USING STATISTICS TO DESCRIBE PENIS SIZE

Discussion in 'New Member Introductions' started by ElCamino55, Sep 9, 2005.

1. ElCamino55 New Member

Joined:
Sep 9, 2005
Messages:
37
2
By using statistics we can describe the variation of sizes in the general population of penises.

First, we must determine what really is "average".

Studies have determined the average penis length is somewhere between 5 and 6 inches. We will settle for labeling "average" as 5.5 inches. Average circumference is between 4 and 5 inches, so we will settle for laberal average circumference as 4.5 inches.

The standard deviation (SD) of penis length is reported to be between 0.5 and 0.8 inch(es). Once again, we will take the middle, and settle for using .65 as the SD for penis length. For circumference there isn&#39;t as much data, but what is available shows the SD to be about 0.4 inches.

Using these numbers we can say that 68% of the population is between 4.85 and 6.15 inches. 95% are between 4.2 and 6.8 inches. 98% are between 3.55 and 7.45 inches. 1% are smaller than 3.55 inches, and 1% are larger than 7.45 inches. The "one in a million" mark is at 8.6 inches - that is, only 1 in 1,000,000 men will be larger than 8.6 inches, or smaller than 2.4 inches (about 5 SD&#39;s from the mean).

As for circumference, 68% are between 4.1 and 4.9 inches. 95% are between 3.7 and 5.3 inches; and 98% are between 3.3 and 5.7 inches. 1% are smaller than 3.3 inches, and 1% are larger than 5.7 inches. The "one in a million" mark is at 6.4 inches for the larger, and 2.6 inches for the smaller.

The most extreme ends of the spectrum (read LARGEST PENIS IN THE WORLD here) will be about 10 SD&#39;s from the mean; about 12 inches in length and about 8.5 inches in circumference.

I have a keen interest in penis size, as I, myself, was blessed (cursed?) with a penis approximately 9 inches in length and 5.5 inches in circumference. Every woman I meet (meat?) in the "real world" is VERY VERY VERY impressed with my size, some are even scared, or quit after some amount of sex (or simply BEG me to cum, so they can get my large penis out of them...). Only in chatrooms do I find "women" that claim to have been with guys that were "at least 12 inches" - never in the "casual relationships" I have with women.

Also, I look at a lot of porn (hey, I have a lot of time on my hands, OK?), and NEVER have I seen a man larger than 11 inches; Lex Steele and Mandingo come to mind automatically - but I sometimes think they look so much larger due to tricky photography, camera angles, lenses, etc. Sometimes they don&#39;t seem much larger than 10 inches...

Anyway, this was my first post...&#33;

#1
Jimmy The Wang and MrHUGE1n like this.
2. B_Hung Muscle New Member

Joined:
Sep 16, 2004
Messages:
3,142
17
Gender:
Male
Location:
NYC but never stop traveling
Good first post, Camino.

I&#39;ve never seen an 11 inch penis either, so I am truly a doubting Thomas about anyone here -- or anywhere -- who claims to have one.

The guys in the Monsters of Cock website Mr. Mark posted here have 9 inch dicks and they are absolutely ginormous&#33;

An eight inch penis is huge and uncommon. 11 to 12 inches? Sorry, I gotta get my own personal ruler out to believe it.

Fire away, boys, but I&#39;m still gonna say your pants are on fire unless I see the goods for myself.

#2
3. SomeGuyOverThere Gold Member

Joined:
Dec 2, 2004
Messages:
1,494
9
Gender:
Male
Location:
Glasgow (GB)
Wait a minute...

Just hold on - Are you trying to tell me that people online, actually... actually lie?&#33;

Good God&#33; Call the President&#33;

[/SARCASM]

Anyway, welcome to the board, and I quite agree, many people arent what they say they are...

#3
4. B_DoubleMeatWhopper New Member

Joined:
Oct 7, 2002
Messages:
5,386
17
Gender:
Male
Location:
Louisiana
They exist. I don&#39;t have one myself, but I&#39;ve seen a few. Of course, I used to be in a position to see unusually large cocks. Though there are some phallic monsters out there, sightings are rarer than reports of Bigfoot.

#4
5. ElCamino55 New Member

Joined:
Sep 9, 2005
Messages:
37
2
They exist. I don&#39;t have one myself, but I&#39;ve seen a few. Of course, I used to be in a position to see unusually large cocks. Though there are some phallic monsters out there, sightings are rarer than reports of Bigfoot.
[post=341892]Quoted post[/post]​
[/b][/quote]

What, er, "position" were you in to see these OUTRAGEOUSLY large dicks?

