statistik dan ekonometrik
DESCRIPTION
Materi Statistik dan Ekonometrik Diklat JFPP XVI Bappenas - MAP UGMTRANSCRIPT
-
5/24/2018 Statistik Dan Ekonometrik
1/38
1-1
Oleh:
Prof. Tri Widodo, Ph.D
-
5/24/2018 Statistik Dan Ekonometrik
2/38
1-2
Statistics is the science
of collecting, organizing,
presen ng, ana yz ng,
and interpreting
in making more
effective decisions.
First PhD Class: Lets cross the street and do your
economics!
What is Meant by Statistics?
-
5/24/2018 Statistik Dan Ekonometrik
3/38
1-3
Statistical techniques are
used extensively by
marketing, accounting,quality control,
,
sports people, hospital
educators, politicians,
physicians, and many
others.
Who Uses Statistics?
-
5/24/2018 Statistik Dan Ekonometrik
4/38
1-4
Descri tive StatisticsDescri tive Statistics: Methods of or anizinsummarizing, and presenting data in an informative way.
EXAMPLE : Election Result
Types of Statistics
-
5/24/2018 Statistik Dan Ekonometrik
5/38
1-5
Inferential StatisticsInferential Statistics:: A decision, estimate,prediction, or generalization about a population,based on a sample.
A PopulationPopulation A SampleSample is as a
of all possibleindividuals
portion, or part,
of the population
objects, ormeasurements of
nterest.
Types of Statistics
-
5/24/2018 Statistik Dan Ekonometrik
6/38
1-6
Contoh: Hasil penelitian heboh mengenai virginitas: 93%
Sampling
Sampel
Parameter Statistics
Statistik Inferensi
Ho:; H1:
-
5/24/2018 Statistik Dan Ekonometrik
7/38
1-7
DATA
Qualitative or attribute Quantitative or numerical
discrete
(number of children)
continuous
(time taken for an exam)
Summary of Types of Variables
-
5/24/2018 Statistik Dan Ekonometrik
8/38
1-8
Describing Data: Frequency Distributions and GraphicDescribing Data: Frequency Distributions and GraphicPresentationPresentation
.
,
polygon, and cumulative frequency polygon.
Present data using such graphic techniques as line
, , .
-
5/24/2018 Statistik Dan Ekonometrik
9/38
1-9
The three commonly used graphic forms are
Histograms, Frequency PolygonsHistograms, Frequency Polygons and a
Cumulative FrequencyCumulative Frequencydistribution.
H stogram s a graph n wh ch the class
midpoints or limits are marked on the horizontal.
The class frequencies are represented by the
adjacent to each other.
Graphic Presentation of aFrequency Distribution
-
5/24/2018 Statistik Dan Ekonometrik
10/38
1-10 3- 10
, ,
variance, and the standard deviation of ungrouped data.
Explain the characteristics, uses, advantages, and
disadvantages of each measure of dispersion.
-
5/24/2018 Statistik Dan Ekonometrik
11/38
1-11
It is calculated byTheArithmetic MeanArithmetic Mean is3- 11
summ ng e va uesand dividing by thenumber o values.
the most widely used
measure of location and
the data.
The major characteristics of the mean are:Average
Joe
It requires the interval scale.
ll values are used.
It is unique.
The sum of the deviations from the mean is 0.
Characteristics of the Mean
-
5/24/2018 Statistik Dan Ekonometrik
12/38
1-12 3- 12
e s e
midpoint of the values after
There are as manyvalues above thefrom the smallest to the
lar est.
the data array.
For an even set of values, the median will be thearithmetic avera e o the two middle numbers and is
found at the (n+1)/2 ranked observation.
The Median
-
5/24/2018 Statistik Dan Ekonometrik
13/38
1-13 3- 13
TheModeMode is another measure of location and
represents the value of the observation that appearsmost frequently.
Data can have more than one mode. If it has twomodes, it is referred to as bimodal, three modes,
trimodal, and the like.
