Chapter 8 Confidence Interval Estimation Chapter Topics State Estimation Process Introduce Properties of Point Estimates Explain Confidence Interval Estimates Compute Confidence Interval Estimation for Population Mean ( known and unknown) • Compute Confidence Interval Estimation for Population Proportion • Compute Sample Size Statistical Methods • • • •
Statistical Methods Descriptive Statistics
Inferential Statistics
Estimation Inference Process
Estimates & Tests
Hypothesis Testing
Population
Sample Statistics X, Ps
Sample
Population Parameters Are Estimated with Point Estimator
Estimate Population Parameter... Mean µ
with Sample Statistic X
Proportion
p
ps
Variance
σ2
s
µ1 − µ2
X1 − X 2
Differences
2
Confidence Interval Estimation Process
Population
Random Sample
Mean, µ, is unknown
Mean X = 50
I am 95% confident that µ is between 40 & 60.
Confidence Interval Estimates Provide range of values – Takes into consideration variation in sample statistics from sample to sample – Is based on observation from one sample – Gives information about closeness to unknown population parameters – Is stated in terms of level of confidence Never 100% certain Elements of Confidence Interval Estimation
A Probability That the Population Parameter Falls Somewhere Within the Interval. Confidence Interval
Confidence Limit (Lower)
Sample Statistic
Confidence Limit (Upper)
Confidence Intervals
X ± Z ⋅σ X = X ± Z ⋅ σ n
µ − 2.58⋅σ X
µ −1.645⋅σ X
µ −1.96⋅σ X
σx_ µ µ +1.645⋅σ X
µ + 2.58⋅σ X
X
µ +1.96⋅σ X 90% Samples 95% Samples 99% Samples
Level of Confidence • Probability that the unknown population parameter falls within the interval • Denoted (1 - =% )α level of confidence α Is Probability That the Parameter Is Not Within the Interval • The typical values are 99%, 95%, 90%. Corresponding Z values are 2.58, 1.96, 1.645 (for two side problems). Experiment: throw 2 dice, use mean ±2 to construct a 94.5% confidence interval estimate for µ. Interval and Level of Confidence
Sampling Distribution of the Mean
µ − Zα / 2σ X Intervals extend from
α /2
σX 1−α
µX = µ
X − Zσ X
X
( 1 − α ) 100%
of intervals constructed contain µ ; α 100% do not.
to
X + Zσ X
µ + Zα / 2σ X
α /2
Confidence Intervals
Factors Affecting Interval Width 1. Data Dispersion Measured by σ 2. Sample Size
X / n 3. Level of Confidence (1 - α) Affects Z Confidence Interval Estimates
Confidence Intervals Mean
σ Known
Proportion
σ Unknown
Confidence Interval Estimate For Mean (σ Known) Assumptions – Population standard deviation (σ) is known – Population is normally distributed – If not normal, can be approximated by normal distribution (n ≥ 30) Confidence Interval Estimate
σ σ X − Zα / 2 ⋅ ≤ µ ≤ X + Zα / 2 ⋅ n n
Example :
Population is normally distributed with σ = 10. The mean of a random sample of n = 25 is X = 50. Set up a 95% confidence interval estimate for µ.
X − Zα ⋅ σ ≤ µ ≤ X + Zα ⋅ σ 2 n 2 n 50−1.96⋅ 10 ≤ µ ≤ 50+1.96⋅ 10 25 25 46.08 ≤ µ ≤ 53.92 Confidence Interval Estimate Mean (σ Unknown) Assumptions Population Standard Deviation (σ) Is Unknown Population Must Be Normally Distributed Use Student’s t Distribution Confidence Interval Estimate:
X − t α / 2, n −1 ⋅
S n
≤ µ ≤ X + t α / 2, n −1 ⋅
S n
Student’s t Table
Upper Tail Area df
.25
.10
.05
α/2
Assume: n = 3 df = n - 1 = 2 α = .10 α/2 =.05
1 1.000 3.078 6.314
2 0.817 1.886 2.920
α/2 =.05
3 0.765 1.638 2.353
t Values
0 2.920
t
Confidence Interval Estimate for Proportion Assumptions Two categorical outcomes Population follows binomial distribution Normal approximation can be used if n·p ≥ 5 and n·(1 - p) ≥ 5 Confidence interval estimate:
p S − Zα / 2
pS ( 1 − pS ) n
≤ p ≤ pS + Zα / 2
pS ( 1 − pS ) n
Example: A random sample of 400 voters showed 32 preferred candidate A. Set up a 95% confidence interval estimate for p. Ps = 32/400 = .08
ps − Z α / 2 ⋅ .08 − 196 . ⋅
ps ⋅ (1 − ps ) ps ⋅ (1 − ps ) ≤ p ≤ ps + Z α / 2 ⋅ n n .08 ⋅ (1−.08 ) 400
. ⋅ ≤ p ≤ .08 + 196
.053 ≤ p ≤ .107
.08 ⋅ (1−.08) 400