It's a shame the "being the same age" item didn't separate the data for men being older from the data for women being older (for heterosexual marriages). With society being somewhat more accepting of older men marrying younger women rather than the other way around, it would be interesting to see if marriage success agreed with that or not.
What makes for a stable marriage? Part 2
11–20 of 79 posts
Re: What makes for a stable marriage? Part 2
#12Earlier quoted context omitted.
Both of those things could be improved by marrying the right person.
survivorship bias much ;)
It's worth pointing out that in the end, all the statistics in the world don't matter to the specific case that you are facing.
This isn't a trivial rhetorical flourish; this is actually a profoundly important truth about the world and statistics. You aren't dating/marrying a population... you're dating/marrying a specific member out of that population, and the direction of causality is that the population has the statistical properties it does due to its individual members. Population statistics do not casually drive the attributes of its members.
Re: What makes for a stable marriage? Part 2
#13I have great advice howto improve your health and productivity tenfold: DO NOT GET MARRIED! EVER! :-)
My first wife really didn't provide any benefit and cost a lot, but the second one has been really beneficial for years. Always someone to come home to who helps with the bills, cooking, laundry, not having to waste time going out to clubs or using Tinder because I'm well taken care of at home, etc.. She even got an investor to say yes to funding a startup me and friends are doing recently by talking the investor's native language.
Re: What makes for a stable marriage? Part 2
#14These are neat comparisons, in both part 1 and part 2 (especially the strikingly opposite effects of big weddings vs. expensive weddings near the end of part 1). But boy, what I wouldn't give to see error bars on those graphs!
All of the differences highlighted are statistically significant (p The downside is that the paper only presents probabilities relative to a reference point, but doesn't give raw probabilities.
Even, say, the difference between "never attend church" and "sometimes attend church" (which evidently makes divorce 10% more likely)? Or how about the difference between household incomes of $85k and $110k (bars differ by 3% out of about 40%)?
But I'm glad to know that these are all results with low p-values, anyway: that adds some real confidence to these results. (Though I ought to ask: how many of these significant p-values were between, say, 0.03 and 0.05? How many different correlations were originally considered in the study before they identified these significant ones?)
Re: What makes for a stable marriage? Part 2
#15#hashtagsarestupid
Re: What makes for a stable marriage? Part 2
#16Earlier quoted context omitted.
All of the differences highlighted are statistically significant (p The downside is that the paper only presents probabilities relative to a reference point, but doesn't give raw probabilities.
Even, say, the difference between "never attend church" and "sometimes attend church" (which evidently makes divorce 10% more likely)? Or how about the difference between household incomes of $85k and $110k (bars differ by 3% out of about 40%)? But I'm glad to know that these are all results with low p-values, anyway: that adds some real confidence to these results. (Though I ought to ask: how many of these significa…
Check out the paper (Table 3) for significance statements: http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2501480
Some of the trends in Part 1 are not statistically significant (e.g., "never attend church" vs. "sometimes attend church"), but I presented them regardless because they have a pretty clear trend. I believe p-values are only presented in comparison to the reference point.
Re: What makes for a stable marriage? Part 2
#17"On the bright side, the longer your marriage lasts, the less likely you are to divorce."
Emmm.. Not too surprising, is it? Divorces kind of tend to terminate marriages early.
Re: What makes for a stable marriage? Part 2
#18I have great advice howto improve your health and productivity tenfold: DO NOT GET MARRIED! EVER! :-)
* Married men are more productive (Or at least earn more): http://econ.ucdenver.edu/public/laura/Class/korenmanneumark.... * married men live longer : http://www.health.harvard.edu/newsletters/Harvard_Mens_Healt...
I didn't read these but the headlines don't surprise me at all. Men who are most productive in their jobs possess characteristics that would seem to make them better "catches" and are more likely to be married. Likewise, men who will live longer are often in better shape and more attractive making them more likely to get married. Nothing about "being married" causes either of these things in my opinion.
Re: What makes for a stable marriage? Part 2
#19"It’s particularly interesting to note that the education difference matters more for women than men: Women are 50% more likely to end up divorced when there is an education difference versus men at only 32% more likely."
For heterosexual marriages, wouldn't the percentages be the same? If a given number of divorces will always produce a equal number of male and female divorcees.
Or is the author saying that the direction of difference is important? Eg, a woman is more likely to divorce her husband if she is more highly educated than him, but not vice versa.
Is there some missing information here, or am I being dense?
Re: What makes for a stable marriage? Part 2
#20"It’s particularly interesting to note that the education difference matters more for women than men: Women are 50% more likely to end up divorced when there is an education difference versus men at only 32% more likely." For heterosexual marriages, wouldn't the percentages be the same? If a given number of divorces will always produce a equal number of male and female divorcees. Or is the author saying that the dire…
The author addresses this in the comments. He states that there are likely more divorces for one gender than the other in his data set. Which implies to me that individuals, rather than couples, are surveyed about their marriages/divorces.
So if he surveyed 10 women and 10 men, those 10 women weren't married to those 10 men.
If that isn't the case, then I'm also not sure how that could be the case given that he states all marriages examined were heterosexual in nature.