The Value of Surveys

Question

The Value of Surveys

Phil Factor

SSC-Insane

Points: 20244
More actions
June 10, 2017 at 12:21 pm

#330875

Comments posted to this topic are about the item The Value of Surveys
Best wishes,
Phil Factor

Viewing 7 posts - 1 through 6 (of 6 total)

You must be logged in to reply to this topic. Login to reply

Jeff Moden SSC Guru Points: 1003863 More actions · Answer 1

Both the Democrats and the Republicans found out both how wrong a survey can be and how it can actually sway what's going to happen if it's published in real time.

--Jeff Moden

RBAR is pronounced "ree-bar" and is a "Modenism" for Row-By-Agonizing-Row.
First step towards the paradigm shift of writing Set Based code:
________Stop thinking about what you want to do to a ROW... think, instead, of what you want to do to a COLUMN.

Change is inevitable... Change for the better is not.

Helpful Links:
How to post code problems
How to Post Performance Problems
Create a Tally Function (fnTally)

Tom Gillies SSCrazy Points: 2761 More actions · Answer 2

Surveys are a useful tool, but if you don't know what the sampling approach is, or the relationship of the sample to the whole population, then they they can be seriously misleading and maybe even dangerous.
A small, quick, informal survey may be useful if we take the results with a pinch of salt. If we extrapolate the results out to the whole world without thinking then bad things can happen.
There is also the possibility that the survey can start to influence what is being surveyed! That is one of the issues with opinion polls especially leading up to elections.
Of course now, thanks to Survey Monkey, everyone can run a survey. 😉

Tom Gillies LinkedIn Profile www.DuhallowGreyGeek.com[/url]

Eric M Russell SSC Guru Points: 125522 More actions · Answer 3

In addition to poor sampling, often times researchers, the media, and politicians try to gleam specific conclusions or score talking points from vaguely defined questions or "facts" that appear alarming on the surface but then quickly become less so once you peel back the headline and start to deconstruct it. For example, attempting to measure the poverty rate using a "statistic" like: "1 In 4 U.S. Kids Don’t Know Where Their Next Meal Is Coming From".

Here is another one:
"Tonight, as I outline the next steps we must take as a country, we must honestly acknowledge the circumstances we inherited. Ninety-four million Americans are out of the labor force," - Donald Trump
http://money.cnn.com/2017/02/28/news/economy/trump-jobs-94-million/index.html

"Do not seek to follow in the footsteps of the wise. Instead, seek what they sought." - Matsuo Basho

Neil Burton SSC-Insane Points: 22918 More actions · Answer 4

Jeff Moden - Saturday, June 10, 2017 5:57 PM
Both the Democrats and the Republicans found out both how wrong a survey can be and how it can actually sway what's going to happen if it's published in real time.

That's one of the reasons why it's illegal in the UK to publish exit poll results while the voting stations are still open. It's even illegal to publish forecasts based on these polls before stations close.

On two occasions I have been asked, "Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out?" ... I am not able rightly to apprehend the kind of confusion of ideas that could provoke such a question.
—Charles Babbage, Passages from the Life of a Philosopher

How to post a question to get the most help http://www.sqlservercentral.com/articles/Best+Practices/61537

Tom Gillies SSCrazy Points: 2761 More actions · Answer 5

Eric M Russell - Monday, June 12, 2017 8:08 AM
In addition to poor sampling, often times researchers, the media, and politicians try to gleam specific conclusions or score talking points from vaguely defined questions or "facts" that appear alarming on the surface but then quickly become less so once you peel back the headline and start to deconstruct it. For example, attempting to measure the poverty rate using a "statistic" like: "1 In 4 U.S. Kids Donâ€™t Know Where Their Next Meal Is Coming From".
Here is another one:
"Tonight, as I outline the next steps we must take as a country, we must honestly acknowledge the circumstances we inherited. Ninety-four million Americans are out of the labor force," - Donald Trump
http://money.cnn.com/2017/02/28/news/economy/trump-jobs-94-million/index.html

That's a fair point. There can be lots of different problems with surveys and sampling.

There is the informal survey which might be mis-applied, usually by extending the scope it is applied to.
There is the survey with questions which are poorly designed through ignorance.
And then the ones you are referring to, which may combine subtly skewed or leading questions to generate "click bait" statements which claim to be supported by statistics. This last category, especially when done with an "agenda", can be positively damaging.

The last one in particular gives rise to Mark Twain's "Lies, damned lies and statistics."

Tom Gillies LinkedIn Profile www.DuhallowGreyGeek.com[/url]

Matt Miller (4) SSC Guru Points: 124210 More actions · Answer 6

Eric M Russell - Monday, June 12, 2017 8:08 AM
In addition to poor sampling, often times researchers, the media, and politicians try to gleam specific conclusions or score talking points from vaguely defined questions or "facts" that appear alarming on the surface but then quickly become less so once you peel back the headline and start to deconstruct it. For example, attempting to measure the poverty rate using a "statistic" like: "1 In 4 U.S. Kids Donâ€™t Know Where Their Next Meal Is Coming From".
Here is another one:
"Tonight, as I outline the next steps we must take as a country, we must honestly acknowledge the circumstances we inherited. Ninety-four million Americans are out of the labor force," - Donald Trump
http://money.cnn.com/2017/02/28/news/economy/trump-jobs-94-million/index.html

The sad part here is the two sides are beating each other up using entirely different definitions of a common term. Pretty much ANY statement using any of the common methods used to track employment is fraught with controversy, simply because those computations are filled with assumptions that skew the numbers one way or the other. The number of people who WANT to work <> the number of people ABLE to work <> the number of people OF AGE to work.

Unless you start from a common ground (a vetted agreed upon question you're trying to answer and a vetted, agreed upon way to measure the answer)., any data gathered from any method can be impugned.

----------------------------------------------------------------------------------
Your lack of planning does not constitute an emergency on my part...unless you're my manager...or a director and above...or a really loud-spoken end-user..All right - what was my emergency again?