Ask your own question, for FREE!
Statistics 7 Online
OpenStudy (followthefez):

Difference between sampling error and non-sampling error?

OpenStudy (followthefez):

Can someone please explain the difference between a sampling error and a non-sampling error? If possible give examples. My lecturer tried to explain it but he's not very good and I got very confused.

OpenStudy (anonymous):

Sol, let me ask you what part was not clear with those concepts?

OpenStudy (followthefez):

Everything. Sorry. I'm not sure which error I can control and which I can't. Or can I not control either of them? I understand the basic concept of error (e.g. taking samples only at one time of day. Inaccurate measurements etc.)

OpenStudy (anonymous):

No need to be sorry! :) Let's review first the concept of the sampling error. In statistics, sampling error is incurred when the statistical characteristics of a population are estimated from a subset, or sample, of that population. Sampling Error: There may be inaccuracy in the information collected during the sample survey, this inaccuracy may be termed as Sampling error. So you can not control Sampling Error, because it does not depend on you. Is that clear? [:

OpenStudy (anonymous):

Sampling error =Frame error + Chance error + Response error.

OpenStudy (followthefez):

So in terms of say, taking a sample of cars, I can't control what type of cars pass through a roundabout at a particular time?

OpenStudy (anonymous):

Yes, that is correct. But what you can control is the way you are going to count the cars. In other words after counting... let's say 1000 cars you can miss one or not.

OpenStudy (followthefez):

Okay. Got it. What about non-sampling error (this is where my lecturer kept confusing me!)

OpenStudy (anonymous):

Well Non-sampling errors can be further divided into converge errors, measurement errors (respondent, interviewer, questionnaire, collection method...), not-response errors and processing errors.

OpenStudy (followthefez):

So they're errors that are people influenced?

OpenStudy (anonymous):

Well you can say that depends on people yes, so you can try to do it in such way that they can be as minimum as it is possible. There would be always non sample errors

OpenStudy (followthefez):

Well that makes more sense! Thank you very much! Much appreciated! :) My lecturer spent half and hour trying to explain it but ended up confusing himself!

OpenStudy (anonymous):

You are welcome~~! I am glad you could see the difference between those concepts. [:

Can't find your answer? Make a FREE account and ask your own questions, OR help others and earn volunteer hours!

Join our real-time social learning platform and learn together with your friends!
Can't find your answer? Make a FREE account and ask your own questions, OR help others and earn volunteer hours!

Join our real-time social learning platform and learn together with your friends!