1. Review
Some Basic
Statistical Concepts

2. Many of the things we will be interested in this class are random variables (RVs); that is, variables whose outcome is subject to chance.
We do not know what value a RV will take until we observe it.
Examples: outcome of coin toss;
your starting salary after graduation.

3. Random Variable random variable:
A variable whose value is unknown until it is observed.
The value of a random variable results from an experiment.
The term random variable implies the existence of some
known or unknown probability distribution defined over
the set of all possible values of that variable.
In contrast, an arbitrary variable does not have a
probability distribution associated with its values.

4. Controlled experiment values of explanatory variables are chosen with great care in accordance with an appropriate experimental design.
Uncontrolled experiment values of explanatory variables consist of non-experimental observations over which the analyst has no control.

5. Discrete Random Variable
A discrete random variable can take only a finite
number of values, that can be counted by using
the positive integers.
Example: Prize money from the following
lottery is a discrete random variable:
first prize: Rs.1,000
second prize: Rs.50
third prize: Rs.5.75
since it has only four (a finite number)
(count: 1,2,3,4) of possible outcomes:
Rs.0.00; Rs.5.75; Rs.50.00; Rs.1,000.00

6. Continuous Random Variable
A continuous random variable can take
any real value (not just whole numbers)
in at least one interval on the real line.
Examples:
Gross national product (GNP)
money supply
interest rates
price of eggs
household income
expenditure on clothing

7. Dummy Variable A discrete random variable that is restricted
to two possible values (usually 0 and 1) is
called a dummy variable (also, binary or
indicator variable).
Dummy variables account for qualitative differences:
gender (0=male, 1=female),
race (0=white, 1=nonwhite),
citizenship (0=Indian., 1=not Indian),
income class (0=poor, 1=rich).

8. Every Random Variable (RV) has a probability distribution.
A probability distribution describes the set of all possible outcomes of a RV, and the probabilities associated with each possible outcome.
This is summarized by a probability distribution function (or pdf).

9. An alternate way to describe a probability distribution is the cumulative distribution function (or cdf).
It gives the probability that a RV takes a value less than or equal to a given value, Pr(X ≤ x).
Example: number of times a laptop crashes before a midterm;

10. Because continuous RVs can take an infinite number of values, the pdf and cdf cannot enumerate the probabilities of each of them.
Instead we describe the pdf and cdf using functions.
Usual notation for the pdf is f(x).
Usual notation for the cdf is F(x) = Pr(X ≤ x).
Because pdfs and cdfs of continuous RVs can also be complicated functions, we will just use pictures to represent them.
We plot outcomes, x, on the horizontal axis, and probabilities, f(x) or F(x), on the vertical axis.
The cdf is an increasing function that ranges from zero to one.

11. A list of all of the possible values taken by a
discrete random variable along with
their chances of occurring is called a probability
function or probability density function (pdf).
die x f(x)
one dot 1 1/6
two dots 2 1/6
three dots 3 1/6
four dots 4 1/6
five dots 5 1/6
six dots 6 1/6

12. f(x) = P(X=xi) 0 < f(x) < 1 A discrete random variable X
has pdf, f(x), which is the probability
that X takes on the value x.
f(x) = P(X=xi)
Therefore,
0 < f(x) < 1
If X takes on the n values: x1, x2, , xn,
then f(x1) + f(x2) f(xn) = 1.
For example in a throw of one dice:
(1/6) + (1/6) + (1/6) + (1/6) + (1/6) + (1/6)=1

13. In a throw of two dice, the discrete random variable X,
f(x) =(1/36)(2/36)(3/36)(4/36)(5/36)(6/36)(5/36)( 4/36)(3/36)(2/36)(1/36)
the pdf f(x) can be shown by the presented by height:
f(x) X
number, X, the possible outcomes of two dice

14. A continuous random variable uses area under a curve rather than the
height, f(x), to represent probability:
f(x)
red area
green area
0.1324
0.8676 . .
Rs.34,000
Rs.55,000 X
per capita income, X, in the United States

15. Since a continuous random variable has an
uncountably infinite number of values,
the probability of one occurring is zero.
P [ X = a ] = P [ a < X < a ] = 0
Probability is represented by area.
Height alone has no area.
An interval for X is needed to get
an area under the curve.

16. The area under a curve is the integral of
the equation that generates the curve: b
P [ a < X < b ] = f(x) dx a
For continuous random variables it is the
integral of f(x), and not f(x) itself, which
defines the area and, therefore, the probability.

17. Rules of Summation Rule 1: xi = x1 + x2 + . . . + xn
Rule 2: kxi = k xi
i = 1
Rule 3: xi +yi = xi + yi
i = 1 n
Note that summation is a linear operator
which means it operates term by term.

