Regression Analysis: Real Estate Sector
By: Rahul Agarwal • Coursework • 1,398 Words • September 21, 2014 • 1,206 Views
Regression Analysis: Real Estate Sector
Regression Analysis: Real Estate Sector |
Avishek Dasgupta 13P136 Rahul Agarwal 13P158 Raman Mahajan 13P160 |
8/2/2014 |
[pic 1][pic 2][pic 3]
TABLE OF CONTENTS
- Objective of the study
- Description of data
- Empirical analysis
- Conclusion
OBJECTIVE OF THE STUDY
To determine the regression equation to forecast real estate index (CNX Realty) with respect to various associated independent variables.
DESCRIPTION OF DATA
Frequency of the data: Monthly
Time span of the data: 37 months (Aug-2011 to Aug-2014)
No. of observations: 37
Dependent Variable:
CNX Realty
Independent Variables:
CNX Metal Index Values
Ultra Tech Cement Prices
Dollar Prices
Interest Rates (Repo rate)
IIP Index Values
Crude Oil Prices
Details of the Dependent Variable
CNX Realty:
CNX Realty Index is designed to reflect the behavior and performance of Real Estate companies. The Index comprises of 10 companies listed on National Stock Exchange of India (NSE).CNX Realty Index is computed using free float market capitalization method, wherein the level of the index reflects the total free float market value of all the stocks in the index relative to particular base market capitalization value.
As the realty sector could be dependent on multiple factors like cement, steel, interest rates in the economy, crude oil prices, Index of Industrial Production (IIP) and dollar value we have considered such variables as independent variable.
Details of the Independent Variables
CNX Metal
The CNX Metal Index is designed to reflect the behavior and performance of the Metals sector (including mining). The CNX Metal Index comprises of 15 stocks that are listed on the National Stock Exchange (NSE).CNX Metal Index is computed using free float market capitalization method, wherein the level of the index reflects the total free float market value of all the stocks in the index relative to particular base market capitalization value.
This variable has been considered as steel is a primary resource in the construction industry and this index captures various steel sector companies.
Ultra Tech Cement
This is one of the major cement companies in India and its price changes would affect the construction industry. Hence this should serve as an important independent variable for analysis.
Dollar Prices
The dollar prices would affect the amount of investment in the realty sector and hence could be an important independent variable for analysis.
Interest Rates
The interest rates primarily the Repo rates will indicate the general lending rate in India and will govern the major financing source of the realty sector. Thus this may be an important independent variable.
Index of Industrial Production
This index captures the growth of various sectors of the economy thereby indicating the wellness of the economy. As the economy would play a major role in realty sector’s growth hence we consider IIP as a independent variable.
Crude Oil
Crude Oil prices generally affect the economy and would in turn indirectly affect the growth of realty sector hence Crude oil has been selected as one of the independent variables.
EMPIRICAL ANALYSIS
Running the regression analysis
The regression analysis is run in the EVIEWS software using the following command
LS CNX_REALTY C CNX_METAL CRUDE_OIL DOLLAR_PRICE IIP INTEREST_RATES ULTRA_TECH_CEMENT
Dependent Variable: CNX_REALTY | ||||
Method: Least Squares | ||||
Date: 08/02/14 Time: 14:09 | ||||
Sample: 2011M08 2014M08 | ||||
Included observations: 37 | ||||
Variable | Coefficient | Std. Error | t-Statistic | Prob. |
C | 535.8208 | 145.3440 | 3.686571 | 0.0009 |
CNX_METAL | 0.055683 | 0.015674 | 3.552637 | 0.0013 |
CRUDE_OIL | -0.005052 | 0.012089 | -0.417867 | 0.6790 |
DOLLAR_PRICE | -5.104570 | 2.134630 | -2.391314 | 0.0233 |
IIP | 0.339317 | 0.485912 | 0.698310 | 0.4904 |
INTEREST_RATES | -28.24337 | 15.61245 | -1.809028 | 0.0805 |
ULTRA_TECH_CEMENT | 0.038290 | 0.024198 | 1.582349 | 0.1241 |
R-squared | 0.798654 | Mean dependent var | 217.5122 | |
Adjusted R-squared | 0.758385 | S.D. dependent var | 38.83500 | |
S.E. of regression | 19.08910 | Akaike info criterion | 8.904770 | |
Sum squared resid | 10931.82 | Schwarz criterion | 9.209539 | |
Log likelihood | -157.7383 | F-statistic | 19.83286 | |
Durbin-Watson stat | 0.945321 | Prob(F-statistic) | 0.000000 | |
We observe that the DW Stat has a value of 0.94 (less than 2.0) which indicates possibility of AUTOCORRELATION. Hence we will apply the Lagrange Multiplier test to check whether there is autocorrelation or not.