How large should n be so that a 95% z-CI for μ (with σ=12) has margin ≤2?
Example 3
hard
xˉ=68, s=12, n=9. Construct a 95% t-CI for μ. Use t∗=2.306 (df =8).
Example 4
challenge
We want a 99% CI for μ with margin ≤1 unit. From a pilot, σ≈8. Find the required sample size.
Example 5
medium
A sample of n=100 has mean xˉ=80 with σ=10. Build a 95% z-interval using z∗=1.96.Sampling distribution of x̄ (n = 100, σ = 10, SE = 1); 95% CI = [78.04, 81.96]
Example 6
medium
A poll of n=900 voters has p^=0.60. Using SE =p^(1−p^)/n and z∗=1.96, find the 95% CI to the nearest 0.01.
Example 7
hard
We want a 95% CI for a proportion with ME ≤0.03, using worst-case p^=0.5 and z∗=1.96. Find the smallest n.
Example 8
hard
Two independent samples give xˉA=70, xˉB=66, with SE(xˉA−xˉB)=1.5. Build a 95% CI for μA−μB using z∗=1.96.
Example 9
medium
A study reports a 95% CI of [2.0,4.0] kg for average weight loss. Translate this into estimate-and-ME form.
Example 10
challenge
A 95% CI for μ uses xˉ=50, s=12, n=36, and t∗≈2.030 (with 35 df). Build the interval and round to 0.01.
Example 11
hard
A sample of 100 students has a mean test score of xˉ=72 with population standard deviation σ=10. Construct a 95% confidence interval for the population mean.
Example 12
hard
A 95% confidence interval for the mean weight of apples is (150g, 170g). Interpret this interval.
Practice Problems
Try each one, then open the solution to compare your method.
Example 1
easy
Write the general form of a confidence interval.
Example 2
easy
A sample mean is 50 with margin of error 3. State the 95% confidence interval.
Example 3
easy
Does a 95% confidence interval mean 95% of the data lies inside it?
Example 4
easy
Which is wider: a 90% confidence interval or a 99% confidence interval from the same data?
Example 5
easy
As sample size grows, what happens to the width of a confidence interval (other things equal)?
Example 6
easy
A 95% CI for a mean is [12, 18]. What is the point estimate (center)?
Example 7
easy
A 95% CI for a mean is [12, 18]. What is the margin of error?
Example 8
easy
Fill in: a confidence interval quantifies the ____ in using a sample to estimate a population value.
Example 9
medium
A sample of n=64 has mean 100, with σ=16. Build a 95% CI using z∗=2.Sampling distribution of x̄: shaded region is the 95% CI [96, 104]
Example 10
medium
A 95% CI for a difference in means is [-1, 5]. Does it provide evidence of a real difference at the 5% level?
Example 11
medium
Going from 95% (z∗=2) to 99.7% (z∗=3) confidence, by what factor does the margin of error grow?Increasing z* from 2 (95%) to 3 (99.7%) stretches the margin of error by a factor of 1.5
Example 12
medium
A poll reports 54% approval with a 95% CI of [50%, 58%]. Interpret what '95% confident' means here.
Example 13
medium
To halve the width of a confidence interval (same confidence, same σ), how must n change?
Example 14
medium
A 90% CI uses z∗=1.645. With SE =4 and estimate 30, give the 90% CI.
Example 15
medium
A 95% CI for a mean is entirely above 0, say [2, 8]. What does this imply about the parameter?
Example 16
medium
Two 95% CIs for a mean: study A gives [48, 52], study B gives [40, 60]. Which study had the smaller standard error?
Example 17
medium
A 95% CI for a mean from n=36, σ=18, xˉ=40 uses z∗=2. Find the interval.Sampling distribution of x̄: SE = 18/√36 = 3; 95% CI
Example 18
challenge
A sample of n=400 has p^=0.5. Build a 95% CI for the proportion using z∗=2 and SE =p^(1−p^)/n.
Example 19
challenge
A 95% CI for a mean from n=100, σ=20 is desired with total width at most 4. Is n=100 enough? If not, find the needed n.
Example 20
challenge
Explain why a single computed 95% CI like [47, 53] should NOT be described as 'the parameter has a 95% probability of lying in [47, 53]'.
Example 21
easy
A sample of n=100 gives xˉ=20 with known σ=5. Compute the 95% CI for μ.Sampling distribution of x̄ (n = 100, σ = 5, SE = 0.5); 95% CI
Example 22
easy
A 95% CI for μ is [10,16]. What is the point estimate?
Example 23
easy
n=400 sampled voters give p^=0.52. Compute the 95% CI for p.
Example 24
easy
xˉ=80, σ=10 known, n=25. Compute the 90% CI for μ.