An 11" dick is as rare as a man about 7&#39;8" tall&#33;&#33;&#33;

In the NBA both Shawn Bradley and Yao Ming are listed at 7&#39;6" tall, just for some comparison of just how RARE 11+" dicks really are...Sure, there are a handful (pun intended) out there, and there probably is a guy or two with 12"s, and there just MIGHT be some guy with 13"s, and if there&#39;s anyone bigger, or more than one 13"er out there, that&#39;s just a statistical abnormality the equivalent of winning the Powerball or Big Game lotteries twice a week for a year (or something else outrageous like that...).

#5
6. ericbear Gold Member

Joined:
Oct 14, 2002
Messages:
1,190
Albums:
1
525
Gender:
Male
Location:
Santa Ana (CA, US)
In my own experience, I&#39;ve encountered cocks from roughly the size of my thumb to my forearm, or about 2.5 to around 11 inches long. While ones at the extreme are rare, I have seen several. However, since I have not seen millions of cocks, I have seen far more large ones than your statistics would predict. For reference, I would estimate that cocks in the 8 to 9 inch range are found on perhaps 1% or so of the men I have played with, not one in a million.

There are perhaps several reasons for this, but the most likely one has to do with improper use and poor understanding of statistical techniques, leading to invalid conclusions. You, and many of the researchers you quote, have assumed that the data has a Gaussian (normal) distribution when applying the concepts of mean and standard deviation (SD), and then using these number to extrapolate the expected frequency of finding any particular size. Unfortunately, this is often done on datasets which are not truly Gaussian.

The mean and SD are valid concepts for data with any distribution. However, using these two values to predict the frequency in the way you did is only valid if the distribution is Gaussian. It is common for researchers to summarize data as the mean and SD, and leave it to readers to assume that the data set is Gaussian, when in fact the accuracy of fit to the Gaussian model was never verified. Just because the distribution curve seems "bell shaped," doesn&#39;t mean that it accurately follows the Gaussian model. Even if the data appears to be a reasonable fit to a Gaussian model, it is important to note that the further you get from the mean, the less accurate the extrapolation may become. This is because the tests used to determine the goodness of fit to the model aren&#39;t very sensitive to points out on the "tails" of the distribution, as there are comparatively few of these points in a dataset of roughly Gaussian shape. So, you have to beware of large extrapolations (many SD) in all cases, and even be skeptical closer to the mean if the goodness of fit to the model is suspect.

To have a true Gaussian distribution, the data has to be truly random in nature. It is doubtful that penis size is truly random, as genetics, mate selection, physical limitations, and other somewhat determinisitic factors are involved. Therefore, it is not surprising that actual experience differs from the results extrapolated using the mean and SD assuming a Gaussian model. Even a subtle deterministic effect can casue large deviations from the model at the "tails" of the curve.

In fact, even if penis length were truly random, the model using a mean length plus/minus so many standard deviations is obviously flawed. For example, you say the world&#39;s largest cock would be at +10 standard deviations, at 12 x 8.5 inches. But, as a Gaussian distribution is symetrical about the mean, this means that the smallest penis, at -10 standard deviations, would be negative 1 inch long by 0.5 in circumference (this is using your numbers; I didn&#39;t bother to verify your caluclations). Since a negative length is physically impossible, it is obvious that your model cannot be accurate at the large extrapolations you make.

When measuring the size of things that vary widely (which cocks do, despite the feel-good BS to the contrary), statistics based on geometric distributions, rather than arithmetic ones, somteimes work out as better fits. For example, the arithmetic Gaussian distribution you assumed predicts that for every cock X inches longer than the arithmetic mean, there is one X inches shorter, given the symetrical distribution curve. However, in a geometric distribution, for every cock Y times the length of the geometric mean, you have one equal to the mean divided by Y. (Note that you can&#39;t get negative lengths this way; just nearly zero.) A simple way to analyze a data set in this way is to take the logarithms of the lengths, then apply the usual arithmetic Gaussian statistics to the logs. This is still assuming a Gaussian distribution (which may not really be true due to deterministics factors), but now applies it to the ratio of the length to the mean. I suspect that will produce results that agree better with observation.

#6
g0nz0 likes this.
7. ElCamino55 New Member

Joined:
Sep 9, 2005
Messages:
37
2

Ah, another statistician - and a well educated one at that&#33;

Your forearm is 11 inches long?

How tall are you?

