IP: Working Paper on 1995 Baseline Internet Estimates

[Dave Farber <farber () central cis upenn edu>]

Well worth reading!!! djf




From: Donna Hoffman <hoffman () colette ogsm Vanderbilt Edu>
Subject: Working Paper on 1995 Baseline Internet Estimates
To: farber () central cis upenn edu
Date: Fri, 12 Apr 1996 09:00:32 -0500 (CDT)


Dave:


Tom Novak, Bill Kalsbeek and I have recently completed the working paper,


"Internet Use in the United States:  1995 Baseline Estimates and 
Preliminary Market Segments"


www2000.ogsm.vanderbilt.edu/baseline/1995.Internet.estimates.html


In a previous note we argued that the publicly released estimates of Internet
use reported in the CommerceNet/Nielsen Internet Demographics Survey are
inflated.  We demonstrate in this paper that the Nielsen estimates suffer
from two serious flaws which render the study conclusions invalid:


1) the weighted sample is not adequately adjusted to the population it
is intended to represent, and


2) the estimates lack logical consistency in their definitions of what an
Internet user is.


The average inflation due to deficient weighting alone is 20.6%, the average
inflation due to inconsistency alone is 13%, and the average total inflation
in the original Nielsen estimates, when adjusted for the combined effect of 
these critical flaws, is 38%.  As such, these estimates lack validity and
are of little value to decision makers.


We obtain new estimates by reweighting the raw data according to key 
demographic variables known to affect Internet usage; develop a set of 
estimates of Internet use based on conceptually valid and logically consistent
definitions of Internet access and use for the United States Internet market;
and derive a set of four Internet market segments, "Hard Core," "Regular,"
"Lapsed Regular," and "Infrequent," that provide important insights into
the nature of the United States Internet experience and facilitate the
study of its evolution over time.


As the Internet is characterized by tremendous uncertainty, we submit a
recommendation for all who must evaluate the results of Internet research.
In essence, we argue that the time has come to insist on a higher standard
for such research; a standard that will not only advance our understanding
of the Internet experience, but contribute to the population's education
of this important societal phenomenon.


Best,


DLH
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Professor Donna L. Hoffman                  hoffman () colette ogsm vanderbilt edu
Owen Graduate School of Management          615-343-6904 voice
Vanderbilt University                       615-343-7177 fax
Nashville, TN 37203                         129.59.210.109 CU-SeeMe


Project 2000:      http://www2000.ogsm.vanderbilt.edu/
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~