|
Post by kamalet on Jan 15, 2013 8:30:29 GMT 3
Here interesting take on the Polls:
Opinion researchers did not doctor data, but sampling raises eyebrows
Politicians and commentators have been dismissing the latest Infotrak polls as “doctored”, without evidence. They simply zeroed in on the company owners and “financiers” of polls.
Mine however, is to dissect the data. First, the sample size was not proportional to the voter registration figures of Rift Valley Province.
The sample size is important in making inferences about a population. When the sample size is not proportional to population, in this case, voter registration, data manipulation sets in.
Voter registration figures used to determine the sample size for Rift Valley was 3.1 million instead of 3.37 million. The effect was that Rift Valley ended with 320 respondents instead of 350 from the national sample of 1500.
Thus 30 respondents were transferred to other province(s). Nairobi was the biggest beneficiary, with 219 instead of 187 respondents after the voter registration was raised from 1.78 million to 2.1 million.
Second, the sample was not well distributed. In Rift Valley the opinion poll was conducted in counties neighbouring Western and Nyanza provinces. Out of the six sampled only Nakuru does not have a border with either of the provinces.
In Eastern, two of the three Ukambani counties were sampled and only one of the three Mt Kenya counties was sampled. In Coast, Lamu, Tana River and Kwale counties which have majority of MPs leaning towards Jubilee were not sampled; instead the sampling was carried out in Mombasa, Kilifi and Taita Taveta which have majority of MPs leaning to CORD.
When observing this distribution of the sampled counties you will notice that 12 counties (50% of the sample) occupy less than 20% of Kenya’s geographic land mass and all in areas west of Kenya. Was this an omission or deliberate?
Infotrak did not manipulate collected data but manipulated the manner in which the sample was allocated and distributed.
PETER NJENGA. Mombasa
|
|
|
Post by mwalimumkuu on Jan 15, 2013 9:09:09 GMT 3
Kamale,
Njenga is hitting at exactly what we have been been saying here, that there was a predetermibed outcome then the whoke thing was worked backwards. In all the interviews the not-so-gracious lady Ambitho has taken so far, she has totally failed or refused to address herself to these issues. Bure kabisa.
|
|
|
Post by mank on Jan 15, 2013 18:21:25 GMT 3
Here interesting take on the Polls: ... Second, the sample was not well distributed. In Rift Valley the opinion poll was conducted in counties neighbouring Western and Nyanza provinces. Out of the six sampled only Nakuru does not have a border with either of the provinces. Such is outrightly unethical of the authors! That's some cherry peaking indeed! From this pattern I can even guess what parts of the single non-Ukambani county was sampled. This is embarrassing! What titles do the authors put against their names on their report? Good job, good question!
|
|
|
Post by raiswakesho on Jan 15, 2013 20:30:57 GMT 3
Just curious, what if another pollster predicts a win for CORD? Will we then seek a court injunction to stop them from publishing any more polls until after March 4TH? I think some moderates from the other side would have been ok with a less than 50% lead for RAO and team CORD, it's the 51% thing that's killing them! Maybe this thing will tighten up as we get closer to the D- Day so let's not lose sleep over Ambitho's numbers!
|
|
|
Post by mank on Jan 15, 2013 22:43:23 GMT 3
Just curious, what if another pollster predicts a win for CORD? Will we then seek a court injunction to stop them from publishing any more polls until after March 4TH? I think some moderates from the other side would have been ok with a less than 50% lead for RAO and team CORD, it's the 51% thing that's killing them! Maybe this thing will tighten up as we get closer to the D- Day so let's not lose sleep over Ambitho's numbers! Speaking for myself: I have no problem with studies showing CORD winning, if that's indeed what is happening. However intellectual corruption and thuggery must be exposed. In this case people seem to be committed to advocacy while pretending to be fact finders. If another pollster predicts a win for CORD, that pollster should be judged on its own merit - does it measure up to the science it alleges to be founded on? That's all ... as far as I am concerned Raila himself can carry out the research. All I wish for is honesty to the science. Let's speak the truth, and let the truth be evident in the way we speak it. That's all!