If your forearm is 11 inches long, you&#39;ve gotta be well over 7 feet tall&#33;

I&#39;m of normal height, and my forearm is about 9-9.5 inches long (depending on from where you measure).

As for the smallest penises being negative - perhaps I&#39;ve overstated the SD, and the largest penises out there aren&#39;t quite so large, since the smallest can&#39;t be quite so small.

Also, the world isn&#39;t perfect, that&#39;s true - there could (and ARE) some abnormalities about the curve. But nothing of the nature to produce 11 inch penises in the kind of abundance needed for the DOZENS of anecdotal stories of which I&#39;ve heard.

I maintain the distribution of penis sizes IS Gaussian ("normal"), and have no reason to believe otherwise. Do you, or do you not agree that the distribution of height is Gaussian? What about hand length, etc.? If you agree those are Gaussian, why not penis size?

#7
8. Dr Rock Gold Member

Joined:
Jan 11, 2005
Messages:
3,687
1
Location:
who lives in the east &#039;neath the willow tree? Sex
huh? my forearms (I&#39;m assuming we&#39;re talking wrist to elbow here) are over 12" long, and I&#39;m only 6&#39;2.

I&#39;ve personally encountered at least half a dozen guys as long or longer than me, which works out to about 2% of all the males with whom I&#39;ve ever gotten messy. I dunno where you&#39;re getting your statistics from, but they&#39;re clearly not applicable to real life.

#8
9. ericbear Gold Member

Joined:
Oct 14, 2002
Messages:
1,190
Albums:
1
525
Gender:
Male
Location:
Santa Ana (CA, US)
My forearms, measured from elbow to the point where the wrist meets the palm, are 11 inches. According to Van Cott and Kincade&#39;s classic Human Factors textbook (reference below), the typical (50th percentile) dimension for an adult male (air force personel) is 11.4 inches. (This is obtained by subtracting the hand length in table 11-57 from the forearm+hand length in table 11-45). Given that these same individuals have a reported typical height of 69.1 inches, and I am a bit taller (72 inches), if anything, I have short arms. I have no idea why your arm measures so short.

The same text makes interesting comments about the use of means and SD to represent anthropometric data. They present most of their data as percentiles (usually 1/5/50/95/99th). They comment that most of the precentiles are calculated directly from the original data sets, without invoking the use of an assumed distribution, mean and SD. In a few places, they caution that their data has been extracted from research published in the form of mean and SD. They carefully mark this data, and explain that it is less reliable, but is better than no data at all.

They give a particular example, that of body weight, where it is well known that the values do not follow a Gaussian distribution. Despite this, they note that much of the data used to create the body weight tables in the text (for populations outside the US military) was originally published in the form of mean and SD. This is an example of researchers simply assuming a Gaussian distribution because it is customary to do so, not because the data is a particularly good fit for that parameter.

In the use of anthropometric data, such as height, arm length, or weight, it is customary to concentrate on the central population, and ignore the extremes. To quote Van Cott and Kinkade:

"Extreme values...for practical purposes should be ignored when designing equipment. Removing 1% at both ends of the range will eliminate most of these extreme values...The designer should attempt to accommodate at least 90% of the population as a minimum, and strive for 98%..."

Note that dropping the extreme 1% at both ends, in the case of a true Gaussian distribution, limits the region of concern to +/- 2.3 SD.

Although the text discourages the use of mean and standard deviation where percentiles can be obtained otherwise (directly from the raw data), the authors do admit that many body dimensions do approximately follow Gaussian distributions, and that this may be adequate for the purposes for which anthrometric data is generally used. Any roughly hump-shaped curve will be reasonably approximated by a Gaussian model in the region around the mean. As you go further away, the error increases. This is because the method used to fit the data (computation of mean and SD) favors the points around the middle of the hump, because there are more of them. Further, the metrics used to measure the "goodness of fit" do the same thing. For most practical use of the data, this is actually desirable. When designing equipment or clothing, for example, you want the model to be most accurate where you have the most customers. If the model becomes inaccurate as you move toward the fringes, this is not a big deal, because there are very few customers out there, and you were probably planning on ignoring the extreme 1% anyway. Hence, even if the model isn&#39;t a perfect fit to the data, it is reasonable, and very useful, to assume a Gaussian distribution, and anthropometric data is often presented as such.

However, in investigating extreme size of any part of the body, you are specifically looking at the very data, the extremes, that is normally excluded in general use of the anthopometric data. You are also looking in the very place where the misfit of the model is expected to be greatest.

