Confidence Intervals and
Two basic uses of inferential statistics are possible:
a)interval estimation Ð so-called "confidence intervals"
b)point estimation Ð so-called "hypothesis testing"
Interval estimation ("Confidence Intervals") and point estimation ("Hypothesis Testing") are two different ways of expressing the same information.
Using Confidence Intervals we make statements like the following:
- the probability that the population mean (µ, or the 'true' value of the population mean) lies between 19 and 23 is 0.80;
- the probability that the population correlation value (r, or the 'true' value of the correlation between these two variables) lies between 0.20 and 0.24 is 0.60;
Using Hypothesis testing we say:
- the probability that our sample mean comes from a population with a mean of 21 is greater than 0.95
- the probability that our two sample means come from the one populations is less than 5% (i.e.,0.05).
- the probability that our sample comes from a population in which the true correlation is zero is 0.60.