1 |
On 12/05/2011 03:09 PM, Chí-Thanh Christopher Nguyễn wrote: |
2 |
> Zac Medico schrieb: |
3 |
>> One person's common-sense behavioral model is another person's baseless |
4 |
>> claim. |
5 |
> |
6 |
> Claims don't have to be based on data. You can come to a conclusion from |
7 |
> experience/knowledge of working/researching/studying in a particular |
8 |
> subject, or from opinions of those who did. Or you can say that this is |
9 |
> your idea of "common sense". Or your can say that it is derived from |
10 |
> your imagination. |
11 |
> |
12 |
> All these claims are valid and deserve attention, but in a discussion |
13 |
> should be clearly labelled as what they are. |
14 |
|
15 |
My intention wasn't to present anything as fact. It was to provide a |
16 |
hypothetical mechanism for sampling bias, in order to demonstrate the |
17 |
kinds of challenges involved in statistical analysis. |
18 |
|
19 |
>>> One way to investigate would be to sample statements in the forum |
20 |
>>> thread, and determining how many responded with personal preference and |
21 |
>>> how many with practical arguments. It would still have to be accounted |
22 |
>>> for those who try to rationalize their pre-conceived opinion with ad-hoc |
23 |
>>> arguments, but better than nothing at all which is the current case. |
24 |
>> |
25 |
>> Sure, but that seems like more of an academic exercise than a practical |
26 |
>> one. I think we'll better of with a judicial approach, where a group of |
27 |
>> judges weighs a set of pros and cons. Gentoo's council is the closest |
28 |
>> thing to that we have to a judiciary. |
29 |
> |
30 |
> I have just given an example of what I would have considered data/fact |
31 |
> regarding the bias claim. |
32 |
|
33 |
And I think that statistics are basically useless in the current |
34 |
context, due to the challenges involved in obtaining a reasonably |
35 |
unbiased sample. That's why I suggest that a judicial approach would be |
36 |
most appropriate. |
37 |
-- |
38 |
Thanks, |
39 |
Zac |