Academic Integrity: tutoring, explanations, and feedback — we don’t complete graded work or submit on a student’s behalf.

An economist at T&TEC is analysing the determinants of electricity demand in his

ID: 3220167 • Letter: A

Question

An economist at T&TEC is analysing the determinants of electricity demand in his country. The independent variables he uses in the model are:

1. nocust - average number of customers in thousands

2. price - the average price in cents per kwh for families

3. incm – Total personal income in $ millions population in thousands

The dependent variable, rekwh, represents the electricity demand, which is the kilowatt-hour sale to residential customers (million).

The results of the regression model along with the correlation matrix and residual plots are shown below:

                                                              Model 2: OLS, using observations N=75

                                                                Dependent variable: reskwh

                                                                Coefficient                          Std. Error             t-ratio                   p-value

Const                                                    -322.52                                 208.941                 -1.5436                 0.12713

Nocust                                                 2.28999                                 0.483557              4.7357                   0.00001

Price                                                      -12.2772                               4.99846                 -2.4562                 0.01649

Incm                                                      -0.0355949                          0.0204259            -1.7426                 0.08573

Mean dependent var                     1027.491                              S.D dependent var                           238.2678

Sum squared resid                           482388.5                              S.E of regression                               82.42696

R-squared                                           0.885176                              Adjusted R-squared                        0.880324

F(3,71)                                                  182.4450                              P-value(F)                                           2.74e-33

Log-liklihood                                      -435.2585                             Akaike criterion                                 878.5170

Schwartz criterion                            887.7870                              Hannan-Quinn                                  882.2184

                Correlation matrix of variables used in the model

Reskwh

Nocust

Price

Incm

Reskwh

1.0000

0.9366

0.7196

0.9245

Nocust

1.0000

0.8211

0.9930

Price

1.0000

0.8056

Incm

1.0000

a. Write down the OLS regression model estimate.   

b. Is the model statistically significant?    

c. Which variables in the model are statistically significant? Use a=5%?

d. What is the term multicollinearity?     

e. Would you use this model to analyze the determinants of demand for electricity? Provide reasons to support your answer.    

Reskwh

Nocust

Price

Incm

Reskwh

1.0000

0.9366

0.7196

0.9245

Nocust

1.0000

0.8211

0.9930

Price

1.0000

0.8056

Incm

1.0000

Explanation / Answer

Answer:

An economist at T&TEC is analysing the determinants of electricity demand in his country. The independent variables he uses in the model are:

1. nocust - average number of customers in thousands

2. price - the average price in cents per kwh for families

3. incm – Total personal income in $ millions population in thousands

The dependent variable, rekwh, represents the electricity demand, which is the kilowatt-hour sale to residential customers (million).

The results of the regression model along with the correlation matrix and residual plots are shown below:

                                                              Model 2: OLS, using observations N=75

                                                                Dependent variable: reskwh

                                                                Coefficient                          Std. Error             t-ratio                   p-value

Const                                                    -322.52                                 208.941                 -1.5436                 0.12713

Nocust                                                 2.28999                                 0.483557              4.7357                   0.00001

Price                                                      -12.2772                               4.99846                 -2.4562                 0.01649

Incm                                                      -0.0355949                          0.0204259            -1.7426                 0.08573

Mean dependent var                     1027.491                              S.D dependent var                           238.2678

Sum squared resid                           482388.5                              S.E of regression                               82.42696

R-squared                                           0.885176                              Adjusted R-squared                        0.880324

F(3,71)                                                  182.4450                              P-value(F)                                           2.74e-33

Log-liklihood                                      -435.2585                             Akaike criterion                                 878.5170

Schwartz criterion                            887.7870                              Hannan-Quinn                                  882.2184

electricity demand = -322.52+2.28999*Nocust-12.2772*price-0.0355949*incm

Calculated F=182.445, P=0.000 which is < 0.05 level.

The model is significant.

c. Which variables in the model are statistically significant? Use a=5%?

The variable nocust is significant, t=4.7357, P=0.00001 which is < 0.05 level.

The variable price is significant, t=-2.4562, P=0.01649 which is < 0.05 level.

The variable incm is not significant, t=-1.7426, P=0.08573 which is > 0.05 level.

d. What is the term multicollinearity?     

Multicollinearity is a state of very high intercorrelations or inter-associations among the independent variables.

Correlation matrix of variables used in the model is used to check for this.

e. Would you use this model to analyze the determinants of demand for electricity? Provide reasons to support your answer.    

The model is significant and 88% variation in electricity demand is explained by the model.

We can use this model to analyze the determinants of demand for electricity.

Hire Me For All Your Tutoring Needs
Integrity-first tutoring: clear explanations, guidance, and feedback.
Drop an Email at
drjack9650@gmail.com
Chat Now And Get Quote