This preview shows pages 1–3. Sign up to view the full content.
1
ECE 514
Lecture 4
Properties of a PDF
±
Lemma:
1.
is a nonnegative function , i.e. ,
2.
integrates to 1.
Note
:
()
X
f
x
() 0
X
fx
≥
x
R
∀∈
X
f
x
1
X
f
xdx
=
∫
lim
( )
( )
1
y
XX
yy
F
yf
x
d
x
−∞
→∞
=
=
∫
±
Question:
How do we use PDF’s to compute
Probabilities?
Lemma
: Recalling that
We have the following:
Question:
Does
satisfy Axiom 3 of
Probability?
x
F
xf
y
d
y
=
∫
(
)
b
X
a
Pa X b
f xdx
+
+
<≤=
∫
(
)
b
X
a
+
−
≤≤=
∫
(
)
b
X
a
−
−
≤<=
∫
(
)
b
X
a
−
+
<<=
∫
(
)
X
a
Pa x
+
∞
<=
∫
X
f
∫
Conditional PDF
±
Consider a probability space
and a
random variable defined on
.
Definition:
The conditional probability density
function of an RV
, given some event A
such that
is defined as:
{, ,}
P
Ω
F
Ω
X
PA
≥
( )
X
X
dF
x A
fxA
dx
=
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document2
Empirical Distribution
Ex:
Suppose you are measuring a voltage V
1
which
is supposed to be constant.
±
As a
sensed voltage, it feeds a regulator(filter)
whose output needs to maintain a constant
temperature to within a
(
for example)
Problem:
To design a regulator we will need the
statistics (variations of
) i.e.
which
we need to establish experimentally.
1
Va
=
1
10
D
1
V
1
ii
n
=+
1,.
..
iT
=
(Continued)
Question:
How would we go about that?
Start with Definition
:
Or:
()
(
)
X
P
Xxd
xP
Xx
fx
dx
≤
+−
≤
≅
(
)
X
f xdx Px X x dx
≅
≤≤+
±
i.e. Find the mass in that fractional
segment.
This is the end of the preview. Sign up
to
access the rest of the document.
 Fall '08
 Krim

Click to edit the document details