Murray’s Margin of Error

Patrick Murray is the founding director of the Monmouth University Polling Institute. According to their website, “The Monmouth University Polling Institute has become a premier independent survey research center known for its in-depth tracking of public policy and quality of life issues.”

Murray is a frequent media commentator on politics and public opinion---in fact, one of the folks that PolitickerNJ.com asked the opinion of each week to see which gubernatorial candidate “Won The Week”. PolitickerNJ.com named him one of 14 People to Watch in New Jersey Politics in 2009. He’s got a fancy looking website, with all sorts of numbers and names, graphs and graphics, statistics and such. Polling Institute director Patrick Murray appears regularly on One-on-One with Steve Adubato, and is a frequent guest on all the shows that cover NJ political scene.

Furthermore, according to their website, “The Monmouth University Poll’s standard methodology utilizes a random digit dial (RDD) ‘probability’ sampling design to select survey participants. All telephone exchanges (i.e., area code and first three digits of the phone number) that reach a household are programmed into a computer…after interviewing is complete, the sample is ‘weighted’ to correct for the fact that some respondents are harder to reach than others…. The Monmouth University Poll either tracks or adjusts for geography, gender, race, age, and education to comport with current U.S. census figures of the adult population. This weighting ensures that findings from a sample can be generalized to the full target population.”

One would think that Mr. Murray could predict anything with extreme accuracy, given all the fancy degrees, computers, and statistics training.

But wait, there is this catch-all disclaimer on all the surveys: “All surveys are subject to ‘sampling error’ ”----you know, that “plus or minus” number at the end of the poll that tells you just how much they could be off by. “This poll has a margin of error of plus or minus 3%” or so is what you’ll hear.

Now, my background---I am just an old, bald, overweight comedian from Brooklyn, with no fancy statistics degree. I don’t have an extravagant office at Monmouth University. I am not on NJN or ‘One on One with Steve Adubato’ each week. I was not named one of PolitickerNJ’s ‘most important’ anything last year or this year. And the same will most likely be the case for next year.

My methods for predicting the results of a contest between two (or more) does not require me to spend hours and hours bothering people of all ages by phone at dinner time, and then weighting the results ‘cause I could not get enough of one type of folk or another.

I just go by my instincts. That’s right—from the gut. My keen insight. My unique sixth sense. And that insight told me the Yanks in Six.

With all his fancy training, stats, and phone calls—what was Murray’s prediction?

That the Phillies repeat.

I guess that would be a margin of error of ---“plus or minus 100%” percent.

“I was looking at the World Series through (Phillies)red-colored glasses,” opined Mr. Murray, paying off on our bet. The result: one hundred dollars from his pocket to the Hole-in-the-Wall Gang Camps for kids with cancer. And he will be sending on a jar of honey to me, too. How sweet it is.

So, the lesson: If you want accurate predictions of who will win political races in NJ, stick with Murray. (I predicted Jon Corzine by 3 points).

However, if you wish to predict the winner of any World Series where the Yankees play the Phillies, call me.

If anyone else want to donate to the Hole-in-the-Wall Gang Camps for kids with cancer, go to www.jumpforjoey.org and follow the links.