Sample Size Estimation

Dear Sir Nayer Sahib,

Please upload the
materials on confidence interval

and sample size.As the previous is

expired.

Thanks regards,

Amin khan

Dear Ameen

I have updated the expired link. Please see again

THANK YOU SIR!!!
It is a nice presentation.
Much Helpful.
Very Easy to understand.

Dear Sir,

Thanks for

uploading.

It is widespread belief among researchers that the bigger the sample, the better the study becomes.This is not necesssarily true. In general it is much better to increase the accuracy of data collection (by giving good training to the interviewers and by pretesting the data collection tools) than to inrease the sample size after a certain point.Also it is better to make extar efforts to get a representative sample rather than to get a larger sample.

As a general rule we say that the desirable sample size is determined by the expected variation in the data, the more varied the data , the larger the sample size we need to attain the same level of accuracy.

For Cross-Sectional surveys and Analytical Studies Precise calculations usually be made that indicate the desireable sample size
For Exploratory Studies We can not say more than that the sample size needs to be large enough to reflect important variations and small enough to allow fro intensive study methods.
Example:-
In a study on attitude towards family planning, you may decide to interview three categories of informants (nonusers,female users,and male users), and start interviews 20 to 30 per category.This number could be increased if the data obtained for each category do not indicate a certain trend or if the results are conflecting.

in short we can say that:-
The final sample size is usually a compromise between what is DERIRABLE and what is FEASIBLE.

Agreed with Abuzar

Thank You Sir!

The feasible sample size is dtermined by the availablity of resources
1. Time
2. Manpower
3. Transport
4. Money

If you include many variables in your study (which is usually the case in exploratory type of sudy) the sample should be relatively small, to avoid problem during analysis. If you have few variable you can afford to have a large sample size.

Here are Genreal Rules which will help you to determine your sample size in any type of study
**The desirable sample size depends on the expected variation in the data, the more the variation the larger the sample size you will need

** In comparative study the greater the difference between the two groups the smaller will be sample size you need to draw
** in a prevalnece determination study the more is the prevelance of the disease under study the smaller will be the sample size
The more you want,that your study should be precise then you will need a comaparative larger size of the sample

Example:

Required sample size for studies of women with Goitre

Estimmated proportion Margin of Error Required
of women with Goitre (95%) precision Sample Size

District Nowshera 1/100 = 1% + 0.5% 1600
-

District Peshawar 1/1000 = 0.1% + 0.05% 16,000
-

Example of Hypothyroidism would have been more relevant specially since most of our MPH students are defacto Ph.D's

Example:
Required Sample size for studies of women with Goiter

........................Estimated Proportion.......Margin of Error ........Required Sample
........................of women with Goitre...... (95% Precision).......,,,Size

District Nowshera....1/100 = 1% ..............+0.5%.......................1600

District Peshawar....1/1000...0.1%.............+.05%......................16,000

in the above example when the prevalence was 1% (High) then we require only 1600 study units
but when it was 0.1% (very low) then we have to increase the sample size to 16,000

Really Good Idea Ha Ha
there are a lot of Positive thing with this idea
1. Samples will be convenience sampling (as we are already there in Abasyn)
2. As the prevalance is very high of your suggested atribute (Hypothyroidism) so the sample size will be very small only Zar Ali and Adnan are enough
3. Yours Most desired Research will be accomplished

Three Cheers!!!!!

Dear Dr Zahid
Please dont post in irrelevant section. Create a new post and then you post your synopsis over there. At the moment, as a warning I am deleting your synopsis from this section

Dear Sir

The above link for sample size estimation donot give the download option, might be disabled for it. Furthermore if you upload the previous lecture on International Health delivered last week.

Regards

Respected Sir

Hope you might have been recovered from illness and discomfort uptil now. May Allah protect you from such discomfort in the future. Moreover we all are waiting for the Lectures remaining to be uploaded on the forum (i.e. Sample size estimation. Intl Health Intro, Swine Flu, Bird Flu.)

Will be very much thankful

Regards

Respected Sir

I tried my best to find the 4 Lectures of International Health delivered uptil now Both on Scribd and Slideshare, but i couldnot find them. Kindly please upload the Lectures on
1) Introduction to Intl Health
2)Swine Flu
3)Bird Flu
4) WHO

Waiting humbly for Reply.

Regards