you just have to compensate for selection bias as much as possible

The major problem with this study is it was voluntary response. People went online and answered because they wanted to, not because the survey was palced in front of them. They had to be motivated to take it.

Which is going to select for victims

i'd say more than 5% of the population are batshit insane enough to roll with a lie like that if they had social incentive

So say 5% of respondents did that (i don't think so but w.e)

That sifts the numbert marginally

5? try 50%, people are as self serving as they come

yeah but it diddnt even work out that well for her

@cmdline well... voluntary response disqualifies the study completely.

not really

you have to concider how many people see the study

if it's not random selection it has no value to me

definitely more effective

@I AM ERROR, I feel like you don't do a lot of social sciences research

i don't

*social* *science*

skeptic hat tilts forward

Then you should probably refrain from laying down the law on this stuff.

hey that's pretty condecending

Oh please, it's got its problems but the socials ciences have been producing meaningful work for almost 100 years

nope. you don't have to work in a field to see flaws in the methods used in it

And " well... voluntary response disqualifies the study completely. if it's not random selection it has no value to me" is a pretty absurd thing to say

100 wolves interviewed said that sheep are tasty 😉

Like I'm sorry sociology isn't physics?

That's just not what happened here...

well... then what do you mean by voluntary response

i posted a poll on 4chan asking if they think cnn is fake news

it's voluntary, of course

I mean the survey was posted online and people were offered 10 dollars on amazon to take it

I'm not sure how knowledge of the survey was disseminated

Pls hold

the results were that 99.998% of the internet thinks CNN is fake news

@I AM ERROR see 3.1.3

@I AM ERROR To recruit the students who were sampled to participate in the CSA Study, we relied on both
recruitment e-mails and hard copy recruitment letters that were mailed to potential
respondents. Sampled students were sent an initial recruitment e-mail that described the
study, provided each student with a unique CSA Study ID#, and included a hyperlink to the
CSA Study Web site. During each of the following 2 weeks, students who had not completed
the survey were sent a follow-up e-mail encouraging them to participate. The third week,
nonrespondents were mailed a hard-copy recruitment letter. Two weeks after the hard-copy
letters were mailed, nonrespondents were sent a final recruitment e-mail. The overall
response rates for survey completion for the undergraduate women sampled at the two
universities were 42.2% and 42.8%, respectively. The response rates for males were lower.
Exhibit 3-1 depicts the response rates in relation to the sampling frames and subframes.
Procedures for addressing response bias are discussed in more detail in the analysis section.

🤔 no men survayed

@ping what?

men were surveyed but did not respond in sufficent numbers

Over 1k males were considered?

i got confused, "the undergraduate women sampled at the two
universities"

i have a problem with the surveyed knowing the topic beforehand, that skewes the results in my eyes.

it sounds like they diddn't even sample undergraduate men