geographical distribution

[pop]

Advertisement (gone after registration)

Genoa, Italy

 

@ Bill: May I respectfully point out that statistics are not conducted over the whole population but on a number of randomly selected samples which are representative of the whole. Therefore the subset of the worldwide M8 population should however provide an indication about how we're scattered.

 

Best regards

Bruno

 

As a matter of fact, OP asked for "M8 forum contributors", not for "M8 users".

[Advertisement]

The Leica Q3 is available for pre-order at B&H Photo Video and Adorama

[carstenw]

@ Bill: May I respectfully point out that statistics are not conducted over the whole population but on a number of randomly selected samples which are representative of the whole. Therefore the subset of the worldwide M8 population should however provide an indication about how we're scattered.

 

Well, there is a small difference between this thread and what you wrote: the people who post their location here are not randomly selected, but self-selecting, which kills all statistical validity in representing the set as a whole. The same goes for the higher layer, i.e. the self-selecting set of forum members, compared to all Leica M8 owners. Still, it is interesting to see who posts here.

[SJP]

I'm from Vulcan. Live long and prosper.

 

If you don't believe me check my "details".

[!Nomad64]

OK folks, you had me to clear my clocks as to statistics: http://en.wikipedia.org/wiki/Sample_(statistics)

 

From there I'd quote the following:

 

[...] In statistics, a sample is a subset of a population. Typically, the population is very large, making a census or a complete enumeration of all the values in the population impractical or impossible. The sample represents a subset of manageable size. Samples are collected and statistics are calculated from the samples so that one can make inferences or extrapolations from the sample to the population. [...]

The best way to avoid a biased or unrepresentative sample is to select a random sample, also known as a probability sample. A random sample is defined as a sample where each individual member of the population has a known, non-zero chance of being selected as part of the sample.[...]

 

The way I see it, the M8 forum contributors are a subset of the whole worldwide M8 users population and the fact that they are self selecting doesn't affect their randomness. They all have a non-zero chance of being selected. Not all of the M8 users know about this forum. Not all of the M8 users nor the M8 forum contributors know about this peculiar thread. Not all of the M8 forum contributors may want to have their location publicly known. Therefore those who attend this poll are pretty good an approximation of random sampling in the sense that they might be here by chance. And IMHO the statistics to be extrapolated from this poll are applicable to the whole worldwide M8 users population.

 

Besides, it's worth reminding that the basic principle behind statistic is that wrong information is preferable to no information at all.

And I'm the first to admit that this may lead to paradoxes such as if we're in two and I eat a whole chicken, on average we ate half a chicken each one, no matter that the other one might be starving to death. And if furthermore the other one happens to be the chicken himself he'll also look like a cannibal...

 

Cheers,

Bruno

[carstenw]

The way I see it, the M8 forum contributors are a subset of the whole worldwide M8 users population and the fact that they are self selecting doesn't affect their randomness.

 

I agree with some of what you wrote, but not this. The fact that the set (twice: forum members, and thread participants) is self-selecting means exactly that they are not random. There is no statistical validity to what we are doing here, just interest.

 

To select a random set, you must know the whole set, and then randomly choose X people to represent the set.

 

If some chosen folk should opt out, they endanger the validity of the chosen set quite rapidly. This is why phone polls can be thrown off by just a few people who won't reveal their political leanings, or whatever is being tested.

 

Besides, it's worth reminding that the basic principle behind statistic is that wrong information is preferable to no information at all.

 

I would rather think that the opposite is true. I am not sure where this principle should come from.

[Clive Murray-White]

Always nice to see where people come from - I'd say that nothing much can be revealed though in this "survey" because its entirely dependant on who chooses to read the thread in the first place.

 

As for Leica dealers! I live in a tiny rural community over 200 kms away from my nearest Leica dealers (Melbourne Australia). In this country every reasonably large town used to have a camera shop but over the past 20 years they have all gone, probably due to eBay and online options. To a certain extent this suits me as I can sit here in the middle of nowhere and buy stuff from all over the world and while our AU dollar remains high I can get some some pretty good bargains.

[bill]

Advertisement (gone after registration)

...a number of randomly selected samples which are representative of the whole.