18. Rules of Summation (continued)
Rule 4: axi +byi = a xi + b yi
i = 1 n n
x1 + x xn
Rule 5: x = xi = 1 n n
i = 1
The definition of x as given in Rule 5 implies
the following important fact: n
xi x) = 0
i = 1

19. Rules of Summation (continued)
Rule 6: f(xi) = f(x1) + f(x2) f(xn)
i = 1 n
Notation: f(xi) = f(xi) = f(xi) n x i
i = 1 n
Rule 7:  f(xi,yj) = [ f(xi,y1) + f(xi,y2) f(xi,ym)]
i = 1 m
j = 1
The order of summation does not matter :
 f(xi,yj) =  f(xi,yj)
i = 1 n m
j = 1

20. The pdf and cdf effectively tell us “everything” we might want to know about a RV.
But sometimes we only want to describe particular features of a probability distribution.
One feature of interest in this course is the expected value or mean of a RV.
Another useful measure of the dispersion

21. The Mean of a Random Variable
The mean or arithmetic average of a
random variable is its mathematical
expectation or expected value, E(X).

22. Expected Value 1. Empirically:
There are two entirely different, but mathematically
equivalent, ways of determining the expected value:
1. Empirically:
The expected value of a random variable, X,
is the average value of the random variable in an
infinite number of repetitions of the experiment.
In other words, draw an infinite number of samples,
and average the values of X that you get.

23. Expected Value 2. Analytically:
The expected value of a discrete random
variable, X, is determined by weighting all
the possible values of X by the corresponding
probability density function values, f(x), and
summing them up.
In other words:
E(X) = x1f(x1) + x2f(x2) xnf(xn)

24. Empirical vs. Analytical
As sample size goes to infinity, the
empirical and analytical methods
will produce the same value.
In the empirical case when the
sample goes to infinity the values
of X occur with a frequency
equal to the corresponding f(x)
in the analytical expression.

25. Empirical (sample) mean:
x = xi/n
i = 1
where n is the number of sample observations.
Analytical mean:
E(X) = xif(xi)
i = 1 n
where n is the number of possible values of xi.
Notice how the meaning of n changes.

26. E (X) = xi f(xi) E (X ) = xi f(xi) E (X )= xi f(xi)
The expected value of X:
E (X) = xi f(xi)
i=1 n
The expected value of X-squared:
E (X ) = xi f(xi)
i=1 n 2
It is important to notice that f(xi) does not change!
The expected value of X-cubed:
E (X )= xi f(xi)
i=1 n 3

27. = 1.9 = 4.9 = 14.5 E(X) = 0 (.1) + 1 (.3) + 2 (.3) + 3 (.2) + 4 (.1)=
= 4.9
E( X ) = 0 (.1) + 1 (.3) + 2 (.3) + 3 (.2) +4 (.1) 3 3 =
= 14.5

28. E [g(X)] = g(xi) f(xi)n
i = 1
g(X) = g1(X) + g2(X)
E [g(X)] = g1(xi) + g2(xi)] f(xi) n
i = 1
E [g(X)] = g1(xi) f(xi) +  g2(xi) f(xi) n
i = 1
E [g(X)] = E [g1(X)] + E [g2(X)]

29. Adding and Subtracting Random Variables
E(X+Y) = E(X) + E(Y)
E(X-Y) = E(X) - E(Y)

30. E(X+a) = E(X) + a E(bX) = b E(X) Adding a constant to a variable will
add a constant to its expected value:
E(X+a) = E(X) + a
Multiplying by constant will multiply
its expected value by that constant:
E(bX) = b E(X)

31. Variance measures dispersion—how “spread out” a probability distribution is.
A large (small) variance means a RV is likely to take a wide (narrow) range of values.

32. Variance var(X) = average squared deviations
around the mean of X.
var(X) = expected value of the squared deviations
around the expected value of X.
var(X) = E [(X - E(X)) ] 2

33. var(X) = E [(X - EX) ] var(X) = E [(X - EX) ] = E [X - 2XEX + (EX) ]
= E(X ) - 2 EX EX + E (EX) 2 2 2
= E(X ) - 2 (EX) + (EX) 2 2
= E(X ) - (EX) 2 2
var(X) = E(X ) - (EX)

34.  var ( X ) = ( xi - EX ) f ( xi ) variance of a discrete
random variable, X: n 
var ( X ) = ( xi - EX ) 2 f ( xi ) i = 1
standard deviation is square root of variance

35. calculate the variance for a discrete random variable, X:2
xi f(xi) (xi - EX) (xi - EX) f(xi)
= (.1) = .529
= (.3) = .507
= (.1) = .009
= (.2) = .098
= (.3) = .867
 xi f(xi) = = 4.3
(xi - EX) f(xi) = = n
i = 1 n 2
i = 1

