Compare 90% and 99% confidence intervals for xˉ=100, s=15, n=36. Calculate both and explain the trade-off between confidence and precision.
Example 3
hard
A factory needs a 95% CI for mean bolt length with E≤0.5mm. Known σ=4mm, z∗=1.96. Smallest n?
Example 4
challenge
A 95% CI for a mean is (80,90) with n=64. Estimate σ assuming z∗=1.96.
Practice Problems
Try each one, then open the solution to compare your method.
Example 1
easy
A 95% CI for a population mean is (42,58). Find the sample mean xˉ and the margin of error E.
Example 2
hard
To achieve a margin of error of E=3 with 95% confidence, given σ=20, find the required sample size n.
Example 3
easy
A sample gives point estimate xˉ=50 with margin of error 4. Write the 95% confidence interval.
Example 4
easy
A 95% CI for a mean is (46,54). What is the point estimate (the center)?
Example 5
easy
A 95% CI is (46,54). What is the margin of error?
Example 6
easy
True or false: increasing the confidence level from 90% to 99% (same data) makes the interval wider.
Example 7
easy
True or false: increasing the sample size n (same confidence) narrows the interval.
Example 8
easy
Which critical value z∗ corresponds to a 95% confidence interval?
Example 9
easy
Should you use a z-interval or a t-interval when σ is unknown and n is small?
Example 10
easy
A 90% CI for a proportion is (0.40,0.50). What is the point estimate p^?
Example 11
medium
A sample has xˉ=100, known σ=15, n=36. Construct the 95% confidence interval (z∗=1.96).
Example 12
medium
A sample has xˉ=200, σ=40, n=64. Find the 90% CI (z∗=1.645).
Example 13
medium
A 95% CI for the mean is (95.1,104.9). A colleague claims 'there is a 95% probability the true mean lies in this interval.' What is the correct interpretation?
Example 14
medium
A 95% CI for the difference in means is (−2,6). Does this suggest a significant difference at α=0.05?
Example 15
medium
To halve the width of a 95% CI for a mean (same σ, same confidence), by what factor must n increase?
Example 16
medium
A poll of n=400 finds p^=0.50. Find the 95% CI (z∗=1.96) using SE =p^(1−p^)/n.
Example 17
medium
A 99% CI (z∗=2.576) uses xˉ=60, σ=10, n=25. Find the interval.
Example 18
challenge
Two 95% CIs are computed from the same data: one for the mean of single observations and one for the sample mean. Why is the CI for the sample mean narrower, and by what factor for n=25?
Example 19
challenge
A 95% CI for μ is (48,52). A two-sided test of H0:μ=50 at α=0.05 would reach what conclusion, and why?
Example 20
challenge
A researcher wants a 95% CI for a mean with margin of error at most 1, where σ=8. What is the smallest sample size n (z∗=1.96)?
Example 21
medium
A sample has xˉ=80, known σ=12, n=144. Build the 95% CI (z∗=1.96).
Example 22
medium
A 95% CI for a proportion is (0.30,0.42). State the point estimate and the margin of error.
Example 23
easy
A 95% CI for μ is (20,30). State the point estimate and the margin of error.
Example 24
easy
True or false: a CI is a statement about the population parameter, not about future samples.
Example 25
easy
A 95% CI for μ is (8,12). What is the width of the interval?
Example 26
easy
True or false: holding everything else constant, a smaller sample size yields a wider CI.
Example 27
easy
A poll reports a margin of error of ±3% at 95% confidence. The estimate is p^=0.47. Write the CI.
Example 28
medium
Compute a 95% CI for μ given xˉ=50, σ=10, n=100, z∗=1.96.
Example 29
medium
Compute a 90% CI for μ: xˉ=72, σ=18, n=81, z∗=1.645.
Example 30
medium
For a proportion with p^=0.6, n=100, build a 95% CI (z∗=1.96).
Example 31
medium
A 95% CI is (10,14). What is the E, and what was xˉ?
Example 32
medium
True or false: 'The probability that the true mean is in this 95% CI is 0.95.' Justify briefly.
Example 33
medium
Given xˉ=120, σ=20, n=400. Build a 99% CI (z∗=2.576).
Example 34
medium
When should you use a t-interval instead of a z-interval?
Example 35
medium
A 95% CI for the difference of means is (1.2,4.8). Is the difference significantly different from zero?
Example 36
hard
A 95% CI for a proportion: p^=0.32, n=400, z∗=1.96. Find the CI.
Example 37
hard
Find the smallest n for a 95% CI for a proportion with E≤0.03, assuming worst case p^=0.5, z∗=1.96.
Example 38
hard
If 100 different 95% CIs are constructed from independent samples, about how many are expected to miss the true mean?
Example 39
hard
Two 95% CIs for treatment means overlap. Does overlap automatically imply no significant difference?
Example 40
hard
A 98% CI for μ with xˉ=50, σ=20, n=100, z∗=2.326. Find the CI.
Example 41
challenge
Researcher reports CI (2.3,5.7) at 95% for the mean difference. Estimate the t statistic value, assuming a t-CI with E= half-width.
What to focus on
Core idea:A confidence interval is a range from sample data that likely contains the true population value, at a stated confidence level.
Common stuck point:The procedure for confidence interval is the easy part; the trap is saying '95% chance the true value is in THIS interval'. Asking "Am I building a range from a sample that likely contains the true population value at a stated confidence?" first is what keeps a correct-looking calculation from being attached to the wrong concept.
Ask yourself:Am I building a range from a sample that likely contains the true population value at a stated confidence?
Concept recap
A range of values, computed from sample data, that is likely to contain the true population parameter with a specified level of confidence.
A confidence interval is a ring toss around a peg you can't see. The peg is the true value, and your sample decides where the ring lands. A 95% method uses a ring sized so that 95% of tosses catch the peg. A bigger ring catches more often but says less about where the peg is, and a ring that has landed either holds the peg or doesn't.