Is statistical probablity accurate in Thailand?

[thailiketoo]

Of course it is.

Statistics defined. A fact or piece of data from a study of a large quantity of numerical data.

Statistical Probability. How likely something is to happen. Many events can't be predicted with total certainty. The best we can say is how likely they are to happen, using the idea of probability. Example: toss a coin 100 times, how many Heads will come up?

Probability says that heads have a ½ chance, so we would expect 50 Heads.

But when you actually try it out you might get 48 heads, or 55 heads ... or anything really, but in most cases it will be a number near 50.

You will get this result in Australia or Thailand. Unless there is bias.

Bias could effect statistics in a number of ways like,
The scales read "1 kg" when there is nothing on them
You always measure your height wearing shoes with thick soles.
A stopwatch that takes half a second to stop when clicked.

There is nothing inherently wrong with Statistics. Statistics are not always made up. Statistics are not always fudged. Statistics are a fact. Statistics are formulas and methods. There is nothing untrue about statistics. However there may be a bias in the interpretation of those numbers.

"Lies, damned lies, and statistics" The term was popularised in the United States by Mark Twain (among others), who attributed it to the 19th-century British Prime Minister Benjamin Disraeli (1804–1881): "There are three kinds of lies: lies, damned lies, and statistics." However, the phrase is not found in any of Disraeli's works and the earliest known appearances were years after his death. Other coiners have therefore been proposed, and the phrase is often attributed to Twain himself.

Sorry but Twain or Disraeli was in error. They did not know the meaning of the word Statistics.

The refrain we frequently hear on TV is, "you can't trust Thai statistics." Then when that is disproved we read, "you can't trust statistics."

Well, I hope I have dispelled the notion that there is something inherently untrue in statistics.

How many Thais need to be in a room to have two with the same birthday?

How many Brits need to be in a room to have two with the same birthday?

See? No difference. Statistics works in Thailand the same as it does in Britain.

[Thakkar]

Bias satisfies. Stats (or facts) disturb the blissful ignorance that satisfies, unless it confirms the bias, then stats are great.

T

[h90]

I made a university course in statistics. The teacher wasn't a regular professor. He was an outsider who had only this course every 2 years and only 10-12 people in the class.

He wasn't a particular good teacher, but he brought some deeper understanding. He mostly worked for governments and he told there is always an unofficial statistic and one with bent results for the public.

And it wasn't empty blabla because he showed the actual statistics and the bent one and told what expectations of the future he must mix into it to get the official results. (Like expecting a decrease in population on the country side and an increase of service jobs in big cities, to get the result that the traffic on the streets won't increase (saves money on street building)).

His big joke was how many children will be in 20 years, so school building can be planed. Government wanted lower numbers. The only assumption that would cause the lower numbers would be having 50% of the men castrated or 50% of the women sterilized. 20 years later his unofficial statistic was spot on.

Point is: These days statistics are often just a justification for some political decisions and the numbers are made up so it fits the results.

[thailiketoo]

I made a university course in statistics. The teacher wasn't a regular professor. He was an outsider who had only this course every 2 years and only 10-12 people in the class.

He wasn't a particular good teacher, but he brought some deeper understanding. He mostly worked for governments and he told there is always an unofficial statistic and one with bent results for the public.

And it wasn't empty blabla because he showed the actual statistics and the bent one and told what expectations of the future he must mix into it to get the official results. (Like expecting a decrease in population on the country side and an increase of service jobs in big cities, to get the result that the traffic on the streets won't increase (saves money on street building)).

His big joke was how many children will be in 20 years, so school building can be planed. Government wanted lower numbers. The only assumption that would cause the lower numbers would be having 50% of the men castrated or 50% of the women sterilized. 20 years later his unofficial statistic was spot on.

Point is: These days statistics are often just a justification for some political decisions and the numbers are made up so it fits the results.

That was my point that you missed or grabbed the fallacy. Your statistical method was accurate but was effected by bias in recording or reporting. There is nothing wrong with statistics. These days statistics are always true. There is bias in the recording or reporting so you are using the wrong word. You didn't make a university course in statistics.

University courses about statistics are mathematical you would have regaled us of learning about the standard deviation (http://www.mathsisfun.com/data/standard-deviation-formulas.html).

