Group Abstract Group Abstract

Message Boards Message Boards

0
|
2.2K Views
|
1 Reply
|
0 Total Likes
View groups...
Share
Share this post:

Statistics Question of a Confidence Interval of a Proportion

Mitchell Sandlin
Posted 3 years ago

Hi;

In my example (see attached notebook), the values calculated by the NormalCI[] function does not equal the values calculated by the table and it my understanding that the two calculation methods should give the same answer since I am using a normal distribution. Using the attached notebook, I tried different confidence intervals in the NormalCI[] function, but none of the results matched the table calculated values. Mostly likely it is something that I am doing incorrectly.

Thanks,

Mitch Sandlin

Attachments:
Proportionsquestion.nb
POSTED BY: Mitchell Sandlin
1 Reply
Sort By:
Jim Baldwin
Jim Baldwin
Posted 9 hours ago

That's because your table values for i are the confidence levels and the table should be constructed in the following manner:

Table[{i, 
  13/147 - InverseCDF[NormalDistribution[0, 1], 1 - (1 - i)/2]*Sqrt[(13/147 (1 - 13/147))/147], 
  13/147 + InverseCDF[NormalDistribution[0, 1], 1 - (1 - i)/2]*Sqrt[(13/147 (1 - 13/147))/147]},
    {i, {.80, .85, .90, .95, .98, .99}}] // TableForm
POSTED BY: Jim Baldwin
Reply to this discussion
Community posts can be styled and formatted using the Markdown syntax.
Tag limit exceeded
Note: Only the first five people you tag will receive an email notification; the other tagged names will appear as links to their profiles.
Reply Preview
Attachments
Remove
or Discard