A true Gaussian distribution is created by a totally random process, and has values from zero (or negative infitinity, where applicable) to infinity, although at infinitessimal probablity. However, when describing certain physical things, the ends of the distribution may be modified because of physical limits. For example, a human taller than some absurd height probably can&#39;t physically exist, due to blood pressure pressure and hydrostatic gradient issues.

On a more realistic note, there are often determinisitic factors superimposed on top of an otherwise random process. For example, we know that there are certain genetic conditions and diseases that can cause people to be very tall, or lanky, or very small. These exceptional cases become superimposed on a distribution curve that might otherwise be random and closely Gaussian. However, these occur rarely. If you look near the center of the curve, the few rare cases are diluted by the vast number of ordinary cases, and the curve shape is relatively unaffected by them. Hence, the curve fit largely ignores these exceptional cases. However, as you move out onto the tails of the curve, where the predicted frequency starts to fall off, these exceptional cases start to become more noticable.

In my previous post, I called these sorts of things deterministic causes, but many years ago Walter Shewhart, the "father of Statistical Quality Control," called them "assignable causes." Shewhart&#39;s basic theory is that variability in a manufacturing process is inherently a purely random thing, and therefore accurately fitted a Gaussian model. However, Shewhart stressed that this is only true if the assignable causes are eliminated. The corenerstone of Shewhart&#39;s method, which is the basis of most manufactring controls today, is that you have to seek out and eliminate the assignable causes in order for stastistical control and analysis to be useful in quality control.

The "assignable causes" that may occur in biology and reproduction, like genetic defects, selective mating, disease, etc, may not be too big a deal when looking at the 1 to 99 percentile. If a genetic condition causing unusual body development occurs 1/1000 of the time, it is only going to account for a small fraction of the cases at the first or 99th percentile, and does not significantly impact the shape of the curve between these points. Therefore, in an overall view, the data might appear quite gaussian.

The problem starts when instead of asking questions like "How big are 98 percent of the people?" you ask questions like "What&#39;s the very biggest?" or "How many extreme cases bigger than X are there?" In these cases, the small number of cases due to the assignable causes may be very much larger than the tiny number predicted by extrapolating from the Gaussian fit of the data.

Now, let&#39;s pretend that 11 inch penii were really found on 0.1% of men, and were due to some assignable cause, just like the well-known causes of abnormal height. Many penis size studies only have a few thousand measurements at most. Therefore, there would only be a couple of points, due to this asignable cause, that didn&#39;t fit the Gaussian model, and the researcher, if he even bothered to check, would say that the model was a good fit to the data, and confidently publish his mean and SD. However, this mean and SD data would give a false underestimate of the number of 11-inch penii, because it does not account for the assignable causes, just as height and limb length statistics are not singificantly skewed by the very few (about 1 in 5000) individuals with Marfan syndrome. But, if you are researching the few individuals with the very longest arms, you are going to find more than predicted by the Gaussian distribution model, because you will encounter individials with this syndrome and other assignable causes that don&#39;t fit the random distribution model.

By the way, the great variability that you note between different penis size studies is an indication that there are assignable causes, whether biological or measurement technique issues, at work. For example, the difference between the various study&#39;s means that you quote are greater than one standard deviation. That is a huge, and difficult to explain, difference, which calls the fit of the data to the model, or the research technique, very much into question.

It is true that people exagerate, invent false personas on the internet, etc. And yes, you are correct that there are not nearly as may huge cocks as you would gather from monitoring a chat room. From some "contact" sites, you would get the impression that there isn&#39;t a man alive shorter than 8 inches. However, your estimate of 1 in a million over that length is equally absurd. The truth, based on my observations, lies closer to 1 in 100 for 8 inches, and perhaps one in some thousands for 10 or 11 inches. Admittedly, my observations may a bit skewed, too, as I frequent events like orgies, sex parties, dungeon parties, clothing-optional hotels, and similar fuckfests, which may tend to prefferentially attract those who like to show off what they have. On the other hand, my observations were fairly well correlated by a person who remarked "Don&#39;t tell me about dick; I was a urology tech in the navy&#33;"

(Reference: Van Cott and Kinkade ed., Human Engineering Guide to Equipment Design. Originally published by McGraw-Hill in 1963, this text was licensed to the US governement printing office, and for many years was the standard manual used by the US Army, Navy, and Air Force.)

#9
g0nz0 likes this.
10. Mr._dB New Member

Joined:
Feb 10, 2004
Messages:
672
8
Gender:
Male
huh? my forearms (I&#39;m assuming we&#39;re talking wrist to elbow here) are over 12" long, and I&#39;m only 6&#39;2.

