The method most often used in anderson sweeny and

This preview shows page 52 - 64 out of 144 pages.

The method most often used in Anderson, Sweeny, and Williams involves comparing a critical value of z to a computed value. This amounts to nothing more than relabeling the x axis in our diagram.
Image of page 52

Subscribe to view the full document.

Look at the picture in terms of z 0.3 0.2 0.1 10 5 0 Normal Density Distribution of sample proportion if the null is true. Accept Reject 3 2 1 0 -1 -2 -3 z α α
Image of page 53
Compute the z that corresponds to our observed value Again, suppose our subject got 28 correct in 100 trials. The z-score is 2.00. Which is greater than the critical z-score of 1.645. So we reject the null hypothesis. .05 .28 .20 .2 .8 100 2.00 1.645 obs obs z z z = × = > =
Image of page 54

Subscribe to view the full document.

Here is the picture 0.3 0.2 0.1 10 5 0 Normal Density Distribution of sample proportion if the null is true. Accept Reject 3 2 1 0 -1 -2 -3 1.645 2.0 .05
Image of page 55