[Home Page] [Previous Page]
[Old Roundtable Archives] [New Roundtable]
Posted by Mike Curtis on July 01, 1998 at 09:16:29:
In Reply to: Re: Re: Re: Re: Re: Re: Re: Re: Re: Re: Banner Ad / Online Survey Combinations posted by Sherman Whipple on June 30, 1998 at 19:32:22:
I'm not sure that I agree with your cause and effect point, Sherman. From a survey research standpoint, there are two types of error which have an effect on data - variance and bias. Variance refers to the "noise" surrounding data and is an indication of the precision, or lack thereof. Bias refers to the distortion of the data, and is an indication of the accuracy of data, or lack thereof. They are subsets or types of survey error, not a result of survey error.
Nonresponse can result in both bias and variance, though the most pressing issue from a data analysis standpoint is bias. It is also possible that nonresponse results in neither - then you have nonresponse, not nonresponse error. As you point out, there is no easy way to tell, so typically your best bet is to minimize nonresponse and you will usually have the impact of reducing nonresponse error as well.
Subject: Re: Re: Re: Re: Re: Re: Re: Re: Re: Re: Re: Re: Banner Ad / Online Survey Combinations