First Results on the Schoen Survey in Liberty Plaza

The pollster Doug Schoen, a Fox News analyst and partner in the polling firm Penn, Schoen, and Berland, claims that his assistant Arielle Alter Confino (and possibly others) conducted 198 interviews in Zucotti Park on October 10 to 11. So far I have not encountered anyone who answered the survey, or even reported seeing it taking place. This last weekend I attempted to carry out a survey to verify the claim.

Unfortunately, my ability to survey was eliminated for much of my time in the area by the record New York snowfall on October 29, and so I was only able to collect data for a few hours on Sunday, October 30. In that process I discovered that data collection in the park is difficult and slow. After conducting interviews, I was only able to find 23 people (including myself) who were in Zucotti Park on the days in question. Of those, none reported responding to a survey on October 10 or 11.

This number of responses is not very low. One other survey has been reported by Fordham professor Costas Panagopoulos. He reported that over the period from October 14 to October 18, five days, his survey only reached 301 respondents. He also reported that he had 15 survey takers, while I only had one.

ANALYSIS

Since there were no respondents who said they answered the Schoen survey, I cannot rule out the possibility that it was not conducted. In order to assess the probabilities, a Bayesian process can be used.

First, an idea of prior probabilities is required by the Bayesian analysis. Zuccotti Park has an area of only 3,100 square meters according to Wikipedia and thus the number of people in it can be at most several thousand. The Schoen survey was taken on a Monday (Columbus Day) and the following Tuesday, so attendance is probably off-peak. However, people can come in and out through the two days. I am fairly confident the number of people who attended on those two days is less than 10,000 and probably is significantly less. Thus, we expect that more than 2% of the sample responded to the Schoen survey.

For the Bayesian analysis, we consider four unmarked boxes. In this analysis, "yes" means that the person I surveyed responded to the Schoen survey. The four boxes are the trick box, which contains no yes responses, and the other three are boxes which contain 2% yes (corresponding to an attendance of 9900), 4% yes (4950 attendance), and 6% yes (3300 attendance). I randomly pick one of the four boxes with equal (25%) probability and draw 23 responses from the box. I can then calculate the probability that the box I selected was either the trick box or one of the other four boxes.

If I chose the trick box, there is a 100% chance I got 23 noes. For the 2% box, the probability of drawing 23 noes is 0.98 to the 23rd power, or 62.835%, for the 4% box, the probability is 39.106%, and for the 6% box, 24.096%. Overall, then, the probability that I drew 23 noes is the average of these four probabilities, or 56.509%.

The possibility that I drew the trick box is 25%. So, the probability knowing that I got 23 noes that I drew the trick box is 25% divided by 56.509%, or 44.2%. The probability I drew the 2% box and got 23 noes is 15.709%, which divided by 56.509% is 27.8%. The probability I drew the 4% box and got 23 noes is 9.777%, which divided by 56.509% is 17.3%, and the probability I drew the 6% box and got 23 noes is 6.024%, which divided by 56.509% is 10.7%.

So, in summary, the probabilities are:

Trick box-- 44.2%

2% box-- 27.8% (attendance is 9900)

4% box-- 17.3% (attendance is 4950)

6% box-- 10.7% (attendance is 3300)

More statistics could bring about much more certainty. In particular, a single respondent who answered the Schoen survey would entirely rule out the trick box. Having just a hundred responses would greatly improve the statistics. For this reason, I would like to repeat the survey on an upcoming weekend.

SUPPORT THIS WORK

The investigator is in need of funding for his travels from Ithaca to Wall Street. Any donations should go to the PayPal account connected to the email address hbowman108@hotmail.com.

Statistical Speech Sunday Oct. 23 2011 Ithaca GA

METHODOLOGY

Mostly the same as October 20, except that there were no supplied questions. A sign directed respondents to check all boxes that apply. The sampling time was from 2:18 PM to 4:30 PM. The facilitator was one of the respondents.

RESULTS:

In original order of the questions:

US Citizen? 16 yes, 1 no

Registered to vote (US citizens): 12 yes, 3 no

Voted in 2010 (US citizens born before Nov 2 1992): 9 yes, 4 no

Voted in 2008 (US citizens born before Nov 2 1990): 10 yes, 3 no

Attended previous Occupy Ithaca events: 15 yes, 1 no

Attended OWS in New York City: 5 yes, 9 no

College student (undergraduate): 2 yes, 11 no

College grad (BS/BA level): 5 yes, 7 no

Age: 1 under 18, 5 18-24, 6 25-44, 2 45-64, 2 over 65

OBSERVATIONS

Numbers responding to questions were more even than last time. Partially this was because there was no ethnicity question and because the age question was multiple choice instead of a series of yes/no questions.

