The current reported disease prevalence is .6% of the population. I've tried using the formula n=Z^2(p(1-p))/M^2 with a confidence level of 95% and M=0.05 but my n value is obviously too small if I plug in 0.006 for p. Do any staticians out there have insights?
We are planning on screening for Sickle Cell Disease in Uganda using hemoglobin electrophoresis. One of our primary objectives is identifying the burden of sickle cell disease in certain districts where we suspect the true figure is higher than what has previously been reported. Obviously, we'd like to screen enough patients to obtain an accurate figure.
Dear Derek
The sample size depends on the type of your population, is it finite population or infinite population.
In the case of finite population, you can use Slovin formula:
n= N / ( 1+ N * e^2 )
But in the case of an infinite population:
The sample size for any study depends on the standard deviation of the variable ( from previous studies ) and the margin of error you decided. The formula:
n= ( Z^2 * S^2) / E^2
where : Z ( 1.96 for 0.05 and 2.58 for 0.01 )
S = standard deviation from previous studies or pilot study
E = significant level
Also, you can use software to calculate sample size ( SPSS , Minitab , G*power )
My advice to use G*Power . 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
I hope that be useful for you.
Good Luck
Hello Derek ,
please what are the following :-
N (number of population)
Sampling techniques (one stage , 2 or 3 stages , etc.) > Design effect.
There are other software online as :-
http://www.raosoft.com/samplesize.html
https://www.medcalc.org/calc/test_one_proportion.php
https://www.surveysystem.com/sscalc.htm
http://www.openepi.com/SampleSize/SSPropor.htm
Can you analyze pooled samples? If the prevalence is so low, you will have a good chance that only very few pools are positive, and only those patients will have to be analyzed individually. You can even think of sereval pooling steps, like pool of 100 -> 2 pools of 50 -> 2 pools of 25 -> 25 individual measurements. Here you need 1+2+2+25 = 30 measurements to identify/count all positive samples instead of 100. And if you consider that many of the pools of 100 will be negative (where no further mesaurements are required), you can screen quite a large sample with quite view measurements.
Another way would be to quantify the mutation in the hemoglobine gene with qPCR. You can pool (same amounts of) DNA of 100 or 1000 people and quantify the proportion of mutated genes within this mixture directly.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size