You are on page 1of 329

:

Statistics status
.

.


.


. .

.

:
.
.
.

.

15
.

:


.

:

.

.


.



.

.

.

)
(
.

.

-:
. .
.

.
.
:

.
.
... .
.
400 145
.
:
.

)Statistical Process
( Control

.


.
.
.

:


.

.




...




/ :


.
. .
.
.



.

:
: .
: .
: .
.
.

.

)(



90 .
.


: .

.

)(

1
2


) (
)
(


:

:

) 8 10 (...


.
.



.
.

Discrete or Continuous



) (

1000



.
.

...
) (
.
11 .
3933 2 26

...
)
( .
250
173 1387
250
138 1387


) (
) (



.
x
x-bar
.



outliers .

X
X n i


50


.



.
1 4 3 8 2 :
8 4 3 2 1 :

8 1 4 3 8 2 :
8 8 4 3 2 1 :
= )3.5 = 2/(4+3


.



.

Minitab:
Variable
Phone
Variable
Phone

N
139

Mean
121.6

Minimum
2.0

Median
60.0
Maximum
2000.0

TrMean
88.1
Q1
30.0

N =

StDev
217.7
Q3
120.0

SE Mean
18.5

:

) (unimodal
)(multimodal

20

0
2.0 2.2 2.4 2.6 2.8 3.0 3.2 3.4 3.6 3.8 4.0

GPAs

Percent

10

GPA


Descriptive Statistics
Variable
GPA

N
92

Mean
3.0698

Variable
GPA

Minimum
2.0200

Median
3.1200
Maximum
3.9800

TrMean
3.0766

StDev
0.4851

Q1
2.6725

SE Mean
0.0506
Q3
3.4675


Variable
Males
Females
All

N
84
89
176

Variable SE Mean
Males
0.331
Females
0.305
All
0.303

Mean
70.048
64.798
67.313
Min
63.0
56.0
56.0

Median
70.000
65.000
67.000
Max
76.0
77.0
77.0

TrMean
70.092
64.753
67.291
Q1
68.0
63.0
64.0

StDev
3.030
2.877
4.017
Q3
72.0
67.0
70.0


Number of Music CDs of Spring 1998 Stat 250 Students

Frequency

20

10

0
0

100

200

300

Number of Music CDs

400

100

200

Number of CDs

300

400


Descriptive Statistics
Variable
CDs

N
92

Mean
61.04

Variable
CDs

Minimum
0.00

Median
46.50
Maximum
400.00

TrMean
52.93
Q1
21.50

StDev
62.90

SE Mean
6.56

Q3
83.00

30

Percent

20

10

0
50

55

60

65

70

75

80

grades

85

90

95 100


Variable
grades
Variable
grades

N
22

Mean
89.18
Minimum
50.00

Median
93.50
Maximum
100.00

TrMean
90.60
Q1
87.00

StDev
12.92

SE Mean
2.76
Q3
98.00



.

.
.



.

.


GPAs of Spring 1998 Stat 250 Students

Frequency

20

10

0
2.0 2.2 2.4 2.6 2.8 3.0 3.2 3.4 3.6 3.8 4.0

GPA


Descriptive Statistics
Variable
GPA

N
92

Mean
3.0698

Variable
GPA

Minimum
2.0200

Median
3.1200
Maximum
3.9800

TrMean
3.0766

StDev
0.4851

Q1
2.6725

1.96 = 2.02 - 3.98 =

SE Mean
0.0506
Q3
3.4675


) 75(
) 25(
IQR = Q3-Q1
.
.


GPAs of Spring 1998 Stat 250 Students

Frequency

20

10

0
2.0 2.2 2.4 2.6 2.8 3.0 3.2 3.4 3.6 3.8 4.0

GPA


Descriptive Statistics
Variable
GPA

N
92

Mean
3.0698

Variable
GPA

Minimum
2.0200

Median
3.1200
Maximum
3.9800

TrMean
3.0766

StDev
0.4851

Q1
2.6725

SE Mean
0.0506
Q3
3.4675

IQR = 3.4675 - 2.6725 = 0.795

.1
.
.2
.
.3
.

2
(x

x
)

2
s
n 1

2
.
s2
.

.
.
.
.


s .