 

Bruno, that is the crux of the matter. I did Advanced Statistics and Quantitative Analysis at college. It made my head hurt then and it makes my head hurt now. But I do understand it, from Spearman-Rank on through. There is nothing more useless than a spurious statistic and that is, unfortunately, for the reasons already stated, what we have here. Have fun, but don't hang your hat on the "results".

 

Regards,

 

Bill

[!Nomad64]

Amending myself, as I went further reading on to find the following: Accidental sampling - Wikipedia, the free encyclopedia

 

[...] Accidental sampling is a type of nonprobability sampling which involves the sample being drawn from that part of the population which is close to hand. That is, a sample population selected because it is readily available and convenient. The researcher using such a sample cannot scientifically make generalizations about the total population from this sample because it would not be representative enough. For example, if the interviewer was to conduct such a survey at a shopping center early in the morning on a given day, the people that he/she could interview would be limited to those given there at that given time, which would not represent the views of other members of society in such an area, if the survey was to be conducted at different times of day and several times per week. This type of sampling is most useful for pilot testing.[...]

 

In view of the above Carstenw and Bill are ultimately right themselves. I surrender to anyone who provided more an appropriate explanation. My apologies for posting bullsh*ts.

 

Cheers,

Bruno

[!Nomad64]

 

 

 

I would rather think that the opposite is true. I am not sure where this principle should come from.

 

Carstenw, that's what I was taught when I attended the university and clashed with statistics... you'll want to blame my teachers :-)

 

Cheers,

Bruno

[carstenw]

In view of the above Carstenw and Bill are ultimately right themselves. I surrender to anyone who provided more an appropriate explanation. My apologies for posting bullsh*ts.

 

No need to apologize, I don't see why we can't discuss statistics as well as boke I had a great prof in statistics, and in spite of my abysmal marks, I remember some of it still.

[carstenw]

Carstenw, that's what I was taught when I attended the university and clashed with statistics... you'll want to blame my teachers :-)

 

I am still skeptical. Wrong information is not desirable. Perhaps they meant any data is better than no data?

[pop]

There's a saying: rather roughly right than exactly wrong. Perhaps that's the rationale.

[hoppyman]

Leaving aside the statistical validity discussion, I think that the OP was just interested for fun! Don't forget tht this is just the English speaking version of the forum of course.

 

There was a mapping appliction like this called Frappr. I think that it has died:(

One of the other Leica related on-line lists, the LUG did have a map and people could input their photo and location plus comments.

 

Probably some social media genius will reinvent this and make a fortune if it doesn't already exist via facebook or something!

[StenSture]

I'm alternating between Stockholm and Kyrkhult, Sweden. A freesingly cold Sweden, for the time being...

[lanetomlane]

I seem to live in 18B; in the 'bubble' on top of the B747. My bricks and mortor however are in Earith, Cambridgeshire in the UK.

______________________

Cheers, Tom

[WestMichigan]

Greetings to You in Your Bubble Tom,

Does 18B refer to a Bar Stool in a 747 Mid-Air Lounge,

A seat in Business Class from frequent jumps across the Pond,

or are you a Communications Officer aboard the 'B' 747 in the President's Air Force One Fleet and fly crammed into it's Comm Space Behind the Flight Deck?

Happy Holidays

Richard in Michigan

I seem to live in 18B; in the 'bubble' on top of the B747. My bricks and mortor however are in Earith, Cambridgeshire in the UK.

______________________

Cheers, Tom

[Knomad]

OK folks, you had me to clear my clocks as to statistics: http://en.wikipedia.org/wiki/Sample_(statistics)

 

From there I'd quote the following:

 

[...] In statistics, a sample is a subset of a population. Typically, the population is very large, making a census or a complete enumeration of all the values in the population impractical or impossible. The sample represents a subset of manageable size. Samples are collected and statistics are calculated from the samples so that one can make inferences or extrapolations from the sample to the population. [...]

The best way to avoid a biased or unrepresentative sample is to select a random sample, also known as a probability sample. A random sample is defined as a sample where each individual member of the population has a known, non-zero chance of being selected as part of the sample.[...]

