01 / 21

Confidence Intervals
for a Population Mean

Learn to estimate population parameters from sample data by constructing and interpreting confidence intervals using \( z \)-scores and \( t \)-scores.

AP Statistics

What Is a Confidence Interval?

A confidence interval is a range of plausible values for an unknown population parameter, computed from sample data. Instead of a single point estimate, it gives a range that likely contains the true value.

Point Estimate
A single value: the sample mean \( \bar{x} \) is our best guess for \( \mu \).
Interval Estimate
A range: \( \bar{x} \pm \text{margin of error} \) captures \( \mu \) with stated confidence.

Key Vocabulary

\( \mu \)
Population mean: the unknown parameter we want to estimate.
\( \bar{x} \)
Sample mean: our point estimate, computed from \( n \) observations.
\( \sigma \) / \( s \)
Population (\( \sigma \)) or sample (\( s \)) standard deviation: measures spread.
Confidence Level
The probability (e.g., 95%) that the interval method captures \( \mu \) in repeated sampling.
Margin of Error
The "half-width" of the interval: \( E = z^* \cdot \frac{\sigma}{\sqrt{n}} \) or \( t^* \cdot \frac{s}{\sqrt{n}} \).

Visualizing the 95% Confidence Interval

\( \bar{x} \)
\( \bar{x} - E \)
\( \bar{x} + E \)
95% 2.5% 2.5% E E

The \( z \)-Interval Formula

When the population standard deviation \( \sigma \) is known and the sampling distribution is approximately normal:

\( \bar{x} \)
Sample mean: the center of the interval.
\( z^* \)
Critical value from the standard normal distribution for desired confidence level.
\( \frac{\sigma}{\sqrt{n}} \)
Standard error: describes spread of the sampling distribution.

Common Critical Values

Confidence Level \( z^* \) Value \( \alpha \)
90% 1.645 0.10
95% 1.960 0.05
99% 2.576 0.01

\( z \)-Interval vs \( t \)-Interval

Feature \( z \)-Interval \( t \)-Interval
When to Use \( \sigma \) is known \( \sigma \) is unknown
Distribution Standard Normal Student's \( t \)
Critical Value \( z^* \) \( t^* \) with \( df = n - 1 \)
Standard Error \( \frac{\sigma}{\sqrt{n}} \) \( \frac{s}{\sqrt{n}} \)
Interval Width Narrower (for same \( n \)) Wider (heavier tails)

Conditions for Valid Inference

1
Random: The data must come from a random sample or randomized experiment.
2
Independence (10% Condition): When sampling without replacement, \( n \leq \frac{1}{10}N \), where \( N \) is the population size.
3
Normal/Large Sample: Either the population is approximately normal, or \( n \geq 30 \) (by the Central Limit Theorem).

Step-by-Step Procedure

1
State the parameter: "We want to estimate \( \mu \), the true mean of..."
2
Check conditions: Verify Random, Independence (10% rule), and Normal/Large Sample.
3
Calculate: Compute \( \bar{x} \pm t^* \cdot \frac{s}{\sqrt{n}} \) (or \( z^* \) if \( \sigma \) is known).
4
Interpret: "We are C% confident that the true mean \( \mu \) lies between [lower] and [upper]."

Example 1: \( z \)-Interval

A factory knows the fill-weight standard deviation is \( \sigma = 2.4 \) grams. A random sample of \( n = 36 \) bottles has \( \bar{x} = 500.8 \) g. Construct a 95% confidence interval for \( \mu \).

Example 2: \( t \)-Interval

A random sample of \( n = 20 \) students scored an average of \( \bar{x} = 74.5 \) with \( s = 8.2 \) on an exam. The population is approximately normal. Build a 99% confidence interval for \( \mu \).

Example 3: Effect of Sample Size

Using the factory example (\( \sigma = 2.4 \), \( \bar{x} = 500.8 \), 95% confidence), compare intervals for different sample sizes:

\( n \) Standard Error Margin of Error Interval Width
9 0.800 1.568 3.136
36 0.400 0.784 1.568
144 0.200 0.392 0.784

Visualizing Interval Widths

\( \bar{x} = 500.8 \)
\( n = 9 \)
\( n = 36 \)
\( n = 144 \)

Interpreting Correctly

✓ Correct
"We are 95% confident that the true population mean \( \mu \) lies between 500.016 and 501.584."
✕ Incorrect
"There is a 95% probability that \( \mu \) is in this interval." (The interval either contains \( \mu \) or it does not.)

Common Mistakes

✕ Wrong Interpretation
Saying "95% probability \( \mu \) is in the interval." Confidence describes the method, not a probability about \( \mu \).
✕ Forgetting Conditions
Not checking Random, Independence, or Normality before building the interval. Always state and verify conditions.
✕ Using \( z^* \) When \( \sigma \) Unknown
If you use \( s \) instead of \( \sigma \), you must use a \( t^* \) critical value with \( df = n - 1 \).

Summary at a Glance

Concept Key Detail
Formula (\( \sigma \) known) \( \bar{x} \pm z^* \cdot \frac{\sigma}{\sqrt{n}} \)
Formula (\( \sigma \) unknown) \( \bar{x} \pm t^* \cdot \frac{s}{\sqrt{n}} \)
Conditions Random, Independent (10%), Normal/Large Sample
Increase Confidence Wider interval (larger \( z^* \) or \( t^* \))
Increase \( n \) Narrower interval (smaller SE)
Interpretation "We are C% confident \( \mu \) is between..."

Question 1 of 5

A 95% confidence interval for \( \mu \) is (42.3, 47.7). What is the sample mean \( \bar{x} \)?

Question 2 of 5

Which condition is not required to construct a confidence interval for \( \mu \)?

Question 3 of 5

A researcher has \( \bar{x} = 82 \), \( s = 6 \), \( n = 25 \). She uses a 95% \( t \)-interval. How many degrees of freedom should she use?

Question 4 of 5

If you increase the confidence level from 90% to 99% while keeping \( n \) and \( s \) the same, what happens to the margin of error?

Question 5 of 5

A 95% confidence interval is (18.2, 23.8). Which interpretation is correct?