"Statistically significant" is a standard, but confusing, term, for "statistically measurable" or discernable -- it does not mean significant for the purpose of the larger inquiry that the statistical measurement is part of.
More than half of Americans are either “satisfied,” 36 percent, or “thrilled,” 18 percent, with the quality of their intimate relationships, according to a study of 10,548 people in the continental United States conducted over more than two years by the nonprofit PAIRS Foundation ...
PAIRS CEO Seth Eisenberg released findings from the 26-month American Relationship Study today that also revealed 27 percent of people to be navigating significant relationship challenges with 18 percent facing high risk of separation or divorce. Four percent of the total study group were at the highest risk for separation or divorce.
PAIRS CEO Seth Eisenberg says more than half of Americans are “satisfied” or “thrilled” with the quality of their intimate relationships.
Eisenberg said findings showed national relationship satisfaction to be fairly even throughout the year, with a small peak in March/April (+2 percent) and seasonal declines in November (-3 percent), December (-4 percent), January (-5 percent) and June (-3 percent).
While Eisenberg said the initial study was not designed to evaluate geographic differences, he said preliminary findings indicate higher levels of relationship satisfaction for people living in Idaho, Montana, Mississippi, West Virginia, Oklahoma, New York, Ohio, Minnesota, Kentucky, Delaware and Colorado. Lower levels were reported by participants in the District of Columbia, Oregon, New Mexico, Maine, Missouri and Rhode Island.
"Much of what we call "big data" was never meant to be accurate, and because so much of it is shared, any inaccuracies can be hard to keep track of.
Even unbiased data can point to trends that no longer exist, or paradigms that are about to change." ...
"The larger our pool of information, the more chance patterns we're likely to find in it, and the easier it becomes to "prove" whatever we like." ...
Big data makes it even harder to remember that there things we do not know: "We are trained to take advantage of the information that is lying in front of our eyes, ignoring the information that we do not see." ...
Here's a link directly to the Pew study which there have been so many newspaper stories about today. In one sense, it isn't news: marriage is at a record low, but it's been steadily declining for 50 years, mostly from increased age at first marriage, much more than from any abandonment of the idea of marriage. And therefore it has ALWAYS been at a record low, at any given time during its 50-year decline.
The study has many other interesting facts about particular demographic groups, including that the decline is mostly among less-educated people, and is worldwide including less-developed countries.
According to an analysis of marriage and divorce from 1860 to 1948, during economic hard times fewer people get married, but then fewer of them get divorced. The author, Thomas Cvrcvk, describes the trends like this:
Large marriage cohorts, formed in the years of economic expansion, disrupted in greater numbers… Conversely, during years of recession, many poorer couples were discouraged from marriage; smaller marriage cohorts with more resilient marriages were formed and their lifetime marriage disruption rate was lower.
So these fewer marriages, formed despite financial obstacles, may reflect the stronger relationships among couples considering marriage.