I made a list tonight of the topics I would like to cover over the next three weeks.
A series on how pollsters define and identify likely voters
Wireless phones
Response rates
The challenge of new registrants
Nightly tracking polls
Automated (IVR) polls
Internet Polls
Electoral College Projections
Nader’s vote
Exit polls
This list is ambitious given the calendar. Many of you have sent other excellent questions, but I will try hard to cover as man of the topics on this list as possible. I may also post occasionally with my thoughts about where the presidential race stands, but you have many sources of analysis on that front.
For tonight, I’m up watching debate coverage. Just as I typed that last sentence, Larry King just asked Candy Crowley to explain how pollsters decide who a likely voter is, and asked Perry Bacon whether we poll people with cell phones. I think that’s a sign…
Mark Blumenthal is political pollster with deep and varied experience across survey research, campaigns, and media. The original "Mystery Pollster" and co-creator of Pollster.com, he explains complex concepts to a multitude of audiences and how data informs politics and decision-making. A researcher and consultant who crafts effective questions and identifies innovative solutions to deliver results. An award winning political journalist who brings insights and crafts compelling narratives from chaotic data.
4 thoughts on “Where I’m headed”
I’d be interested in a “Day in the Life of the Pollster” blog once in a while. Meaning, polling aside, what is it like to be a pollster in a campaign. What are the tensions, pecking order, pulls and pushes. What’s the typical day look like. Do most pollsters work from standard core surveys that they cart from campaign to campaign. In short, what are the logistics of polling in a campaign, from question generation to conducting surveys, analysis and how all of those pieces are operationalized in the field. Maybe a good serial blog once the election is over. As always, keep up the great work and thanks!!
Pollsters also don’t call the military personnel. There are 1.5 million of them, many of them overseas and on bases in the US. Most don’t have phones where pollsters can reach them. These are all left out.
It might be interesting to discuss how to evaluate pollsters. I.e., after the election, is there a way of telling which pollsters were more accurate or “fairer” or had a better methodology overall?
The “proof of the pudding” is how well a pollster’s final pre-election poll matches the actual results. Here is an historical chart from 1936-2000: http://www.ncpp.org/1936-2000.htm
I’d be interested in a “Day in the Life of the Pollster” blog once in a while. Meaning, polling aside, what is it like to be a pollster in a campaign. What are the tensions, pecking order, pulls and pushes. What’s the typical day look like. Do most pollsters work from standard core surveys that they cart from campaign to campaign. In short, what are the logistics of polling in a campaign, from question generation to conducting surveys, analysis and how all of those pieces are operationalized in the field. Maybe a good serial blog once the election is over. As always, keep up the great work and thanks!!
Pollsters also don’t call the military personnel. There are 1.5 million of them, many of them overseas and on bases in the US. Most don’t have phones where pollsters can reach them. These are all left out.
It might be interesting to discuss how to evaluate pollsters. I.e., after the election, is there a way of telling which pollsters were more accurate or “fairer” or had a better methodology overall?
The “proof of the pudding” is how well a pollster’s final pre-election poll matches the actual results. Here is an historical chart from 1936-2000:
http://www.ncpp.org/1936-2000.htm