Monday, June 11, 2012

A Rolling Average

One or two persistent, clueless and rude commenters have been making a fuss about Rasmussen poll results and, in particular, assertions that your humble blog host does not understand what the term 'rolling average' means.  Here, from Wikipedea is a slightly flawed definition.  (The author doesn't know the difference between 'mean' and 'average.')

In statistics, a moving average, also called rolling average, rolling mean or running average, is a type of finite impulse response filter used to analyze a set of datum points by creating a series of averages of different subsets of the full data set.
Given a series of numbers and a fixed subset size, the first element of the moving average is obtained by taking the average of the initial fixed subset of the number series. Then the subset is modified by "shifting forward", that is excluding the first number of the series and including the next number following the original subset in the series. This creates a new subset of numbers, which is averaged. This process is repeated over the entire data series. The plot line connecting all the (fixed) averages is the moving average. A moving average is a set of numbers, each of which is the average of the corresponding subset of a larger set of datum points.

Anyone who has spent any time in the Life industry quickly learns to understand the rolling average when calculating 'persistency.'   But dumbarse commenters wouldn't know anything about that.

Daily tracking results are collected via telephone surveys of 500 likely voters per night and reported on a three-day rolling average basis. To reach those who have abandoned traditional landline telephones, Rasmussen Reports uses an online survey tool to interview randomly selected participants from a demographically diverse panel. The margin of sampling error for the full sample of 1,500 Likely Voters is +/- 3 percentage points with a 95% level of confidence. 



Just for them, here's a hypothetical seven days polling using a three day simple rolling average.  There is nothing in Rasmussen's notes to suggest the use of anything other than a simple rolling average.  There is no suggestion it is a cumulative, weighted or modified rolling average.  However, if anyone can produce evidence to the contrary, I'll stand to be corrected.


Day 1 2 3 4 5 6 7








Obama 46 45 44 45 46 36 42








Romney 44 45 46 42 41 45 41








Three day Rolling Average












Obama

45 45 45 42 41








Romney

45 44 43 43 42








Result

even Obam +1 Obam +2 Rom+1 Rom+1








12 comments:

Anonymous said...

Saved by Wikipedia! You're an expert now! This post had no point did it? You're claim that there was some monstrous shift in voting intentions was nonsense yesterday and nothing in this cut and paste job changes that. Keep trying.

Anonymous said...

This also reinforces how wrong your biased analysis is:

http://fivethirtyeight.blogs.nytimes.com/

Adolf Fiinkensein said...

No wonder you blokes support Obama.

You're just like him. All bullshit and no substance when called upon to deliver.

Anonymous said...

Your substance is a cut and paste from Wikipedia, and actually proves your assertions incorrect. As you've done that to yourself, we don't have to do it for you. Thanks for that.

Adolf Fiinkensein said...

God, you Anonymongs are pathetic.

Who is 'we?' You and all your other anonymongs? Are you too gutless to stand on your own feet or think for yourself?

Still no substance and, of course, there never will be.

Anonymous said...

You've provided the substance from Wikipedia. You claimed there had been some massive shift in voter intentions because the three day rolling average showed a three percent swing. You've subsequently demonstrated what everyone else already knew, ie that that was laughable nonsense. Not as bad as your claim that Rasmussen is the most accurate pollster because its polling 5 months out from an election was the closes to the actual result on election day, but still funny.

Anonymous said...

How many times can Adolf be pwned in a week do you think?

Adolf Fiinkensein said...

Anon @ 3:16

Actually I made no such claim. I simply stated that there had to be a very large swing to shift a three day rolling average by three points. An entirely different thing. You have not rebutted that mathematical fact of life.

Comments closed.

Adolf Fiinkensein said...

To the last troll who can't read:-

Comments were closed because none of you clowns could point to an error. Just 'See! It proves you're wrong' and similar claptrap without saying why..

You'll be pleased to know your bandy legged Jack Ass is three points behind this morning.

You're in good company

Anonymous said...
This comment has been removed by a blog administrator.
Judge Holden said...
This comment has been removed by a blog administrator.
Anonymous said...

Awwwww, poor wee man. Reduced to shutting down discussion of his inadequacies and all round stupidity. When are you going to do another post? This is fun!