-
5/24/2018 Statistik Dan Ekonometrik
14/38
1-14
is ersionis ersion
30
3- 14
refers to the
spread or 1520
variability inthe data.0
5
10
0 2 4 6 8 10 12
easures o spers on nc u e e o ow ng: ,,
mean deviation, variance, and standardmean deviation, variance, and standard
deviationdeviation.
value Measures of Dispersion
-
5/24/2018 Statistik Dan Ekonometrik
15/38
1-15 3- 15
s2 = (X - X)-
2ss =
Sample variance and standard deviation
-
5/24/2018 Statistik Dan Ekonometrik
16/38
1-16
Chapter Four
DataData
Develop and interpret a stem-and-leaf display.
Develop and interpret a dot plot.
Compute and interpret quartiles, deciles, and percentiles.
Compute and understand the coefficient of variation and the
coefficient of skewness.
Draw and interpret a scatter diagram.
-
5/24/2018 Statistik Dan Ekonometrik
17/38
1-174-17
Dot Plot
Dot plots: Report the details of each observation
Dot Plot
-
5/24/2018 Statistik Dan Ekonometrik
18/38
1-184-18
Stem-and-leaf Displays
Note: an advanta eStem-and-lea
of the stem-and-leafdisplay over adisplay: A statisticaltechnique forrequency
distribution is we do
not lose the identit
sp ay ng a se odata. Each
numerical value isof each observation.divided into two
parts: the leading
stem and thetrailing digits the
Stem-and-leaf Displays
leaf.
-
5/24/2018 Statistik Dan Ekonometrik
19/38
1-194-19
ox p ot is a graphicaldisplay, based on quartiles,
data.
are needed to
construct a box plot:the inimum Value,the First Quartile,
,Third Quartile, andtheMaximum
Box Plots
a ue.
-
5/24/2018 Statistik Dan Ekonometrik
20/38
1-204-20
Q1 Q3MaxMin Median
12 14 16 18 20 22 24 26 28 30 32
-
5/24/2018 Statistik Dan Ekonometrik
21/38
1-214-21
Skewness is the
lack of symmetry ofthe distribution.
Thecoefficient ofA value o 0 indicates a s mmetric
s ewnesscan rangefrom -3.00 up to 3.00
distribution.
formula:
Some software packages use a different formula
which results in a wider range for the coefficient.
MedianXsk = 3Movie
-
5/24/2018 Statistik Dan Ekonometrik
22/38
1-224-22
diagram: A
techni ue
ar a es mus e a eas n erva sca e .
used to showthe
Relationship can be positive (direct) or
relationship
between .
Example
The twelve days of stock prices and the overall marketindex on each day are given as follows:
Scatter diagram
-
5/24/2018 Statistik Dan Ekonometrik
23/38
1-23
Estimation an on i ence Interva sEstimation an on i ence Interva s
.
.
-
5/24/2018 Statistik Dan Ekonometrik
24/38
1-24
con idence interval
A point estimate is
is a range of values
w i t h i n w h i c h t h e(statistic) used to
e s t i m a t epopulation parameter
is expected to occur.population value( p a r a m e t e r ) .
The two confidencen erva s a are use
extensively are then Interval Estimate
s t a t e s t h e r a n g e.
population parameter
Point and Interval Estimates
-
5/24/2018 Statistik Dan Ekonometrik
25/38
1-25
standard deviation is
unknown, the
s
underlying population
is approximately
normal and the sam le
n
size is less than 30 we
use the t distribution.
The value of t for a given confidence level depends
upon its degrees of freedom.
Point and Interval Estimates
-
5/24/2018 Statistik Dan Ekonometrik
26/38
1-26
Confidence interval for the mean
szX
95% CI for the population mean
s
X 96.1 n
s
Intervals for n.
