Scribd
Upload
19 views

Normal Q-Q Plot: - 2 - 1 0 1 2 Theoretical Quantiles

1) A sample of 50 random variables was generated from a gamma distribution with shape 1 and rate 1. A normal Q-Q plot showed that the dots did not form a straight line, indicating the data did not come from a normal distribution. 2) The mean of the sample was calculated to be 1.5, which matches the expected mean of 1 from the gamma distribution that was used. A sample table of 1000 experiments showed consistency with the whole population. 3) For random uniform data sets of size 10000, the sample variance approximated the theoretical population variance of 1/12. The sample size was sufficient to estimate the population values.

Uploaded by

njs5277
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as ODT, PDF, TXT or read online on Scribd
19 views

Normal Q-Q Plot: - 2 - 1 0 1 2 Theoretical Quantiles

1) A sample of 50 random variables was generated from a gamma distribution with shape 1 and rate 1. A normal Q-Q plot showed that the dots did not form a straight line, indicating the data did not come from a normal distribution. 2) The mean of the sample was calculated to be 1.5, which matches the expected mean of 1 from the gamma distribution that was used. A sample table of 1000 experiments showed consistency with the whole population. 3) For random uniform data sets of size 10000, the sample variance approximated the theoretical population variance of 1/12. The sample size was sufficient to estimate the population values.

Uploaded by

njs5277
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as ODT, PDF, TXT or read online on Scribd
You are on page 1/ 3

> x=rgamma(50,1,1)

> qqnorm(x); qqline(x, col=2)


11.b) They could not hae come !rom a normal di"tribution becau"e the dot" do not !orm a "traight line.
2.1)#hen ty$ing in mean(x) % got an out$ut o! 1.&5. Thi" i" ex$ected becau"e in ' i" the mean in the
di"tribution.
- 2 - 1 0 1 2
0
1
2
3
4
5
6
N o r m a l Q - Q P l o t
T h e o r e t i c a l Q u a n t i l e s
S
a
m
p
l
e

Q
u
a
n
t
i
l
e
s
2.2)(utcome)
> table(x)*1000
x
0 1 2 + '
0.0,1 0.25' 0.+-2 0.255 0.05.
% "hould ex$ect thi" outcome becau"e the rbinom() !unction generate" random ariable" !or a certain
number o! ex$eriment", /ith a certain number o! ob"eration" $er ex$eriment", and the $robability o!
"ucce"" o! each o! tho"e ex$eriment". #hen /e u"ed the table(x)*1000 !unction it ba"ically changed the
original 1000 ex$eriment" /e had to a one then $ut thi" in a table. Thi" can be u"ed to "ee the
con"i"tency in a "am$le $o$ulation " the /hole $o$ulation.
+.1)The $o$ulation di"tribution" !or x and y i" 0(1)(mean) and the ariance i" ar(2) 3 4ar(5)3
206(270(2))(570(5))8
+.2) > "et."eed=11;x=runi!(10000);y=runi!(10000)
> ar(x3y);ar(x7y)
618 0.1-+1-+.
618 0.1--+.-
> "et."eed=11;x=runi!(10000);y=runi!(10000)
> ar(x3y);ar(x7y)
618 0.1-&&-'.
618 0.1-5',0,
The "am$le "i9e that /a" u"ed i" 10000. :rom the"e t/o data $oint" it i" ea"y to "ee that the "am$le
ariance;" a$$roximate the "ame quantity
+.+)<ll command" u"ed are $o"ted aboe
'.1) =inomal di"tribution /ith a ariance equal to n$($71)
'.2) > x=rbinom(10000,+,.-)
> mean(x)
618 1..11.
> ar(x)
618 0.,1'2522
> "d(x)
618 0..'51+''
The "am$le ariance i" .0,1'
The "am$le "tandard deiation i" ..'5
'.+)
> a=.,1'52
> b=..'51+'
> !=a3b
> !
618 1.55&-5'
> mean(!)
618 1.55&-5'
> !=(a3b)*(2)
> !
618 0.,,&.2,
#hen ta>ing the $o$ulation mean and ariance it i" ea"y to "ee that they are "imilar to the "am$le
mean and ariance.

You might also like