Age of BoB members

[dwyermw]

New pipe smoker here aged 70

 

[Old Uncle Mike]

55 but body feels 80 and mind feels like im still 30

Exactly, but I’m 66.

 

[mosin1932]

I don't want to be pedantic, but the median is not is not the average--the mean is. But including the median is a good idea, since the distribution is asymmetric. And the "outliers" need to be included, unless all you want is the average age of the old members.

"The average is the statistical summary, in one value, of a group of numbers.

There are three main types of averages:

• the mean (the sum or product of the values of a group of numbers divided by how many numbers there are in the group);
• the median (the middle value of a group of numbers);
• the mode or modus (the most common value of a group of numbers)."

I will agree that "average" has become so synonymous with "mean" in modern parlance that it might as well be the same word. Which really is a shame because even with something as straightforward as calculating the average age of a group of handsome pipe smokers, the mean isn't very accurate unless you omit some data. Without using statistical tests like standard deviation, deciding which data to omit can end up being arbitrary and subjective, or more typically it's used to make the "average" look a certain way to push a narrative, like every stat you'll hear in the news or from someone with an agenda.

In our case 30 and 32 looked like outliers but are well within two standard deviation (16.85) of the mean. If we then incorporate some probability statistics we can say with 95% certainty that every brother on here is between 25 and 92.

With Dwyer and Uncle, our new numbers are now:

Mean: 60.14
Median: 66
Standard Deviation: 15.87

 

[Eutychus]

"The average is the statistical summary, in one value, of a group of numbers.

There are three main types of averages:

• the mean (the sum or product of the values of a group of numbers divided by how many numbers there are in the group);
• the median (the middle value of a group of numbers);
• the mode or modus (the most common value of a group of numbers)."

I will agree that "average" has become so synonymous with "mean" in modern parlance that it might as well be the same word. Which really is a shame because even with something as straightforward as calculating the average age of a group of handsome pipe smokers, the mean isn't very accurate unless you omit some data. Without using statistical tests like standard deviation, deciding which data to omit can end up being arbitrary and subjective, or more typically it's used to make the "average" look a certain way to push a narrative, like every stat you'll hear in the news or from someone with an agenda.

In our case 30 and 32 looked like outliers but are well within two standard deviation (16.85) of the mean. If we then incorporate some probability statistics we can say with 95% certainty that every brother on here is between 25 and 92.

With Dwyer and Uncle, our new numbers are now:

Mean: 60.14
Median: 66
Standard Deviation: 15.87

@mosin1932, I think I would agree with all of the above with the exception of the issue of outliers. Unless there is a good reason to exclude the two young members, even if they fall beyond 2 SD, then they are members of the population we are analyzing.

I'm sure you can appreciate the vital importance of this question, given everything that depends on it. It deserves our very best thinking.

 

[fireman11]

This is an issue I will ponder deeply as I smoke my pipe later.

 

[Old Uncle Mike]

55 but body feels 80 and mind feels like im still 30

Same here but I’m 66.

 

[Balisong]

@Eutychus & @mosin1932
I only took a couple of statistics courses during my college days and I can't remember the median or mode ever referred to as averages. The average or mean of a data set was the sum of the members divided by the number of members. Spreadsheets that I've used all have an average function and I've never found a mean function. There are also functions that return the median and mode are found by algorithm. The algorithm sorts the data set. To determine the median add the first and last data points and divide by two. You can say that the result is the average of the largest and smallest data points but it is not the average of the data set, you've effectively created a new data set containing 2 members. The mode is the value the appears most frequently in the data set and is an enumeration not a calculation.

Sorry for being so winded but my second stint in college centered on Mathematics and Philosophy. After writing computer code containing many "if" statements for over a decade I wanted to find out what was true beyond Mathematics.

 

[Eutychus]

@Eutychus & @mosin1932
I only took a couple of statistics courses during my college days and I can't remember the median or mode ever referred to as averages. The average or mean of a data set was the sum of the members divided by the number of members. Spreadsheets that I've used all have an average function and I've never found a mean function. There are also functions that return the median and mode are found by algorithm. The algorithm sorts the data set. To determine the median add the first and last data points and divide by two. You can say that the result is the average of the largest and smallest data points but it is not the average of the data set, you've effectively created a new data set containing 2 members. The mode is the value the appears most frequently in the data set and is an enumeration not a calculation.

