Purpose of the Project: Forecasting the price of single family homes in the Bowie area, using multiple regression model.
Write the linear multiple regression equation clearly identifying the independent and. dependent variables.
HMPRICE= home price-dependent variable
NUBEBRM= Number of Bedroom
LIVSPACE= Living Space
GARAGE= Car garage
YERSBUT=Years Built (age)
ACERAGE= acreage (lot size)
FANCED= Is fenced
FINBASMT= Has a finished basement
I. How many homes are surveyed in this study?
2. Give the meanprice, number of bedrooms, bathrooms, square footage?
3. In which of the three variables is there the most variability?
4. What percent of the home are fenced?
5. What percent of the homes have finished basements?
6. Give the statistical jargon used for variables such as finished/unfinished basements, fenced/unfenced, etc.
7. How strong a relationsh ip is there between the dependent and set of independent variables? Explain using statistical concepts.
8. Do you believe the result?
9. Test the model for significance (F-test).
10. Test the statistical significance of the individual coefficients; ~I , ~2, ~3, etc. (t-test)
1J. Forecasting the price of home that has the following characteristic; has 5 bedrooms, 12,000 sq foot
of living space, 2 car garages, is 10 years old, is build on an acre of land, has a finished basement
and is fenced.
1. The sample size is 40 for this, so 40 homes are surveyed in this study.
2. Mean price is 654119,75, mean number of bedrooms is 4.70, mean number of bathroom is not any variable and square footage is 1605.25
3. Price, Living space and Years Built (age) has the most variability because the standard deviation is large for these variables.
4. 53% of the homes are fenced because mean is 0.53 and n is 40. So the sum of fenced is 21.2 which means that 53% of homes are fenced.
5. 75% of the homes have finished basements because mean is 0.75 and n is 40. So the sum of finished basements is 30 which means that 75% of homes that have …
The expert forecasting the price of single family homes for multiple regression.