03 September 2009

Two wrongs… and you get a news story

Both VOCM and the Telegram incorrectly reported the latest poll results from government sponsored polls on Thursday.

VOCM reported that the “latest numbers from Corporate Research Associates show Danny Williams and the PC's gaining strength, despite being almost halfway through their second term.”

The Telly reported that the “province’s decided voters are showing more support for the Progressive Conservative government…”.  The story is on page three of the Thursday edition but isn’t available online.

As a famous politician likes to say,  nothing could be further from the truth.

Both reported the numbers given in response to a question on which political party respondents would pick if an election were held tomorrow. 

The problem comes from the fact that the provincial government’s pollster – Corporate Research Associates – gives its results as a percentage of decided voters, not as a percentage of all people whose answers are included in the poll data.  The change in the number of undecideds can affect the relative share of decideds any one party has.

The corrected figures are shown in the chart below based on the results reported by Corporate Research Associates. [text continues below illustration]

cra august 2009

Support for the Conservatives (shown by the blue line) declined steadily from November 2007 until November 2008, going from 67% of respondents to 56%.  Support rebounded to 60% and has polled consistently at that level through the last three quarters.

In itself, that consistency is odd since the reported Conservative party support in the province has moved only by small fractions of one percent over the past nine months.  This steadiness supposedly comes at a time of economic downturn and the closure of the Grand Falls-Windsor paper mill. 

In the most recent poll, CRA results would show an increase in a support despite more political problems across the province in the quarter.  That result goes against what one would expect to see base don other factors.

The orange line is the PC party vote in the last provincial general election presented on the same basis – percentage of all eligible voters-  as the corrected CRA poll results.  This indicates the discrepancy between CRA’s figures and the only other source of poll data for the period in question.

But look at that blue line again. 

Not only is actual support in the poll sometimes as much as 17 percentage points  lower than the figure reported by CRA, the overall trending is decidedly different.

CRA’s polling shows support at 78% in November 2008 followed by a decline to the lowest point - 71% in February 2009 – followed by a dramatic increase in the last quarter to roughly where the support was a year ago.

Actual support showed no movement at all.  The variation has come solely as a result of CRA’s dubious reporting method.

The actual trend was down, followed by an absolute flat line for the past nine months.

-srbp-

3 comments:

Anonymous said...

during the last nine months, name a leader in North America that wouldn't be jumping for joy after maintaining a "flat line"?

Anonymous said...

LOL, Ed that is lame, very lame.
You can't be serious in your analysis. the numbers speak for themselves. The Man and the Party (Gov't) are popular and liked. the Libs and Dippers aren't.

End of story.

Edward G. Hollett said...

But of course, 2000 and 2020 your comments miss the point of the post.

First, that isn't what CRA reported, 2000.

Second, the very existence of a flat line measured to within fractions of a percentage point over such a long period of time is so bizarre as to warrant a round of headscratching.

Most researchers would wonder what was up with that.

Heck most people would wonder how it is possible for public opinion to stay that steady despite all that has gone on in the province over the last year.

A satisfaction rate running consistently between 85% and 90% at a time when 12 thousand more people were out of work (the May employment figures), industries were shut down, the fishery is in the slings...

It sounds pretty much impossible, doesn't it?

Most reasonable people would conclude it is, I should think.

And that of course if the bit 2020 missed as well.

The poll on which 2020 rests his or her entire case is suspect.