It was surprising that only one respondent had not been to an Occupy Ithaca event before. Perhaps more effort needs to be put into promotions.

General Protocol Advice for Facilitators

In the protocol described for the October 20 General Assembly in Ithaca, the only protocol concerns were that results should be accurately and promptly reported and methodology should be explained in full. In particular, no question should be unreported due to concerns about the results' value to the facilitator or to a movement. That is what partisan polling firms do.

In more complex speech protocols, reporting may be limited due to privacy concerns. I have considered having a methodology with individual questionnaires, and in that case I recommend that reporting be limited to the aggregate number of responses for questions, and the aggregate numbers for pairs of responses. For instance, facilitators may report how many people voted in 2010 in a subsample of questionnaires such as speakers with reported ages between 25 and 44. However, posting complete results of all of the individual questionnaires should only be done with individual consent.

First Statistical Speech Oct. 20 Ithaca NY OWS General Assembly

METHODOLOGY

Two poster boards were set out at the Occupy Ithaca General Assembly on the evening of Thursday October 20, 2011. At the announcements part, participants (henceforth called "speakers") were encouraged to speak statistically and sampling commenced at 7:47 PM. It lasted for one hour, ending at 8:47 as the meeting winded down.

One poster board contained only yes or no questions provided by myself (Harry Bowman, 108 N. Geneva St. Apt. 8, Ithaca NY 14850, @HBowman108, hbowman108@hotmail.com). The second was open to questions submitted by the speakers themselves.

RESULTS:

This is the original order of the questions I provided:

White? 23 yes, 0 no

Black? 0 yes, 8 no

Asian? 1 yes, 8 no

Latino? 0 yes, 8 no

US Citizen? 21 yes, 3 no

Registered to Vote (US citizens only)? 18 yes, 4 no

Voted in 2010 (US citizens born before Nov. 2 1992)? 15 yes, 6 no

Voted in 2008 (US citizens born before Nov. 4 1990)? 16 yes, 4 no

Live in City of Ithaca? 17 yes, 6 no

Male? 14 yes, 3 no

Female? 9 yes, 6 no

Employed (other than participating in OWS)? 17 yes, 4 no

College Student (undergrad)? 7 yes, 10 no

College Graduate? 15 yes, 5 no

Native speaker of English? 19 yes, 3 no

Submitted questions (in submission order):

From Finger Lakes area? 5 yes, 5 no

Aged under 18? 1 yes, 4 no

19-25? 4 yes, 3 no

26-45? 6 yes, 1 no

46-64? 1 yes, 2 no

Over 65? 2 yes, 3 no

LBCATQ? 2 yes, 2 no

What is your economic background? 2 responses: $120,000 a year, $12,000 a year

Indigenous? no yes, 2 no

OBSERVATIONS (includes personal opinions of the author)

On some questions, it may be useful to explicitly describe the format. Results suggest that many speakers may have viewed the ethnicity questions as not being independent and only submitted a single response. My intent was to allow multiple responses as is allowed on the US Census. The age question was different, as speakers presumably should only identify with a single age group, and for this multiple choice may be a better format than yes or no.

One question was submitted without a yes or no answer. Such questions are more difficult to report if the number of responses is large.

I found that facilitators may need more pens than I thought due to the often chaotic conditions under which statistical speech may occur. In large settings such as Liberty Plaza, boxes of writing instruments will probably be needed and I will check on prices on those. I recommend that pens should be used instead of pencils since the marks may smudge in transport away from the speech site.

SUPPORT THIS WORK

Donations to the facilitator of this statistical speech should be sent to PayPal at the account linked to my email address, hbowman108@hotmail.com. Facilitators are free to link to statistical speeches in the comments section or elsewhere.

Introducing Statistical Speech

Statistical Speech is a new process to be used at events such as Occupy Wall Street. It allows people to express themselves in the aggregate and post results easily to the Internet.

In recent weeks, the right-wing pollster Doug Schoen has posted results from an alleged survey of 198 Occupy Wall Street participants taken in Liberty Plaza (aka Zuccotti Park) on October 10 and October 11, the weekend of Columbus Day. I did not see any evidence of survey taking, and I have not talked to anyone who has. Unless someone can show otherwise, I suspect the survey may be a fake. So, we see that data is not required for the political establishment to "pigeonhole" the movement. The only way to counteract this narrative is for us to speak statistically ourselves.

So far, the method used in Statistical Speech is simply to set out poster boards with questions to be answered. The results are then tabulated and posted. The method is intended to be carried out by entirely autonomous individuals, and can be conducted at very low cost.