“Maybe among the most irresponsible reporting I’ve ever seen”

Timothy Kincaid reiterates the major objection I made to the NY Times report on same-sex couples and polyamory, and raises more of his own:

this study tells us nothing whatsoever about gay marriage and little about monogamy within gay relationships as a whole.In order for a study to report on the characteristics of a population, it must be representative of that population. If a study selects a convenience sample rather than a statistically valid sample, the non-representative demographics of the sample cannot be presented as a “finding”.

For example, if I went to Dodger Stadium, i might find a sample which was useful to tell me whether Dodger fans think Dodger Dogs taste better than garlic fries, but I could not claim that my sample proves that 80% of all baseball fans support the Dodgers. That is simply a non-representative demographic of my sample, not a finding of my study.

So to see if this study supported the claim that half of gay marriages are open (non-monogamous), I contacted the study authors and obtained previously published information that reveals the sample methodology. I do not have all of the data on which the final study is to be reported, but the sampling methodology was consistent.

Let’s look at how the sample for this study was constructed and how that differs from the population as a whole.

Definition of relationship:

To be eligible participants had to have been at least 18 years old, have been in a their current relationship for at least 3 months, have knowledge of their own and their partner’s HIV status, be fluent in English, and be residents of the San Francisco Bay Area.

All were men. Contrary to James’ breathless reporting (and the example with which he started his article) the researchers said nothing about lesbian relationships. They were excluded.

The study was conducted in several phases and the details of each is not available, but the sampling methods were consistent. The breakout for Study 2 found that only 13% of participants identified as being married (perhaps the 2004 San Francisco variety) and only a third had made any sort of public commitment.

It is ludicrous to suggest that a study which includes three month long relationships without any public commitment is informative about marriage. The average length of the relationships was 7 years (more or less) but the median length was about three years earlier (half of the relationships were less than 4 years in length), suggesting that there were a few very long relationships and many much shorter ones.

The way this study has been reported, it has been suggested that gay relationships are more likely to be open than straight relationships, but no comparison was made and I’m not aware of any study that looked at the level of fidelity in three-month-old heterosexual relationship and pretended that they were representative of straights as a whole.

As the research was not applied separately by relationship structure or length, this study says nothing about gay marriage or even domestic partnerships. And any use of the results which makes (or even implies) a comparison to straight relationships is bogus and irresponsible.

Location and social perspective of the population sampled:

It must be emphasized that gay men living in the San Francisco Bay Area are not representative of gay men as a whole. In fact, it would be difficult to identify a group of gay men less representative of the US gay population.

Significant factors in the consideration of monogamy surely must include attitudes about sexuality and whether one’s general approach is more conservative or liberal overall. Additionally, the perspectives of the community in which one lives most certainly effect the values that one adopts.

While I cannot point to a study and state with certainty that those who view themselves as “conservative” are more likely or less likely to value monogamy, I can state that selecting only participants from the SF area sharply skews the sample towards those who identify as “liberal” and significantly under-represents a sizable segment of the gay community.

 

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: