The Regnerus Study, Debunked Yet Again

That infamous study on gay parents by Mark Regnerus has been roundly denounced by other sociologists, who note that the methodology he used was so bad as to be laughable. Now a new study of his own data finds that if you correct some of those methodological problems, the rational conclusion is the opposite of the one he reached.

Indiana University’s Brian Powell and the University of Connecticut’s Simon Cheng didn’t just find methodological flaws in Regnerus’ research — they took the data he collected, cleaned it up, and redid the study, coming to a very different conclusion about families led by same-sex couples. Their article will be published in “Social Science Research,” the same journal that published the Regnerus study.

By eliminating suspect data — for example, a 25-year-old respondent who claimed to be 7’8” tall, 88 pounds, married 8 times and with 8 children, and another who reported having been arrested at age 1 — and correcting what they view as Regnerus’ methodological errors, Cheng and Powell found that Regnerus’ conclusions were so “fragile” that his data could just as easily show that children raised by gay and lesbian parents don’t face negative adult outcomes.

“[W]hen equally plausible and, in our view, preferred methodological decisions are used,” they wrote, “a different conclusion emerges: adult children who lived with same-sex parents show comparable outcome profiles to those from other family types, including intact biological families.”

In other words, as University of Maryland sociologist Philip Cohen put it, “when you clean the data and fix the things that are fixable, the results just don’t hold up.”

Regnerus is little but a punchline in sociology now, as he should be. Only one thing needs to be said to discredit his study: The groups he compared were in no way remotely comparable. He compared intact families with broken families where one of the parents were gay (more accurately, if one of the parents had ever had even a single gay sexual experience) and said, “Gee, the outcomes for the second group are worse than for the second group.” Yeah, no shit. People from broken families don’t fare as well as people from intact families. The fact that none of the second group actually involved families led by a stable gay couple alone shows how slanted and ridiculous his study was.

"Couple charged with assault in shooting, melee ... - The Seattle Timeshttps://www.seattletimes.co......Apr 24, 2017 - ..."

Three Racists Arrested for Attempted Murder ..."
"Police release suspect in UW Trump protest shooting | KING5.comwww.king5.com/news/local/se...Jan 22, 2017 - SEATTLE – ..."

Three Racists Arrested for Attempted Murder ..."
"Imagine a country of 65 million with only 664 murders in a year. That's less ..."

Trump Passes on False Story from ..."
"Man shot outside Milo Yiannopoulos event at University of Washington ...https://www.cbsnews.com/.........Jan 21, 2017 - Last ..."

Three Racists Arrested for Attempted Murder ..."

Browse Our Archives

Follow Us!


What Are Your Thoughts?leave a comment
  • StevoR

    Yup. Bet the homophobic bigots keep desperately citing it though. Its all they have.

    Which in itself tells you all you really need to know.

  • themadtapper

    for example, a 25-year-old respondent who claimed to be 7’8” tall, 88 pounds, married 8 times and with 8 children, and another who reported having been arrested at age 1

    Jesus, I knew the Regnerus study was bad, but I didn’t realize it was THAT bad.

  • http://onhandcomments.blogspot.com/ left0ver1under

    Ah, but the facts only convince those willing to think, not those willing to believe the lie.

    Those with malicious disposition are prone to have a malicious predisposition.

  • John Pieret

    Regnerus is little but a punchline in sociology now

    He presumably has tenure at the University of Texas but, like Michael Behe, his own Department disowns him:

    https://www.utexas.edu/cola/depts/sociology/news/7572

    I wonder if advancing his bigotry was worth the loss of his academic reputation.

  • StevoR

    @ ^ John Pieret : At a guess, no – but then he may disagree with that. For now anyhow. In another decade or two who knows?

    (Hey, maybe some of those folks who opposed interracial marriage might have an idea how that feels so maybe wec an ask one of them .. )

  • http://motherwell.livejournal.com/ Raging Bee

    …for example, a 25-year-old respondent who claimed to be 7’8” tall, 88 pounds, married 8 times and with 8 children, and another who reported having been arrested at age 1…

    They didn’t rule those out at the outset?! That alone is enough to discredit the study: a) they’re not at all plausible; and b) even if they were real, they’re still such extreme outliers that no statistician or analyst worth their salt would include them in any study of any large population.

  • colnago80

    Re John Pieret

    I’m sure that the loss of whatever scientific reputation he had will cause him to cry all the way to the bank.

  • cptdoom

    I can’t remember exactly where I read it, but there were reports that the database Regnerus used was actually an on-line database of information for which the respondents were paid. It was actually more of a marketing database than a data set one would use for scientific purposes (like the census).

  • http://www.ranum.com Marcus Ranum

    the database Regnerus used was actually an on-line database of information for which the respondents were paid

    A self-selected sample? Fuck me incompetently!

    I remember back in the early days of Internet Marketing there was a company that was trying to gather poll data by offering respondents a chance at winning a laptop or something like that. The eventual results they collected correlated highly with a) being unemployed b) being retired. At least the company collecting the data threw it out, rather than try to spin it into a public policy discussion.

  • hunter

    “The fact that none of the second group actually involved families led by a stable gay couple alone shows how slanted and ridiculous his study was.”

    There were actually two subjects who were raised for a significant portion of the childhoods by lesbian couples. Regnerus admitted that their outcomes were comparable with those of subjects raised in intact families.