PING! 
Your One Stop Resource For All The California Recall News!
Want on our daily or major news ping lists? Freepmail DoctorZin.
Posted on 08/25/2003 3:33:28 PM PDT by DiamondDon1
Welcome to the world of the Left Angeles Times…
On August 24, 2003 the Los Angeles Times released the results of a survey which has been touted by many as a huge boost for Cruz Bustamante’s chances to become the next governor.
Problem. The poll contacted 1351 registered voters but did not achieve the appropriate number of Latino voters. So the “main sample”, whatever that is supposed to mean was supplemented by an unknown number of Latinos in order to provide 125 additional Latino “likely voters”. Even by the Times own numbers, this little bit of skewing affects the numbers by 9 percent plus or minus.
Now when I took statistics, a “random” sample was just that “random”. When a poll is taken where “supplemental voters” and added to provide additional voters in one category that is a problem, the conclusions reached cannot be trusted.
When you read the poll below, take your time. Look at what they asked, and how they theoretically asked it (because such things as voice inflection can skew results).
We can look at the results differently than the Times and arrive at completely different numbers…such as:
Removing the Times supplementing process, we have 801 – 125 or 676 likely voters. If these 125 Latino “likely voters” were removed (51 percent according to the Times support Bustamante, and 12 percent support Arnold), the numbers change thus:
Bustamante = 280 – 64 = 216 likely voters or 32 percent
Arnold = 176 – 15 = 161 likely voters or 24 percent
Now while this in itself changes the numbers from a 13 percent lead for Cruz, to 8 percent other factors should also be considered.
Review the questions shown below. Notice anything? Notice a slanted bias? Note that the questions below occur before the candidate questions, and thereby influences the participant.
“In a recall election, a replacement candidate does not have to win by a majority vote. Because there are so many candidates on the replacement ballot, it is possible a new governor could be chosen with the support of less than 20 percent of the voters-even if, for example, Davis lost the recall election by 51 percent to 49 percent. Does knowing this could possibly happen make you more likely to vote in favor of recalling Gov. Davis, or more likely to vote against recalling Gov. Davis, or won’t it change the way you are likely to vote one way or the other?”
“As you may know, 135 candidates were certified to be on the ballot as candidates to replace Governor Davis if the recall passes. Does the fact that so many candidates will be on the ballot make you more likely to vote in favor of recalling Governor Davis, or won’t it change the way you are likely to vote one way or the other?”
Down a few questions…
“Some people say that the recall election is an attempt by Republicans to overturn an election they lost in November 2002. Do you agree or disagree?”
“Some people say that recall elections like this one interfere with an elected state official’s ability to fulfill his or her duties and efficiently run state government. Do you agree or disagree?”
“Does the fact that the special recall election will cost taxpayers at least 66 million dollars enter into your decision to vote yes or no to recall Governor Davis, or does that fact not enter your decision at all?”
Read the link below for yourself…there are many more questions similar to those above that appear skewed to make the recall sound like a right-wing power grab that is ethically, and morally wrong…
http://images.latimes.com/media/acrobat/2003-08/9130937.pdf
One only knows what the actual (unsupplemented) numbers regarding the recall “yes or no” are…
DD
We cannot bury our heads and must realize Bustamante is the favorite and has a solid bloc which will vote for him simply because of the D.
For example, the following statements are basically the same:
Your face could stop a clock!
When a look at your face, time stands still...
So you have left-leaning polesters asking the questions, questions prior to the candidate question were anti-Republican in general...so what other than they held a poll (and nobody cared...)
DD
Cruz will get anywhere from 30 - near 50% of the vote.
Skewed poll or not, this is reality.
It all depends on how it's done.
For instance, if I want to survey a population and compare let's say three age groups. If one of the age groups is underrepresented in the population, and I draw a random sample, I may not get enough of the oldest age group.
There just aren't that many of them and a random sampling will give me about 30 old respondents. That's not a big enough sample to compare them to the other groups.
So, I purposely interview 100 old respondents even though a random sample would not give me this result.
Now all I have to do is weight the old respondents down from 100 to 30, when extrapolating to the entire population.
That is only one of the many ways populations are over and under sampled. As long as you weight them back to their proper proportions, before extrapolating to the whole, your fine.
The proper method is to keep dialing randomly until you get a large enough group of Latino voters to complete the survey.
Then I can compare the answers of say White and Latino voters, and retain the ability to weight them back to the entire population, when looking at the population in total.
I'm not saying that a poll can't be skewed, even on purpose. But, over and under sampling is a valid procedure.
That being said, the pollster is paid by someone. I'd never put my name on a skewed poll, but I can't vouch for all of us.
Then I can compare the answers of say White and Latino voters, and retain the ability to weight them back to the entire population, when looking at the population in total.
Agreed...it is doubtful that this pollster suddenly found God, and took the time to randomly call people (white, black, asian, latino) to actually find the Latino likely voters...
I agree with your analysis on the 30 year old, however every community has 30 year olds, but if it were 90 year olds you're missing, it is all but too tempting to call retirement homes, rather than do it right...
I am glad that you would not put your name to this...
DD
However the pollster corrects this misconception before asking which canidate they would vote for (besides all the other push poll type questions).
As I have said before on other threads, Bustamante is going to take a hit from Democrats who don't bother to vote on question two, but the LA poll seems designed specifically not to reflect this.
Only the most die-hard liberals will bother to vote, many will not bother to vote for a canidate. By contrast the conservatives are reved up and anxious to get to the polls.
If a major media company called me for a poll I would probably suffer through it to give them the answers they really don't want.
They could then either:
A) Toss my answers and substitute what they think I really meant.
B) Add ten more "supplemental" samples to balance my opinions.
C) Remove my opinions from the population of likely voters, since I have voted in every election in the last 20 years and I am surely too tired to vote in another.
D) All of the above.
The bozos helped Bush waste time and money by saying their polls showed he had a chance to beat Gore and the race was very close.
They are incompetent boobs and get snookered again and again.
Not taking the Dems and how they will support Bustamante in lock step for the most part is a recipe for loss.
Better then bitter pessimism. I recall the 2002 election polls had Davis winning by a lot more then he did. If the Pubbies were a little more confident and reved up Davis probably would not have won.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.