 

The way I see it, the M8 forum contributors are a subset of the whole worldwide M8 users population and the fact that they are self selecting doesn't affect their randomness. They all have a non-zero chance of being selected. Not all of the M8 users know about this forum. Not all of the M8 users nor the M8 forum contributors know about this peculiar thread. Not all of the M8 forum contributors may want to have their location publicly known. Therefore those who attend this poll are pretty good an approximation of random sampling in the sense that they might be here by chance. And IMHO the statistics to be extrapolated from this poll are applicable to the whole worldwide M8 users population.

 

Besides, it's worth reminding that the basic principle behind statistic is that wrong information is preferable to no information at all.

And I'm the first to admit that this may lead to paradoxes such as if we're in two and I eat a whole chicken, on average we ate half a chicken each one, no matter that the other one might be starving to death. And if furthermore the other one happens to be the chicken himself he'll also look like a cannibal...

 

Cheers,

Bruno

 

No, it's not a random sample.

 

To get a full random sample you'd take a list of all M8 owners, and randomly select a subset of them... say, by assigning them sequential numbers, or using the SN of their cameras, and then using an online random number generator to pull the subset.

 

Or, let's talk specifically about forum members. You could use the same method to select a random subset of members, who would then, if the sample size were large enough, tell you something valid about the distribution of all members. Although if we knew which ones had M8s it would probably be more efficient to just generate a list of all forum members and assign map coordinated to each, there can't be that many of us.

 

Anything self-selecting would certainly have bias, so by definition it's non-random.. People in certain time zones might have been more likely to miss the OP and major secondary flurries of posts. Certain demographics are presumably more or less likely to be active on forums, and so on.

[WestMichigan]

I am going to make a Blanket Generalization here so, in all sincerity, please don't take offense anyone. But...

 

The More I Read About Statistics In This Thread,

The More It Sounds Like "

Crop Circle Science

"!

 

"

Tangible

" Measurements Are Obtained, But

Are Only As'

Real

' As The Individual Processing The

Measurements - Some Are Scientists And Some

Wear Tin Foil To Block The Mind Control Waves.

 

Stepping off the 'Soap Box',

These discussions of scientific and mathematical processes seem gloriously fun, assuming talents and/or understandings of them... Bit like Geek Mind Soccer!

 

Go Manchester United!

 

R. in Mi.

 

No, it's not a random sample.

 

To get a full random sample you'd take a list of all M8 owners, and randomly select a subset of them... say, by assigning them sequential numbers, or using the SN of their cameras, and then using an online random number generator to pull the subset.

 

Or, let's talk specifically about forum members. You could use the same method to select a random subset of members, who would then, if the sample size were large enough, tell you something valid about the distribution of all members. Although if we knew which ones had M8s it would probably be more efficient to just generate a list of all forum members and assign map coordinated to each, there can't be that many of us.

 

Anything self-selecting would certainly have bias, so by definition it's non-random.. People in certain time zones might have been more likely to miss the OP and major secondary flurries of posts. Certain demographics are presumably more or less likely to be active on forums, and so on.

[Advertisement]

Hallo,

Look here: Leica M

[martha]

These discussions of scientific and mathematical processes seem gloriously fun, assuming talents and/or understandings of them... Bit like Geek Mind Soccer!

 

Go Manchester United!

 

R. in Mi.

 

What started out as a straightforward (really, rather innocent) question has turned into a statistical free for all and I am loving it!!!!! ONLY in the Leica Forum, where to own one is to be brainey (present company excepted, of course! I avoided Statistics in college; that's one of the reasons I was an English Major!)

 

Martha in Maine.

[Knomad]

What started out as a straightforward (really, rather innocent) question has turned into a statistical free for all and I am loving it!!!!! ONLY in the Leica Forum, where to own one is to be brainey (present company excepted, of course! I avoided Statistics in college; that's one of the reasons I was an English Major!)

 

Martha in Maine.

 

My favorite stats book is "Biometry" by Sokal and Rohlf, it's a little old now, but they had a sense of humor which is all too rare in quantitative sciences... here's their take on random sampling:

 

"Now let us imagine the following experiment: we try to sample a student at random from among the student body at Matchless University. This is not as easy a task as might be imagined. If we wish to do this operation physically, we would have to set up a collection or trapping station somewhere on campus. We should try to locate our trap at some station where each student has an equal probability of passing...."

 

Clever enough that I remembered it all these years later