For example, "

STAT111 - Introductory Statistics ( Course Syllabus - 2010B)

Introduction to concepts in probability. Basic statistical inference procedures of estimation, confidence intervals and hypothesis testing directed towards applications in science and medicine. The use of the JMP statistical package."

Edited June 26, 2014 by thailiketoo

[MRYANG]

Statistics tells us that a man can shower for 1 minute in cold water and 1 minute in hot water and on average he had 2 minutes of very nice shower.

[thailiketoo]

Statistics tells us that a man can shower for 1 minute in cold water and 1 minute in hot water and on average he had 2 minutes of very nice shower.

Ah Mr Yang no statistical education eh? OK. No they don't. Now digest the attached photos and decide which you have said.

Edited June 26, 2014 by thailiketoo

[JLCrab]

In probability theory there is the Law of Large Numbers (LLN) which some here might interpret as the more times that I post the closer to the real answer I will be.

[Thai at Heart]

Stats in Thailand make no allowance for chok dee.

[thailiketoo]

Stats in Thailand make no allowance for chok dee.

Yes they do. Luck is assumed not to be a part of any survey conducted by NSO Thailand.

http://web.nso.go.th/en/kno/data_kno/offstatun.pdf

[MRYANG]

Statistics tells us that a man can shower for 1 minute in cold water and 1 minute in hot water and on average he had 2 minutes of very nice shower.

Ah Mr Yang no statistical education eh? OK. No they don't. Now digest the attached photos and decide which you have said.

Ah thailiketoo no sense of humour eh? OK.

[Swiss1960]

Statistics are neither true nor false. They show exactly what the person that drafted the statistics wanted to show.

The numbers used for a statistic however can be "false", meaning manipulated. You can always omit numbers by declaring them as statistically irrelevant (i.e. statistical outliers). You can of course manipulate numbers by using "wrong" samples, too small samples etc.

The interpretation of a statistic can be true or wrong and it is impossible to interpret, read, understand statistics without reading the fineprint, i.e. how the numbers were drafted, what data was omitted and eliminated etc. etc.

[chiang mai]

No, statistics over time show trend.

[thailiketoo]

Statistics are neither true nor false. They show exactly what the person that drafted the statistics wanted to show.

The numbers used for a statistic however can be "false", meaning manipulated. You can always omit numbers by declaring them as statistically irrelevant (i.e. statistical outliers). You can of course manipulate numbers by using "wrong" samples, too small samples etc.

The interpretation of a statistic can be true or wrong and it is impossible to interpret, read, understand statistics without reading the fineprint, i.e. how the numbers were drafted, what data was omitted and eliminated etc. etc.

The OP is

Is statistical probability accurate in Thailand?

[Thai at Heart]

Stats in Thailand make no allowance for chok dee.

Yes they do. Luck is assumed not to be a part of any survey conducted by NSO Thailand.

http://web.nso.go.th/en/kno/data_kno/offstatun.pdf

Well, everyone knows that there is more luck available to be garnered in thailand. All u have to do is go to the temple and pick it up.

[Seastallion]

Statistics can be flawed if the data gathering procedure was flawed or interpretation of the data was flawed.

[thailiketoo]

Statistics can be flawed if the data gathering procedure was flawed or interpretation of the data was flawed.

The OP is, "Is statistical probability accurate in Thailand?"

Statistical Probability. How likely something is to happen. Many events can't be predicted with total certainty. The best we can say is how likely they are to happen, using the idea of probability. Example: toss a coin 100 times, how many Heads will come up?

I didn't say anything about data gathering. Statistical probability works the same in Thailand as any place else. That was my point. People lump data gathering with statistical probability and say statistics lie. It's not true.

If a person says data gathering in Thailand is not accurate that's OK then we have a starting point of discussion. However to say statistics always lie is not true.

[Swiss1960]

Statistics are neither true nor false. They show exactly what the person that drafted the statistics wanted to show.

The numbers used for a statistic however can be "false", meaning manipulated. You can always omit numbers by declaring them as statistically irrelevant (i.e. statistical outliers). You can of course manipulate numbers by using "wrong" samples, too small samples etc.

The interpretation of a statistic can be true or wrong and it is impossible to interpret, read, understand statistics without reading the fineprint, i.e. how the numbers were drafted, what data was omitted and eliminated etc. etc.

