On Tue, May 31, 2011 at 8:48 AM, Melissa P <takingupspace...@gmail.com>wrote:
> I’m pretty much in agreement with what you’ve said below. But keep in > mind that the most serious problem affecting survey research right now is > the increasing number of cell phone-only households in the United States. I > guess it’s somewhat of an exaggeration to say that it’s wreaking havoc on > sampling, but it probably actually is. > > > > Also, Ron said: > > > > “56% of Twitter users, for example, are in the 30-54 year old target demo” > > > > According to the Pew Research Center, only 8% of Americans are using > Twitter, so while Twitter response might approach usefulness for teenage > girls, it’s not much of an answer for everyone else. > > > > It’s nice to have extra information about TV viewing habits, but at this > point in time we really don’t know how reliable it is. And, it may take > years for us to know the answer to that question. Although Nielsen numbers > are far from perfect – and getting less perfect every day -- they’re still > the best we’ve got. > The Cell phone problem had thrown a huge money wrench into typical sampling procedures - even the years between the last presidential election cycle and the next will likely see a huge change on this characteristic alone. This is likley to be even more of a problem for those particularly interested in understanding young adults. At least with political polling there is an actual criterion score that can be used to correct and adjust sampling models - I don't know how this can really be done for television viewing (how will we ever know how many people "really" watch a particular program on a given night? Maybe every 4 years we could have 2 weeks when the only way to access any program on any platform would be to log-in and complete some basic demographics, and this could be used as a baseline to adjust sampling methods. I don't fully understand what Nielsen does - if it were me I would try to get demographically accurate samples of the US population, then get as rich a record of total viewing behavior as possible from each individual in the sample (e.g. tv sets, computers, bars, college dorms, airplanes, etc). A method that relies just on monitoring what programs are tuned on specific household television sets seems doomed to being wildly inaccurate. -- TV or Not TV .... The Smartest (TV) People! You received this message because you are subscribed to the Google Groups "TV or Not TV" group. To post to this group, send email to tvornottv@googlegroups.com To unsubscribe from this group, send email to tvornottv-unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/tvornottv?hl=en
