Home
Publications
Search
Register
Log inThe challenge of exit polls
5 posters
Page 1 of 1
The challenge of exit polls
by confuzzled dude Mon May 12, 2014 12:37 pm
Most of the exit polls broadcast on May 6, 2004, had given the NDA 248 or more seats in the 543-seat house, and the Congress no more than 190. Eventually, the UPA won 219 seats, and the NDA just 187.
The closest prediction had been that of AC Nielson, who said the NDA would get no fewer than 230 seats and the UPA no more than 205.
Five years later, all exit pollsters gave the UPA the edge over the NDA — but only just. Eventually, the difference between the seats won by the two major political formations was a whopping 103 — the UPA won 262 and the NDA 159.
http://www.abplive.in/india/2014/05/12/article311131.ece/The-challenge-of-exit-polls
The closest prediction had been that of AC Nielson, who said the NDA would get no fewer than 230 seats and the UPA no more than 205.
Five years later, all exit pollsters gave the UPA the edge over the NDA — but only just. Eventually, the difference between the seats won by the two major political formations was a whopping 103 — the UPA won 262 and the NDA 159.
http://www.abplive.in/india/2014/05/12/article311131.ece/The-challenge-of-exit-polls
confuzzled dude- Posts : 10205
Join date : 2011-05-08
Re: The challenge of exit polls
by truthbetold Mon May 12, 2014 9:19 pm
CD
The Indian pollsters are not at the american level. But India is also a complex nation to poll. It is difficult to define a sampling plan that is reflective of diverse indian electorate. The western models did not do well in indian fractured society.
A percentage of voters are individual and independent. { no idea on the exact size of this block, may 20% may be 40%). Rest of the population is for voting purposes, a collection of large groups of different interests.
They are getting direction of result and some level of success with final number. They did well with 2013 state elections. They could not find a way to cope with AAP's growth in Delhi.
They are getting better. Wait for 50 more years to perfect prediction.
The Indian pollsters are not at the american level. But India is also a complex nation to poll. It is difficult to define a sampling plan that is reflective of diverse indian electorate. The western models did not do well in indian fractured society.
A percentage of voters are individual and independent. { no idea on the exact size of this block, may 20% may be 40%). Rest of the population is for voting purposes, a collection of large groups of different interests.
They are getting direction of result and some level of success with final number. They did well with 2013 state elections. They could not find a way to cope with AAP's growth in Delhi.
They are getting better. Wait for 50 more years to perfect prediction.
truthbetold- Posts : 6799
Join date : 2011-06-07
Re: The challenge of exit polls
by confuzzled dude Tue May 13, 2014 12:20 pm
"There's a multitude of reasons why polling in India is a difficult task, some of which are simple things like scale (India is really big and diverse) and technology (many people don't have phones or Internet access still). As Jonah Force Hill wrote in the Diplomat in February, few polling companies actually have the resources to do so many face-to-face interviews on a national scale and thus are forced to extrapolate data for their forecasts.
The practical difficulties feed into another issue – a widespread belief, perhaps justified, that political surveys in India are biased. Almost all polls are conducted by Indian media companies, many of which are thought to have an implicit or even explicit bias: One TV news sting operation from earlier this year reportedly found that 11 polling companies were willing to alter their results for a fee."
http://www.washingtonpost.com/blogs/worldviews/wp/2014/05/12/why-indian-exit-polls-arent-trusted/
The practical difficulties feed into another issue – a widespread belief, perhaps justified, that political surveys in India are biased. Almost all polls are conducted by Indian media companies, many of which are thought to have an implicit or even explicit bias: One TV news sting operation from earlier this year reportedly found that 11 polling companies were willing to alter their results for a fee."
http://www.washingtonpost.com/blogs/worldviews/wp/2014/05/12/why-indian-exit-polls-arent-trusted/
confuzzled dude- Posts : 10205
Join date : 2011-05-08
Re: The challenge of exit polls
by Marathadi-Saamiyaar Tue May 13, 2014 12:39 pm
confuzzled dude wrote:"There's a multitude of reasons why polling in India is a difficult task, some of which are simple things like scale (India is really big and diverse) and technology (many people don't have phones or Internet access still). As Jonah Force Hill wrote in the Diplomat in February, few polling companies actually have the resources to do so many face-to-face interviews on a national scale and thus are forced to extrapolate data for their forecasts.
The practical difficulties feed into another issue – a widespread belief, perhaps justified, that political surveys in India are biased. Almost all polls are conducted by Indian media companies, many of which are thought to have an implicit or even explicit bias: One TV news sting operation from earlier this year reportedly found that 11 polling companies were willing to alter their results for a fee."
http://www.washingtonpost.com/blogs/worldviews/wp/2014/05/12/why-indian-exit-polls-arent-trusted/
it is funny how the Cong(i) and the family loyalists are twisting, reasoning, and hoping for a miracle....
