## The Annals of Mathematical Statistics

### On the Cost of not Knowing the Variance when Making a Fixed-Width Confidence Interval for the Mean

Gordon Simons

#### Abstract

It is shown that the mean of a normal distribution with unknown variance $\sigma^2$ may be estimated to lie within an interval of given fixed width at a prescribed confidence level using a procedure which overcomes ignorance about $\sigma^2$ with no more than a finite number of observations. That is, the expected sample size exceeds the (fixed) sample size one would use if $\sigma^2$ were known by a finite amount, the difference depending on the confidence level $\alpha$ but not depending on the values of the mean $\mu$, the variance $\sigma^2$ and the interval width $2d$. A number of unpublished results on the moments of the sample size are presented. Some do not depend on an assumption of normality.

#### Article information

Source
Ann. Math. Statist., Volume 39, Number 6 (1968), 1946-1952.

Dates
First available in Project Euclid: 27 April 2007

https://projecteuclid.org/euclid.aoms/1177698024

Digital Object Identifier
doi:10.1214/aoms/1177698024

Mathematical Reviews number (MathSciNet)
MR239699

Zentralblatt MATH identifier
0187.15805

JSTOR