Source: Wikipedia, the free encyclopedia.
In May 2009
WP:LAYOUT.
[C] Below are the results.
[D]
Study one results
Footer type
Count
Proportion
Error bound[iii]
References
979
48.95%
±2.19%
Notes[i]
89
4.45%
±1.04%
Bibliography[i]
35
1.75%
±0.57%
Footnotes
13
.65%
±0.352%
Sources
1
0.05%
[ii]
Works cited
1
0.05%
[ii]
Citations
0
0%
[ii]
^ a b Possible confounding
^ a b c Sample size too small to calculate reliably
^ Error bounds are calculated with a 95% confidence interval
[E]
Study two results
Sections
Blocked: Articles with sections
Category
Count
Proportion
Error[ii]
Single
114
46.53%
±6.246%
Yes
93
37.959%
±6.0765%
No
35
14.285%
±4.3815%
Maybe
3
[i]
[i]
^ a b Sample size too small to calculate reliably
^ Error bounds are calculated with a 95% confidence interval
[E]
Applicable
Blocked: Applicable by WP:LAYOUT
Category
Count
Proportion
Error[note 1]
Yes
93
70.992%
±7.77%
No
35
26.717%
±7.577%
Maybe
3
[note 2]
[note 2]
^ a b Sample size too small to calculate reliably
^ Error bounds are calculated with a 95% confidence interval
[E]
Notes
At this point the author would like to interrupt this list to indicate a possible application of the value attribute found in Template:Cnote2 . Very long lists similar to this one may benefited by having it be broken down. Remember to remove the link to an inline occurrence, giving the feel of an regular list, set n=0.
^ ChyranandChloe ; et al. (5 May 2009). "Standard Appendicies Conformity Statistics" . Journal of Wikipedia Layout (in Chinese). 1 (1). San Francisco, United States: Wikimedia Foundation: 3–4. Retrieved 2009-09-19 .
^ Null hypothesis tests have been omitted.
Assumption
n > 30
np0 > 10
n(1-p0 ) > 10
Simple Random Sample
^ a b c Note that
binomial distributions are discrete, these error bounds assume a
normal distribution . Calculated as
p
^
±
z
∗
p
^
(
1
−
p
^
)
n
{\displaystyle {\hat {p}}\pm z^{*}{\sqrt {\frac {{\hat {p}}\left(1-{\hat {p}}\right)}{n}}}}
, distributed as such: