I didn't look at the raw data, but it also seems like some of the info might be inherently linked. Eloping might imply you don't regularly attend church, or if you do that you're marrying outside the church consent. Regularly attending church can bring with it a relatively stable set of defaults to invite to a wedding. A large attendee list also might imply affluence, or having taken longer to plan the wedding, implying a longer pre-marriage relationship. All just flippant conjecture, of course, but interesting.
I wonder if there's anything in the data you could use as a sort of halfway proxy for whatever you'd consider a 'happy' or contented relationship.
I grew up in a church environment as well, and I saw my share of marriages held together by social pressure, but I also wonder if some of the other marriages are better because a lot of people I knew very much had the idea that "this is forever, so I don't even have to think about it anymore." It wasn't even a point of consideration anymore. I wonder if that can relieve some level of psychological stress in a marriage that's not absolute Perfect, but pretty decent, instead of wondering if you missed some distorted version of "the one". (again more conjecture)
They have a very large variable space (one variable per question) and they want to reduce that to the ones that are actually interesting. Hopefully they did some sort of dimensionality reduction to find the important variables, and I expect a lot of those new dimensions were comprised of many variables, for example, wealth and money spent on wedding are probably correlated.
Social supports smooth out money problems, health problems, and relationship problems. Money+health problems are the number one cause of divorce in America (that is, money discussions are the number one marriage stressor in the US, and health problems are the number one cause of bankruptcy in the US). If your parents/church/friends/cousins can help out with a loan/childcare/outright monetary gifts when certain economic or health sh&t goes down, your marriage is more likely to survive. That's not even counting emotional support and feelings-conversations.
I think that it's not a problem of a specific religion. Most religion has peaceful periods but 300 years later the "same" religion has a violent period and 300 year later the "same" religion is peaceful again, ...
And sometimes, some members of the same church are peaceful and some are violent. It's more complicated.
(Obviously, your point is important in a larger context. :)
I think a big thing that commitment devices (religion, family ...) help with is that when the going gets touch for a little while, you stay together, which is usually good in the long run.
If your marriage sucks for several years, or if there's abuse, then breaking it may be OK; but many of the issues you discard would also signal people not committed, and marriages breaking because they suck for a couple of months.
It depends on what you think is the purpose of marriage. The traditional view you're questioning is that marriage is a very serious contract that is never to be broken (usually with a few exceptions, like infidelity or abuse). I suspect this view is historically an economic device for raising children: the woman raises children while the man provides for the family (please note, I'm making no normative argument for these roles). Monogamy is obviously historically useful for ensuring paternity, and there's obvious selective pressure for that norm to arise (although I've seen studies claiming that humans have always tended to practice punctuated monogamy).
These days, that view of marriage is less vital in the Western world (at least the economic part), but it still has a lot of cultural momentum. Aside from that, the only modern purpose of official marriage is legal benefits: taxes, wills, medical discretion, child custody, etc. Apart from those, I see little difference in a "marriage" and simple long-term cohabitation other than the notion that the former is a life-long commitment.
In short, in Quebec today, less than half of kids born are from non-married parents. Marriage is seen by many as irrelevant, bureaucratic, peer-pressure consumerist obligation. According to QC civil law, once a couple has a kid, they have the same legal obligations to the kid as a married couple (i.e. contributing to supporting the kid in a way proportional to their revenue/salary). As the tacky government slogans like to remind us.. "in a couple one day, parents always" i.e. marriage has little relevance.
Also, just look at every single chart and data point mentioned in the article. All are about one dependent variable: divorce rate. Even if there is room for reasonable disagreement about the implications of the word "stable," reading the article makes it abundantly clear which definition was intended.
On the other side we have the word "divorce", which everyone agrees means "definitely unhappy". However, "not divorced" is definitely not a sufficient condition for "happy". The word "stable" is in the middle and can go either way. In one sense I agree it has a strong similarity to "not divorced". But in another sense, I think a lot of people read "stable marriage" as being very similar to "happy marriage". So to the extent that stable == happy, it's missing the point of the actual stats. And to the extent that stable != happy and a good proxy for not divorced, it's missing the point of what people really want out of life (and marriage).
This brings us to your response to my other comment, and there I think you're right on the money. The purpose of marriage is the main issue here. In my mind, the traditional view is synonymous with "stable" and not getting divorced. And the fact that the OP is talking about "stable" and "divorce" in the way it is suggests that the traditional view of marriage is a strong influence (although maybe my religious background is biasing me here). But none of this is very relevant if "happy" is what people are really after.
That's a very reasonable assumption. But it's also reasonable to analyse divorce rate data. You can't just assume that anyone studying marriage will only be studying how to keep marriages happy. I don't see any claim that this study is the ultimate study on marriage.
Since you cannot a/b test this in individual cases and can only say "people who left earlier have these corresponding average experiences or outcomes compared to people who stayed longer," I think it's a terrible disservice to many people with big life challenges to act like they were just being neurotic to stay as they long as they did.
I know there are people who claim "divorce as such" is bad for kids but I'm very doubtful about that. Divorce can be good or bad depending on how it's done, and how interested both the parents are in their kid's well-being.
So I hypothesize that what really matters is not divorce rate, but happy marriage rate. Unfortunately that data is not in this study. And furthermore, if it was, I would suspect significant bias. In the church world that I was a part of there was significant pressure to keep up appearances. So I don't think you would be able to trust either the married persons' self assessment of happiness nor the external assessment of the people who know them.
With this new metric in mind, I went back and re-thought the logic in each of the OP's significant predictors. First stop, "How much money you make". IMO this one falls flat on its face. It's easy to imagine situations where someone would stay in an unhappy marriage just because their partner has money. It's also easy to imagine situations where someone makes a lot of money, but stays in an unhappy marriage because their partner would get half of it in a divorce. Another factor that I think is suspect is "How many people attended the wedding". When a lot of people saw you get married it seems like there might be more pressure to stay in an unhappy marriage to save face to all the people who attended your wedding. I'm a little bit less confident about the reasoning here, but it still seems plausible.
The rest of the predictors seem reasonable to me, especially "How long you were dating". This one stands up under the happiness test and just seems to make sense, provided that the extended dating years were as similar as possible to the married years, minus the marriage license.