 min. & σ = 2 min. If you select random samples of 25 cases, what is the sampling distribution of the mean? n =16 σσ X = 2.5 µ X- = 50 X Sampling Distribution Solution* If you select random samples of 25 cases from a normal distribution (or population) with µ = 8 min. & σ = 2 min. The sampling distribution of the mean is normal distribution with mean = 8 min., and standard deviation = 2/5 = .4 min. Samp.. D. - 5 Samp σ n Samp.. D. - 2 Samp Sampling from Normal Populations Samp.. D. - 3 Samp σx = Samp.. D. - 4 Samp Continue the Application Waiting times at a certain type of clinic are normally distribution with µ = 8 min. & σ = 2 min. If you select random samples of 25 cases, what is the probability that the sample mean of a random sample of 25 cases is between σ σX = .4 7.8 & 8.2 minutes? Samp.. D. - 6 Samp 7.8 8 8.2 X Sampling Distribution and Confidence Interval 6-2 Standardizing Sampling Distribution of Mean Z == Sampling Sampling Distribution Distribution X −− µµ x X −− µµ == σ σ σ σx n σ X Sampling Distribution Solution* Z == Standardized Standardized Normal Normal Distribution Distribution σ=1 Sampling Sampling Distribution Distribution of of sample sample mean mean Z == X −− µµ 7.8 −− 8 == == −−.50 σσ n 2 25 X −− µµ 8.2 −− 8 == == .50 Standardized Standardized σσ n 2 25 Normal Normal Distribution Distribution σ σ =1 σ σX = .4 .383 µ X µ =0 X -.50 0 .50 7.8 8 8.2 X Z Samp.. D. - 7 Samp Z The probability that the sample mean would be between 7.8 & 8.2 minutes is .383. Samp.. D. - 8 Samp Central Limit Theorem Central Limit Theorem In the previous problem the data was from normally distributed population. What if the population is not normally distributed? If a relative large random sample is taken from a population that has a mean µ and a standard deviation σ, regardless of the distribution of the population, the distribution of the sample means is approximately normal with µx = µ σx = Samp.. D. - 9 Samp Samp.. D. - 10 Samp Sampling from Non-Normal Populations Central Limit Theorem As sample size gets large enough (n ≥ 30) ... σx = Central Tendency σ n sampling distribution becomes almost normal. X X µx = µ Population Distribution σσ = 10 µx = µ Dispersion σx = n n Samp.. D. - 11 Samp σ n σ n Sampling Sampling with with replacement replacement µµ = 50 n = 30 σσ X = 1.8 n=4 σσ X = 5 µµX- = 50 Samp.. D. - 12 Samp X Sampling Distribution X Sampling Distribution and Confidence Interval 6-3 Central Limit Theorem Example: Consider the distribution of serum cholesterol levels for all 20- to 74-year-old males living in United States has a mean of 211 mg/100 ml, and the standard deviation of 46 mg/100 ml. If a random sample of 100 individuals from the population, what is the probability that the average serum cholesterol level of these 100 individuals is higher than 225? Samp.. D. - 13 Samp Central Limit Theorem Solution: The sampling distribution of the mean is normal with mean µµ x == µµ = 211 and standard error .001 P(X > 225) = P(Z > [225 - 211]/4.6) = P(Z > 3.04) = 0.001 1. State What Is Estimated 2. Distinguish Point & Interval Estimates 3. Explain Interval Estimates 