Group project combined individual parts-hanah McCloy. Hanah's data has a much higher yellow count than The Class data. The only reason one person got 46 total candies is that they had many broken candies so those weren't counted.
Group project combined individual parts-hanah McCloy. Hanah's data has a much higher yellow count than The Class data. The only reason one person got 46 total candies is that they had many broken candies so those weren't counted.
Group project combined individual parts-hanah McCloy. Hanah's data has a much higher yellow count than The Class data. The only reason one person got 46 total candies is that they had many broken candies so those weren't counted.
Sample
Group
Count
Red
Count
Orange
Count
Yellow
Count
Green
Count
Purple
#
in
bag
Hanah's
Bag
11
13
18
9
10
61
Hanah's
Proportions
18%
21%
30%
15%
16%
100%
Class
Proportions
19.52%
19.60%
20.72%
22.33%
17.83%
The
Class
data
is
split
fairly
even
between
all
colors,
which
was
roughly
1/5
of
the
skittles
per
color.
However
my
data
has
a
much
higher
yellow
count
than
the
class
data.
I
believe
my
yellow
count
would
be
considered
an
outlier,
and
that
also
pushed
the
other
colors
to
be
a
bit
smaller,
just
because
the
bags
were
all
very
close
to
the
same
amount
of
skittles.
It
would
be
interesting
to
see
how
these
values
differ
based
off
of
where
they
were
purchased
from,
or
some
other
details
like
that.
Part
3
Total
Candies
The
total
candies
in
each
of
the
bags
was
grouped
fairly
close
together,
except
for
the
one
person
who
got
46,
without
the
46
the
distribution
would
have
been
roughly
bell
shaped
or
standard.
My
own
bag
had
just
one
more
than
the
average--but
that
put
me
up
to
the75th
percentile
with
just
61.
The
graphs
do
reflect
what
I
expected
where
most
people
are
grouped
closely
together.
The
only
reason
I
can
think
of
for
how
that
one
person
got
46
total
candies
would
be
that
they
had
many
broken
candies
so
those
werent
counted.
Otherwise
I
dont
think
they
would
have
measured
the
correct
ounces.
Categorical
data
would
be
data
that
we
can
divide
up
into
groups,
like
in
the
last
part
of
the
project
where
we
showed
how
many
colors
of
each
candy
were
in
each
bag.
I
feel
the
most
descriptive
graph
for
this
type
of
data
would
be
a
pareto
chart,
because
frequency
for
each
group
is
the
easiest
way
to
identify
and
compare.
In
this
data
type
it
would
be
impossible
to
make
a
boxplot
that
made
any
sense
because
the
numbers
for
each
category
are
not
dependant
on
each
other.
When
calculating
information
for
this
data
type
one
way
I
found
was
most
informative
was
mode,
to
see
which
group
appeared
more
often.
You
cant
take
a
median
from
Red,
Orange,
Yellow,
Green
or
Purple.
Quantitative
data
would
be
when
you
can
attach
numbers
to
the
data,
like
in
this
current
part
of
the
project
where
we
counted
the
amount
of
skittles
in
each
persons
bag
and
compared.
The
easiest
and
most
informative
graph
here
is
the
boxplot.
This
is
the
first
time
I
have
ever
learned
about
boxplots
and
I
love
how
much
information
you
can
immediately
take
in
by
glancing
at
it.
This
type
of
data
can
be
summarized
easily
with
the
5
number
summary.
It
is
not
as
useful
to
know
the
mode
in
these
data
types.