Author Topic: Overheard at Work: The Anti-Antimustachian Edition  (Read 271783 times)

1967mama

  • Handlebar Stache
  • *****
  • Posts: 2099
  • Age: 50
  • Location: Canada
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #150 on: November 25, 2014, 02:17:07 AM »
I've been a SAHM for over 20 years now, so I guess I retired really early ... haha!

One thing I do recall from my working days was how everyone in the staffroom brought either leftovers or homemade sandwiches for lunch. Someone buying their lunch would have been a real oddity in my workplace back in 1988!

Awesome thread -- just read it from start to finish!

RetiredAt63

  • Walrus Stache
  • *******
  • Posts: 5134
  • Location: Eastern Ontario, Canada
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #151 on: November 27, 2014, 11:54:42 AM »
A bunch of us (mostly retired) were sitting around at coffee this morning, and we got to talking vacations.  I am in a mustachian hotbed.  They all pay their credit cards off in full every month, no-one pays interest.  They all have either a reward miles or cash-back card or both.  Some (not all) of them are visiting "home" in Europe (dual citizens), so their travel is not cheap, but with the card rewards they are not spending much.  They book last minute cruises (cheap).  It was wonderful.

(And to refute some of the guys on this forum who have posited that women are "spendypants", these were all women.  Mind you, their spouses are on board with this sensible spending.)

MBot

  • Bristles
  • ***
  • Posts: 363
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #152 on: November 27, 2014, 08:41:32 PM »
Ground beef was on sale today so we stocked up with 20 pounds. Divided it into ziploc half pound portions, flatten and freeze them .

Husband just talked to a friend online and she said "oh yeah, we saw that sale and stocked up too!" Apparently she freezes portions the same way!

skunkfunk

  • Handlebar Stache
  • *****
  • Posts: 1059
  • Age: 30
  • Location: Oklahoma City
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #153 on: November 27, 2014, 10:09:57 PM »

(And to refute some of the guys on this forum who have posited that women are "spendypants", these were all women.  Mind you, their spouses are on board with this sensible spending.)

Are you sure? I think mustachian women might actually be somewhat more common than men. All anecdotally derived statements wrong or your money back, of course.

GrayGhost

  • Bristles
  • ***
  • Posts: 299
  • Location: USA
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #154 on: November 27, 2014, 10:18:33 PM »
I assume that everyone I come across online is a man, but in fairness, I know there are definitely a few mustachian ladies out there. It's just a different set of temptations for them than there are for men. They're told that they must spend money on clothing and makeup, we're told we must spend money on sportscars and I don't know/care what else.
Student of Mustachianism since 2013

Rural

  • Magnum Stache
  • ******
  • Posts: 3971
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #155 on: November 28, 2014, 02:41:23 AM »
I assume that everyone I come across online is a man, but in fairness, I know there are definitely a few mustachian ladies out there. It's just a different set of temptations for them than there are for men. They're told that they must spend money on clothing and makeup, we're told we must spend money on sportscars and I don't know/care what else.


This forum is majority female:


http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/

RetiredAt63

  • Walrus Stache
  • *******
  • Posts: 5134
  • Location: Eastern Ontario, Canada
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #156 on: November 28, 2014, 06:07:07 AM »
Sorry in advance, I am going to totally derail this mini-thread.

Lots of us probably have gender neutral names - I do.

So GrayGhost, why do you assume everyone you come across online is a man?  There are lots of women (clearly identified as such) posting on the journal group.

When I am on Ravelry I assume the odds are high (but definitely not 100%) that a gender-neutral name is a female poster, but there are men there too.  However it is a site about an activity that tends to be engaged in more by women.  Finance is gender neutral.  0r to be more realistic, since on average women live longer than men, we should be more interested in our financial futures, not less, than men are.  So should I assume that most people on here, not clearly identified as men, are women?  Especially since my gut feeling is that women are more likely to be ambiguous about gender identificaiton on an open forum?

