Professional Documents
Culture Documents
Michael Wijaya
19016055
I. Problem Identification
Investigate Multicollinearity between Bank 90 Day Bill with other financial variable
II. Methodology
Variable Identification
Statistic Method
Since the purpose is for prediction with only one metric dependent variables and the independent
variables are metric, the appropriate statistical technique is Multi-Linear Regression with the estimate
equation as follow:
The sample size used in this research is 71 observations and confidence level is 95% (significance
level of 0.05)
III. Result and Analysis
Model Summaryb
a. Predictors: (Constant), CPI, Retail, Gold, Prop, Transport, Build, Unemploy, Mining,
Energy, Finance, Develop, Indust, Resources, Bank, AllOrds
b. Dependent Variable: BankBill
ANOVAa
Total 94.385 70
1. Multiple R
Multiple R is the correlation coefficient that reflects only the degree of association between dependent
variable with independents variables. The result shows that the model‘s multiple R is 0.978 which
reflects user wiki is considered highly associated with Bank, AllOrds, Develop, Mining, Gold, Build, Prop,,
Indust, Energy, Finance, Resources, Transport, Retail, Unemploy, CPI
2. R Square
R square (R2) refers to as the coefficient of determination that indicates the percentage of total
variation dependent variable explained by the regression model. The model has R square value 0.956
which indicates that 95.6% of the total variation of user wiki explained by the regression model
consisting Bank, AllOrds, Develop, Mining, Gold, Build, Prop,, Indust, Energy, Finance, Resources,
Transport, Retail, Unemploy, CPI.
3. Adjusted R Square
Adjusted R square shows the proportion of variation in Y explained by all X variables adjusted for the
number of X variables used relative to the sample size. The adjusted R square of 0.945 indicates that
94.5% variation in Wikipedia users is explained by Bank, AllOrds, Develop, Mining, Gold, Build, Prop,,
Indust, Energy, Finance, Resources, Transport, Retail, Unemploy, CPI.
4. Standard Error of the Estimate
The standard error of the estimate is another measure of the accuracy of the model predictions. It
represents an estimate of the standard deviation of the actual dependent values around the regression
line; that is, it is a measure of variation around the regression line. Thus, Wikipedia users, given the
sample, disperse about 0.27334 or 27.334% from the model predicted values.
Coefficientsa
Standardized
Unstandardized Coefficients Coefficients Collinearity Statistics
1. Intercept
Intercept or constant value can be interpreted as the expected value of dependent variable when the
independent variable(s) is equal to zero. The intercept is 9.889. Therefore, the expected value of
Wikipedia users, given all of the predictor values are equal to zero, is 9.889.
On the other word, the 90 days bank bill is valued 9.889 when other variables are nonexistent. when it
has perceived usefulness, perceived ease of use, perceived enjoyment. This interpretative value
becomes dubious, additionally, the standard error for this estimation is relatively moderate with
standart error of 10.361 when at constant, and very low in other variables. Further interpretation will be
discussed in t value section.
4. t Value of Variables
The t value of variables indicates whether the researcher can confidently say, with a stated level of
error, that the coefficient is not equal to zero. The t value for constant, Bank, Develop, Mining, Gold,
Build, Energy, and CPI are statistically insignificant which can be seen from the significance level of
greater than 0.05. Thus, the all mentioned variables can be dropped from the equation. However, the
other regression coefficients are statistically significant. It means that the estimated regression
coefficient for AllOrds, Prop, Industry, Finance, Resources, Transport, Retail, Unemployment.
Regression Equation
Based on the SPSS results and analysis before, here is the regression equation for predicting annual net
sales.
with:
Y = 90 Days Bank Bill
X1 = AllOrds
X2 = Prop
X3 = Industry
X4 = Finance
X5 = Resources
X6 = Transport
X7 = Retail
X8 = Unemployment
Conclusion
1.
Based on the results and analysis, it can be conclude that:
1. X1 = AllOrds
2. X2 = Prop
3. X3 = Industry
4. X4 = Finance
5. X5 = Resources
6. X6 = Transport
7. X7 = Retail
8. X8 = Unemployment
Are significant to influence 90 days bank bill
2.
Factor that most account for increasing 90 Days Bank Bill is
With the variables that most increase bank bill is Resources, followed by Industry, Finance, and Retail.