That may be the issue to you but it is not the point of the report. Nor was it the point of my comment.
My point is simply that you have to normalize data to be sure you aren’t comparing apples and oranges. I suspect this wasn’t done well and maybe not at all.
If, for example, in AL, an area of religious concentration, the divorce rates among the population (religious and non religious) are higher than the divorce rates among those same groups in (presumably less religious) CT , how does that prove that religious concentration is the cause?
Unless you normalize for income levels, education level, age at time of marriage, age at time of divorce, etc. you ain’t got nothing but another colossal waste of research dollars.
Sure it is. Read the title of the article again.