[/b][/quote]

I just attempted to measure my forearm. I couldn&#39;t get an accurate outside reading (point of elbow to wrist) but from the inside of my elbow to my wrist is 10.5", and I&#39;m 5&#39;10" tall and I have proportionately short limbs for my height. (30" inseam)

#10
11. philberttrw New Member

Joined:
Jul 10, 2004
Messages:
239
Albums:
1
1
Location:
Charlottesville, VA
Ericbear, I suddenly find you EXTREMELY attractive. Who knew you aresuch a brainiac&#33;

#11
12. VeeP Gold Member

Joined:
Sep 3, 2005
Messages:
1,787
Albums:
1
12
Gender:
Male
Who&#39;da known we&#39;d all be measuring our forearms&#33;&#33; (11.25" here, FWIW...)

:shrug:

#12
13. madame_zora Gold Member

Joined:
May 5, 2004
Messages:
10,249
9
Location:
Ohio

Yeah, I&#39;m right there with you, Philbert. *fans flushed face furiously*

#13
14. ElCamino55 New Member

Joined:
Sep 9, 2005
Messages:
37
2
So, with all that being said above...

It could be possible that there is some sort of "genetic mutation" that produces larger penises at a higher rate than the "normal curve" would predict.

With that being said, what other attributes are associated with this genetic mutation, if any? If, indeed, there is a genetic mutation, I&#39;m sure medical science would like to know about it&#33;

Anyway, where does one find pictures of all of these 11 inch dicks out on the internet?

It seems to me, if there were indeed MORE of the 11 inch dicks out there, they would be more easily found in "big dick" porn, for which there seems to be a rather high demand.

Once again, using an NBA analogy, the tallest men in the NBA are about 8 SD from the mean, which is the equivalent to about a 10 inch dick - which is what Lexington Steele seems to be (he MIGHT be 11 inches, but I don&#39;t really know...).

#14
15. hippyscum New Member

Joined:
Apr 20, 2005
Messages:
368
0
That&#39;s the thing about statistics; they rarely can be applied to real life.

#15
16. LloydBaker Active Member

Joined:
Sep 6, 2005
Messages:
971
241
Gender:
Male
Location:
Detroit (MI, US)
That&#39;s the thing about statistics; they rarely can be applied to real life.
[post=341995]Quoted post[/post]​
[/b][/quote]

Large cocks seem more common than they are because small dick guys are much, much less active sexually. Many small dick guys even avoid locker rooms.

I think the distribution curve bunches up tight from average (5.5") to 5" and stretches out long(&#33 from 5.5 to to 10 or whatever. So a guy like me 1" under average or less is much much less common than a guy 1" or more over averge&#33; MUCH LESS&#33;

#16
17. Geekyraccoon Member

Joined:
Sep 6, 2005
Messages:
44
0
Location:
Portland (ME, US)

There really is something about a really smart man... *swoon*

That starts raising issues of the Large Brain Support Group.

#17
18. philberttrw New Member

Joined:
Jul 10, 2004
Messages:
239
Albums:
1
1
Location:
Charlottesville, VA

There really is something about a really smart man... *swoon*

That starts raising issues of the Large Brain Support Group.
[post=342015]Quoted post[/post]​
[/b][/quote]

Heh, heh. So true. We should all petition Mistah Mark for one of those, you know? it&#39;d be like LPSG&#39;s own MENSA group&#33;

Anyways, Ericbear, I was quite intrigued by what you said, and have to say that I couldn&#39;t agree more.

As for my own take on the subject, I think that others have already hit on the subject; men with smaller penises tend to be subversive about the fact, and hide their size from others, and abstain from the frequency of sexual activity that above-average men ascribe to. You have to admit, many, if not most, of the well-hung men out there know they are a novelty, and are happy to please the masses. Additionally, I think that since many of these well-hung gents really get around, mostof these big-cock sightings could very well be repeat performances. I know that it&#39;s a small world out there... My gay friend in high school went on to be freinds (and more) with a guy whom I dated and broke up with in Northern VA, who also knew and fooled around with a friend I later met at Virginia Tech, and then this guy moved to San Franciso, where my friend from Charlottesville was vacationing at and met at a club and had a fling with. It truly is a small world. What is also true, however, is that this friend of mine was NOT small. Heh, heh... aska bout the details ;-)

#18
19. eyemready Active Member

Joined:
May 10, 2004
Messages:
880
29
will you talk statistics with my dick in your mouth? mmmmm

#19

Joined:
May 19, 2004
Messages:
278