|
On April 27 2012 03:23 chuky500 wrote:Show nested quote +On April 25 2012 20:59 sAsImre wrote:
The surveys had a 3% precision where your 0.5% comes from? (samples are always around 1000ish)
First, if you have a 3 point precision you announce candidates like Cheminade at 3% not 0.5%... Because that would mean he could get a score of -2.5% which is absurd. A result of 0.5% means you have a precision of 0.5 points or better. Then the 3% precision is totally made up and unscientific to say the least. Just look at the results announced at 8 o' clock : Le Pen was said to be at 20% while the official results were 18%. That's a 10% mistake and it's not a survey it's the actual counted votes ! If they can't achieve better than 10% accurate results I'm calling BS on the 3point precision surveys.
I don't think you understand what 3% precision means. It's not 3% of each announced score. It's 3% overall. The difference between 20% and 18% is 2%, less than 3%, which is perfectly in line with the error margin they announced.
If they had announced Cheminade at 3%, with the 3% margin of error it would have meant their survey indicated he could get from 0% to 6%, which is not what their survey showed. The survey showed that he should get around 0,5%, with a 3% margin of error, which means from 0% to 3,5%.
|
You're wrong. You're mixing points and %.
If you have a precision of 3% you have to announce de result between 0 and 6% you just can't say 0.5%. A result from 0% to 3.5% would be 1.75% with a precision of 1.75 points.
|
Damn france, you've got a lot of nazis over there...
|
On April 27 2012 04:00 chuky500 wrote:
You're wrong. You're mixing points and %.
If you have a precision of 3% you have to announce de result between 0 and 6% you just can't say 0.5%. A result from 0% to 3.5% would be 1.75% with a precision of 1.75 points.
No, it wouldn't. The reason it was from 0% to 3,5% is that it couldn't go into the negatives. No survey published this year had a 0.5 point precision margin.
|
What about saying his score would be 0.001 % with a 20 point precision ? You can't announce a result more precise than the precision.
|
On April 27 2012 04:29 chuky500 wrote:
What about saying his score would be 0.001 % with a 20 point precision ? You can't announce a result more precise than the precision.
Yes you can. It's a confidence level. You don't have to present ranges.
Edit: Obviously presenting 0.001% scores with a confidence level that makes it irrelevant makes it stupid, but it doesn't make it wrong.
|
Hm, thanks for the thread, I've definitely heard Le Pen somewhere before. Was her father active during the Chirac days?
|
On April 27 2012 04:29 chuky500 wrote:
What about saying his score would be 0.001 % with a 20 point precision ? You can't announce a result more precise than the precision.
Obviously you can, and they did throughout the pre-election season... Where does your knowledge of surveys come from?
|
Why don't you tell me how a difference between 20% and 18% is a 2% mistake ?
|
Guys, official results are official. Everything before is either projection or surveys. Don't get worked up on that.
|
On April 27 2012 04:41 chuky500 wrote:
Why don't you tell me how a difference between 20% and 18% is a 2% mistake ?
What do you get when you subtract 18% from 20%?
|
On April 27 2012 04:41 chuky500 wrote:
Why don't you tell me how a difference between 20% and 18% is a 2% mistake ?
You are incorrect, most surveys when saying 3% precision, mean that when they say X% for a candidate it means that (X-3, X+3) is the interval where the actual value most likely lies.
The confusion you have is caused by the fact that in this case the actual measurement is in %. Analogy when measuring length would be precision 3m meaning interval (X-3m,X+3m). % here is not percentage of the value it is the actual value. If someone said 3% precision when measuring length you would be correct, but in case of measuring popularity it may mean two things and the accepted meaning is mostly not the one you used. For 0.5% the 3% precision means (0,3.5) interval.
|
1st : surveys don't say 3% precision they say 3 point precision.
2nd : A difference between announcing a result of 20% when the actual result is 18% is a 10% mistake not 2%. If you don't believe me calculate it with the raw figures. And the precision wasn't even told here since it was intermediate results.
|
On April 27 2012 04:33 leperphilliac wrote:
Hm, thanks for the thread, I've definitely heard Le Pen somewhere before. Was her father active during the Chirac days?
Father was(is) an extermist (and claiming to be one), ex military (algerie mainly), member of parliament for the first time in 1956. Tried for presidence first in 1974 (got less than 1%), failed to qualify for the first round in 1981. Then between 1981 and 1988 he got invited in to known talk shows and got media time (some say invited by the socialist party to try and fight Chirac's rising popularity). In 1988 he got 14.5%, in 1995 15%. He got international exposure in 2002 when he qualified for 2nd round with 18%. He went down to 10.5% in his 2007 run then retired to give the lead to his daughter.