.

.


Fastest Ever Driving Speed
226 Stat 100 Students, Fall '98

100
Men

126
Women
70

80

90

100 110 120 130 140 150 160


Speed (MPH)


Sex
N
female 126
male
100
female
male

Mean
91.23
06.79

Minimum
65.00
75.00

Median
90.00
110.00
Maximum
120.00
162.00

TrMean
90.83
105.62

StDev SE Mean
11.32
1.01
17.39
1.74

Q1
85.00
95.00

Q3
98.25
118.75

Females: s = 11.32 mph and s2 = 11.322 = 128.1 mph2


Males: s = 17.39 mph and s2 = 17.392 = 302.5 mph2


Fastest Ever Driving Speed

Sex
male

female

120

170

220

KPH

270


Sex
female
male

N
126
100

Mean
152.05
177.98

Sex
Minimum
female 108.33
male
125.00

Median
150.00
183.33

Maximum
200.00
270.00

TrMean
151.39
176.04

Q1
141.67
158.33

StDev SE Mean
18.86
1.68
28.98
2.90

Q3
163.75
197.92

Females: s = 18.86 kph and s2 = 18.862 = 355.7 kph2


Males: s = 28.98 kph and s2 = 28.982 = 839.8 kph2



100



.


Sex
N
Mean
female 126 91.23
male
100 106.79
female
male

Minimum
65.00
75.00

Median
90.00
110.00
Maximum
120.00
162.00

TrMean
90.83
105.62

StDev SE Mean
11.32
1.01
17.39
1.74

Q1
85.00
95.00

Females: CV = (11.32/91.23) x 100 = 12.4


Males: CV = (17.39/106.79) x 100 = 16.3

Q3
98.25
118.75


Sex
female
male

N
126
100

Mean
152.05
177.98

Sex
Minimum
female 108.33
male
125.00

Median
150.00
183.33

Maximum
200.00
270.00

TrMean
151.39
176.04

Q1
141.67
158.33

StDev SE Mean
18.86
1.68
28.98
2.90

Q3
163.75
197.92

Females: CV = (18.86/152.05) x 100 = 12.4


Males: CV = (28.98/177.98) x 100 = 16.3


...



.

.

.




,A, B, C .

1
.
.
.
.
A ) P(A .

:

.


.
.
.



...


IQ
(Intervals of size 20)
40

Percent

30

20

10

0
55

75

95

IQ

115

135


=
IQ
(Intervals of size 20)

Density

0.02

0.01

0.00
55

75

95

IQ

115

135

...
IQ
(Intervals of size 10)

Density

0.02

0.01

0.00
55

65

75

85

95

IQ

105

115

125

135

...
IQ
(Intervals of size 5)
0.03

Density

0.02

0.01

0.00
50

60

70

80

90

100

IQ

110 120

130 140

...


.:
)P(X > 120), P(X<100), P(110 < X < 120
=
= 1
0 .
P(X=120) = 0

p.d.f
Bell-shaped curve
0.08
Mean = 70 SD = 5

0.07

Density

0.06
0.05
0.04

Mean = 70 SD = 10

0.03
0.02
0.01
0.00
40

50

60

70

Grades

80

90

100



.
.
.

.

75
Probability student scores higher than 75?
0.08
0.07

Density

0.06
0.05
P(X > 75)

0.04
0.03
0.02
0.01
0.00
55

60

65

70

Grades

75

80

85


.

.
)
(
standardize.

...

x
. z .:
Z = (X- )/

0
Z
.1
z .

z
Standard Normal Curve
0.4

Density

0.3

0.2
Tail probability
P(Z > z)

0.1

0.0
-4

-3

-2

-1

70 65

0.08
0.07

Density

0.06
0.05
P(65 < X < 70)

0.04
0.03
0.02
0.01
0.00
55

60

65

70

Grades

75

80

85

65

0.08
0.07

Density

0.06
0.05
0.04
0.03
0.02

P(X < 65)

0.01
0.00
55

65

75

Grades

85

!

.

.
! ) (




.
:



.

.
:
20


.
)(

.



7/2
100

9/2
7/2

100



.
) :
(

. .

)(
:

.
.



) the null hypothesis (H0

) and the alternative hypothesis (HA
H0:
HA:




.