|
|
|
Post by reporter911 on Jan 16, 2013 9:21:30 GMT 3
Ivyu tu.. "CORD" wave is unstoppable.. ask Mudavadi, who is begging for a free ride to statehouse,
|
|
|
Post by kamalet on Jan 16, 2013 9:42:42 GMT 3
Just curious, what if another pollster predicts a win for CORD? Will we then seek a court injunction to stop them from publishing any more polls until after March 4TH? I think some moderates from the other side would have been ok with a less than 50% lead for RAO and team CORD, it's the 51% thing that's killing them! Maybe this thing will tighten up as we get closer to the D- Day so let's not lose sleep over Ambitho's numbers! Wa Kesho If Ipsos came with a poll that had Jubilee leading I would expect people to ask similar questions that have been asked of Ambitho. It is the same story if Ipsos were to have their poll similar to that of Ambitho with CORD leading we will still ask the same questions! What surprises me is that the CORD supporters are not asking the questions I am suggesting they should ask for the danger with not doing so and believing the polls is that people could actually not turn up to vote on the basis the election is already won!
|
|
|
Post by reporter911 on Jan 16, 2013 9:53:00 GMT 3
Just curious, what if another pollster predicts a win for CORD? Will we then seek a court injunction to stop them from publishing any more polls until after March 4TH? I think some moderates from the other side would have been ok with a less than 50% lead for RAO and team CORD, it's the 51% thing that's killing them! Maybe this thing will tighten up as we get closer to the D- Day so let's not lose sleep over Ambitho's numbers! Wa Kesho If Ipsos came with a poll that had Jubilee leading I would expect people to ask similar questions that have been asked of Ambitho. It is the same story if Ipsos were to have their poll similar to that of Ambitho with CORD leading we will still ask the same questions! What surprises me is that the CORD supporters are not asking the questions I am suggesting they should ask for the danger with not doing so and believing the polls is that people could actually not turn up to vote on the basis the election is already won! Nonsense, take your desperation elsewhere, the polls are head on.. "CORD" is now at 59% the Tsunami wave is ashore.. what happened to the votes from Mudavadi? lets remove them from Uhuruto and now they are down to 29% that is a combined central province Block votes and few votes from Rift valley for poor Ruto.. Jubilee is still going down.. Desperation is a bad disease, it can make ones tongue very loose with nonsensical propaganda:)
|
|
|
Post by bkichwa on Jan 22, 2013 13:26:53 GMT 3
Here's a good example why our local polls can't be relied on to give an accurate picture of the country's voting preferences. Infotrak and Ipsos Synovate simultaneously conducted polls last week between the 17th and 20th. Both polls were sponsored by Royal Media Services. Perhaps also worth noting is that Royal Media Services owner S.K. Macharia is a publicly declared Raila supporter. See in article below the dumbfounding, glaring differences in these poll results (see comparative poll results table after the story). www.kenyan-post.com/2013/01/raila-odinga-will-beat-uhuru-kenyatta_22.html
|
|
|
Post by kamalet on Jan 22, 2013 13:41:17 GMT 3
Here's a good example why our local polls can't be relied on to give an accurate picture of the country's voting preferences. Infotrak and Ipsos Synovate simultaneously conducted polls last week between the 17th and 20th. Both polls were sponsored by Royal Media Services. Perhaps also worth noting is that Royal Media Services owner S.K. Macharia is a publicly declared Raila supporter. See in article below the dumbfounding, glaring differences in these poll results (see comparative poll results table after the story). www.kenyan-post.com/2013/01/raila-odinga-will-beat-uhuru-kenyatta_22.htmlYou make a valid point. What surprised me was the lack of enthusiasm by Hon. Mbandi when the poll figures were read and he did not put up much of a defence! The difference in the numbers showed the problem you highlight as a 10% difference does not make sense at all. Even worse was the reduction of Jakom's lead from 51% to 48% by Infotrack which begs the question if the moderation of the result is driven by the sponsors?
|
|
|
Post by gemagema on Jan 22, 2013 20:45:56 GMT 3
The ratio is the same....hence there is not much difference between these two pollsters Ofcourse Jubilee-ians want to make sure that their tribal Maths are also manifested in the Poll results...hehehe
|
|