370 replies to this topic

[Mike in STL]

Gallup is a scientific poll with lots of attention paid to who comprises the sample. This is not one of those... so, nope...

If they ask 1 player that is qualified to weigh in on the subject, that is .001333% of major leaguers. Gallup is .000005% of Americans. One major leaguer is a larger sample size than 1500 Americans.

I would think of 240 ball players polled, At least 1 is qualified to answer the question.

[RShack]

If they ask 1 player that is qualified to weigh in on the subject, that is .001333% of major leaguers. Gallup is .000005% of Americans. One major leaguer is a larger sample size than 1500 Americans.

I would think of 240 ball players polled, At least 1 is qualified to answer the question.

 

But which one?   

[Mackus]

If they ask 1 player that is qualified to weigh in on the subject, that is .001333% of major leaguers. Gallup is .000005% of Americans. One major leaguer is a larger sample size than 1500 Americans.

I would think of 240 ball players polled, At least 1 is qualified to answer the question.

Yeah but there are only 2 options when they ask 1700 or whatever it is Americans the same question. You can get a pretty good sample from a small subset. Just gotta make sure the subset you ask represents the larger group you are hoping to appproximate.

Not flawless. And people seem to never pay attention to the margin for error that is stated on all polls.

[BSLSteveBirrer]

Again, all the discussion about deviation, reliability, sample size is nice but pretty meaningless. I think Mackus said earlier the best response..."its certainly not a positive."

[RShack]

The media is so bought and paid for and in lockstep with the overlords desired message, they were mainly just completely convinced Trump had no legitimate chance. So insanely foolish and naive from jump street, but instead of reporting facts along the way, they HELPED get him elected.

Yes, they did.

 

They failed to cover any issues of actual policy at all. They simply refused to talk about it whatsoever. Hillary had 209 policy papers on her web site explaining in some detail what she proposed to do about, well, 209 policy things. Trump had zero... none. Did the media focus on that? No, they did not. Instead they put Trump on TV 24/7 and never asked any real questions about anything substantive or reported anything that took the least bit of work to find out.

 

TV-people don't understand how their own medium is powerful. Roger Ailes did, but the rest of them don't.

[BSLChrisStoner]

I understand how this came up in regards to the reliability of polling; but we dont have to go further down this path.

[JeremyStrain]

It's been proven to work.  The main trick is making sure you've selected the right 1400 people.

 

Yeah this is what I was getting at. People go, oh 31%, that's a sound number, must be fact.

 

In reality though, you can skew whatever result you want by selecting a CERTAIN 31%.

 

Say if you polled all 1,000 members of a group. 30% sounds like a good enough sample size to get whatever number you are looking for. But say those results of all 1000 break down to 50% red, 30% white and 20% blue. If you wanted to show that Blue was the winning opinion, you could just choose to poll all the people you estimate to poll blue, and then 10% of white. If your results from a 30% study then show 66% percent blue, 34% white and 0% red, you would be very wrong if you just extrapolated those numbers and thought 30% polled was significant enough to draw that conclusion.

 

Studied these a lot in psych class, it was almost a philisophical debate within a psychology class of how you know you got an accurate sampling group.

[birdwatcher55]

The word "rebuilding" is not in Buck's vocabulary. That Melewski interview is priceless. Total joke.

[mweb08]

I'm pretty sure those that conducted this survey weren't looking for a certain 31%.

Definitely not seeking out a group that would specifically be anti-Buck.

And considering that there are 30 managers in baseball and considering how many respondents there were to this survey, there's clearly an abnormally high number of players that would not want to play for Buck more so than any other manager. As Mackus said, it's certainly not a positive. That's about as pro Buck as this can be spun imo.

[bmore_ken]

Studied these a lot in psych class, it was almost a philisophical debate within a psychology class of how you know you got an accurate sampling group.

Which is why I place no stock in polls.

[RShack]

Studied these a lot in psych class, it was almost a philisophical debate within a psychology class of how you know you got an accurate sampling group.

 

I think a lot of that was because the prof was intro'ing the basic lay of the land.  Hard to discuss sampling decisions when the discussion is kinda high level... it can get a lot more concrete when you do specific case studies... but those take a bunch of time to do well, and I'm guessing there wasn't time to fit very much of that into the syllabus...