I have a problem with the calculation of sample size of my study.
Design: each participant will value 4 health states, including one 'baseline' state and 3 new states of interest. The sequence of the 3 new states will be randomly assigned to each participant. This is similar to cross-over study with 3 treatments.
Outcome: The value of each state will be bounded to 0 and 1 (continuous in-between).
The study question: are there any difference between value of the 3 new states?
The results will be examined using generalized linear mixed model with patients as random effect.
With Regards
Dear Przemysław Holko,
The following links may be useful for you.
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2876926/
http://www.statisticssolutions.com/sample-size-calculation-and-sample-size-justification/
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3775042/
https://www.unc.edu/~rls/s151-2010/class23.pdf
http://stattrek.com/sample-size/simple-random-sample.aspx?Tutorial=Stat
http://www.jpma.org.pk/full_article_text.php?article_id=3482
http://www.theanalysisfactor.com/5-steps-for-calculating-sample-size/
I hope it will help.
All the best !
Dear Przemysław
The sample size for any study depends on standard deviation ( from previous studies ) and the margin of error you decided .
G*Power software is effective tool to calculate sample size for many ranges of experiments. Also, you can determine effect size and power of the test, G*Power is free to download and easy to use after reading the manual, the download link:
http://download.cnet.com/G-Power/3000-2054_4-10647044.html
The link to download G*Power manual:
http://www.gpower.hhu.de/fileadmin/redaktion/Fakultaeten/Mathematisch-Naturwissenschaftliche_Fakultaet/Psychologie/AAP/gpower/GPowerManual.pdf
Good Luck
With all of these tools, be careful about what assumptions they are making. If you want to sure about what assumptions you are making, you may be better off running simulations.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size