I assume that everyone I come across online is a man, but in fairness, I know there are definitely a few mustachian ladies out there. It's just a different set of temptations for them than there are for men. They're told that they must spend money on clothing and makeup, we're told we must spend money on sportscars and I don't know/care what else.


This forum is majority female:


http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/

DeepEllumStache

  • Handlebar Stache
  • *****
  • Posts: 2160
  • Age: 34
  • Location: Dallas
  • Formerly of the Deep Ellum Variety
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #157 on: November 28, 2014, 08:22:55 AM »
On Wednesday, I contacted our 401k plan administrator and found out that the mega Backdoor Roth is a valid option at my company. My coworker overheard, leading to an in depth discussion on how this changed the game since he and his wife also max out their 401ks. He got excited when he read the Mad FIentist article and was going to bring the article home to discuss strategy with his wife.

He also talked about how he was excited that his 8 year old son could get a job when he hit 16 just so he could help him start a Roth.
And a journal because I #REF occasionally

LennStar

  • Pencil Stache
  • ****
  • Posts: 780
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #158 on: November 28, 2014, 10:20:55 AM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Rural

  • Magnum Stache
  • ******
  • Posts: 3971
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #159 on: November 28, 2014, 10:37:21 AM »


On the topic of assumptions: Most forums have male dominance. Males do more internet, too.


Data?

Gin1984

  • Magnum Stache
  • ******
  • Posts: 4099
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #160 on: November 28, 2014, 10:44:30 AM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.
Actually for a survey that actually may hit statistical significance. But you'd have to account for self-selection and I don't have the stats on the difference between men and women in filling out online surveys.

Albert

  • Handlebar Stache
  • *****
  • Posts: 1254
  • Location: Switzerland
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #161 on: November 30, 2014, 02:43:17 PM »
I spoke few days ago with one of the trainees (a student basically) we have at work about the expense of living here and was really impressed that he manages to live just fine on about 1,000$ a month. Just for a perspective the equivalent would be living in NYC or San Francisco on 20k. May apartment alone costs 1,600….

FoundPeace

  • Stubble
  • **
  • Posts: 171
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #162 on: December 01, 2014, 04:02:52 PM »
A coworker from a different location told me today that he plans to retire between 30 and 35. He hasn't exactly figured out how to do it yet, but he is saving a good deal of his pay check to do so. I excitedly told him that I was doing this too. I then told him about index funds and that I was currently doing some tax reduction planning. He said that he would look at MMM and look into index funds.

I haven't ever gotten along with the guy, but maybe things will change now.

Alenzia

  • 5 O'Clock Shadow
  • *
  • Posts: 70
  • Age: 30
  • Location: Colorado
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #163 on: December 16, 2014, 12:24:23 PM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

dios.del.sol

  • Stubble
  • **
  • Posts: 131
  • Location: Los Angeles
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #164 on: December 16, 2014, 01:25:24 PM »
Running a quick Chi square test...
Someone just got nerd sniped! That's never happened to me. ;)

skunkfunk

  • Handlebar Stache
  • *****
  • Posts: 1059
  • Age: 30
  • Location: Oklahoma City
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #165 on: December 16, 2014, 03:04:52 PM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.

Gin1984

  • Magnum Stache
  • ******
  • Posts: 4099
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #166 on: December 16, 2014, 03:59:23 PM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.
.064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know.

skunkfunk

  • Handlebar Stache
  • *****
  • Posts: 1059
  • Age: 30
  • Location: Oklahoma City
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #167 on: December 16, 2014, 04:27:22 PM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.
.064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know.

.05 is a pretty arbitrary cutoff. I think in this instance we don't need to have any more confidence to call the race, assuming of course like you say there isn't any bias we are missing. It's not like we actually need to be right, anyway. If anything of significance was riding on this I would call for more testing, but meh.

Gin1984

  • Magnum Stache
  • ******
  • Posts: 4099
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #168 on: December 16, 2014, 04:44:00 PM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.
.064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know.

.05 is a pretty arbitrary cutoff. I think in this instance we don't need to have any more confidence to call the race, assuming of course like you say there isn't any bias we are missing. It's not like we actually need to be right, anyway. If anything of significance was riding on this I would call for more testing, but meh.
Yes, it is but it is a cut off determined by researchers in human research for many years.  Unless we get there I am going to stick with, we don't know.

skunkfunk

  • Handlebar Stache
  • *****
  • Posts: 1059
  • Age: 30
  • Location: Oklahoma City
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #169 on: December 16, 2014, 04:46:59 PM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.
.064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know.

.05 is a pretty arbitrary cutoff. I think in this instance we don't need to have any more confidence to call the race, assuming of course like you say there isn't any bias we are missing. It's not like we actually need to be right, anyway. If anything of significance was riding on this I would call for more testing, but meh.
Yes, it is but it is a cut off determined by researchers in human research for many years.  Unless we get there I am going to stick with, we don't know.

93.6% chance we're right isn't good enough? The usual cutoff of. 05 is more when you can start to mention it in a paper, not that it didn't tell you which direction you should be looking.

johnny847

  • Magnum Stache
  • ******
  • Posts: 3150
    • My Blog
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #170 on: December 16, 2014, 06:24:01 PM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.
.064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know.

.05 is a pretty arbitrary cutoff. I think in this instance we don't need to have any more confidence to call the race, assuming of course like you say there isn't any bias we are missing. It's not like we actually need to be right, anyway. If anything of significance was riding on this I would call for more testing, but meh.
Yes, it is but it is a cut off determined by researchers in human research for many years.  Unless we get there I am going to stick with, we don't know.

93.6% chance we're right isn't good enough? The usual cutoff of. 05 is more when you can start to mention it in a paper, not that it didn't tell you which direction you should be looking.
This is not what the p value means. From Wikipedia (if you don't trust Wikipedia, I'm sure I could find a better source with better searching).
Quote
There are several common misunderstandings about p-values.[15][16]

    The p-value is not the probability that the null hypothesis is true, nor is it the probability that the alternative hypothesis is false – it is not connected to either of these. In fact, frequentist statistics does not, and cannot, attach probabilities to hypotheses. Comparison of Bayesian and classical approaches shows that a p-value can be very close to zero while the posterior probability of the null is very close to unity (if there is no alternative hypothesis with a large enough a priori probability and which would explain the results more easily). This is Lindley's paradox. But there are also a priori probability distributions where the posterior probability and the p-value have similar or equal values.[17]
    The p-value is not the probability that a finding is "merely a fluke." Calculating the p-value is based on the assumption that every finding is a fluke, that is, the product of chance alone. Thus, the probability that the result is due to chance is in fact unity. The phrase "the results are due to chance" is used to mean that the null hypothesis is probably correct. However, that is merely a restatement of the inverse probability fallacy, since the p-value cannot be used to figure out the probability of a hypothesis being true.
    The p-value is not the probability of falsely rejecting the null hypothesis. This error is a version of the so-called prosecutor's fallacy.
    The p-value is not the probability that replicating the experiment would yield the same conclusion. Quantifying the replicability of an experiment was attempted through the concept of p-rep.
    The significance level, such as 0.05, is not determined by the p-value. Rather, the significance level is decided by the person conducting the experiment (with the value 0.05 widely used by the scientific community) before the data are viewed, and is compared against the calculated p-value after the test has been performed. (However, reporting a p-value is more useful than simply saying that the results were or were not significant at a given level, and allows readers to decide for themselves whether to consider the results significant.)
    The p-value does not indicate the size or importance of the observed effect. The two do vary together however–the larger the effect, the smaller sample size will be required to get a significant p-value (see effect size).

domustachesgrowinhouston

  • Stubble
  • **
  • Posts: 109
  • Location: Colorado Springs
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #171 on: December 16, 2014, 07:49:58 PM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.
.064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know.

.05 is a pretty arbitrary cutoff. I think in this instance we don't need to have any more confidence to call the race, assuming of course like you say there isn't any bias we are missing. It's not like we actually need to be right, anyway. If anything of significance was riding on this I would call for more testing, but meh.
Yes, it is but it is a cut off determined by researchers in human research for many years.  Unless we get there I am going to stick with, we don't know.