The OP is

Is statistical probability accurate in Thailand?

Yep, and the answer is in the last paragraph of my post... "probability" is not coming from the statistic, but from the interpretation of the statistics. Reading a "probability" out of the statistic is a question of understanding statistics as such and therefore understanding the data / sample size behind the statistic you are using for an accurate probability statement based on a statistic.

You are of course right that this does not depend on whether it is Thailand or not, the question however is whether the data gathering in Thailand is as "accurate" or independent or representative as it is in other countries.

[thailiketoo]

Statistics are neither true nor false. They show exactly what the person that drafted the statistics wanted to show.

The numbers used for a statistic however can be "false", meaning manipulated. You can always omit numbers by declaring them as statistically irrelevant (i.e. statistical outliers). You can of course manipulate numbers by using "wrong" samples, too small samples etc.

The interpretation of a statistic can be true or wrong and it is impossible to interpret, read, understand statistics without reading the fineprint, i.e. how the numbers were drafted, what data was omitted and eliminated etc. etc.

The OP is

Is statistical probability accurate in Thailand?

Yep, and the answer is in the last paragraph of my post... "probability" is not coming from the statistic, but from the interpretation of the statistics. Reading a "probability" out of the statistic is a question of understanding statistics as such and therefore understanding the data / sample size behind the statistic you are using for an accurate probability statement based on a statistic.

You are of course right that this does not depend on whether it is Thailand or not, the question however is whether the data gathering in Thailand is as "accurate" or independent or representative as it is in other countries.

Exactly my point. We can discuss data gathering intelligently. We can discuss the bathwater without throwing out the baby. One guy above said statistics were not accurate because he didn't know the difference between mean, median and mode.

Edited June 26, 2014 by thailiketoo

[Jack Mountain]

It's accutare as long as the answer is 'mai pen rai'.

[wprime]

How many Thais need to be in a room to have two with the same birthday?

How many Brits need to be in a room to have two with the same birthday?

The correct answer to these two questions is 2. Their race doesn't matter.

[thailiketoo]

It's accutare as long as the answer is 'mai pen rai'.

Ahh no. National Statistics Office Thailand NSO.

The NSO's major users combine the Office of the National Economic and Social Development Board, the Ministry of Labour and Social Welfare, the Ministry of Public Health, the Ministry of Agriculture and Cooperatives, the Bank of Thailand and international organizations such as World Bank, IMF, ILO, ADB, ESCAP, JICA, MITI, etc. More information please send email to [email protected]

[robblok]

Statistics are neither true nor false. They show exactly what the person that drafted the statistics wanted to show.

The numbers used for a statistic however can be "false", meaning manipulated. You can always omit numbers by declaring them as statistically irrelevant (i.e. statistical outliers). You can of course manipulate numbers by using "wrong" samples, too small samples etc.

The interpretation of a statistic can be true or wrong and it is impossible to interpret, read, understand statistics without reading the fineprint, i.e. how the numbers were drafted, what data was omitted and eliminated etc. etc.

The OP is

Is statistical probability accurate in Thailand?

Yep, and the answer is in the last paragraph of my post... "probability" is not coming from the statistic, but from the interpretation of the statistics. Reading a "probability" out of the statistic is a question of understanding statistics as such and therefore understanding the data / sample size behind the statistic you are using for an accurate probability statement based on a statistic.

You are of course right that this does not depend on whether it is Thailand or not, the question however is whether the data gathering in Thailand is as "accurate" or independent or representative as it is in other countries.

Exactly my point. We can discuss data gathering intelligently. We can discuss the bathwater without throwing out the baby. One guy above said statistics were not accurate because he didn't know the difference between mean, median and mode.

That is the whole point of statistics if done correctly they are as true here as anywhere else. But if done to get a certain answer they are as faulty as anywhere else. Thailand is not the only country where statistics are manipulated. you can show a lot of things with statistics it all depends on how it is done.

Do I believe statistics here.. some sure.. some I don't same as back home.

[Soutpeel]

Statistics are neither true nor false. They show exactly what the person that drafted the statistics wanted to show.

