Sender: |
|
Subject: |
|
From: |
|
Date: |
Wed, 7 Feb 1996 15:09:31 EST |
In-Reply-To: |
note of 02/07/96 11:47 |
Comments: |
Converted from OV/VM to RFC822 format by PUMP V2.2X |
Reply-To: |
|
Parts/Attachments: |
|
|
Bill --
Sounds like one of your problems is with the form of the questionnaire.
Instead of having a paper and pencil questionnaire, have you thought
about using an interviewer-administered one? Although the up-front
costs are higher (you have to hire interviewers), the data quality
is also better, since you can insure random selection and need fewer
interviews. BTW, most self-administered interviewing situations
do not produce random samples. Even if visitors are selected at random
participants tend to be self-selected. The big problem is in determining
the extent of the bias due to self-selection. At least with the interviewer
administered study you can measure the extent of bias (through a logistic
regression on the probability of refusal) and adjust your sample accordingly.
These may not help you with your Feb. study, but you might want to
consider it. E-mail me privately if you want to see some examples.
--Adam
Adam Bickford, Smithsonian Institution,
Institutional Studies Office:: [log in to unmask]
(202) 786-2289
|
|
|