G'morning Bob, 

 MM> Not unless you want to... I just want to see some proper
 MM> poll- dancing ...
 BK>  I would ask what poll-dancing has to do with our discussion of
 BK>  elections, but I suspect I don't want to know.

The current poll-dance is created by sloppy sampling - one party 
ahead by 8 percent in the morning poll,  and behind by 9 percent 
in the afternoon.   Of course, both polls claim the maximum error 
of totally random samples of 1000 people who all responded - you 
know, 2*SQRT(50*50/(1000-1)) or, as they publish it, "plus or 
minus 3.163859986"...

When you ring up and ask for their response rates,  you discover 
they selected 2000 people to get their 1000 answers - making the 
maximum error 10 times larger,  and the apparent swing just an 
artifact of their sloppy sampling.

Bah humbug !

Quackery !

Give me proper polls whose trails I can trust....

:-)))
 
___ MultiMail/MS-DOS v0.45

--- Maximus/2 3.01