Aside from his extremist views,
- got convicted for death threats and aggravated assault in the 60s
- got convicted a few time for racists statements and statements minimizing the reality/use of gaz chambers in WWII (the only restrictions to free speach France has as far as I know)
- got convicted for assaulting the mayor of a city he was visiting in 1998 (resulting in a 2 years ban from any election)
...
(his record has abour 40 lines :p)
Also known for a fortune he inherited partly from childless members of the party at their death, for admitting having tortured prisonners during the Algerie war ... A really nice guy.
|
On April 27 2012 05:53 chuky500 wrote:
1st : surveys don't say 3% precision they say 3 point precision.
2nd : A difference between announcing a result of 20% when the actual result is 18% is a 10% mistake not 2%. If you don't believe me calculate it with the raw figures. And the precision wasn't even told here since it was intermediate results.
Jesus, talk about refusing to take a step back and admit your mistake. Look, here's what you stated in your original post:
On April 25 2012 02:01 chuky500 wrote:
Why all year long were surveys announced with a 0.5 point precision
No survey was published with a margin of error of 0.5 percentage point. None.
The "2%" and "3%" that were mentioned as margins of errors are "shortcuts" to mean "2 percentage points" and "3 percentage points". It doesn't mean "2% of 20%". The difference between 18% and 20% is two percentage points. With a margin of error of 3 percentage points, that was completely fine.
For Cheminade, the surveys put him at 0.5% with a margin of error of 3 percentage points. It therefore meant that the interval was 0%-3,5% because you can't get a negative number of votes in an election.
|
On April 27 2012 06:20 Oshuy wrote:
for admitting having tortured prisonners during the Algerie war ... A really nice guy.
I'm pretty sure he won every trial against people who accused him of this, so I don't think he has admitted hasn't he ?
That being said, from what I know of his military affectation during the war, er... you see what I mean.
|
On April 25 2012 22:27 kwizach wrote:Show nested quote +On April 24 2012 05:06 Wegandi wrote:On April 24 2012 04:33 SiroKO wrote:On April 24 2012 02:56 Kukaracha wrote:
You didn't understand what I said. I said that to stop immigration, and in particular illegal immigration, there is no other short term solution than violence. This is why people in Calas, or if you want to be picky about it, Saint-Denis, have a hard life, because it's the people's barrier to foreigners. To decrease drastically illegal immigration, you need to drastically raise violence.
This is NOT what I want, but this is how it works. If you refuse citizenship to people who were born in this country, then they become sub-citizens. It's a form of violence. It's all done to discourage migrations towards our territory. And foreigners can only legally stay in France for a short period of time unless they obtain a visa. What happens when it expires? They have to be physically expelled from the country. Reducing the number of people allowed to become French would require to send back "home" thousands and thousands of people.
So, yes, any of those problems quoted above end up with violence, because violence is the easiest way to force or prevent migrations.
And yes, it's important in Le Pen's campaign, where you often hear the phrase "la France aux français", which translates to "France belongs to the French", implying that the country belongs to white people who have lived here for an arbitrary amount of generations. They are close to the Vlaams Belang too. I don't see how you can deny that. Ye sure, violence is at the origins of each country on the planet. It's through violence that France unified itself, and defended its borders and sovereignty through history. Borders are actually what define countries, and once people stop fighting for their owns, they get crossed, and the natives get either annihilated, conquered or colonized. Nothing wrong with immigration, the problem is the Welfare State which subdizies and encourages the poor of the world rushing into the country, which results in a heavy drain of the countries prosperity and wealth. So, then, what's the answer? Get rid of the Welfare System. The last thing you want is a Welfare State and a Police State. As long as that incentive is there to come into your country no matter what (surely better to be in a French prison with food and shelter than languishing in a third world hell hole or more than likely on the dole without need of work and toil), then if you want to stop the flood of people it requires massive violence and Police State. Not desirable. Immigration in sustainable numbers (e.g. without a Welfare State) is highly desirable and wanted. Open borders + Welfare State = a disaster. Welfare State + Police State = disaster. Open borders + No Welfare State = healthy & desirable. Here's a study which completely debunks that claim: immigration actually has an incredibly positive net impact on the state's finances in France: http://www.courrierinternational.com/article/2010/12/02/les-tres-bons-comptes-de-l-immigration
Does an English version exist?
|
The 3 point error was for regular surveys. The 20-18 mistake was based on official results that were already known in most places. That's why it's crazy to have such a big error. That's why I say they announced false results on purpose to make the results look more obvious.
The margin of error means the "amount of things you don't know". 3% of the 36 million counted votes represent 1.1 million votes. If you announce a result within a 3 point margin it means for each candidate you have a window of 2.2 million votes you don't know. 0.5 represents 180 000 votes. When you announce 0.5% with a 3 point precision it means you're confident enough to say there'll be exactly 180 000 votes within a 2.2 million range. And then what stops you from announcing 18 votes within that range ? The point is you don't know enough to tell what you think you know. If you don't know 2.2 millions don't tell 180 000, tell the safest figure, the one in between, tell 1.1 million with a 1.1 million precision.