93.6% chance we're right isn't good enough? The usual cutoff of. 05 is more when you can start to mention it in a paper, not that it didn't tell you which direction you should be looking.
This is not what the p value means. From Wikipedia (if you don't trust Wikipedia, I'm sure I could find a better source with better searching).
Quote
There are several common misunderstandings about p-values.[15][16]

    The p-value is not the probability that the null hypothesis is true, nor is it the probability that the alternative hypothesis is false – it is not connected to either of these. In fact, frequentist statistics does not, and cannot, attach probabilities to hypotheses. Comparison of Bayesian and classical approaches shows that a p-value can be very close to zero while the posterior probability of the null is very close to unity (if there is no alternative hypothesis with a large enough a priori probability and which would explain the results more easily). This is Lindley's paradox. But there are also a priori probability distributions where the posterior probability and the p-value have similar or equal values.[17]
    The p-value is not the probability that a finding is "merely a fluke." Calculating the p-value is based on the assumption that every finding is a fluke, that is, the product of chance alone. Thus, the probability that the result is due to chance is in fact unity. The phrase "the results are due to chance" is used to mean that the null hypothesis is probably correct. However, that is merely a restatement of the inverse probability fallacy, since the p-value cannot be used to figure out the probability of a hypothesis being true.
    The p-value is not the probability of falsely rejecting the null hypothesis. This error is a version of the so-called prosecutor's fallacy.
    The p-value is not the probability that replicating the experiment would yield the same conclusion. Quantifying the replicability of an experiment was attempted through the concept of p-rep.
    The significance level, such as 0.05, is not determined by the p-value. Rather, the significance level is decided by the person conducting the experiment (with the value 0.05 widely used by the scientific community) before the data are viewed, and is compared against the calculated p-value after the test has been performed. (However, reporting a p-value is more useful than simply saying that the results were or were not significant at a given level, and allows readers to decide for themselves whether to consider the results significant.)
    The p-value does not indicate the size or importance of the observed effect. The two do vary together however–the larger the effect, the smaller sample size will be required to get a significant p-value (see effect size).

What a beautiful example of alliteration.

LennStar

  • Pencil Stache
  • ****
  • Posts: 780
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #172 on: December 17, 2014, 03:35:50 AM »
Running a quick Chi square test...
Someone just got nerd sniped! That's never happened to me. ;)
hmm...
3pt for skunkfunk and Gin1984 each
1pt each for WP quoter and Alliteration?
=8PT
not bad for one post.

Alenzia

  • 5 O'Clock Shadow
  • *
  • Posts: 70
  • Age: 30
  • Location: Colorado
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #173 on: December 17, 2014, 09:58:31 AM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.
.064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know.

.05 is a pretty arbitrary cutoff. I think in this instance we don't need to have any more confidence to call the race, assuming of course like you say there isn't any bias we are missing. It's not like we actually need to be right, anyway. If anything of significance was riding on this I would call for more testing, but meh.
Yes, it is but it is a cut off determined by researchers in human research for many years.  Unless we get there I am going to stick with, we don't know.

93.6% chance we're right isn't good enough? The usual cutoff of. 05 is more when you can start to mention it in a paper, not that it didn't tell you which direction you should be looking.

Given that the initial hypothesis was that there are significantly more men than women on the forum, which later was argued against using the survey data (and stating that there are more women than men), I'd say that the survey results do disprove that there are more men than women on the forum at the very least. Yay surveys!

Also, it made me glad to see that there are many other women on this forum - yes, there are women who are anti-mustachian with additional expenses like makeup, jewelry, and clothes, but there are many who aren't that way!

Gin1984

  • Magnum Stache
  • ******
  • Posts: 4099
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #174 on: December 17, 2014, 10:52:49 AM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.
.064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know.

.05 is a pretty arbitrary cutoff. I think in this instance we don't need to have any more confidence to call the race, assuming of course like you say there isn't any bias we are missing. It's not like we actually need to be right, anyway. If anything of significance was riding on this I would call for more testing, but meh.
Yes, it is but it is a cut off determined by researchers in human research for many years.  Unless we get there I am going to stick with, we don't know.

