mo&ro 1.regresi (dr.etty elika)
TRANSCRIPT
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
1/28
Regression Analysis
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
2/28
Scatter plots
Regression analysis requires intervaland ratio-level data.
To see if your data fits the models of
regression, it is wise to conduct ascatter plot analysis.
The reason?
Regression analysis assumes a linearrelationship. If you have a curvilinearrelationship or no relationship,regression analysis is of little use.
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
3/28
Types of Lines
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
4/28
Scatter plot
15.0 20.0 25.0 30.0 35.0
Percent of Population 25 years and Over with Bachelor's Degree or More,March 2000 estimates
20000
25000
30000
35000
40000
Pe
rsonalIncomePerCap
ita,currentdollars,
1999
Percent of Population with Bachelor's Degree by Personal Income Per Capita
This is a linearrelationship
It is a positiverelationship.
As population withBAs increases sodoes the personal
income per capita.
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
5/28
Regression Line
15.0 20.0 25.0 30.0 35.0
Percent of Population 25 years and Over with Bachelor's Degree or More,March 2000 estimates
20000
25000
30000
35000
40000
PersonalIncomePerCapita,currentdollars,
1999
Percent of Population with Bachelor's Degree by Personal Income Per Capita
R Sq Linear = 0.542
Regression line isthe best straight linedescription of the
plotted points anduse can use it todescribe theassociation between
the variables.
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
6/28
Things to remember
Regressions are still focuses on
association, not causation.
Association is a necessaryprerequisite for inferring causation,
but also:1. The independent variable must preceded
the dependent variable in time.
2. The two variables must be plausibly linedby a theory,
3. Competing independent variables mustbe eliminated.
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
7/28
Regression Table
The regressioncoefficient is not agood indicator for thestrength of the
relationship.Two scatter plots withvery different
dispersions couldproduce the sameregression line.
15.0 20.0 25.0 30.0 35.0
Percent of Population 25 years and Over with Bachelor's Degree or More,March 2000 estimates
20000
25000
30000
35000
40000
Per
sonalIncomePerCapita,
currentdollars,
1999
Percent of Population with Bachelor's Degree by Personal Income Per Capita
R Sq Linear = 0.542
0.00 200.00 400.00 600.00 800.00 1000.00 1200.00
Population Per Square Mile
20000
25000
30000
35000
40000
PersonalIncomePerCapita,
currentdollars,
1999
Percent of Population with Bachelor's Degree by Personal Income Per Capita
R Sq Linear = 0.463
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
8/28
Regression coefficient
The regression coefficient is the slope ofthe regression line and tells you whatthe nature of the relationship betweenthe variables is.
How much change in the independentvariables is associated with how muchchange in the dependent variable.
The larger the regression coefficient themore change.
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
9/28
Pearsons r
To determine strength you look at howclosely the dots are clustered around theline. The more tightly the cases are
clustered, the stronger the relationship,while the more distant, the weaker.
Pearsons r is given a range of-1 to + 1
with 0 being no linear relationship at all.
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
10/28
Reading the tables
When you run regression analysis on SPSS you get a3 tables. Each tells you something about therelationship.
The first is the model summary.
The R is the Pearson Product Moment CorrelationCoefficient.
In this case R is .736
R is the square root of R-Squared and is thecorrelation between the observed and predictedvalues of dependent variable.
Model Summary
.736a .542 .532 2760.003Model1
R R Square
Adjusted
R Square
Std. Error of
the Estimate
Predictors: (Constant), Percent of Population 25 years
and Over with Bachelor's Degree or More, March 2000
estimates
a.
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
11/28
R-Square
R-Square is the proportion of variance in thedependent variable (income per capita) which can bepredicted from the independent variable (level ofeducation).
This value indicates that 54.2% of the variance inincome can be predicted from the variable education.
R-Square is also called the coefficient ofdetermination.
Model Summary
.736a .542 .532 2760.003Model1
R R Square
Adjusted
R Square
Std. Error of
the Estimate
Predictors: (Constant), Percent of Population 25 years
and Over with Bachelor's Degree or More, March 2000
estimates
a.
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
12/28
Adjusted R-square
The adjusted R-square attempts to yield a more honestvalue to estimate the R-squared for the population. Thevalue of R-square was .542, while the value of AdjustedR-square was .532. There isnt much difference because
we are dealing with only one variable.When the number of observations is small, there will bea much greater difference between R-square andadjusted R-square.By contrast, when the number of observations is very
large, the value of R-square and adjusted R-square willbe much closer.
Model Summary
.736a .542 .532 2760.003
Model
1
R R SquareAdjustedR Square
Std. Error ofthe Estimate
Predictors: (Constant), Percent of Population 25 years
and Over with Bachelor's Degree or More, March 2000
estimates
a.
ANOVA
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
13/28
ANOVA
The p-value associated with this F value is very small (0.0000).These values are used to answer the question "Do theindependent variables reliably predict the dependent variable?".
The p-value is compared to your alpha level (typically 0.05) and,if smaller, you can conclude "Yes, the independent variablesreliably predict the dependent variable".