But well the 3 point precision doesn't actually represent anything since the method used isn't scientific at all (quotas method). It's just a figure they claim to look serious. 2 weeks ago journalists said the raw figures of surveys on the radio for Le Pen, they said only 2% people actually said they would vote for her. This means on the 1000 people asked, that's only 20 people that confessed to vote for her. Out of these 20 people they managed to make highly scientific calculations and say she'd have about 16%. Believe the 3 point precision if you want, I don't.
|
On April 27 2012 07:33 Madkipz wrote:Show nested quote +On April 25 2012 22:27 kwizach wrote:On April 24 2012 05:06 Wegandi wrote:On April 24 2012 04:33 SiroKO wrote:On April 24 2012 02:56 Kukaracha wrote:
You didn't understand what I said. I said that to stop immigration, and in particular illegal immigration, there is no other short term solution than violence. This is why people in Calas, or if you want to be picky about it, Saint-Denis, have a hard life, because it's the people's barrier to foreigners. To decrease drastically illegal immigration, you need to drastically raise violence.
This is NOT what I want, but this is how it works. If you refuse citizenship to people who were born in this country, then they become sub-citizens. It's a form of violence. It's all done to discourage migrations towards our territory. And foreigners can only legally stay in France for a short period of time unless they obtain a visa. What happens when it expires? They have to be physically expelled from the country. Reducing the number of people allowed to become French would require to send back "home" thousands and thousands of people.
So, yes, any of those problems quoted above end up with violence, because violence is the easiest way to force or prevent migrations.
And yes, it's important in Le Pen's campaign, where you often hear the phrase "la France aux français", which translates to "France belongs to the French", implying that the country belongs to white people who have lived here for an arbitrary amount of generations. They are close to the Vlaams Belang too. I don't see how you can deny that. Ye sure, violence is at the origins of each country on the planet. It's through violence that France unified itself, and defended its borders and sovereignty through history. Borders are actually what define countries, and once people stop fighting for their owns, they get crossed, and the natives get either annihilated, conquered or colonized. Nothing wrong with immigration, the problem is the Welfare State which subdizies and encourages the poor of the world rushing into the country, which results in a heavy drain of the countries prosperity and wealth. So, then, what's the answer? Get rid of the Welfare System. The last thing you want is a Welfare State and a Police State. As long as that incentive is there to come into your country no matter what (surely better to be in a French prison with food and shelter than languishing in a third world hell hole or more than likely on the dole without need of work and toil), then if you want to stop the flood of people it requires massive violence and Police State. Not desirable. Immigration in sustainable numbers (e.g. without a Welfare State) is highly desirable and wanted. Open borders + Welfare State = a disaster. Welfare State + Police State = disaster. Open borders + No Welfare State = healthy & desirable. Here's a study which completely debunks that claim: immigration actually has an incredibly positive net impact on the state's finances in France: http://www.courrierinternational.com/article/2010/12/02/les-tres-bons-comptes-de-l-immigration Does an English version exist?
I haven't come across one so far. Basically it looks at the net impact of immigration on the French welfare system, and immigrants put in much more money than they take out.
|
On April 27 2012 08:08 chuky500 wrote:
The 3 point error was for regular surveys. The 20-18 mistake was based on official results that were already known in most places. That's why it's crazy to have such a big error. That's why I say they announced false results on purpose to make the results look more obvious.
The margin of error means the "amount of things you don't know". 3% of the 36 million counted votes represent 1.1 million votes. If you announce a result within a 3 point margin it means for each candidate you have a window of 2.2 million votes you don't know. 0.5 represents 180 000 votes. When you announce 0.5% with a 3 point precision it means you're confident enough to say there'll be exactly 180 000 votes within a 2.2 million range. And then what stops you from announcing 18 votes within that range ? The point is you don't know enough to tell what you think you know. If you don't know 2.2 millions don't tell 180 000, tell the safest figure, the one in between, tell 1.1 million with a 1.1 million precision.
But well the 3 point precision doesn't actually represent anything since the method used isn't scientific at all (quotas method). It's just a figure they claim to look serious. 2 weeks ago journalists said the raw figures of surveys on the radio for Le Pen, they said only 2% people actually said they would vote for her. This means on the 1000 people asked, that's only 20 people that confessed to vote for her. Out of these 20 people they managed to make highly scientific calculations and say she'd have about 16%. Believe the 3 point precision if you want, I don't.
I don't really know what to add to what I already said - your comments show that you don't seem to understand how surveys work and certainly don't understand what the margin of error is.
|
|
|
|
|
|
EPT