93.6% chance we're right isn't good enough? The usual cutoff of. 05 is more when you can start to mention it in a paper, not that it didn't tell you which direction you should be looking.

Given that the initial hypothesis was that there are significantly more men than women on the forum, which later was argued against using the survey data (and stating that there are more women than men), I'd say that the survey results do disprove that there are more men than women on the forum at the very least. Yay surveys!

Also, it made me glad to see that there are many other women on this forum - yes, there are women who are anti-mustachian with additional expenses like makeup, jewelry, and clothes, but there are many who aren't that way!
I like makeup (expensive kind), jewelry and clothes.  However, I like time more than makeup so only use it when dressing up/presenting and because it is a good quality, it lasts.  I get giving most of my jewelry and what I buy is normally used.  And clothes, well that is used or gifted normally as well.  Just because people like those items does not mean they cannot be mustachian. 

Alenzia

  • 5 O'Clock Shadow
  • *
  • Posts: 70
  • Age: 30
  • Location: Colorado
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #175 on: December 17, 2014, 10:57:19 AM »
That's true, Gin1984, I'm sorry I made the assumption.

intirb

  • 5 O'Clock Shadow
  • *
  • Posts: 79
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #176 on: December 17, 2014, 01:48:22 PM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

Or we could take a Bayesian approach to the problem.  Let's say there are two people:  Blue believes that most internet forums are generally evenly distributed, and Red believes that forums are typically about 70% male, with <10% of forums having 50% or more women.  These are just beliefs that two people have accumulated through experience, and without any other information, it makes sense for Red and Blue to make similar assumptions about this forum.  Now we've got some data, through the survey, and Bayes' rule tells each person how to update their beliefs about this forum with the given data.



For both Red and Blue, the additional data now lead them both to believe that there are likely more women than men in this forum.  The outcomes are slightly different, since they had different starting beliefs, but 355 people is a lot of people, so the data are definitely dominating the outcome.  Maybe someone can help me add in assumptions about women being more likely to answer the poll.


This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

There's a famous joke about this..  If you don't believe a small random sample can work, then when you need to get bloodwork done, tell your doctor to take it all.  Statistics were designed precisely to help us draw inferences from small samples, and actually, 2% sampling is a huge amount compared to a lot of work being done all the time.

Something sort of on topic, because I realize I've veered way off course: today we had a going away party for a coworker during lunch, and we celebrated by everyone bringing their packed lunch and eating together in the break room.  The departing coworker brought cake.

viper155

  • Bristles
  • ***
  • Posts: 258
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #177 on: December 22, 2014, 11:27:56 AM »
I love when my work buddies all sit around and brag about their iPhones. I casually break out my 8 year old flip phone and let them make fun of it then gently tell them I own the greatest Apple product of them all......their stock. Then thank them for their "donations".

Less

  • Stubble
  • **
  • Posts: 177
  • Age: 30
  • Location: New Zealand
    • Journal
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #178 on: December 22, 2014, 12:07:46 PM »
I am sure this has done the rounds, but for those of you who missed it:
https://kyleconroy.com/apple-stock

Elderwood17

  • Pencil Stache
  • ****
  • Posts: 504
  • Location: Western North Carolina
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #179 on: December 22, 2014, 12:10:26 PM »
I love when my work buddies all sit around and brag about their iPhones. I casually break out my 8 year old flip phone and let them make fun of it then gently tell them I own the greatest Apple product of them all......their stock. Then thank them for their "donations".
I like it!  May have to borrow that line.

golden1

  • Handlebar Stache
  • *****
  • Posts: 1267
  • Location: MA
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #180 on: December 22, 2014, 12:15:56 PM »
The co worker who trained me is the most mustachian person I know.  He eats rice and beans most days for work and never eats out.  He takes the train to work, doesn't even own a car.  He paid off his mortgage on his condo years ago.  He only drinks water, never any coffee or anything like that.  He basically sends his salary home to his family in Venezuela and saves the rest.   He always inspires me to be thankful for what I have.

viper155

  • Bristles
  • ***
  • Posts: 258
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #181 on: December 23, 2014, 08:31:05 AM »
Colleague's status on facebook:
Our society is so obsessed with STUFF that there is an entire store built around only selling containers to put all of our STUFF in, and it makes enough money to survive in Manhattan.