.




.
.


.
) (
) . (.

) (



.

.


.


...

:
:
.
: .

.



6/98


80
4/98 .

80

)(

H0: = 98.6
HA: < 98.6

= 98.6.
: 80
4/98 .
80 4/98
6/98

p-value

p-value
.
.
p-value
.
p-value ) 05/0
.

( )


MINITAB

p-value
.

Test of mu = 98.6000 vs mu < 98.6000


The assumed sigma = 0.600
Variable N
Temp
80

Mean
98.4

StDev
0.67

. p

SE Mean
Z
0.0671 -2.80

p-value

P
0.0026

)(
p-value 0026/0
6/98
80
.4/98
:
6/98.



6/98 .

6/98 .

6/98
.



7/2
100

9/2
7/2

100

100
9/2 7/2

P
=H0: = 2.7
<HA: = 2.7
100 9/2
6/0 P :

]) P( X 2.9) P[Z (2.9 2.7) /(0.6 / 100


P[Z 3.33] 0.0004


P .
9/2
7/2.
.
7/2.


HA: > 2.7 H0: = 2.7

P .
Z = 3.33
.
P
05/0
05/0 . .
=0.05 .



6/98


80
4/98 .

80

80
4/98 6/98

P
=H0: = 98.6
>HA: = 98.6
80 4/98 6/0
P :

]) P( X 98.4) P[Z (98.4 98.6) /(0.6 / 80


P[Z 2.98] 0.001


P
4/98
6/98.
.
6/98 .


HA: < 98.6 H0: = 98.6

P .
Z = -2.98
P 02/0
02/0
. . = 0.02.



20

17
16
.

64

64 17
23 20

P
=H0: = 20
HA: = 20 #
64 17 16
P :

]) P( X 17) P[Z (17 20) /(16 / 64


P[Z 1.5] 0.067
P( X 23) 0.067
P-value = 0.067 2 = 0.134


P .
17 23
20
.
.
20
.


HA: # $20 H0: = 20

P .
Z = -1.5

.


n > 60.


P
.



.

Testing Hypotheses Made about the Means of Two


Populations
START
Are the
two samples
dependent?

Paired t test (samples must come


from normal populations):
d d
t
sd n

Yes

No

where df = n - 1

z (x1 x2)(1 2)
s12 s22

n1 n2

Yes

Do n1 and n2
both exceed
30?
No

z test (normal distribution):

No

Are both populations


normally distributed?
Yes
After applying the F
test, what do we conclude
2
2
about 1 2 ?

Use nonparametric methods


Reject

12 22

separate variances t test


(samples must come from
normal populations)

Fail to reject
12 22
Pooled variances t test (samples must
come from normal populations):
t (x1 x2)(12)
sp 1 1
n1 n 2

where
and

(n1 1) s12 (n2 1)s22


s p (n1 1) (n2 1)
2

df n1 n2 2

.1 Nominal scale
. )
(

.2 :ordinal scale




.
.

.3 Interval Scale


.
20
10 10 .

.4 Ratio Scale




.
-



.

)
(

(1
(2 (3


.

(1
(2



.




.

) (
.
.
.




.
)
( ) (
.

30

20

10

40


2
.

.1 :


.


.


.1
.2
.3
.4

.
.
10
) 5 (
.
50 .

.
)
(

.2 )(T


.

.

.

.3 phi



.



.
.

.4
Pearson s coefficient contingency
C


.
.

.5 :





.

.1
kendall s rank correlation coefficient


.


. -1 +1
.

.2 Gamma coefficient


.

.

.3
Spearman Rank Correlation Coefficient

) ... 3 2 (1
.

.
rs +1 -1


.


Pearson Correlation Coefficient

r .

+1 -1
.

.

V -

) b (
)c (

-


.
-

.



.
-
.



) (
) (


.


t F

.


.
t F
.

t F :
.

)
(
.

.

.

- :t
.
) (

- ) F (ANOVA
.
)
(
: F

.

) (Scheffe test LSD
Tukey Duncan .

.


.



.
) (ANOVA

.


j
.


.

:

ANOVA .
A B C
A B B
C A .C
t
t
.
)
.

:
One-way Analysis of Variance
)(

.

