Academics around the world may be shaking their fists at the air, whingeing about today’s teenagers. A new study in the American Journal of Public Health reveals how teens are skewing the results of LGBT research by giving bogus answers.
Study author Joseph R. Cimpian, an economics professor at New York University, tells The Daily Beast he first learned of this issue when he realized a weirdly high percentage of survey respondents reported being gay and blind.
“What we found is that ‘gay’ kids are way more likely to be blind and to be deaf and to have three or more children of their own and all sorts of things,” he explains. “When you look at these data, you think, ‘This is ridiculous!’”
Related: Teen’s parents threw him to the curb for being gay, but just look at him now
How about we take this to the next level?
Our newsletter is like a refreshing cocktail (or mocktail) of LGBTQ+ entertainment and pop culture, served up with a side of eye-candy.
Alternatively, these so-called “mischievous responders” would also report being extremely tall and/or eating carrots four or more times a day.
“Clearly the kids are messing with us,” Cimpian concludes.
The professor and his colleagues have been using machine learning and supercomputers to statistically filter out the mischievous responders — a majority of whom, unsurprisingly, are teenage boys.
The results of this process suggest the disparity between straight and queer teens’ excessive alcohol and drug use are “not as big as the literature previously would have suggested,” Cimpian reports.
But the hoodwinking hasn’t affected the statistics about bullying, depression, and suicidal ideation among LGBT teens. “It actually shows that [the LGBT mental health disparity] is a very robust finding,” Cimpian explained.
Related: High school football player and swimmer boyfriend share prom pics, melt hearts
The “mischievous responders” issue is a big problem — especially because these surveys have been used to shape public policy — but Cimpian observes that it’s hard to get teens to take their role in the research seriously.
“A lot of times when I even talk to fellow faculty members about this, they say things like, ‘Oh, I would have been the kid that you would call a mischievous responder,’” he says.
Or, as The Daily Beast’s Samantha Allen writes, “The allure of depicting yourself as a 10,000-foot-tall, carrot-chomping, gay cocaine addict may, for some youth, be too great to resist.”
Bob LaBlah
Just curious but the very people those surveys are aimed at pay the survey nor its results any attention so why would mischievous deeds by a few of them matter?
Vince
When has an online survey ever mattered? I do them here and there myself but take it with a grain of salt since so many people lie.
Creamsicle
Online surveys are used a lot in psychological and sociological research. I’ve always considered them a terrible tool for data collection, but mostly because of how they find their participants.
Anonymity is believed to be the reason why the responses are trustworthy, but it’s just as likely that some a-hole will deliberately skew your data either through malice or incompetence.
misterjack
Millennials are not the on;y ones skewing online polls, I would venture to guess.
Creamsicle
Online surveys are actually really common in research since they’re cheap to set up and can potentially gather data from a large pool of participants.
But honestly, this is just showing why online surveys are an awful tool. Your data can be skewed easily by one crank, or incompetent users. They really are a flawed data collection tool and they enable lazy scholarship and research since there is no way to verify that your anonymous data came from the population you wanted to study.
You either open yourself up to skewed data by indiscriminately asking for participation and allowing malicious people to skew your data. Or you unconsciously skew your results by asking small pools of people to participate (and you’re no longer getting a random sample. Your results therefore have little to no bearing on the general population).