Could be that in Manhattan it's not an abundance of stuff but a lack of square footage to keep it in.

mtn

  • Handlebar Stache
  • *****
  • Posts: 1127
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #182 on: December 23, 2014, 08:58:51 AM »
For the most part, the people here are pretty mustachian. I believe that my manager is actually on this site, or has been in the past. Another guy rents an apartment with a roommate, just bought a new Honda Accord that I expect he'll keep for 15 years. Another walks to work, another makes her own laundry detergent. Obviously everyone has non-mustachian aspects to their lives as well, but I have very few anti-mustachian stories from here. Most of the ones I do have would still be considered financially sound--they'd probably fit in at the Boglehead forums.

I suspect I'm the only one putting away over 40% of my paycheck, but I wouldn't be surprised to find out that I'm not.

Cinder

  • Bristles
  • ***
  • Posts: 474
  • Location: Central PA
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #183 on: December 24, 2014, 07:32:59 PM »
It's not at work, but it's at home while on vacation from work, so it counts ;)

While at my family Christmas gathering, my aunts and uncles (7 including my father) were reliving their childhood.    They were talking about how as members of a large family while times were tough, they each only got ONE present each Christmas.  In lieu of actual toys, they would cut out the people from the Sears-Roebuck catalogue. They would cut out clothes for the people, they would cut out a picture of a washing-machine to 'wash their clothes'.  They would cut out tires from cars, put them on cardboard and stick them on the side of shoe boxes.   You could tell by the gleam in their eye that they probably had just as much fun with cutouts from the catalogue  as they would have from real toys.


babysnowbyrd

  • Stubble
  • **
  • Posts: 198
  • Age: 30
    • My Journal
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #184 on: December 24, 2014, 10:46:54 PM »
Surprised to find I'm enjoying this thread even more than the other one!

Agreed! Unfortunately my stories will belong in the other thread.

Hey It's Moe

  • Pencil Stache
  • ****
  • Posts: 699
    • Moe's Journal
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #185 on: December 24, 2014, 11:11:26 PM »
CW (age 50-ish): "I was talking to my friend and he's taking a loan from his 401(k).  Guess how much he has?  Only 7,000.  What an idiot."
Me (~1 year out of college): "Holy !@#$%^&*, *I* have more than that."
CW: "Yeah, I think my cat has more than that."

That cat is part of the 1%.

Hey It's Moe

  • Pencil Stache
  • ****
  • Posts: 699
    • Moe's Journal
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #186 on: December 24, 2014, 11:39:46 PM »
http://littlemissdorkette.tumblr.com/post/3118512524/date-a-girl-who-reads-by-rosemarie-urquico

Reading this moved me far more than I expected. Thank you SO much for sharing - you made my day (at 2am, no less.)

Hey It's Moe

  • Pencil Stache
  • ****
  • Posts: 699
    • Moe's Journal
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #187 on: December 24, 2014, 11:43:49 PM »
Colleague's status on facebook:
Our society is so obsessed with STUFF that there is an entire store built around only selling containers to put all of our STUFF in, and it makes enough money to survive in Manhattan.

LOL

LennStar

  • Pencil Stache
  • ****
  • Posts: 780
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #188 on: December 25, 2014, 01:47:44 AM »
http://littlemissdorkette.tumblr.com/post/3118512524/date-a-girl-who-reads-by-rosemarie-urquico

Reading this moved me far more than I expected. Thank you SO much for sharing - you made my day (at 2am, no less.)
Pleased to hear that ^^
It moved me a lot, too.
If you like it, perhaps you will also like the "Book Girl" (bungaku shoujo) series. I just got the book 2-8 for christmas after seeing the film and reading the first book. I just adore Tohko (the book girl, who... no, thats a secret :D).

Hey It's Moe

  • Pencil Stache
  • ****
  • Posts: 699
    • Moe's Journal
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #189 on: December 25, 2014, 06:11:22 AM »
They said if we would max out our 401k (and also get the *50%* match)

HOLY COW.

Hey It's Moe

  • Pencil Stache
  • ****
  • Posts: 699
    • Moe's Journal
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #190 on: December 25, 2014, 06:37:37 AM »
I assume that everyone I come across online is a man, but in fairness, I know there are definitely a few mustachian ladies out there. It's just a different set of temptations for them than there are for men. They're told that they must spend money on clothing and makeup, we're told we must spend money on sportscars and I don't know/care what else.


This forum is majority female:


http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/

Or... do women answer surveys more often then men?

Hey It's Moe

  • Pencil Stache
  • ****
  • Posts: 699
    • Moe's Journal
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #191 on: December 25, 2014, 06:44:35 AM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.
.064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know.

In the interest of stopping this discussion... here is the alexa data on MMM users. (http://www.alexa.com/siteinfo/mrmoneymustache.com+)
« Last Edit: December 25, 2014, 06:50:42 AM by moe_rants »

mm1970

  • Magnum Stache
  • ******
  • Posts: 4091
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #192 on: December 25, 2014, 09:21:20 AM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.
.064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know.

In the interest of stopping this discussion... here is the alexa data on MMM users. (http://www.alexa.com/siteinfo/mrmoneymustache.com+)
That was interesting.

I'm no statistician (and my grad school stats class was almost 2 decades ago), but in my engineering job, if I get 0.1, we consider it a very strong suggestion of a correlation.

skunkfunk

  • Handlebar Stache
  • *****
  • Posts: 1059
  • Age: 30
  • Location: Oklahoma City
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #193 on: December 26, 2014, 09:19:02 AM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.
.064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know.

In the interest of stopping this discussion... here is the alexa data on MMM users. (http://www.alexa.com/siteinfo/mrmoneymustache.com+)
That was interesting.

I'm no statistician (and my grad school stats class was almost 2 decades ago), but in my engineering job, if I get 0.1, we consider it a very strong suggestion of a correlation.

Agreed!

Gin1984

  • Magnum Stache
  • ******
  • Posts: 4099
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #194 on: December 26, 2014, 10:41:11 AM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.
.064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know.

In the interest of stopping this discussion... here is the alexa data on MMM users. (http://www.alexa.com/siteinfo/mrmoneymustache.com+)
That was interesting.

I'm no statistician (and my grad school stats class was almost 2 decades ago), but in my engineering job, if I get 0.1, we consider it a very strong suggestion of a correlation.
P=.1?  Really?  As someone whose undergrad had a concentration in stats, that scares me.  We teach freshman year stats students that significance is .05 or less (for some fields even .01).  I am in research and if someone even did a poster with .1, I'd be rolling my eyes.  What kind of engineering do you do? 

skunkfunk

  • Handlebar Stache
  • *****
  • Posts: 1059
  • Age: 30
  • Location: Oklahoma City
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #195 on: December 26, 2014, 10:43:23 AM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.
.064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know.

In the interest of stopping this discussion... here is the alexa data on MMM users. (http://www.alexa.com/siteinfo/mrmoneymustache.com+)
That was interesting.

I'm no statistician (and my grad school stats class was almost 2 decades ago), but in my engineering job, if I get 0.1, we consider it a very strong suggestion of a correlation.
P=.1?  Really?  As someone whose undergrad had a concentration in stats, that scares me.  We teach freshman year stats students that significance is .05 or less (for some fields even .01).  I am in research and if someone even did a poster with .1, I'd be rolling my eyes.  What kind of engineering do you do?

You wouldn't take this as a hint that you might be looking in the right direction? Really? "Guys, P was only .1, we have nothing here. Scrap it."

I wouldn't put it in a paper, but with a limited sample, it's a nice clue.

LennStar

  • Pencil Stache
  • ****
  • Posts: 780
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #196 on: December 26, 2014, 10:45:20 AM »
P=.1?  Really?  As someone whose undergrad had a concentration in stats, that scares me.  We teach freshman year stats students that significance is .05 or less (for some fields even .01).  I am in research and if someone even did a poster with .1, I'd be rolling my eyes.  What kind of engineering do you do?
from my experience either Deutsche Bahn Wettervorhersage or something with terrorism.

Gin1984

  • Magnum Stache
  • ******
  • Posts: 4099
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #197 on: December 26, 2014, 10:48:43 AM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.
.064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know.

In the interest of stopping this discussion... here is the alexa data on MMM users. (http://www.alexa.com/siteinfo/mrmoneymustache.com+)
That was interesting.

I'm no statistician (and my grad school stats class was almost 2 decades ago), but in my engineering job, if I get 0.1, we consider it a very strong suggestion of a correlation.
P=.1?  Really?  As someone whose undergrad had a concentration in stats, that scares me.  We teach freshman year stats students that significance is .05 or less (for some fields even .01).  I am in research and if someone even did a poster with .1, I'd be rolling my eyes.  What kind of engineering do you do?

You wouldn't take this as a hint that you might be looking in the right direction? Really? "Guys, P was only .1, we have nothing here. Scrap it."

I wouldn't put it in a paper, but with a limited sample, it's a nice clue.
As I said ".064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know."   Given that the sample size is large enough, unless there is data to suggest that one gender does online surveys more than the other, there is nothing more to be done.  It is not like the sample size is ten or something. 

jba302

  • Pencil Stache
  • ****
  • Posts: 624
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #198 on: December 26, 2014, 11:58:16 AM »

Miamoo

  • Stubble
  • **
  • Posts: 238
  • Location: Somewhere near Chicago
Re: Overheard at Work: The Anti-Antimustachian Edition
« Reply #199 on: January 01, 2015, 09:41:08 AM »

This forum is majority female:
http://forum.mrmoneymustache.com/welcome-to-the-forum/what-gender-are-you/
So, from 355 votes (and I think males vote less on that) you say that the majority of of 14682 total members is male?
Get a statistics class please ;)
(On that a sidenote: NEVER trust a poll where you dont know the excact question and how they did it. Depeding on the wording of the question alone you can get 91% for and 92% against something.)

On the topic of assumptions: Most forums have male dominance. Males do more internet, too.

Running a quick Chi square test with an assumed 50/50 distribution, we get a two-tailed P=0.064, which is barely not enough to reject the null hypothesis that there are as many men as women on this forum (P>0.05). A bigger N actually may have pushed it over to prove that there are more women than men here.

It of course does not assume any selection bias, but I wouldn't be too concerned about the phrasing of a question of gender, since it's not an ambiguous question (as opposed to "are you for or against" type questions). I would not assume that most people on this forum are men.

.064 hints very, very strongly, more strongly than other stuff that has been acted upon before.
.064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know.

In the interest of stopping this discussion... here is the alexa data on MMM users. (http://www.alexa.com/siteinfo/mrmoneymustache.com+)
That was interesting.

I'm no statistician (and my grad school stats class was almost 2 decades ago), but in my engineering job, if I get 0.1, we consider it a very strong suggestion of a correlation.
P=.1?  Really?  As someone whose undergrad had a concentration in stats, that scares me.  We teach freshman year stats students that significance is .05 or less (for some fields even .01).  I am in research and if someone even did a poster with .1, I'd be rolling my eyes.  What kind of engineering do you do?

You wouldn't take this as a hint that you might be looking in the right direction? Really? "Guys, P was only .1, we have nothing here. Scrap it."

I wouldn't put it in a paper, but with a limited sample, it's a nice clue.
As I said ".064 is not statistically significant.  All it hints is that we may be able to get significance if we increase the N large enough.  However, for a survey over 300 is normally enough unless their is bias, which I don't know."   Given that the sample size is large enough, unless there is data to suggest that one gender does online surveys more than the other, there is nothing more to be done.  It is not like the sample size is ten or something.

I have a headache now.