If the p-value were greater than 0.05, you would say that thegroup of independent variables does not show a statisticallysignificant relationship with the dependent variable, or that thegroup of independent variables does not reliably predict thedependent variable.
ANOVAb
4.32E+08 1 432493775.8 56.775 .000a
3.66E+08 48 7617618.586
7.98E+08 49
Regression
ResidualTotal
Model
1
Sum of
Squares df Mean Square F Sig.
Predi ctors: (Constant), Percent of Population 25 years and Over with Bachelor's
Degree or More, March 2000 estimates
a.
Dependent Variable: Personal Income Per Capi ta, current doll ars, 1999b.
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
14/28
Coefficients
B - These are the values for the regression equationfor predicting the dependent variable from the
independent variable.These are called unstandardized coefficientsbecause they are measured in their naturalunits. As such, the coefficients cannot be comparedwith one another to determine which one is moreinfluential in the model, because they can bemeasured on different scales.
Coefficientsa
10078.565 2312.771 4.358 .000
688.939 91.433 .736 7.535 .000
(Constant)
Percent of Population
25 years and Over
with Bachelor's
Degree or More,
March 2000 estimates
Model
1
B Std. Error
Unstandardized
Coefficients
Beta
Standardized
Coefficients
t Sig.
Dependent Variable: Personal Income Per Capita, current dollars, 1999a.
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
15/28
Coefficients
This chart looks at two variables and shows howthe different bases affect the B value. That is whyyou need to look at the standardized Beta to seethe differences.
Coefficientsa
13032.847 1902.700 6.850 .000
517.628 78.613 .553 6.584 .000
7.953 1.450 .461 5.486 .000
(Constant)
Percent of Population
25 years and Over
with Bachelor's
Degree or More,
March 2000 estimates
Population Per
Square Mile
Model
1
B Std. Error
Unstandardized
Coefficients
Beta
Standardized
Coefficients
t Sig.
Dependent Variable: Personal Income Per Capita, current dollars, 1999a.
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
16/28
Coefficients
Beta - The are the standardized coefficients.
These are the coefficients that you would obtain if youstandardized all of the variables in the regression, includingthe dependent and all of the independent variables, and ranthe regression.
By standardizing the variables before running the regression,you have put all of the variables on the same scale, and youcan compare the magnitude of the coefficients to see whichone has more of an effect.
You will also notice that the larger betas are associated with
the larger t-values.
Coefficientsa
10078.565 2312.771 4.358 .000
688.939 91.433 .736 7.535 .000
(Constant)
Percent of Population
25 years and Over
with Bachelor's
Degree or More,
March 2000 estimates
Model1
B Std. Error
Unstandardized
Coefficients
Beta
Standardized
Coefficients
t Sig.
Dependent Variable: Personal Income Per Capita, current dollars, 1999a.
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
17/28
The Basic Regression Model
Simple Linear RegressionY = a + bX
Multiple Linear Regression
Y = a + b1X1 + b2X2 +b3X3 +
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
18/28
Model Summary
.849a .721 .709 2177.791
Model
1
R R Square
Adjusted
R Square
Std. Error of
the Estimate
Predictors: (Constant), Population Per Square Mi le,
Percent of Population 25 years and Over with
Bachelor's Degree or More, March 2000 estimates
a.
ANOVAb
5.75E+08 2 287614518.2 60.643 .000a
2.23E+08 47 4742775.141
7.98E+08 49
Regression
Residual
Total
Model
1
Sum of
Squares df Mean Square F Sig.
Predictors: (Constant), Population Per Square Mil e, Percent of Population 25 years
and Over with Bachelor's Degree or More, March 2000 estimates
a.
Dependent Variable: Personal Income Per Capi ta, current dollars, 1999b.
Multiple
Regression
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
19/28
Coefficientsa
13032.847 1902.700 6.850 .000
517.628 78.613 .553 6.584 .000
7.953 1.450 .461 5.486 .000
(Constant)
Percent of Population
25 years and Over
with Bachelor's
Degree or More,
March 2000 estimates
Population Per
Square Mile
Model
1
B Std. Error
Unstandardized
Coefficients
Beta
Standardized
Coefficients
t Sig.
Dependent Variable: Personal Income Per Capita, current dollars, 1999a.
Multiple
Regression
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
20/28
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
21/28
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
22/28
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
23/28
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
24/28
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
25/28
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
26/28
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
27/28
1.00.80.60.40.20.0
Observed Cum Prob
1.0
0.8
0.6
0.4
0.2
0.0
Ex
pectedCumP
rob
Normal P-P Plot of Regression Standardized Residual
Dependent Variable: Jumlah Penjualan
T
-
7/31/2019 Mo&Ro 1.Regresi (Dr.etty Elika)
28/28
Tugas
Pilih salah satu kasus pada bidang
apa saja yang dapat analisis denganRegresi Berganda
Olah Data anda menggunakan salahsatu perangkat lunak yang sesuai.
Maknai hasil pengolahan data
tersebut.