Marathadi-Saamiyaar- Posts : 17675
Join date : 2011-04-30
Age : 110
Re: The challenge of exit polls
by indophile Tue May 13, 2014 12:51 pm
All are saying the same thing - NDA victory. They only differ in their forecasts of that victory margin.
http://www.thehindu.com/news/national/exit-polls-sweeten-countdown-for-nda/article6002282.ece?ref=relatedNews
http://www.thehindu.com/news/national/exit-polls-sweeten-countdown-for-nda/article6002282.ece?ref=relatedNews
indophile- Posts : 4338
Join date : 2011-04-29
Location : Glenn Dale, MD
Re: The challenge of exit polls
by confuzzled dude Tue May 13, 2014 12:55 pm
Right but there is a huge difference between winning 225 seats vs 300.indophile wrote:All are saying the same thing - NDA victory. They only differ in their forecasts of that victory margin.
http://www.thehindu.com/news/national/exit-polls-sweeten-countdown-for-nda/article6002282.ece?ref=relatedNews
confuzzled dude- Posts : 10205
Join date : 2011-05-08
Re: The challenge of exit polls
by indophile Tue May 13, 2014 1:04 pm
The range that's shown at the Hindu link I posted is 249-289 for NDA. That's a 40 point spread, not 75.
Usually in a wave, as is predicted right now, the forecasts will be proved conservative after-the-fact. So 300 for NDA is not implausible. Sure, they may not be able to win 360 (for 2/3 majority); that could be a stretch.
Usually in a wave, as is predicted right now, the forecasts will be proved conservative after-the-fact. So 300 for NDA is not implausible. Sure, they may not be able to win 360 (for 2/3 majority); that could be a stretch.
indophile- Posts : 4338
Join date : 2011-04-29
Location : Glenn Dale, MD
Re: The challenge of exit polls
by confuzzled dude Tue May 13, 2014 1:10 pm
I was not referring to the Hindu article there are some exit polls that predicted 340.indophile wrote:The range that's shown at the Hindu link I posted is 249-289 for NDA. That's a 40 point spread, not 75.
Usually in a wave, as is predicted right now, the forecasts will be proved conservative after-the-fact. So 300 for NDA is not implausible. Sure, they may not be able to win 360 (for 2/3 majority); that could be a stretch.
confuzzled dude- Posts : 10205
Join date : 2011-05-08
Re: The challenge of exit polls
by truthbetold Tue May 13, 2014 3:52 pm
Cd
statistical prediction is based on empirical models. they can be misused by applying it in the wrong location i.e. Delhi urban model would fail in rural bihar. or the could fail to include changing factors such as raising popularity of aap in Delhi elections. Exit polls are weak tools to predict # of seats but are excellent predictor of
direction.2013 state election were well predicted.
in any case, it is usually the losing side that complains about opinion polls and exit polls.
the most dangerous problem with polls is the manipulation of a poll result to meet paid objective. that will kill public confidence.
statistical prediction is based on empirical models. they can be misused by applying it in the wrong location i.e. Delhi urban model would fail in rural bihar. or the could fail to include changing factors such as raising popularity of aap in Delhi elections. Exit polls are weak tools to predict # of seats but are excellent predictor of
direction.2013 state election were well predicted.
in any case, it is usually the losing side that complains about opinion polls and exit polls.
the most dangerous problem with polls is the manipulation of a poll result to meet paid objective. that will kill public confidence.
truthbetold- Posts : 6799
Join date : 2011-06-07
Re: The challenge of exit polls
by rawemotions Fri May 16, 2014 1:27 am
it appears that the only exit poll which was truly right was the Chanakya Poll which predicted 340 +/- 14confuzzled dude wrote:I was not referring to the Hindu article there are some exit polls that predicted 340.indophile wrote:The range that's shown at the Hindu link I posted is 249-289 for NDA. That's a 40 point spread, not 75.
Usually in a wave, as is predicted right now, the forecasts will be proved conservative after-the-fact. So 300 for NDA is not implausible. Sure, they may not be able to win 360 (for 2/3 majority); that could be a stretch.
http://www.todayschanakya.com/loksabha_result_2014.html
Bang on target on all three parameters, (Congress totals, NDA totals and BJP totals) and also on the totals in most states. Amazing!
rawemotions- Posts : 1690
Join date : 2011-05-03
Re: The challenge of exit polls
by confuzzled dude Fri May 16, 2014 1:37 am
Yup That's what I meant by 340. I read that it was bang on with AAP results in Delhi but I discounted it given the small area. man was I wrong.rawemotions wrote:it appears that the only exit poll which was truly right was the Chanakya Poll which predicted 340 +/- 14confuzzled dude wrote:I was not referring to the Hindu article there are some exit polls that predicted 340.indophile wrote:The range that's shown at the Hindu link I posted is 249-289 for NDA. That's a 40 point spread, not 75.
Usually in a wave, as is predicted right now, the forecasts will be proved conservative after-the-fact. So 300 for NDA is not implausible. Sure, they may not be able to win 360 (for 2/3 majority); that could be a stretch.
http://www.todayschanakya.com/loksabha_result_2014.html
Bang on target on all three parameters, (Congress totals, NDA totals and BJP totals) and also on the totals in most states. Amazing!
confuzzled dude- Posts : 10205
Join date : 2011-05-08
Re: The challenge of exit polls
by truthbetold Fri May 16, 2014 3:51 am
Exit polls were right. They clearly identified winners. They have problems with exact seats. Exit polls are well equipped to catch the magnitude of a wave.
truthbetold- Posts : 6799
Join date : 2011-06-07
Re: The challenge of exit polls
by truthbetold Fri May 16, 2014 5:00 am
That should read exit polls are not well equipped ......truthbetold wrote:Exit polls were right. They clearly identified winners. They have problems with exact seats. Exit polls are well equipped to catch the magnitude of a wave.
truthbetold- Posts : 6799
Join date : 2011-06-07
Similar topicsPage 1 of 1
Permissions in this forum:
You cannot reply to topics in this forum|
|
|