Confidence

Table of contents
  1. Confidence Intervals
  2. Normal Interval

Confidence Intervals

There is a fixed true parameter θ that we want to estimate.

A confidence interval Cn=(a,b) is a random interval, and the calculation of a and b is a function of the sample X1,,Xn.

Cn is a random variable.

Since Cn is a random variable, there can be many realizations of Cn depending on the data.

If the calculation of Cn is repeated many times, and Cn contains θ with probability 1α, then Cn is a 1α confidence interval for some significance level α.

P(θCn)1α


Normal Interval

The quantile or the inverse CDF of the standard normal distribution tells us the value of z such that:

P(zZz)=1α

where ZN(0,1).

For a sample mean X, we know that by CLT:

Xμσ/nN(0,1)

Then, we can use the quantile of the standard normal distribution to say that the following is a 1α confidence interval for μ:

XzσnμX+zσn