Sorry for being so winded but my second stint in college centered on Mathematics and Philosophy. After writing computer code containing many "if" statements for over a decade I wanted to find out what was true beyond Mathematics.

I was also unaware "average" could refer to anything other than mean. But it looks like it can. But I knew about median and mode. Although our subject isn't at all "vital", it's fun to put to work our old noggins (not counting the outliers).

 

[Aussiemike]

@Eutychus & @mosin1932
I only took a couple of statistics courses during my college days and I can't remember the median or mode ever referred to as averages. The average or mean of a data set was the sum of the members divided by the number of members. Spreadsheets that I've used all have an average function and I've never found a mean function. There are also functions that return the median and mode are found by algorithm. The algorithm sorts the data set. To determine the median add the first and last data points and divide by two. You can say that the result is the average of the largest and smallest data points but it is not the average of the data set, you've effectively created a new data set containing 2 members. The mode is the value the appears most frequently in the data set and is an enumeration not a calculation.

Sorry for being so winded but my second stint in college centered on Mathematics and Philosophy. After writing computer code containing many "if" statements for over a decade I wanted to find out what was true beyond Mathematics.

I left school at 15yo and struggled at maths but I put my head down in the last year and got a pass ohhh also woodwork the "passion paws" thing started early as I was **** at dovel tails but an expert in sandpaper fights I always wished I had learnt microsoft excel as I thought what an excellent tool it was seeing other people do great calculations on it

 

[Balisong]

(not counting the outliers).

Adding in the two data points and omitting the outliers smoothed out the data tests. The standard deviation dropped roughly a third to 10.37. The average (mean) is 65, the media is 67, and the mode 68. It's a good result.

@Aussiemike
I believe there is a spectrum of thought that ranges from Arts to Sciences. I believe Popeye put it something like this, "I am what I am cause that's what I am"

 

[mosin1932]

@mosin1932, I think I would agree with all of the above with the exception of the issue of outliers. Unless there is a good reason to exclude the two young members, even if they fall beyond 2 SD, then they are members of the population we are analyzing.

I'm sure you can appreciate the vital importance of this question, given everything that depends on it. It deserves our very best thinking.

I was the one saying we should include the outliers from the beginning! Lol

And I figured if there ever was a group to support some over-analysis and spirited discussion of something silly, it's right here!

 

[Timbo]

A 1975 model piping in here, quite enjoying the banter gents.

 

[Eutychus]

Adding in the two data points and omitting the outliers smoothed out the data tests. The standard deviation dropped roughly a third to 10.37. The average (mean) is 65, the media is 67, and the mode 68. It's a good result.

@Aussiemike
I believe there is a spectrum of thought that ranges from Arts to Sciences. I believe Popeye put it something like this, "I am what I am cause that's what I am"

@Balisong, I hadn't thought about it that way. If we take out two more outliers, one at each end of the distribution, we might be able to smooth it out even more, and drop that standard deviation even further.

 

[Balisong]

If we take out two more outliers, one at each end of the distribution, we might be able to smooth it out even more, and drop that standard deviation even further.

That's why I don't trust statistics from food and drug companies! BTW if we qualify the stats to be BoB members 50 or over the median will be the same as the mode at 68 and with @Timbo added in the average would be just under 68 with a SD under 8.

 

[fireman11]

That's why I don't trust statistics from food and drug companies!

Fixed it.

 

[Eutychus]

That's why I don't trust statistics from food and drug companies! BTW if we qualify the stats to be BoB members 50 or over the median will be the same as the mode at 68 and with @Timbo added in the average would be just under 68 with a SD under 8.

Since my age is 68, I recommend we remove the @Timbo outlier from BoB altogether.

 

[Balisong]

Oops, I listed @Timbo as 75 not remembering he listed his birth year! Back to the spreadsheet!

 

[Rev.Smokethrower]

Been piping for about 4 years and I'm 52 years young. Let's see if that lowers the median/mode/ average.

 

[Eutychus]

Oops, I listed @Timbo as 75 not remembering he listed his birth year! Back to the spreadsheet!

A true outlier.

 

[Balisong]

Currently using the full data set

Average
58.9375
Median
64.5
Mode
68
Standard Deviation
15.11379061