:
Two way Analysis of Variance





)

(...





.

:

.1



.
.2
.
.3
.




.

: 1.

.

:

) (Two related

)
(

.1
)
( .
) (Ho
) ( .
.2 1000


.

.3

Wilcoxon Test




.

.
:

.

.4

Fridman Test


F
F .
.
: 30
) 1 ( ) 5 (
.

.5



:
.
:
) (
) (
) (
-

.6 -
Mann Whitney Test



.
: 30

1 5 .

.7 -
Kolmogrov Smirnov Test


20 5


50
.
.
.

.8 -
Kruskal Wallis Test



.

.
: 90
.
) 1 ( ) 5 ( .
:.
Ho

.

Median test


.


.
:

40 ) (
.



.



.





:
.1

.2

.3


.

) (Dependenc Technique
) (Interodependence Technique .



.


. .


.
*

.


.

.

.

.



) (0 1
.





.
:
:
) (
.

:


) (



.
SAS, SPSS, S-plus, R, MATLAB,


:

:


.




.


.



1877 .

.
:



)(Regress



:
)
( ) (


) ( .





.

) ( .

.

.




) ( .

.

.



.


.



y 1 2 1

y 1 2 12 3 1


2 1

y 1

)(

u
) (


)
(.
i

yi 1 2 i ui

y

.
:
.1
.
.2 .
.3
.
.4
.
.5 .
.6 )
( .



)Ordinary Least Square (OLS


)

(.

yi 1 2 i ui

yi 1 2 i ei

yi yi ei ei yi yi

e1 e2 e3 e4

2
2
Min e yi yi yi 1 2 i
2
i

2 1
2

e
i
.

i2 yi2 i i yi

1
2
2
2
i i

y
i

2
i


) (


) (
)
(


1
2 OLS

2
1

2 1
.



ui i
:

yi i 2 i ui

Ui

i
.

i
i

i
i
1
.



:
:1 ui

E ui i 0

ui Xi .

:2 u

cov ui , u j E ui E ui ui E u j E uiu j 0

u

.

:3 )( Ui
var ui xi E ui E ui E ui 0
2

Y
X .

y
X
.

:4 Ui , Xi

cov ui , xi E ui xi 0

x ) u
( y X
u . y
. X u
X u u
X u X u
u X u Y
.

:5
) (


.

. :
.1
.2

.3 Yi Xi ui



.




.


1
Yi 1 2
Xi

Yi 1 2 X i

:
-

.1
.2
.3

2
) (BLUE 2 :
.
Y .

E(2 ) 2


)
(.

The Gauss-Markov Theorem:


are the best linear unbiased
estimators (BLUE).

-


BLUE.

) r2 (

r2
:
.1
.2
.3
.4
.5
.6
.7

r .
+1 -1.
x y rxy
y ) x (ryx.
.
x y r = 0
) h (

. Y=X2h
r .
r
.


r2 r
r2
r
. )=r (R
.

R
2

R2 R2


R2 .

R2

.

R2 R2
.

ui
) (OLS

ui .
ui

.


OLS

.


ui .


E ui 0

E ui2 2

E ui u j 0

ui uj

) ui N (0,
2

OLS

.1
.2
.3



:

1

.5

.4

.6
.7
.8

N 2 ) (N-2 .

2 2 .
2

) (BLUE.

pr 2 2 1

1
.


: .
: .

.

.1 :1
)x( .
.2 :2 ui .
.3 :3 .
.4 :4 .
ui .
.5 :5 )x( .
.6 ui :6 1 2
.
.7 :7
.


) (OLS
BLUE.

4 1 6 :
:1 :

.
:4 : x
u x
.
:6 :u
. .


Multicollinearity
x3

x2

50

10

75

15

90

18

120

24

150

30



x


.

y 0 1 x1 2 xi2 2 xi3 ui

x
) . (
BLUE
.


- OLS
- : )
(
- :r t
.
R2 - .
- OLS


-
.1 .

.
.2


.
-
R2. 1 t
.2
.3
.4
.5 ) (Eigenvalue )(Condition Index
SAS .

:

.
.1 )(
.2 )
(
.3
.4
.5 ) (

Heteroscedasticity

ui
E (ui ) 2

)(
. )(


2
BLUE


) (GLS .

