Professional Documents
Culture Documents
21.0%
Total
Number
of
Candies
of
Each
Color
1200
1180
1189
1160
1164
Total
Amount
1140
1120
1100 1117
1080 1093 1087
1060
1040
1020
Yellow Red Orange Purple Green
Skittle
Color
3. A
random
sample
is
a
type
of
method
where
all
parts
of
the
population
have
a
fair
and
equal
chance
of
being
selected.
Our
class
used
93
bags
of
2.17-‐
ounce
bag
of
Original
Skittles,
this
is
our
random
sample.
The
population
is
all
the
bags
of
2.17-‐
ounce
bags
of
Original
Skittles.
When
collecting
my
own
data,
I
guessed
that
there
would
be
almost
an
even
amount
of
every
color
of
skittles.
When
I
collected
my
data,
I
saw
that
my
guess
was
pretty
accurate.
There
are
about
the
same
number
of
each
color.
The
color
I
had
the
most
was
purple
and
yellow,
with
13
of
each.
The
least
amount
I
had
was
red,
with
9.
There
were
no
real
surprises
from
the
graphs.
The
chart
above
doesn’t
show
that
there
was
one
color
that
was
drastically
more
than
the
other.
When
looking
at
the
pie
graph,
each
color
represents
about
20%.
If
you
look
at
the
pareto
graph,
they
also
display
the
same
data
when
comparing
the
total
amount
of
each
color.
When
looking
at
the
other
classes
data
there
could
have
been
some
outliers.
Some
students
reported
only
having
37
or
40
total
skittles
in
their
bag.
This
seems
unlikely
since
the
average
was
somewhere
around
60
(5650/93=~60).
I
assume
each
bag
of
skittles
gets
weighed
before
being
sold.
Some
students
reported
having
78-‐82
skittles
in
their
bag.
Again,
this
also
seems
unlikely.
This
type
of
data
can
throw
of
our
overall
class
values.
Some
colors
could
be
over
or
underestimated.
There
is
also
some
error
here
since
perhaps
some
students
could
have
bought
the
wrong
size
of
bag
or
not
original.
The
distribution
of
colors
for
the
class
total
somewhat
matches
my
own
distribution.
Yellow
and
Purple
were
the
two
colors
I
had
the
most
of
and
most
students
also
said
they
had
a
lot
of
yellow
but
not
as
much
as
purple.
Red
was
my
lowest
amount,
but
the
class
total
shows
that
other
students
had
average
amounts
of
red
in
their
skittles
bags.
Part
Three:
Organize,
Display
Quantitative
Data
Mean
60.11
STD
17.06
Min 16
48
Q1
Median 58
Q3
71.5
Max
108
1.
Write
a
paragraph
discussing
your
findings
about
the
variable
“Total
candies
in
each
bag”.
Address
the
following
in
your
writing:
i.
What
is
the
shape
of
the
distribution
of
this
variable?
The
shape
of
the
frequency
diagram
is
bell
shaped.
This
is
reasonable
since
all
the
bags
will
be
weighed
before
being
shipped
out.
Since
a
single
skittle
probably
all
weigh
the
same,
it
makes
sense
that
most
of
the
bags
had
the
same
amount
totals.
ii.
Do
the
graphs
reflect
what
you
expected
to
see
or
are
there
some
surprises?
Overall
there
are
no
surprises.
It
was
expected
that
each
class
member
would
find
roughly
the
same
amount
of
skittles
in
each
bag.
Since
each
of
us
were
told
to
get
a
specific
weight
of
skittles
bag
and
type,
I
guessed
that
we
would
all
have
the
same.
There
are
some
outliers
but
that
could
be
due
to
human
error
or
input
error.
iii.
Does
the
overall
data
collected
by
the
whole
class
agree
with
your
own
single
bag
data?
My
individual
bag
did
agree
with
the
rest
of
the
class.
My
total
amount
in
my
bag
was
58.
The
mean
was
roughly
60.
That
makes
mine
a
little
less
than
average
but
still
really
close
to
what
everyone
else
got
for
their
total
number
of
skittles
in
a
bag.
Include
the
number
of
candies
from
your
own
bag
and
the
total
number
of
bags
in
the
class
sample
in
your
discussion.
The
total
number
of
candies
in
my
bag
was
58.
The
total
number
of
bags
in
the
class
in
our
sample
was
97
bags.
In
a
half
page,
explain
the
difference
between
categorical
and
quantitative
data.
Variables
can
either
be
categorical
or
quantitative.
Categorical
variables
are
also
known
as
qualitative
data.
This
type
of
data
can
be
arranged,
order
and
put
into
many
different
groups.
Categorical
data
deals
more
with
descriptions
that
are
observed
and
not
measured.
Categorical
often
measure
the
quality
of
what
is
being
observed.
Examples
of
qualitative
data
are
gender,
color,
appearance,
taste
and
names
of
people.
Categorical
data
usually
cannot
be
expressed
as
a
number.
Quantitative
data
is
information
that
can
be
measured.
The
data
is
in
numbers.
Some
examples
of
quantitative
data
are
length,
ages,
cost,
temperature
and
weight.
This
type
of
data
can
also
be
ordered
in
many
different
ways
to
give
meaning
to
the
data
that
it
reflects.
Bar
graphs
are
used
to
show
quantitative
data
because
it
is
an
easy
way
to
compare
quantities
next
to
each
other
by
using
the
height
of
each
bar.
Pie
charts
are
not
as
useful
for
quantitative
data
because
it
is
more
difficult
to
compare
the
side
of
each
category
in
a
slice
rather
than
being
lined
up
next
to
one
another
like
a
bar
graph.
