sample size for correlation

[SoS Statistical Services]

Hi

  I need to do a sample size calculation for a correlation study. The correlation coefficient in the pilot study is 0.5.

  For the sample size calculation I need to decide what correlation I want to be able to detect as statistically significant i.e. different from zero. Using the website http://www.stat.uiowa.edu/~rlenth/Power/index.html a correlation of  0.2 would require a sample size of 195 whereas a correlation of  0.4 would only require 46. If I use the correlation of 0.5 from the pilot study then that gives me a sample size of only 28 which seems very small.

  Am I on the right track? Can anyone advice me as to the best course of action. I would appreciate any advice.

  Thanks

  Evie


Evie Gardner
SoS Statistical Services
Email: [hidden email]
Tel:   [phone] Mobile [phone]

---------------------------------
 Rise to the challenge for Sport Relief with Yahoo! for Good

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD