Need help calculating sample size

kerryf

New member
Joined
Feb 13, 2019
Messages
5
Hey guys, I need some help calculating the minimum sample size needed for my upcoming trial. I’m doing higher degree research on eHealth, so I have little knowledge about statistics and sample size calculation. Was doing loads of research online and trying out online calculators but I’m still not too sure.


So basically I’ve done an initial trial on a small sample of 24 participants, randomly allocated to two groups (13 in control group and 11 in intervention group), the aim is to see whether the use of an IT based intervention can improve health supplement adherence rate when compared to a control group using a pillbox. Below is the result from the initial trial:


Control group- average baseline adherence rate before trial was 86%, and after trial the average adherence rate increased to 95%
Intervention group- average baseline adherence rate before trial was 81%, and after trial the average adherence rate increased to 98%


So what I would like to know is: what is the minimum number of participants I will need for each group (I want a 2:1 ratio, so more people in the intervention group). I need to know the very minimum number as I was having problem recruiting enough participants in the initial trial, and I’m currently starting the recruitment process for the upcoming full trial. I plan to recruit about 40 people in intervention and 20 in control, is this enough?


Power=at least 80%, and alpha=0.05


I’ve tried this online calculator, but unsure what to put in the anticipated incidence sections, or if it is the right calculator to use in my case: https://clincalc.com/stats/samplesize.aspx


Any help will be appreciated.
 
Hey guys, I need some help calculating the minimum sample size needed for my upcoming trial. I’m doing higher degree research on eHealth, so I have little knowledge about statistics and sample size calculation. Was doing loads of research online and trying out online calculators but I’m still not too sure.


So basically I’ve done an initial trial on a small sample of 24 participants, randomly allocated to two groups (13 in control group and 11 in intervention group), the aim is to see whether the use of an IT based intervention can improve health supplement adherence rate when compared to a control group using a pillbox. Below is the result from the initial trial:


Control group- average baseline adherence rate before trial was 86%, and after trial the average adherence rate increased to 95%
Intervention group- average baseline adherence rate before trial was 81%, and after trial the average adherence rate increased to 98%


So what I would like to know is: what is the minimum number of participants I will need for each group (I want a 2:1 ratio, so more people in the intervention group). I need to know the very minimum number as I was having problem recruiting enough participants in the initial trial, and I’m currently starting the recruitment process for the upcoming full trial. I plan to recruit about 40 people in intervention and 20 in control, is this enough?


Power=at least 80%, and alpha=0.05


I’ve tried this online calculator, but unsure what to put in the anticipated incidence sections, or if it is the right calculator to use in my case: https://clincalc.com/stats/samplesize.aspx


Any help will be appreciated.

Tiny, TINY populations. If your calculator does not know about the Finite Population Correction Factor, your results are likely to demand more than 100% of your population. That's no good.
 
Tiny, TINY populations. If your calculator does not know about the Finite Population Correction Factor, your results are likely to demand more than 100% of your population. That's no good.

So I’ll have to use the Finite Population Correction calculation? Does that gives a minimum number of sample size needed?
 
So I’ll have to use the Finite Population Correction calculation? Does that gives a minimum number of sample size needed?

1) Absolutely.
2) The FPCF is part of the usual calculation for sample size.
3) These are such small populations you are talking about. Are you SURE you can't do a complete survey?
4) Rule of Thumb. If your calculation requires more than about 5% of your population, use the FPCF version.
5) 5% of 20 is 1.
 
Last edited:
1) Absolutely.
2) The FPCF is part of the usual calculation for sample size.
3) These are such small populations you are talking about. Are you SURE you can't do a complete survey?
4) Rule of Thumb. If your calculation requires more than about 5% of your population, use the FPCF version.
5) 5% of 20 is 1.
24 is all I had that completed the initial trial/pilot. I had 50 people registered, but a lot didn’t respond, few didn’t match the inclusion criteria and 2 dropped out. So I was left with 24 that completed the study. I’m doing the study on participants that take health supplement as a surrogate to prescribed medication to reduce the possible health risks involved, and there isn’t much existing literature of research done on health supplements participants or my intervention (which is Facebook chatbot). Most of the existing literatures are on medications and simple reminders like sms. But research have shown that more than 60% of Australian people takes some kind of health supplements, so that’s a big population group, and yeah my sample of 24 is very small compared to the population, but the main aim of the pilot was to find the effectiveness of the intervention and uses the feedbacks I’ve gathered to modify the intervention to be used on this upcoming second/full trial, so the pilot wasn’t really done to give me a sample number estimation for the full trial.
 
1) Absolutely.
2) The FPCF is part of the usual calculation for sample size.
3) These are such small populations you are talking about. Are you SURE you can't do a complete survey?
4) Rule of Thumb. If your calculation requires more than about 5% of your population, use the FPCF version.
5) 5% of 20 is 1.

The aim of my initial trial/pilot was mainly to gather adherence rates and feedbacks in order to improve the technology for the intervention group for this upcoming full trial. It wasn’t conducted to help calculate the sample size needed for the full trial. But I was wondering that since I had some results, if I can use that to calculate the sample size. But if 24 participants from the pilot is too small of a sample I don’t have to use it. I can try and find existing literatures on similar study done on larger population but I doubt I’d find anything too similar as the technology intervention I used is quite new, plus I’m doing the study on people taking supplements as a surrogate to prescribed medication, and most existing literatures and researches are done on people taking medications. But study have shown that more than 60% of Australians takes health supplements.
 
Top