-
5/24/2018 Statistik Dan Ekonometrik
27/38
1-27
Ekonometrik
Ekonomi Matematika
-
5/24/2018 Statistik Dan Ekonometrik
28/38
1-28
Linear Regression an orre ationLinear Regression an orre ation
Draw a scatter diagram.
Understand and interpret the terms dependent variable and independent
variable.
Calculate and interpret the coefficient of correlation, the coefficient of
determination, and the standard error of estimate.
Conduct a test of hypothesis to determine if the population coefficient of
correlation is different from zero.
Calculate the least squares regression line and interpret the slope and interceptvalues.
Construct and interpret a confidence interval and prediction interval for the
dependent variable.
Set up and interpret an ANOVA table.
-
5/24/2018 Statistik Dan Ekonometrik
29/38
1-29
Correlation Anal sisCorrelation Anal sis is a rou o statistical techni ues tomeasure the association between two variables.
Advertising Minutes and $ Sales
is a chart that portrays10
15
20
25
30
les($thousan
ds)
between two variables.0
70 90 110 130 150 170 190
Advertising Minutes
S
TheIndependentIndependent
VariableVariableprovides theTheDependentDependent
basis for estimation. Itis the predictor variable.
being predicted or estimated.
Correlation Analysis
-
5/24/2018 Statistik Dan Ekonometrik
30/38
1-30
The Coe icient o CorrelationCoe icient o Correlation (r) is a measure of thestrength of the relationship between two variables.
Also called Pearsons r and It re uires interval or
Pearson s
earson s pro uct moment
correlation coefficient. ratio-scaled data.
-1.00 to 1.00.
-
-1 1
. .
indicate perfect and
trong correlation.
Negative values indicate aninverse relationship and
Values close to 0.0 indicateweak correlation.
The Coefficient of Correlation, r
direct relationship.
1 31
-
5/24/2018 Statistik Dan Ekonometrik
31/38
1-31
10
9
8
7
6
4
32
1
Y
0
0 1 2 3 4 5 6 7 8 9 10
X
Perfect Negative Correlation
1 32
-
5/24/2018 Statistik Dan Ekonometrik
32/38
1-32
10
9
8
7
6
4
32
1
Y
0
0 1 2 3 4 5 6 7 8 9 10
X
Perfect Positive Correlation
1 33
-
5/24/2018 Statistik Dan Ekonometrik
33/38
1-33
10
9
8
7
6
4
32
1
Y
0
0 1 2 3 4 5 6 7 8 9 10
X
Zero Correlation
1 34
-
5/24/2018 Statistik Dan Ekonometrik
34/38
1-34
10
8
7
6
5
4
3
2
1
Y
X
Strong Positive Correlation
1-35
-
5/24/2018 Statistik Dan Ekonometrik
35/38
1 35
2
proportion of the total variation in the dependent
variable Y that is ex lained or accounted or b the
variation in the independent variable (X).
It is the square of the coefficient of correlation.
It ranges from 0 to 1.It does not give any information on the direction
of the relationship between the variables.
Coefficient of Determination
1-36
-
5/24/2018 Statistik Dan Ekonometrik
36/38
1 36
variable (X) to estimate the dependent variable (Y).
The relationship Both variables
variables is linear.
interval scale.
The least squares criterion
is used to determine the
equation. That is the term(Y Y)2 is minimized.Regression Analysis
1-37
-
5/24/2018 Statistik Dan Ekonometrik
37/38
The regression equation is Y= a + bXThe regression equation is Y= a + bX
wherewhere
Y is the average predicted value of Y for any X.Y is the average predicted value of Y for any X.
a is the Ya is the Y--intercept.intercept.
s e es ma e va ue w en =s e es ma e va ue w en =
,,in Y for each change of one unit in Xin Y for each change of one unit in X
The least squares principle is used to obtain aThe least squares principle is used to obtain aand b.and b.
Regression Analysis
1-38
-
5/24/2018 Statistik Dan Ekonometrik
38/38
er ma as