36. Z = a + cX var(Z) = var(a + cX) = E [(a+cX) - E(a+cX)] = c var(X)2 2 2
var(a + cX) = c var(X)

37. An important aside and a preview of things to come
In some sense, a RV’s probability distribution, expected value, and variance are abstract concepts.
More precisely, they are population parameters, characteristics of the whole set of possible observations of a RV.
As econometricians, our goal is to estimate these parameters (with varying degrees of precision).
We do that by computing statistics from a sample of data drawn from the population.
The usefulness of econometrics comes from learning about

38. Covariance cov(X,Y) = E[(X - EX)(Y-EY)]
The covariance between two random
variables, X and Y, measures the
linear association between them.
cov(X,Y) = E[(X - EX)(Y-EY)]
Note that variance is a special case of covariance.
cov(X,X) = var(X) = E[(X - EX) ] 2

39. cov(X,Y) = E [(X - EX)(Y-EY)]
= E [XY - X EY - Y EX + EX EY]
= E(XY) - EX EY - EY EX + EX EY
= E(XY) - 2 EX EY + EX EY
= E(XY) - EX EY
cov(X,Y) = E(XY) - EX EY

40. Y = 1
Y = 2
X = 0
.45
.15
.60
EX=0(.60)+1(.40)=.40
.40
.05
.35
X = 1
covariance
.50
.50
cov(X,Y) = E(XY) - EX EY
= (.40)(1.50) =
= .15
EY=1(.50)+2(.50)=1.50
EX EY = (.40)(1.50) = .60
E(XY) = (0)(1)(.45)+(0)(2)(.15)+(1)(1)(.05)+(1)(2)(.35)=.75

41. Joint pdf A joint probability density function,
f(x,y), provides the probabilities
associated with the joint occurrence
of all of the possible pairs of X and Y.

42. joint pdf f(x,y) f(0,1) f(0,2) .45 .15 .05 .35 f(1,1) f(1,2)
Survey of College City, New Delhi
college grads
in household
joint pdf
f(x,y)
Y = 1
Y = 2
f(0,1)
f(0,2)
X = 0
.45
Special
homes
owned
.15
.05
.35
X = 1
f(1,1)
f(1,2)

43. E[g(X,Y)] =   g(xi,yj) f(xi,yj)
Calculating the expected value of
functions of two random variables.
E[g(X,Y)] =   g(xi,yj) f(xi,yj) i j
E(XY) =   xi yj f(xi,yj) i j
E(XY) = (0)(1)(.45)+(0)(2)(.15)+(1)(1)(.05)+(1)(2)(.35)=.75

44. Marginal pdf f(xi) =  f(xi,yj) f(yj) =  f(xi,yj)
The marginal probability density functions,
f(x) and f(y), for discrete random variables,
can be obtained by summing over the f(x,y)
with respect to the values of Y to obtain f(x)
with respect to the values of X to obtain f(y).
f(xi) =  f(xi,yj)
f(yj) =  f(xi,yj) j i

45. marginal f(X = 0) .45 .15 .60 f(X = 1) .40 .05 .35 .50 .50 f(Y = 1)
pdf for X:
f(X = 0)
X = 0
.45
.15
.60
f(X = 1)
.40
.05
.35
X = 1
marginal
pdf for Y:
.50
.50
f(Y = 1)
f(Y = 2)

46. Conditional pdf f(x,y) f(x,y) f(x|y) = f(y|x) = f(y) f(x)
The conditional probability density
functions of X given Y=y , f(x|y),
and of Y given X=x , f(y|x),
are obtained by dividing f(x,y) by f(y)
to get f(x|y) and by f(x) to get f(y|x).
f(x,y)
f(x,y)
f(x|y) =
f(y|x) =
f(y)
f(x)

47. conditonal
Y = 1
Y = 2
f(Y=1|X = 0)=.75
f(Y=2|X= 0)=.25
.75
.25
.45
.15
.60
X = 0
f(X=0|Y=1)=.90
f(X=0|Y=2)=.30
.90
.30
f(X=1|Y=1)=.10
f(X=1|Y=2)=.70
.10
.70
X = 1
.05
.35
.40
.125
.875
f(Y=1|X = 1)=.125
f(Y=2|X = 1)=.875
.50
.50

48. Independence f(xi,yj) = f(xi) f(yj) X and Y are independent random
variables if their joint pdf, f(x,y),
is the product of their respective
marginal pdfs, f(x) and f(y) .
f(xi,yj) = f(xi) f(yj)
for independence this must hold for all pairs of i and j