The numbers used for a statistic however can be "false", meaning manipulated. You can always omit numbers by declaring them as statistically irrelevant (i.e. statistical outliers). You can of course manipulate numbers by using "wrong" samples, too small samples etc.

The interpretation of a statistic can be true or wrong and it is impossible to interpret, read, understand statistics without reading the fineprint, i.e. how the numbers were drafted, what data was omitted and eliminated etc. etc.

The OP isIs statistical probability accurate in Thailand?

Yep, and the answer is in the last paragraph of my post... "probability" is not coming from the statistic, but from the interpretation of the statistics. Reading a "probability" out of the statistic is a question of understanding statistics as such and therefore understanding the data / sample size behind the statistic you are using for an accurate probability statement based on a statistic.

You are of course right that this does not depend on whether it is Thailand or not, the question however is whether the data gathering in Thailand is as "accurate" or independent or representative as it is in other countries.

Exactly my point. We can discuss data gathering intelligently. We can discuss the bathwater without throwing out the baby. One guy above said statistics were not accurate because he didn't know the difference between mean, median and mode.

Jeez...what do you for a living ? An accountant ? Someone getting excited about discussing statistics ?

I mean you really want to discuss this at least make it interesting like the demographic of bar girls in pattaya, how many people have a pet gerbil or something

[thailiketoo]

The OP is

Is statistical probability accurate in Thailand?

Yep, and the answer is in the last paragraph of my post... "probability" is not coming from the statistic, but from the interpretation of the statistics. Reading a "probability" out of the statistic is a question of understanding statistics as such and therefore understanding the data / sample size behind the statistic you are using for an accurate probability statement based on a statistic.

You are of course right that this does not depend on whether it is Thailand or not, the question however is whether the data gathering in Thailand is as "accurate" or independent or representative as it is in other countries.

Exactly my point. We can discuss data gathering intelligently. We can discuss the bathwater without throwing out the baby. One guy above said statistics were not accurate because he didn't know the difference between mean, median and mode.

That is the whole point of statistics if done correctly they are as true here as anywhere else. But if done to get a certain answer they are as faulty as anywhere else. Thailand is not the only country where statistics are manipulated. you can show a lot of things with statistics it all depends on how it is done.

Do I believe statistics here.. some sure.. some I don't same as back home.

I'm trying to get across the point that statistical probability and data gathering or interpretation are different things.

[thailiketoo]

The OP isIs statistical probability accurate in Thailand?

Yep, and the answer is in the last paragraph of my post... "probability" is not coming from the statistic, but from the interpretation of the statistics. Reading a "probability" out of the statistic is a question of understanding statistics as such and therefore understanding the data / sample size behind the statistic you are using for an accurate probability statement based on a statistic.

You are of course right that this does not depend on whether it is Thailand or not, the question however is whether the data gathering in Thailand is as "accurate" or independent or representative as it is in other countries.

Exactly my point. We can discuss data gathering intelligently. We can discuss the bathwater without throwing out the baby. One guy above said statistics were not accurate because he didn't know the difference between mean, median and mode.

Jeez...what do you for a living ? An accountant ? Someone getting excited about discussing statistics ?

I mean you really want to discuss this at least make it interesting like the demographic of bar girls in pattaya, how many people have a pet gerbil or something

I know someone made you read this thread and comment. I'm sorry. I'll give your guard a call.

[robblok]

I'm trying to get across the point that statistical probability and data gathering or interpretation are different things.

Yes they are.. and the statistical probability of something in Thailand could be the same as in other places. However if you look at the probability of an accident here compared to in my country they will differ.

Your coins experiment would indeed be the same.

[FinanceGuy]

How many Thais need to be in a room to have two with the same birthday?

Is it 18 or 23?

I remember this question from a book by Warren Buffet.

[Swiss1960]

How many Thais need to be in a room to have two with the same birthday?

Is it 18 or 23?

I remember this question from a book by Warren Buffet.

A graph showing the computed probability of at least two people sharing a birthday amongst a certain number of people.

[taotoo]

"Sorry but Twain or Disraeli was in error. They did not know the meaning of the word Statistics. "

And you obviously don't know the meaning of the quote. It is making the point that anybody can 'prove' anything by offering selected statistics that meet their agenda, while not offering related statistics that don't.

[CharlieH]

Post removed, no personal attacks or insults please.