Home > Statistics Every Writer Should Know > The Stats Board > Discusssion
Will pay reasonable fee to have survey data analyzed
Message posted by Danelle Russillo (via 192.127.94.7) on December 12, 2001 at 1:56 PM (ET)
I am in the midst of conducting a survey and am wondering if anyone could plug the results in and analyze the data with a view to determining answers to some specific qeustions? I would be happy to pay a modest fee for your time.
READERS RESPOND:
(In chronological order. Most recent at the bottom.)
Re: Will pay reasonable fee to have survey data analyzed
Message posted by Tomi (via 213.133.214.2) on December 13, 2001 at 4:50 AM (ET)
When you say "plug the data in" do you mean that you want someone to do the data entry for you as well? That part could more easily be done by a secretary or someone with typing skills.I'd like to know what data you have and what questions you would like to ask before committing myself.
Also, what timescale are you talking about?
Re: Will pay reasonable fee to have survey data analyzed
Message posted by JG (via 128.8.23.28) on December 13, 2001 at 9:58 AM (ET)
For this type of situation, it is best to start with a 'toy' model. That is, with a small portion of the data or even with a small problem that is similar. Also, it the customer has a study that has already been done as an example of what type of data he has and what he wishes to accomplish, that can be very helpful. However, there are many questions to ask - validity and reliability of the data - how was the data obtained - is it a random sample - what is the population etc. Other issues are, does the customer wish to study a problem or just obtain evidence to support a pre-determined conclusion. Usually, data suitable for statistical analysis has to be gathered by a statistically valid process that has been carefully checked for both validity and reliability. Otherwise, GIGO . For instance, does the customer understand that only a random sample can be statistically analyzed and the 'in real life' we usually have a sample that is partly random, partly judgement, partly what ever is available which we then 'assume' to be random and hope that this is a reasonable assumption.
Your $5 contribution helps cover part the $500 annual cost of keeping this site online.