Example 25
medium
xˉ=15.2, s=2.4, n=16. Compute the 95% t-CI for μ. Use t∗=2.131.
Example 26
medium
A 95% CI for μ is [48,52]. Interpret correctly.
Example 27
medium
n=900, p^=0.30. Find the 90% CI for p.
Example 28
medium
n=25, xˉ=72, s=10. Find the 95% t-CI for μ. Use t∗=2.064.
Example 29
medium
Two polls each report 95% CIs [42,48] and [45,51] for p in two populations. Does this show the populations differ?
Example 30
medium
n=200, p^=0.25. Compute the 95% CI for p.
Example 31
medium
A 95% CI for μ is [40,46]. Construct an approximate 95% lower bound for μ.
Example 32
medium
xˉ=200, s=24, n=36. Find the 95% t-CI for μ. Use t∗=2.030.
Example 33
medium
Two-sample 95% CI for μ1−μ2: [−1.5,4.5]. Can we reject H0:μ1=μ2 at α=0.05?
Example 34
hard
Plan: estimate a proportion within ±0.03 at 95% confidence with no prior info. What is the conservative required n?
Example 35
hard
A 95% CI for p is [0.40,0.50]. What is the approximate sample size if the CI uses z∗=1.96 and p^=0.45?
Example 36
hard
Two-sample data: xˉ1−xˉ2=4.0, pooled SE=1.5. Approximate 95% CI for μ1−μ2 using z∗=1.96.
Example 37
hard
A 95% CI for μd (paired differences) is [−0.2,1.4]. Conclude about a paired test of H0:μd=0.
Example 38
easy
A 90% confidence interval for a mean is [42,50]. What is the point estimate?
Example 39
easy
A 95% CI for a proportion is [0.42,0.58]. What is the margin of error?
Example 40
easy
A 95% CI for the mean test score is [72,78]. State the interval width.
Example 41
easy
A sample proportion is p^=0.40 with margin of error 0.05. State the 95% confidence interval.
Example 42
medium
A 99% CI for a difference in means is [2,8]. Does the data give evidence that the means differ?
Example 43
medium
Going from n=100 to n=400 (same data spread, same confidence), by what factor does the margin of error shrink?
Example 44
medium
A 95% CI for the average commute time is [28,34] minutes. Which interpretation is correct: (A) 95% of commuters are in [28,34]; (B) the procedure produces an interval containing the true mean 95% of the time?
Example 45
medium
A 95% CI for μ is [10,18]. Without new data, what is the 95% CI for μ/2?
Example 46
medium
A 95% CI for a treatment effect is [−0.5,2.5]. Does the data show statistically significant evidence of an effect at α=0.05?
Example 47
medium
Why does using a t-distribution instead of a z give a wider CI for the mean when σ is unknown?
Example 48
hard
A 95% CI for μ has half-width 4. To cut the half-width to 1 at the same confidence (same σ), what new sample size is required if the current n=50?
Example 49
hard
A 95% CI for the ratio μA/μB is [0.9,1.4]. Does the data support that the two means differ?
Example 50
hard
Researcher A builds a 95% CI: [10,20]. Researcher B uses the same data but builds an 80% CI. Will B's interval contain the value 15?
Example 51
hard
A claim says 'the true mean is in [42,50] with probability 95%.' Under the frequentist interpretation, what is wrong with the wording?
Example 52
hard
A 95% CI for one mean is [5,15] and an independent 95% CI for another mean is [10,20]. Can you conclude the means differ at α=0.05 just because the intervals overlap?
Example 53
hard
A sample of 64 has xˉ=50 and σ=8. Find the 99% confidence interval (z∗=2.576).
Example 54
hard
A 90% confidence interval for a population mean is given as 68 to 74. What are the sample mean and the margin of error?
What to focus on
Core idea:A sample estimate usually lands within about two standard errors of the truth, so the truth usually lies within two standard errors of the estimate. The confidence level is the long-run hit rate of that procedure, not a probability about any one interval.
Common stuck point:Students often know a procedure related to confidence interval but skip the recognition step: Is the goal to report a range of plausible values for an unknown population mean or proportion, built from one sample? That leads to a calculation or graph that looks reasonable but answers a different question.
Ask yourself:Is the goal to report a range of plausible values for an unknown population mean or proportion, built from one sample?
Concept recap
A confidence interval is a range of values, calculated from sample data, constructed so that the procedure captures the true population parameter a specified percentage of the time (e.g., 95%). It quantifies the uncertainty inherent in using a sample to estimate a population value.
Ring toss with a peg you cannot see: the peg (the true value) never moves, and each sample throws a ring (the interval) centered on its own estimate. A 95% method rings the peg on about 95 throws out of 100. Once a ring has landed, it either circles the peg or it doesn't; the 95% describes the thrower, not that throw.