4. Compute Confidence Interval Estimates for Population Mean (& Proportion) 5. Compute Sample Size Samp.. D. - 15 Samp Population Mean, µ, µ is unknown J J Sample J J J J Samp.. D. - 17 Samp 3.04 Thinking Challenge Suppose you’re interested in the average body temperature of healthy adults in Northeastern Ohio (the population). How would you find out? How can we estimate this average with a measure of reliability? Samp.. D. - 16 Samp Estimation Process J 0 Samp.. D. - 14 Samp Learning Objectives J J σ σ = 4.6 (= 46/10). n σ σ x == Random Sample JMean J X = 98 I am 95% confident that µµ is between 97 & 99, or 98±±1 Unknown Population Parameters Are Estimated Estimate Population Parameter... Mean µ Proportion π Variance σ Differences Samp.. D. - 18 Samp 2 µ1 - µ 2 with Sample Statistic x p s2 x1 − x2 z Sampling Distribution and Confidence Interval 6-4 Estimation Methods Point Estimation 1. Provides Single Value n Estimation Point Estimation Interval Estimation Based on Observations from 1 Sample 2. Gives No Information about How Close Value Is to the Unknown Population Parameter 3. Example: Sample Mean MeanX = 3 Is Point Estimate of Unknown Population Mean Samp.. D. - 19 Samp Samp.. D. - 20 Samp Key Elements of Interval Estimation Interval Estimation 1. Provides Range of Values n Based on Observations from 1 Sample A probability that the population parameter falls somewhere within the interval. 2. Gives Information about Closeness to Unknown Population Parameter n Confidence interval Sample statistic (point estimate) Stated in terms of Probability l Knowing Exact Closeness Requires Knowing Unknown Population Parameter 3. Example: Unknown Population Mean Lies Between 50 & 70 with 95% Confidence Samp.. D. - 21 Samp Confidence limit (lower) Samp.. D. - 22 Samp Sampling Error Confidence limit (upper) x ± Margin of Error Sampling Distribution of the Mean σx_ Confidence interval Sample statistic (point estimate) µµ - ? σσx x µ x Sampling Error = | µ– x | Samp.. D. - 23 Samp .025 .025 µ X µµ + ?σσx x Within how many standard deviations of the mean will have 95% of the sampling distribution? Samp.. D. - 24 Samp Sampling Distribution and Confidence Interval 6-5 A Special Notation Size of Interval zα = the z score that the proportion of the standard normal distribution to the right of it is α. Z .05 .06 .07 z.025 = 1.96 1.8 .9678 .9686 .9693 z.010 = ? σx_ µµ - 2.58σ 2.58σσ x µµ - 1.65σσx µµ-1.96σ µ-1.96 σσ x 1.9 .9744 .9750 .9756 µ X µµ + 1.65σσ x µµ + 2.58σσx µµ+1.96σσ x µ+1.96 90% Samples z .025 2.0 .9798 .9803 .9808 95% Samples 2.1 .9842 .9846 .9850 99% Samples Samp.. D. - 25 Samp Samp.. D. - 26 Samp Confidence Interval Mean ( σ Known) The Confidence Interval σx_ Confidence Level α/2 1.96 = z.025 α/2 = .025 1- α = .95 µ µµ - 1.96σ 1.96σσx (1-α (1α)· 100% Confidence Interval Estimate X x ( X − Zα / 2 ⋅ µµ + 1.96σσx x or 95% Samples Confidence Interval => x - 1.96σ 1.96σσx X ± Zα / 2 ⋅ σ n x + 1.96σσx x Samp.. D. - 27 Samp σ σ , X + Zα / 2 ⋅ ) n n Samp.. D. - 28 Samp Confidence Interval of Mean (σ (σ Known) The Confidence Interval σx_ Assumptions n n n Population Standard