Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
71 views2 pages

Week 2 Tutorial Solution

The document summarizes regression analysis conducted on data for 1080 houses containing variables for sale price, house size, age, and other features. The linear regression model estimated sale price (PRICE) as a function of house size (SQFT). It found that for each additional square foot, price increased by an estimated $92.75 on average. The intercept was interpreted as predicting a negative price for a house with zero square feet, which is meaningless. Predicted price for a 1500 sqft house was $78,263.54.

Uploaded by

Fira Syawalia
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
71 views2 pages

Week 2 Tutorial Solution

The document summarizes regression analysis conducted on data for 1080 houses containing variables for sale price, house size, age, and other features. The linear regression model estimated sale price (PRICE) as a function of house size (SQFT). It found that for each additional square foot, price increased by an estimated $92.75 on average. The intercept was interpreted as predicting a negative price for a house with zero square feet, which is meaningless. Predicted price for a 1500 sqft house was $78,263.54.

Uploaded by

Fira Syawalia
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

ETF2100/5910 Introductory econometrics

Tutorial exercises for week 2:

Introduction to EViews and simple linear regression


The file br2.wf1 contains data for 1080 houses on sale price, the house size in square feet, its
age, whether it has a pool or fireplace or is on the waterfront.

(a) What is the sample mean of sale price? $154,863.20


500
Series: PRICE
Sample 1 1080
400 Observations 1080

Mean 154863.2
300
Median 130000.0
Maximum 1580000.
Minimum 22000.00
200
Std. Dev. 122912.8
Skewness 6.291909
100 Kurtosis 60.94976

Jarque-Bera 158243.7
0 Probability 0.000000
1 250001 500001 750001 1000001 1250001 1500001

(b) Plot house price against house size for all houses and comment on the relationship
between the two variables.
1,600,000

1,400,000

1,200,000

1,000,000
price

800,000

600,000

400,000

200,000

0
0 1,000 3,000 5,000 7,000

sqft

There seems to be a strong positive linear relationship between the house size
(SQFT) and its price (PRICE). As the house size gets bigger, the price gets higher.
(c) Estimate the linear regression model
PRICE = 1 + 2 SQFT + e
(i) Report results.
̂ = −60861.46 + 92.75 𝑆𝑄𝐹𝑇
𝑃𝑅𝐼𝐶𝐸 𝑅2 = 0.5786
se (6110.19) (2.4104)

This is based on the EViews output below.


Dependent Variable: PRICE
Method: Least Squares
Sample: 1 1080
Included observations: 1080

Variable Coefficient Std. Error t-Statistic Prob.

C -60861.46 6110.187 -9.960655 0.0000


SQFT 92.74737 2.410502 38.47637 0.0000

R-squared 0.578648 Mean dependent var 154863.2


Adjusted R-squared 0.578257 S.D. dependent var 122912.8
S.E. of regression 79821.70 Akaike info criterion 25.41483
Sum squared resid 6.87E+12 Schwarz criterion 25.42406
Log likelihood -13722.01 Hannan-Quinn criter. 25.41832
F-statistic 1480.431 Durbin-Watson stat 1.886466
Prob(F-statistic) 0.000000

(ii) What is the estimate of the slope parameter. Interpret this estimate.
The slope coefficient is 92.75. We estimate that each additional square foot of
house size is associated with an increase in the expected house price of 92.75
dollars. The coefficient is positive as expected. It makes sense that larger
houses sell for higher prices.

(iii) What is the estimate of the intercept? Interpret this estimate.


The intercept coefficient is -60,861.46. It represents the expected value of
PRICE when the house size equals 0 square feet. The intercept, if taken literally,
suggests a house with zero square feet would cost $-60,861.44. This does not
make sense. We need to be cautious when interpreting the intercept. This
negative value of house price is meaningless; there is no data in the region of
zero square feet. The minimum house size in the sample data is 662 sqft. The
model should not be accepted as a serious one in the region of zero square
feet.

(iv) Predict the estimated price of a 1500 sqft house.


̂ = −60861.46 + 92.75 (1500) = 78,263.54
𝑃𝑅𝐼𝐶𝐸
We predict that a house with 1500 sqft would cost on average $78,263.54.

You might also like