Chance News 30: Difference between revisions

From ChanceWiki
Jump to navigation Jump to search
Line 12: Line 12:
Test and CI for Two Proportions  
Test and CI for Two Proportions  


Sample  X  N  Sample p
<table width="49%" border="1">
 
  <tr>
1       5  6  0.833333
    <td width="33%"><div align="center">Sample</div></td>
 
    <td width="13%"><div align="center">X</div></td>
2      2  7  0.285714
    <td width="12%"><div align="center">N</div></td>
 
    <td width="42%"><div align="center">Sample p</div></td>
Difference = p (1) - p (2)
  </tr>
 
  <tr>
Estimate for difference:  0.547619
    <td><div align="center">1</div></td>
 
    <td><div align="center">5</div></td>
95% CI for difference:  (0.0993797, 0.995858)
    <td><div align="center">6</div></td>
 
    <td><div align="center">.0.833333</div></td>
Test for difference = 0 (vs not = 0):  Z = 2.39  P-Value = 0.017
  </tr>
 
  <tr>
 
    <td><div align="center">2</div></td>
Fisher's exact test: P-Value = 0.103
    <td><div align="center">2</div></td>
 
    <td><div align="center">7</div></td>
a.. NOTE * The normal approximation may be inaccurate for small samples.
    <td><div align="center">0.285714</div></td>
 
  </tr>
===Discussion===
</table>
 
1.. Assume you are a frequentist, what about statistical significance?  Note the discrepancy between the exact P-Value and the P-Value using the normal approximation. <br>
2.. Assume you are a Bayesian and thus immune to P-Value whether exact or due to a normal approximation, pick your priors and find the probability that there is a difference between the effect of the supplement and the effect of the placebo. <br>
3.. Aside from the choice of inference procedure, frequentist or Bayesian, what other flaws do you see in this study with regard to sample size and measurement of success?<br>  
4.. Speculate as to why this study was reported in a Twin Cities newspaper and probably not elsewhere.  
5.. Speculate on what might happen if the 11 who did not respond to the supplement originally were put on the follow-up study.
 
Submitted by Paul Alper


==item2==
==item2==

Revision as of 17:55, 13 September 2007

Quotations

Forsooth

Supplement may help treat gambling addiction

Miniapolis Star Tribune, September 12, 2007

There seems to be a never-ending supply of questionable statistical studies. Consider the recent Minneapolis Star Tribune account of September 12, 2007. A University of Minnesota researcher publishing in the September 15, 2007 issue of Biological Psychiatry treated "27 pathological gamblers for eight weeks" with an amino acid supplement, N-acetyl cysteine . "By the end, 60 percent said they had fewer urges to gamble." Of the 16 who reported a benefit, "13 remained in a follow-up study.five out the six on the supplement reported continued improvement, compared to two out of seven on a placebo." According to the researcher, "There does seem to be some effect, but you would need bigger numbers."

Here are the results of the follow-up study as seen by Minitab:

MTB > PTwo 6 5 7 2.

Test and CI for Two Proportions

Sample
X
N
Sample p
1
5
6
.0.833333
2
2
7
0.285714

item2

Retrieved from "https://www.causeweb.org/wiki/chance/index.php?title=Chance_News_30&oldid=4536"