Another Biased Poll

You all know my love for Polls.  You all know that I love to check for biased questioning and biased methods.  Well, It has been done again.  Regardless of whether you feel that polling is news or not, the newspapers are treating it as such, so we need to address it.

Dan Jones and Associates, the Deseret News, and KSL-TV have conducted another poll of Utahns to discover what they think about the possibility of a tax cut.  I was amazed to see the results.  Supposedly 63% of Utahns favor spending more on State “needs.”

That seemed just way too high for my likings.  So, I go to the heart of the survey.  Unfortunately, the news article on the subject presents us with only one question.  It reads:

Utah is currently running large tax surpluses.  Between the current fiscal year and the next fiscal year, budget experts say an extra $700 million will be coming in to the state.  Some legislators are talking about tax cuts to go along with the tax reform.

In general, do you favor cutting taxes or using the extra money for state needs like education funding, road construction and/or health care for the needy?

Warning lights should be going off for the honest survey statistician.  About half way through the first paragraph of that one question (yes, there was only one question there), the survey taker fell asleep.  So, when it finally comes time to answer the question, all the respondent thinks of is care for the needy.  So, of course, I strongly favor caring for the needy.

There are however, other real concerns with the survey. This is to be a study that reflects the opinion of roughly 2 million Utahns.  For a body of people that big, the minimum survey participants should be 2,000 people.  So, how many people participated?  That’s right a gigantic 413.  Not even a quarter of the recommended minimum for a statistically valid statistic.

This sample size leads to the next revealing factor in this survey.  It has a margin of error of +/- 5.0 percent.  That is statistically acceptable, and an okay margin of error.  However, we must note that +/- 5.0 percent is the minimum standard for a publishable survey.  The closer to 0.0 percent the margin of error is the better the survey.

Well, the article argues that 63% are in favor of increase government spending.  But the 63% is a composite of 2 numbers.  thus, when you calculate the +/- 5.0 you need to double it.  Thus it is really +/- 10.0 percent.  That means the real number is possibly 53% and the highest possibility is 73% favor increased spending.

That tells us nothing!!!!

Sure it still looks like more Utahns favor increased spending.  But you need to take into account the biasing question.  I don’t believe it.  I just can’t believe that 63% (or even 53%) of Utahns don’t want a tax cut.

So, in an attempt to sound like a broken record, Where’s my tax cut??????


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: