Page 32 - Quality control of pharmaceuticals (07-PA 704)
P. 32

importance because many statistical tests are performed on the
     mean and assume that it is normally distributed.
Since in practice we can assume that distributions of repeated
     measurements are at least approximately normally distributed, it is
     reasonable to assume that the means of quite small samples (say n>5)
     are also normally distributed.
Inferential Statistics
The objective of inferential statistics is to make inferences about
     population parameters based on information contained in a
     sample.
Inferences About a Population Mean
Large Sample Results
Estimation procedures can be divided into two types:
We can calculate a single number, called a point estimate, from the

      sample data and use this value to estimate the parameter of interest.
Or we can compute two numbers from the sample data and use the

      interval formed by the two numbers as an interval estimate of the
      parameter of interest.
The distinction between the two is quite simple. In the first case we
      compute one number and infer that the parameter is that
      number. In the second case we compute two numbers and infer
      that the parameter lies in the interval between them.
Point Estimation of a Population Mean, μ
  Point estimate of : Ῡ
   27   28   29   30   31   32   33   34   35   36   37