Exercise data 2_-_forecasting
Download as PPTX, PDF0 likes180 views
This document discusses forecasting using econometric analysis. It provides data on income, competitors, population, and customers for 10 observations of restaurants. Multiple regression analysis was performed on the data to develop a model. The regression output shows an adjusted R-squared value of 43.8%, indicating the model explains a moderate amount of variation in the number of customers. The regression equation developed relates the number of customers (Y) to income (I), number of competitors (N), and population (P) within a 3 km radius.
Exercise data 2_-_forecasting
- 1. ECONOMETRIC “FORECASTING” BY DR. ILHAM SENTOSA dr.ilhamsentosa@limkokwing.edu.my
- 2. Exercise Data 3 - Business Analysis
- 3. Perform Business Analysis • Data on the average of customer’s income in radius 3 km from restaurant (I); • Number of competitor in radius 3 km (N); • Number of population in radius 3 km from restaurant (P); • Number of customer per year (Y).
- 4. Case Study • I = Income – 3 km from restaurant • N= Competitor in 2 km • P = Population in 3 km from restaurant • Y = No of Customer
- 5. Data of Income, Competitor, Population and Customers Obs. I N P Y 1 13,240 3 65,044 107,919 2 22,554 5 101,367 118,866 3 16,916 7 124,989 98,579 4 20,967 2 55,249 122,015 5 19,576 3 73,775 152,827 6 15,039 5 48,484 91,259 7 21,857 8 138,809 123,550 8 26,435 2 50,244 160,931 9 24,024 6 104,300 98,496 10 14,987 2 37,852 108,052
- 6. Instructions 1. Data Key In 2. Perform Multiple Regression Analysis 3. Analyze: Model Summary Table and Coefficient table
- 7. SPSS Output : Adj R 2 Model Summary Change Statis tics Adjus ted Std. Error of R Square Model R R Square R Square the Es tim ate Change F Change df1 df2 Sig. F Change 1 .791a .626 .438 17.263183 .626 3.342 3 6 .097 a. Predictors: (Cons tant), P, I, N
- 8. PREDICTION USING REGRESSION COEFFICIENTS a Coefficients Uns tandardized Standardized Coefficients Coefficients Correlations Collinearity Statis tics Model B Std. Error Beta t Sig. Zero-order Partial Part Tolerance VIF 1 (Cons tant) 82.167 28.171 2.917 .027 I 2.518 1.472 .477 1.711 .138 .564 .573 .427 .801 1.248 N -11.008 6.184 -1.058 -1.780 .125 -.437 -.588 -.445 .177 5.658 P .427 .405 .650 1.055 .332 -.163 .396 .264 .165 6.075 a. Dependent Variable: Y
- 9. Multiple Regressions Equation Y = 82.167 – 11.008(N) + 0.427(P) + 2.518(I)
- 10. Y = 82.167 – 11.008(N) + 0.427(P) + 2.518(I) • Analysis: 1. 1 New Restaurant (N) in 3 km, Customer reduce to 11.008 person. 2. Population in 3km increase to 1000 people, customer increase to 427 person. (Population Increase for 1 person , Customer increase to 0.427 person). 3. Customer Income in 3km Increase for RM.100 per year, Customer to serve also increase for 251 person per year. (Income increase for RM.1, Customer to serve in crease for 2.5 people). 4. Adjusted R2 = 43.8% , high influence
- 11. What is Your Decision?
- 12. Thank You