Other
graphs
used
for
quantitative
include
boxplots.
Pie
charts
are
the
best
for
categorical
data
because
they
help
us
easily
see
what
percentage
each
groups
contains.
They
require
all
the
data
points
to
be
included
in
the
graph.
Bar
graphs
are
not
as
useful
because
they
can
be
more
flexible
with
which
data
is
displayed.
Pie
charts
must
use
all
or
none
of
the
data.
For
categorical
data
it
is
best
to
use
nominal
when
no
order
can
be
determined
and
ordinal
when
there
is
no
significant
differences
between
each
category
(A,B,C).
For
quantitative
data
use
interval
when
there
is
no
meaningful
zero
(IQ
scores)
and
ratio
when
there
is
a
meaningful
zero
(weight).
Part
4:
Confidence
Interval
Estimate
Question
1.
99%
CIE
population
proportion
of
yellow
candies
x
=
1189
yellow
candies
n
=
5650
pieces
of
candy
#
𝑃 =
=
1189/5650
=
0.2104424
$
𝛼
=
1
-‐
.99
=
.01
&
=
.01/2
=
.005
'
&
Z
=
invNorm(.01/2,
0,
10)
=
-‐2.57582
'
& ( )*( .'),-- )*
.'),--
E
=
Z
*
=
2.57582
=
0.013968
' $ /0/,
We
are
99%
confident
that
the
true
proportion
of
yellow
candies
falls
between
.1964714
and
.2244024.
Question
2
95%
CIE
for
true
mean
number
of
candies
per
bag
𝑥
=
60.1
S
=
5.556
n
=
94
df
=
n
-‐
1
=
93
𝛼
= 0.05
𝑇& = 1.986
'
< /.//0
𝐸 =
𝑇: ( ) = 1.986 = 1.379
; $ >-
Confidence
Interval
=
𝑥
− 𝐸 <
𝜇 <
𝑥 + 𝐸 = 60.1
− 1.379 <
𝜇 < 60.1 + 1.379 =
58.7 <
𝜇 < 61.5
We
can
be
95%
certain
that
the
true
population
mean
falls
within
the
range
of
58.7
to
61.5.
Question
3.
98%
CIE
for
the
population
standard
deviation
of
the
number
of
candies
per
bag
n
=
94
df
=
n
-‐
1
=
93
s
=
5.556
𝑠 ' = 30.869
𝛼 = 0.02
&
= 0.01
'
𝑥 ' 𝐿 = 1 − 0.01 =
. 99
𝑥 ' 𝑅 = 0.01
Chart
A-‐4
𝑥 ' 𝑅 = 0.01 = 124.116
𝑥 ' 𝐿 =
.99
=
61.754
$*) < ; $*) < ;
<𝜎 <
= 4.809 <
𝜎 < 6.818
#;J #;L
We
are
98%
confident
that
the
population
standard
deviation
falls
between
4.809
and
6.818
Question
4.
We
are
99%
confident
that
the
true
proportion
of
yellow
candies
falls
between
.1964714
and
.2244024.
For
the
true
mean
number
of
candies
per
bag,
we
can
be
95%
certain
that
the
true
population
mean
falls
within
the
range
of
58.7
to
61.5.
And
for
the
population
standard
deviation
we
are
98%
confident
that
the
population
standard
deviation
falls
between
4.809
and
6.818
Part
5:
Reflection
Who
knew
you
could
learn
so
much
from
a
bag
of
skittles.
This
semester,
our
term
projects
had
us applying what we have learned in class. For our term project we learned how to collect,
analyze, organize, display and create confidence intervals for the data that we collected. By the
end of the semester, I knew more than I ever wanted to know about skittles (next time maybe
do M&M’s for the chocolate fans out there). This statistical data on skittles helped me to
understand and apply the concepts to material I was learning in school, and it will help me in
This class project has already helped me better understand the class that I am currently taking. I
am taking a Human Physiology Lab. This lab requires us to make scatter plots, bar graphs,
compute r-‐squared values, t-‐tests and interpret the p-‐values. Each lab report always has us
report a p-‐value and we have to interpret if our hypothesis was supported or rejected. Learning
about these in the last exam has helped me a lot! This class project will also help me in my
future career. I plan on being a physical therapist. I have currently worked at an out-‐patient
clinic for a couple of years now. Physical therapy is based on continuing clinical research to help
find and prove the best methods for recovery. This studies often will collect and interpret the
data using statically analysis. Being able to interpret the data and understanding it will help me
This class project will also help me in my everyday life. I feel like I learned that the data can
sometimes be skewed are seem more persuasive than it actually is. Knowing what to look for in
a research article in a fitness magazine or some new claim better have some strong statistical
evidence
to
prove
it.
Just
the
other
day
I
was
buying
toothpaste.
On
the
box
it
said,
“Nine
out
of
10
dentist
recommend
Crest.”
This
statement
got
me
thinking
about
where
did
this
Leland
Black Term Project Part 5 Reflection claim come from, where is the data and who are these nine
dentists anyways. These types of claims are EVERYWHERE in our society today. Statistics play an
important role in marketing and can influence us what to purchase. By participating in this class
project, I have have applied it to my everyday life and will hopefully become a smarter
consumer.
What’s in a bag of skittles? Turns out to be a lot actually. This semester we opened up almost
100 bags of skittles and applied what we learned in class. By applying different test, we were
able to learn a lot that eventually helped me in my school work and will continue to help me in