Deviation Is Known Population Is Normally Distributed If Not Normal, Can Be Approximated by Normal Distribution (n (n ≥ 30) 95% Samples µµ - 1.96σ 1.96σσx µ X x µµ + 1.96σσx x 95% Confidence Interval Confidence Interval => x - 1.96σ 1.96σσx Samp.. D. - 29 Samp Samp.. D. - 30 Samp x - 1.96σ 1.96σσx Sampling Distribution and Confidence Interval 6-6 Factors Affecting Interval Width The Confidence Interval σx_ 2.5% 1. Data Dispersion 2.5% 95% Samples µ n X 95 % of intervals contain µ. 2.5 % do not. Samp.. D. - 31 Samp Measured by σ Intervals Extend from x - zα/2 σ X to x + zα/2 σX αα/2· σ αα/2 · σ 2. Sample Size n σX = σ n 3. Level of Confidence (1 - α) n Affects Z Samp.. D. - 32 Samp Confidence Interval Mean ( σ Known) (1-α (1α)· 100% Confidence Interval Estimate ( X − Zα / 2 ⋅ σ σ , X + Zα / 2 ⋅ ) n n or X ± Zα / 2 ⋅ σ n Samp.. D. - 33 Samp Estimation Example Mean ( σ Known) The mean of a random sample of n = 25 isX = 50. Set up a 95% confidence is interval estimate for µ if σ = 10. 1 − α = .95 , α = .05, α 2 = .025, z α 2 = 1.96. σ σ , X + Zα / 2 ⋅ ) n n 10 10 ( 50 − 1 . 96 ⋅ , 50 + 1 .96 ⋅ ) 25 25 Samp.. D. - 34 ( 46 .08 , 53 .92 ) or 50 ± 3.92 Samp ( X − Zα / 2 ⋅ Confidence Interval Estimate We can be 95% confident that the population mean is in (46.08, 53.92). We can be 95% confident that the maximum sampling error using this interval estimate for estimating mean is within 3.92. Samp.. D. - 35 Samp You’re a Q/C inspector for Coke. The σ for 2-liter bottles is .05 liters. A random sample of 100 bottles showed showed X = 1.99 liters. What is the 90% confidence interval estimate of the true mean amount in 2-liter bottles? Samp.. D. - 36 Samp Sampling Distribution and Confidence Interval 6-7 Confidence Interval Solution* Confidence Interval Mean ( σ Unknown) 1 - α = .90, α = .1, α /2 = .05, Z α / 2 = 1.64 ( X − Z α /2 ⋅ ( 1. 99 − 1. 64 ⋅ σ σ , X + Zα / 2 ⋅ ) n n 1. Assumptions n n .05 .05 , 1.99 + 1.64 ⋅ ) 100 100 Population Standard Deviation Is Unknown Population Must Be Normally Distributed 2. Use Student’s t Distribution 3. Confidence Interval Estimate ( X − tα / 2 ,n −−1 ⋅ ( 1.982 , 1. 998 ) Samp.. D. - 37 Samp S S , X + t α / 2,n −−1 ⋅ ) n n Samp.. D. - 38 Samp Student’s t Table Student’s t Distribution Standard Normal (Z) x−µ t= s n t (df ( df = 13) Bell-Shaped Symmetric t (df ( df = 5) ‘Fatter’ Tails α/2 df .90 .95 .975 1 3.078 6.314 12.706 For a 90% C.I.: n=3 df = n - 1 = 2 α α = .10 α α/2 α/2 =.05 2 1.886 2.920 4.303 .05 3 1.638 2.353 3.182 0 Z t Samp.. D. - 39 Samp 0 t values 2.920 Samp.. D. - 40 Samp Estimation Example Mean ( σ Unknown) A random sample of n = 25 has hasx = 50 & s = 8. Set up a 95% confidence interval estimate for µ. 1 - α = .95, α = .05, α/2 = .025, t α 2 , df =24 = 2. 064 S S , X + tα / 2 ,n−1 ⋅ ) n n 8 8 ( 50 − 2. 064 ⋅ , 50 + 2 .064 ⋅ ) 25 25 Samp.. D. - 41 Samp ( 46 . 69 , 53 . 30 ) Thinking Challenge You’re a time study analyst in manufacturing. You’ve recorded the following task times (min.): 3.6, 4.2, 4.0, 3.5, 3.8, 3.1. 3.1. What is the 90% confidence interval estimate of the population mean task time? ( X − tα / 2,n −1 ⋅ Samp.. D. - 42 Samp t Sampling Distribution and Confidence Interval 6-8 Confidence Interval Solution* X = 3.7 One-Sided C. I. (Error in the Note) Z C.I.: σ ( − ∞ , X + Zα ⋅ ) Lower interval n σ Upper interval ( X − Zα ⋅ , ∞) S = 0.38987 n = 6, df = n - 1 = 6 - 1 = 5 n S / √n = 0.38987 / √6 = 0.1592 t .05,5 = 2.015 ( 3.7 - (2.015)(0.1592) , 3.7 + (2.015)(0.1592) ) ( 3.379, 4.021 ) t C.I.: σ ( − ∞ , X + tα ⋅ ) Lower interval n σ Upper interval ( X − tα ⋅ , ∞) n Samp.. D. - 43 Samp Samp.. D. - 44 Samp Size of Interval σx_ 0.025 µµ-1.96σ µ-1.96 σσx σx_ 0.025 0.05 .95 .95 µ Lower Interval X µ µµ+1.96σσx µ+1.96 x X µµ+ 1.64σσx µ+ x z α = z .05 95% Samples Samp.. D. - 45 Samp 95% Samples Samp.. D. - 46 Samp Estimation Example Mean ( σ Known) The mean of a random sample of n = 25 isX = 50. Set up a upper 95% confidence is interval estimate for µ if σ = 10. 1 − α = .95 , α = .05, zα = 1.64. σ ( X − Zα ⋅ , − ∞) n 10 ( 50 − 1 .64 ⋅ , − ∞) 25 ( 46 .72 , − ∞ ) Samp.. D. - 47 Samp Finding Sample Sizes for Estimating µ C.I. : x ± z 2 ⋅ σ n α Margin of Error = B = Zα 2 ⋅ σ n 2 2 zα 2 ⋅ σ 2 n= B B = Margin of Error or Bound Samp.. D. - 48 Samp I don’t want to sample too much or too little! Sampling Distribution and Confidence Interval 6-9 Sample Size Example What sample size is needed to be 90% confident of being correct within ± 5? A pilot study suggested that the standard deviation is 45. Z.05 σ2 (1.645) (45 ) = = 219.2 ≅ 220 B2 (5)2 2 n= 2 2 Samp.. D. - 49 Samp C.I. Example You plan to survey employees to find their average auto insurance. You want to be 95% confident that the sample mean is within ± $50.. $50 A pilot study showed that σ was about $400 $400.. What sample size do you use? Samp.. D. - 50 Samp Sample Size Solution* 2 n= Z0. 0252σ B Sampling Distribution of Proportion The sampling distribution of sample proportion, p, if nπ ≥ 5 and n(1 (1−π −π)) ≥ 5, is approximately normal, with 2 2 2 1.96) (400) =( (50) 2 µp = π , = 245. 86 ≅ 246 Samp.. D. - 51 Samp 1. Assumptions n n π (1 − π ) n Samp.. D. - 52 Samp Confidence Interval Proportion n and σ p = Two Categorical Outcomes Population Follows Binomial Distribution Normal Approximation Can Be Used l np ± 3 np(1 − p ) Does Not Include 0 or 1 Estimation Example Proportion A random sample of 400 graduates showed 32 went to grad school. Set up a 95% confidence interval estimate for π. ( p − Zα / 2 ⋅ 2. Confidence Interval Estimate p ⋅ (1 − p ) p ⋅ (1 − p ) ( p − zα 2 ⋅ , p + zα 2 ⋅ ) n n Samp.. D. - 53 Samp ( .08 − 1.96 ⋅ Samp.. D. - 54 Samp p ⋅ (1 − p ) p ⋅ (1 − p) , p + Zα / 2 ⋅ ) n n .08 ⋅ (1 − .08) . 08 ⋅ (1 − .08) , .08 + 1.96 ⋅ ) 400 400 ( . 053 , . 107 ) Sampling Distribution and Confidence Interval 6-10 Confidence Interval Solution* Example You’re a production manager for a newspaper. You want to find the % defective. Of 200 newspapers, 35 had defects. What is the 90% confidence interval estimate of the population proportion defective? ( p − zα / 2 ⋅ ( .175 − 1 .645 ⋅ p ⋅ (1 − p) , p + zα / 2 ⋅ n .175 ⋅ (. 825) .175 ⋅ (. 825 ) , .175 + 1.645 ⋅ ) 200 200 ( .1308 , .2192 ) Samp.. D. - 55 Samp Samp.. D. - 56 Samp p ⋅ (1 − p ) ) n