A disease affects approximately 1% of women.
If we want to look for a sequence variations in certain gene that might be responsible for this condition. How would we calculate the sample size?
You might collect case-control sample due to very small prevalence of disease.
The sample size can be decided by the expected association between a gene and disease.
Unfortunately, this information is not enough to decide sample size.
Power analysis? Read this for a good introduction: http://www.amazon.com/Experimental-Design-Data-Analysis-Biologists/dp/0521009766
Free trial:
http://www.ncss.com/ads/adwords_PASS001.html?gclid=CIH-trv8qq8CFaJYmAodRVIMXA
Hi Mahmood,
If the sample size you mean is the number of women that you will carry out the study on, then this formular might be useful: n = Z2pq/ d2
where,
Z2 = Z raised to power 2
d2 = d raised to power 2
n = minimum sample size
Z2 = Standard score corresponding to a given confidence level. Example, at 95% Confidence Level or 5% level of significance ( = 0.05), Z = 1.96.
P = Prevalence of of disease in women is 1%
q = (1 – p) or percentage of failure which is 100 - 1 = 99%
d = Precision limit or proportion of sampling error which is usually 5% confidence limit.
n = Z2P (1-q)/ d2
Best of luck!
Uchendu Florence
All the above are fine. There are many methods used to determine the sample size, however, Uchendu Florence has nailed it. You still need to determine a sample mean and so forth from previous studies. You can also check this link for clarity http://www.isixsigma.com/tools-templates/sampling-data/how-determine-sample-size-determining-sample-size/
Good luck!
otto rigaba
This is a rare disease you can chose case control study design and non probability sampling other wise you have to provide some more information
A case control study design will be appropriate in such a situation. If our purpose is to know whether or not a sequence variation in a certain gene is responsible for the disease, then a case control is ideal. Use OpenEpi for the calculation of sample size for the same. http://www.openepi.com/OE2.3/Menu/OpenEpiMenu.htm
Thank you all for very useful information
To complete information required by Sangchoon Jeon, in one of the studies 07 out of 332 patients had mutation in this particular gene. Would this information be helpful in calculating sample size.
Thank you Flo Uchendu for the formula. Would the sample formula would be used for calculating the number of patients and the number of normal control?
Thank a lot again
Hi Mahmood,
The formular is meant to calculate the number of patients and not control.
Regards,
Hi Flo
Thanks for the information. What is the formula for calculating normal control?
The following formula is used to calculate the size of the required sample
n = (z)2 p ( 1 – p ) / d2
or when p = 1/2 (0.5)
n = (z)2 / 4d2
n = sample size
z = level of confidence according to the standard normal distribution (for a level of confidence of 95%, z = 1.96, for a level of confidence of 99%, z = 2.575)
p = estimated proportion of the population that presents the characteristic (when unknown we use p = 0.5)
d = tolerated margin of error (for example we want to know the real proportion within 5%)
Examples
1) To calculate a proportion with a 95% level of confidence and a margin of error of 5% we obtain
n = (1.96)2 / 4(0.05)2 = 384.16
2) To calculate a proportion with a 95% level of confidence and a margin of error of 7% we obtain
n = (1.96)2 / 4(0.07)2 = 196
3) To calculate a proportion with a 99% level of confidence and a margin of error of 2% we obtain
n = (2.575)2 / 4(0.02)2 = 3218.75
IN YOUR CASE:
n = (z)2 p ( 1 – p ) / d2
z=1.96
p=0.01=1/100 ( A disease affects approximately 1% of women )
d=0.05
n=(1.96)2 0.01(1-0.01)/(0.05)2
n=15.212736
You'll need to use the following formula if you have a very large population or an unknown one. If you still have values for the remainder of the variables, use the equation:
- Sample Size = [z2 * p(1-p)] / e2
- z = z-score e = margin of error p = standard of deviation
- Please refer to this website: https://www.wikihow.com/Calculate-Sample-Size?fbclid=IwAR03h3mzLy_frmcGZamM_CpA8rtKj8FZjuwCMkyPu-yR_ryh5FgYpBJCe6M
The formula to calculate sample size is given by
n = z^2 * p * (1 - p) / e^2
Where:
n is the sample size,
z is the z-score associated with a level of confidence,
p is the sample proportion, expressed as a decimal,
e is the margin of error, expressed as a decimal,
N is the population size.
What's the name of this sampling formula? Who formulated it and in which year?
- Badges
- Science topic
- Similar topics
- Social Psychology
- Attitude