Re: You seem to have perfected whining to a Talent... - Edit 1
Before modification by Tor at 11/11/2012 08:45:42 PM
So, I went and had a look at some statistics texts, and here are a few juicy quotes (emphasis mine):
---
Self-selection bias is the problem that very often results when survey respondents are allowed to decide entirely for themselves whether or not they want to participate in a survey. To the extent that respondents' propensity for participating in the study is correlated with the substantive topic the researchers are trying to study, there will be self-selection bias in the resulting data.
Nice. But why did you ignore the very next sentence?
In most instances, self-selection will lead to biased data, as the respondents who choose to participate will not well represent the entire target population.
That's exactly what I've been saying. A self-selected sample is not representative of the entire population. 1000 women is too low a sample number when they're self-selected. So you see a bias in one way. The very next 1000 self selected women from the same area might have been biased in the opposite way, or biased even more towards weak women. The point is, in a non-random sample, you'll almost certainly see bias. There is no one reason for this.
---
A voluntary response sample consists of people who choose themselves by responding to a general appeal. Voluntary response samples are biased because people with strong opinions, especially negative opinions, are most likely to respond.
---
A voluntary response sample consists of people who choose themselves by responding to a general appeal. Voluntary response samples are biased because people with strong opinions, especially negative opinions, are most likely to respond.
---
This is the case with political poll. In epidemiology (which the current case is closer to, since channeling the OP is not an opinion, it is a genetic and metaphysical predisposition), it is not the strong opinions of respondents that leads to sample skewing.
A sample of convenience is a sample that is not drawn by a well-defined random method. The big problem with samples of convenience is that they may differ systematically in some way from the population. For this reason, samples of convenience should not be used, except in situations where it is not feasible to draw a random sample. When it is necessary to draw a sample of convenience, it is important to think carefully about all the ways in which the sample might differ systematically from the population. If it is reasonable to believe that no important systematic difference exists, then it may be acceptable to treat the sample of convenience as if it were a simple random sample.
Ok, so the point of these quotes was to back up what I've been saying all along, and which you have protested, i.e., that there has to be a specific mechanism which links the probability that a person will volunteer for the test with the characteristic you are testing for there to be a self-selection bias. Personally, I prefer arguments and reason instead of the authority of a book, but since you asked for books, I guess you don't.
But there is reason to know a systematic difference exists. Its not a matter of belief here. We know for a certain fact that this non-random population is showing characteristics markedly different from the norm.
I guess this sums it up. If you are now saying that there is a reason to assume a systematic bias in this particular sample, then I can't argue with that, except to say that in my opinion it seems more likely that RJ made a mistake with one of the two numbers, rather than adding a massive bias to those novices as a plot device.
However, I would be very interested (and I'm not being sarcastic, I would actually be very interested) to hear what you think the mechanism of the bias would be.
Your thought experiment is so stupid I'm at a loss for words. It is not remotely comparable because the probability of a coin landing heads or tails is decided at that very moment, and depends on the property of the coin, not the person tossing it!
But in the other post, you agreed that strength in channeling is essentially a random number assigned at birth, unknown until you are tested. I fail to see how this is different from a bunch of people flipping a coin, marking the result without looking at it, and then at some later point volunteering to have their coin tested.
Edit: Fixed a missing quote-tag