Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
I.
Definitions
to
know
1.
EventAny
collection
of
results
or
outcomes
of
a
procedure.
2.
Simple
EventOutcome
or
event
that
can
not
be
broken
down
into
any
smaller
event.
(think
atoms)
3.
Sample
SpaceMathematical
space
that
consists
of
all
possible
simple
events.
Example
01:
Use
b
to
denote
the
simple
event
of
having
a
baby
that
is
a
boy,
and
g
to
denote
the
simple
event
of
having
a
baby
girl.
Event
Example
off
an
Sample
Space
Event
Single
Birth
{b,g}
3 Births
B.
Notation
1.
P denotes a probability
2.
3.
P(A),
P(B),
P(C)the
probability
of
event
A,
B,
or
C
occurring.
C.
Computational
Probability
1.
Classical
Approach
a)
This
approach
requires
equally
likely
outcomes
(ie
.50/.50,
.333,
.333.
.333
etc)
b)
If
a
given
procedure
has
(n)
different
equally
likely
outcomes,
then
the
probably
is:
(1.1)
D.
2.
Then
the
approximate
probability
is
given
by:
#_ pf _times _ A_occured
P(A) =
#_of _times _event _ was _repeated
!
Example
03
Relative
Frequency
A
recent
Harris
Poll
of
1010
adults
in
the
United
States
showed
that
202
of
the
adults
smoked.
Find
the
probability
that
a
randomly
selected
adult
in
the
U.S
smokes.
Let
A=smoker
202
P(A) =
= 0.200
1010
!
*notice
that
picking
a
non-smoker
vs.
picking
a
smoker
are
not
equally
likely
events,
because
there
are
more
non-smokers
vs.
smokers.
E.
F.
Interpreting
Events
1.
An
event
is
considered
unlikely
(for
now)
if
its
probability
is
very
small,
less
than
or
equal
to
0.05.
2.
UnlikelyEvent
with
a
small
probability
of
less
than
or
equal
to
0.05.
3.
Unusual
or
Extremethe
number
of
outcomes
is
far
above
or
far
below
theoretical
values.
**If
time
is
left,
do
in
class
worksheet,
if
not
send
it
home
as
homework.
Lesson
Reflections:
II.
Definitions:
1.
Compound
Eventany
event
combining
two
or
more
simple
events.
Stat
Student
2.
ComplementIf
an
event
is
denoted
by
A,
then
its
complement
is
denoted
by
(~A)
meaning
not
A.
B.
3.
Disjoint
SetsEvents
A
and
B
are
disjoint
if
they
can
not
happen
at
the
same
time.
Example
4.2.1:
Example
of
Disjoint
events
A
=
is
a
registered
democrat
B
=
is
a
registered
republican
A
Registered
Democrat
B
Registered
Republican
Example
of
Non-disjoint
events
Randomly
selecting
someone
taking
a
statistics
course.
Randomly
selecting
someone
who
is
female.
(Someone
can
be
both)
3.
Caution:
Errors
made
when
applying
the
addition
rule
usually
happen
because
of
double
counting.
One
indicator
that
you
have
double
counted
is
that
the
probability
is
greater
than
1.
C.
Female
2.
If
two
sets
are
disjoint
then
!P(A B) = 0
and
!P(A B) = P(A)+ P(B) 0
Stat
Student
And
Female
1.
Complementary
Events
1.
!A
and
!A
are
mutually
exclusive,
that
is,
they
are
disjoint
sets.
Thus
we
can
say
the
following:
!P(A)+ P(A) = 1
2.
This
result
leads
to
the
following
three
results:
P(A)+ P(A) = 1
P(A) = 1 P(A)
!P(A) = 1 P(A)
Example
04
Devilish
Belief:
Based
on
data
from
a
Harris
Poll,
the
probability
of
randomly
selecting
someone
who
believes
in
the
devil
is
0.6,
so
P(believes
in
devil)=0.600
Find
the
probability
for
selecting
someone
who
does
not
believe
in
the
devil.
III.
B.
Definitions
1.
Two
events
A
and
B
are
independent
of
the
occurrence
of
one
does
not
effect
the
probability
of
the
occurrence
of
the
other.
If
events
A
and
B
are
not
independent,
then
they
are
dependent.
**Dont
think
that
just
because
one
event
depends
on
another
that
one
event
causes
the
other.
This
is
the
error
of
causation.
C.
Sampling
Methods
1.
Sampling
with
replacement,
selections
are
independent
events.
2.
Sampling
without
replacement,
selections
are
dependent
events.
3.
When
calculations
with
sampling
are
very
cumbersome
and
the
sample
size
is
no
more
than
5%
the
size
of
the
population,
treat
the
selections
as
being
independent.
Example
05:
Airport
Baggage
Scale
Airport
baggage
scales
can
show
that
bags
are
overweight
and
high
additional
fees
can
be
imposed.
The
New
York
City
Department
of
Consumer
Affairs
checked
all
810
scales
at
JFK
and
La
Guardia,
and
102
scales
were
found
to
be
defective
and
ordered
out
of
use.
(source:
New
York
Times).
B.
At
Least
one
1.
At
least
one
means
one
or
more.
2.
The
compliment
of
getting
at
least
one
particular
event
is
that
you
get
no
occurrences.
Example
06:
Topford
Development
supplies
DVD
in
lots
of
50,
and
has
a
reported
defective
rate
of
0.05%,
so
the
probability
of
an
individual
disk
being
defective
is
0.005.
It
follows
that
the
probability
of
a
disk
being
good
is
1-0.005
=
0.995.
What
is
the
probability
of
getting
at
least
one
defective
disk
in
a
lot
of
50?
Step
1:
Let
A=at
lest
1
of
the
50
disks
is
defective.
Step
2:
Identify
the
event
that
is
the
Complement
of
A.
P(A) = 1 P(A)
!= 1 0.778 = 0.222
In
a
lot
of
50
DVDs,
there
is
a
0.222
probability
of
getting
at
least
1
defective
DVD.
Conditional
Probability
1.
A
conditional
probability
of
an
event
is
a
probability
obtained
with
the
additional
information
that
some
other
event
has
already
occurred.
!P(B | A)
denotes
the
conditional
probability
of
event
B
occurring,
given
that
event
A
has
already
occurred.
!P(B | A)
can
be
found
by:
P(B | A) =
!
P(A B)
P(A)
Example
07:
Pre-Employment
Drug
Screening
Pre-Employment
Screening
Positive
Test
Negative
Test
Results
Results
Subject
uses
44
6
Drugs
Subject
does
90
860
Not
use
drugs
If
1
of
the
1000
test
subjects
is
randomly
selected,
find
the
probability
that
the
subject
has
a
positive
test
result
given
that
the
subject
actually
uses
drugs.
A
=
Subject
uses
drugs
=
44
+
6
=
50
B
=
Positive
test
results
given
Subject
uses
drugs
=
44
P(A B) 44
P(B | A) =
=
= 0.88
P(A)
50
!
Find
the
probability
the
subject
actually
used
drugs
given
the
subject
had
a
positive
test
result.
44
P(A|B) =
= 0.328
134
!