I am having 23 factors identified for my study. How to calculate exact sample size for non random sampling?
Dear Prachi Ingle. Concerning your issue about the calculation of the exact sample size for non random sampling. Calculating the right sample size is crucial to gaining accurate information! In fact, your survey’s confidence level and margin of error almost solely depends on the number of responses you received. For more details, I think the following below links may help you in your analysis:
http://fluidsurveys.com/university/calculating-right-survey-sample-size/
http://www.ph.ucla.edu/epi/rapidsurveys/RScourse/RSbook_ch3.pdf
https://www.gfmer.ch/SRH-Course-2013/Geneva-Workshop/pdf/Sampling-techniques-Ali-2014.pdf
Thanks
Confidence intervals and standard error rates have no meaning when the sampling (or at least the assignment to test groups) is not random regarding the factors that you want to test. Test-theory expects that measurement error is random and that by computing the mean of the scores of a group the error tends to get smaller. If you do not expect that your testscores come from a random sample regarding this testscore then you will need an idea of the sample error - else the mean value can not be seen as the best estimate of the true score.
The sample size calculation is the same in both cases. The interpretation of the results may not be the same.
Random sampling is seldom random. In random sampling any outcome is possible and accepted. So I have a population of 100,000, I want to take a random sample of 40. I assign all member of the population a number, and use a computer random number generator to select the individuals that will be chosen. It is unlikely, but the computer could chose individuals 5, 6, 7, ... 45. Most of the time a scientist would not accept this result ... so what we get is a "sensored random sample," or it might be a "pseudo-random sample."
The purpose of random is to reduce the chance that hidden biases influence the data. So in the above problem I might be better off selecting every 2500th individual and make sure that samples were dispersed evenly through the entire population.
If you select individuals from the population based on a specific trait (eye color and hair color) and then look at the influence of omega3 fatty acid intake on BMI one is thereby changing the population. Your results only apply to people with green eyes and black hair. As long as your sample is well dispersed through this population, the experiment is fine, only the population (and population size) has changed.
Below thread can be helpful:
https://www.researchgate.net/post/Do_you_know_any_sample_size_calculation_for_nonprobability_purposive_sampling_technique
Thanks,
Alok
https://www.researchgate.net/post/Do_you_know_any_sample_size_calculation_for_nonprobability_purposive_sampling_technique
Dear RG colleague,
Determining the sample sizes involve resource and statistical issues. Usually, researchers regard 100 participants as the minimum sample size when the population is large. However, In most studies the sample size is determined effectively by two factors: (1) the nature of data analysis proposed and (2) estimated response rate.
For example, if you plan to use a linear regression a sample size of 50+ 8K is required, where K is the number of predictors. Some researchers believes it is desirable to have at least 10 respondents for each item being tested in a factor analysis, Further, up to 300 responses is not unusual for Likert scale development according to other researchers.
Another method of calculating the required sample size is using the Power and Sample size program (www.power-analysis.com).
Regards,
In qualitative study where we select sample through purposive sampling technique. There is no need for a statistical representative sample. Any number of sample (sample size) can be selected, which can serve the purpose of the researcher.
This forum may help you.
https://www.quora.com/How-can-I-get-a-sample-size-when-using-purposive-sampling
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size