49. not independent f(X = 0) .45 .15 .60 f(X = 1) .40 .05 .35 .50 .50
Y = 1
Y = 2
marginal
pdf for X:
.50x.60=.30
.50x.60=.30
f(X = 0)
X = 0
.45
.15
.60
f(X = 1)
.40
.05
.35
X = 1
.50x.40=.20
.50x.40=.20
The calculations
in the boxes show
the numbers
required to have
independence.
marginal
pdf for Y:
.50
.50
f(Y = 1)
f(Y = 2)

50. Correlation cov(X,Y) (X,Y) = var(X) var(Y)
The correlation between two random
variables X and Y is their covariance
divided by the square roots of their
respective variances.
cov(X,Y)
(X,Y) =
var(X)
var(Y)
Correlation is a pure number falling between -1 and 1.

51. Y = 1
Y = 2
EX=.40 2 2 2
EX=0(.60)+1(.40)=.40
X = 0
.45
.15
.60 2 2
var(X) = E(X ) - (EX)
= (.40)
= .24 2
.40
.05
.35
X = 1
cov(X,Y) = .15
correlation
.50
.50
EY=1.50
cov(X,Y) 2 2 2
(X,Y) =
EY=1(.50)+2(.50) = = 2 2
var(Y) = E(Y ) - (EY)
= (1.50)
= .25
var(X)
var(Y) 2
(X,Y) = .61

52. Zero Covariance & Correlation
Independent random variables
have zero covariance and,
therefore, zero correlation.
The converse is not true.

53. E[c1X + c2Y] = c1EX + c2EY E[c1X1+...+ cnXn] = c1EX1+...+ cnEXn
Since expectation is a linear operator,
it can be applied term by term.
The expected value of the weighted sum
of random variables is the sum of the
expectations of the individual terms.
E[c1X + c2Y] = c1EX + c2EY
In general, for random variables X1, , Xn :
E[c1X cnXn] = c1EX cnEXn

54. var(c1X + c2Y)=c1 var(X)+c2 var(Y) + 2c1c2cov(X,Y)
The variance of a weighted sum of random
variables is the sum of the variances, each times
the square of the weight, plus twice the covariances
of all the random variables times the products of
their weights.
Weighted sum of random variables: 2 2
var(c1X + c2Y)=c1 var(X)+c2 var(Y) + 2c1c2cov(X,Y)
Weighted difference of random variables: 2
var(c1X  c2Y) = c1 var(X)+c2 var(Y)  2c1c2cov(X,Y) 2

55. Y ~ N(,2) The Normal Distribution - exp f(y) = y (y - )2  2 2
2 2
(y - )2 - 1
exp
f(y) =
2  2
f(y) y 

56. Z = (y - )/ Z ~ N(,) - The Standardized Normal exp f(z) = z2 2 2 1
exp
f(z) = 2
2 

57. y Y ~ N(,2)  f(y)    a Y -  a -  a - 
P [ Y > a ] = P > = P Z >   

58. y Y ~ N(,2)  f(y)      a b a -  Y -  b - 
P [ a < Y < b ] = P < <
= P < Z <   
a - 
b -   

59. W ~ N[ E(W), var(W) ] W = c1Y1 + c2Y2 + . . . + cnYn
Linear combinations of jointly
normally distributed random variables
are themselves normally distributed.
Y1 ~ N(1,12), Y2 ~ N(2,22), , Yn ~ N(n,n2)
W = c1Y1 + c2Y cnYn
W ~ N[ E(W), var(W) ]

60. Chi-Square If Z1, Z2, . . . , Zm denote m independent
N(0,1) random variables, and
V = Z1 + Z Zm
, then V ~ (m) 2
V is chi-square with m degrees of freedom.
If Z1, Z2, , Zm denote m independent
N(0,1) random variables, and
V = Z1 + Z Zm
, then V ~ (m) 2
V is chi-square with m degrees of freedom.
mean: E[V] = E[ (m) ] = m 2
variance: var[V] = var[ (m) ] = 2m 2

62. Student - t ~ t(m) t = t is student-t with m degrees of freedom.
If Z ~ N(0,1) and V ~ (m) and if Z and V
are independent then, 2 Z
t =
~ t(m) V m
t is student-t with m degrees of freedom.
mean: E[t] = E[t(m) ] = 0 symmetric about zero
variance: var[t] = var[t(m) ] = m/(m-2)

63. F Statistic ~ F(m1,m2) F = F is an F statistic with m1 numerator
If V1 ~ (m1) and V2 ~ (m2) and if V1 and V2
are independent, then 2 2 V1 m1
F =
~ F(m1,m2) V2 m2
F is an F statistic with m1 numerator
degrees of freedom and m2 denominator
degrees of freedom.