OLS


t F .


.1

:

ei2

.

x .

.2
.3
.4
.5
.6

:
.
-





.
:

) (
(
)
E (uiu j ) 0 i j .



) (

OLS

GLS
BLUE OLS
. OLS
.

OLS
)
(

) OLS (GLS

OLS


.
R2 .
t F


.

:
.1
.2
: DW.3

D.W
.1
.2
.3
.

.4
.
.5 .


.
.
:

.1
.2

.3
.4
.5
.6




.





5

.

: )(
.
:

.
:

: )(
.


:
) (
.

.


.
.

) . (
) ( ) (

) (F

) (
Reset



)
(


) (...
) (... .




.
) (Dummy Variable .


.

.



) (ACOV.
:
m m-1

) (




) (653
] [1 ] [2 ] [3 ][4


.
)(

.

.
.

. OLS
.
.


.
.

y Taybad .Taybad Khaf .Khaf Torbat jam .Torbat jam Roshan .Roshan Sradary .Sardary
Gaskojen .Gaskojen Abideym . Abideym Model .Model Omr .Omr Tarikh .Tarikh Saat .Saat



Torbatjam Khaf Taybad .
Torbatjam
Khaf

Taybad
.


. .

.



Roshan Sardary Gaskojen . S68
Model .
S68 .
Abideym
.



Omr Tarikh Saat .

Omr Tarikh 84 Saat

12
.
F t
.




. .


0 1 .


:
.1
.2
.3

)linear probability model (LPM


)(Logit
)(Probit


. ) (
) ( .
)
x y
.

)(
) ( .
) (OLS
.

.





OLS
.
:

)(2SLS
)(3SLS
)(I3SLS

)(LIML
)(FIML




.

.




.


Sewell Wright .
Formulated in series of papers published in
1918, 1921, 1934, 1960


.

.




.
.


= +


.
:

.1
.2
.3
.4
.5
.6
.7
.8
.9
.10

- :

. :
:
.
:

.


):(1380
-1 :

.
-2 :
.



.
.

.



.
x y
x1 y

x y
.




.
:

) ( P1 .
) (P5
) (P6 ) (P2
) (P4 ).(P6
) (P3
) (P4 )(P6
) (P6 .








e1 ) (P7

.
e2 ) (P8

.
e3 ) (P9



.

)(
.
)
( .
.


)
( .
e1)( x1 + =
.1

=
e2)( x3 +)( + x2 +)(x1
.2
e3)( + x2 +)(x1 =
.3


) (
.
e1)( x1 + =
.1

=
e2)( x3 +)( + x2 +)(x1
.2
e3)( + x2 +)(x1 =
.3

) (1 :2P
) (2 1P 2P 3P
) (3 5P 4P .

.

.
2
.

1
R




.



.


) (- 08/0
.
:

(57/0 47/0) = 27/0


(28/0 58/0) = 16/0
(28/0 22/0 47/0) = 03/0

27/0 + 16/0 + 03/0 = 46/0.


08/0 + 46/0 = 38/0 .

.

.


. ) P5 (P4
: )(P1

)(P3 ) (P2 ) .(P3


r
:
+
() x2 +
e1
e2)( x3 +

)(x1 + a =
+)(x1 =
() x2 +


.

. :
)
=
(p5) + (p1)(p3
)
=
(p4) + (p2)(p3

p3

X1 x4



4
x4
X1



1
x1
X4
1 4

...
OLS . OLS

.

2SLS
.


Factor Analysis



:
.1

.2
.3
.4


)


(.


.





.

:


) (1963
) (
.

:
.

.

.


.

82/0

63/0

44/0

78/0

35/0

51/0

68/0

64/0

21/0

...

...

...

...

...

...

...

...

32/0

68/0

17/0

25/0

43/0

12/0

49/0

09/0

60/0









) (exploratory
) (confirmatory .

) (field
. ) (1904
.
) .
(.



.
) (1973 .


.1
.
.2
.
.3 .



KMO
0 1 .

KMO 5/0
. 5/0 69/0
.
7/0
.
Kaiser-Meyer-Olkin


50 100
.
.

.
.

R .

.


.

You might also like