Practice free →
HomeAP StatisticsStatisticsConfidence Intervals › Older statistical practice used the normal appro…

Older statistical practice used the normal approximation for large samples and the Student's t-distribution only for samples of at most 30. What does modern practice, with graphing calculators and computers, now use instead?

AThe normal distribution for every sample, regardless of size
BThe t-distribution only for samples smaller than 10
CThe t-distribution whenever s is used as an estimate for σ
DWhichever distribution gives the narrower confidence interval
Answer & Solution
Correct answer: C. The t-distribution whenever s is used as an estimate for σ
1. Historically, statisticians switched between normal and t-distribution methods based on a sample-size cutoff of 30. 2. With modern computing power, that cutoff is no longer necessary. 3. Current practice is to use the t-distribution any time the sample standard deviation s stands in for an unknown σ, regardless of n. 4. Option D describes cherry-picking a method by interval width, which is never recommended. _Source: OpenStax Introductory Statistics (CC BY 4.0), Ch 8 "Confidence Intervals", section 8.2 A Single Population Mean using the Student t Distribution_
Solve this in the app — AP Statistics practice & 24k+ MCQs →
Related questions