NONE: RE: ONLINE-ADS>> Online marketing research dilemmas
RE: ONLINE-ADS>> Online marketing research dilemmas
Hairong Li (hairong_at_pilot.msu.edu)
Tue, 16 Jun 1998 12:33:16 -0400
It seems to me that there are three types of surveys on the Internet. The
first is what I call "closed" surveys. Examples would include the Opinion
Place on AOL, run by Digital Marketing Services (http://www.dmsdallas.com/).
AOL users could volunteer to participate in a survey in the Opinion Place
for some rewards. A set of screening criteria are used for quality control.
It's reported that some comparison studies by DMS have found no significant
differences in demographics and responses to same questions between
telephone samples and online samples of AOL users. I did an online survey in
a free net in Missouri a couple of years ago. I compared the age
distribution of the user population (from registration database) with that
of my online sample using a chi-square test, the difference was not
significant either. So I believe that in a closed system with a definite
population, online surveys could be reliably generalized to the population
from which a survey sample is recruited online.
The second type of surveys is what I call "semi-closed." In this system,
survey volunteers are recruited with some rewards into a pool, and then
randomly selected and notified for participation of a survey. Quotas are
often used to make the sample representative to a desired population in
terms of major demographic variables. I think the results could be reliably
generalized to the pool if the survey is managed well, and lesser reliably
generalized to the Internet population as a whole. Examples would include
Connect Consultant International (http://www.cciresearch.com/).
The third one is what I call "open" surveys, like the Georgia Institute of
Technology's GVU's WWW User Survey and other similarly designed and executed
surveys. I think it's less meaningful to talk about "self-selection" issue
of online surveys in general. Self-selection is indeed an issue for online
surveys, same as for mail or telephone surveys but it may not necessarily be
a problem for a given online survey. It will affect the generalizability of
an online survey to various degrees, depending on the type and execution of
an online survey.
Hairong Li, Ph.D.
Department of Advertising
Michigan State University
East Lansing, MI 48824
Phone: 517-355-1739
http://www.admedia.org/
========================================================================
------------------------------------------------------------------------
This week's Online Advertising Discussion List sponsors:
ICONOCAST, Larry Chase and ChannelSeven.com
"This continues to be the 'coolest' and most informative e-mail
newsletter I get." Randy Haldeman, Director of Marketing, TEN-TV
To subscribe, visit http://www.iconocast.com
---
Free sample chapter to
"Essential Business Tactics for the Net," by Larry Chase
http://LarryChase.com
---
Subscribe to the NEW ChannelSeven Newsletter - News, Ad Case Studies,
Mrkt Research, Turbo-Ad Resources, Event Info & People-On-The-Move...
EMAIL: ch7-news-request_at_list.channelseven.com with "SUBSCRIBE" in subj.
------------------------------------------------------------------------
========================================================================
Online Advertising Discussion List To Unsubscribe send UNSUBSCRIBE
http://www.o-a.com/ to online-ads-request_at_o-a.com
