Appeal to Mitofsky's citizenship and ethical duty

[dargondogon]

December 7, 2004

Mr. Warren Mitofsky
Mitofsky International
1776 Broadway
Suite 1708
New York, NY 10019

Dear Mr. Mitofsky:

As a highly respected, innovative and conscientious pollster, you’ve led the world in developing exit polling techniques and enhancing democracy by amplifying the voice of the public.

You, more than I, certainly, and more than most anyone else on earth, understand the value of accountability in polling. You understand the fragility of public trust in polling, the temptations of apathy and the cynicism of critics who dismiss the value of polling.

That’s why I appeal to you to release the raw data from the Nov. 2 exit polling: to encourage you to trust the science you’ve developed.

Polling is more than collecting data: It's a science that requires its practitioners to allow others to attempt to replicate their work.

Of course we cannot replicate an election and its exit polls. But your calibrations of your data should be made available for replication. Without that crucial final step of releasing data for replication, your work is not relevant, not scientific and not reputable.

I urge you to abide by the polling standards promulgated by the American Association for Public Opinion Research by publicly:

-- Discussing possible sources of error.
-- Describing any special scoring, editing, data adjustment or indexing procedures (or calibration) used.
-- Describing your sample design.
-- Describing your sample selection procedure.
-- Delivering a full accounting of the final outcome of all "sample cases."
-- Describing how non respondents differ from respondents.

The data no longer have proprietary value to your subscribers. Election Night is long over, they hired you to help them promptly report results. Now it's time to make a transition to public service, Mr. Mitofsky.

Fond regards,

[texpatriot2004]

1. Hey, I just read this, it's good...thanks for posting. n/t

[RevCheesehead]

2. Not to nit-pick, but I have one grammatical point to make:

If you haven't sent it, the last paragraph should read "the data no longer has...".

(thank you to Mrs. Kohls, high-school English teacher, and the Chief of Grammar Police.)

[mulethree]

3. data is technically plural, nowadays either form works.

One datum no longer has value
Two data no longer have value

The data set no longer has value

But thats old fashioned. Using singular verbs and pronouns with 'data' has been acceptable for years.

[Paligal]

6. Exactly. Just as it is "media ARE" not "media is"

Just my pet peeve that people often believe that the word "media" is singular. It's pretty much the norm now for people to say "The media is ignoring us", rather than "The media are ignoring us". The latter is actually grammatically correct, though the incorrect form is used so often that people would find it strange sounding to say "media are".

[xpat]

8. British usage

"Media is" or "media are" depends whether you speak/live on an island off the coast of Europe or on a continent somewhat to the west.

I think one of the hidden causes of the American Revolution was our refusal to further suffer the British affectation of construing collective nouns in the plural.

BTW, the BBC are, too. However, as well all agree, NBC is. ;)

[RevCheesehead]

7. But "data" as a whole is singular! (at least in modern usage)

Data = a collection of information.
For example:
The collection IS singular.
The individual facts ARE plural.

[ClintCooper2003]

4. I thought I read somewhere that his phone number is listed in NYC.

[Carolab]

5. May I make a suggestion?

Please forward a copy to KO at MSNBC. I have asked him to get the raw data on behalf of MSNBC as a subscriber to the "polls".

[mulethree]

9. I bet the poll questionnaires don't require a signature

So the people who donated their opinions/answers had a reasonable expectation that the data would be publicly available, at least in some form of aggregation.

I doubt they signed over ownership of their data to the polling companies or to the media consortium.

It must be public data, no? Else class action suit on behalf of the
anonymous polled seeking fulfillment of implied contract to make data public?

I can't believe the DNC didn't subscribe or that the DNC or one of the media companies haven't been over it with a magnifying glass by now.

[fasttense]

10. Does Anyone get the irony in this?

I mean look at us US citizens we've been running elections for years with no way to prove the election was valid. A media group gets a profit making organization to do exit polls (which in most other countries are used to verify fair elections). Now both the media group and the profit making organization have a vested interest in the outcome of the election. Can we trust them to do fair exit polls?

Not to mention the Democrats sit idly by and don't even bother to get the results of the exit polls. All I can do is shake my head in wonder.

[carolinalady]

11. Most likely Repub and BFEE--forget it -- SUBPEONA

If he was ethical and moral he would be doing everything he could to assist the process.

[reality_bites]

12. You are beating a dead horse. The data isn't his to release. n/t

[mulethree]

13. He Can release it Because he's a dead horse :)

Since they've ruined his career, company and reputation by fouling up his biggest assignment - the entire U.S. presidential-year election.

What else does he have to loose?

A little security lapse and oops! some reporter paid $5K to an unknown lackey to write a DVD with the data and sneak it out? Oh my how unfortunate.

But seriously its cbsnbcabccnnapfox who own the data? Get one to agree to release it and they can point their finger at the rest and accuse them of journalistic non-integrity and perhaps shame them into consenting.

[electropop]

14. Clear, to the point, and polite.

Too bad Mitovsky doesn't seem to care about ethics.