Real Estate Sales Forecasting Regression Model of Pueblo neighborhood North Elizabeth Data sources from Pueblo County Website

I select 5 variables. Dependent variable—price. Independent variable—Bathroom, Bedroom, Lot(sqft), Sqft. PriceBathroomBedroomLot(sqft)Sqft

Run the model and from the results we can see that: “Sqft” is the most significant one than others. Select “Sqft” as the only independent variable SUMMARY OUTPUT Regression Statistics Multiple R R Square Adjusted R Square Standard Error Observations19 ANOVA dfSSMSF Significan ce F Regression43.99E E E-06 Residual146.2E E+08 Total184.61E+10 Coefficients Standard Errort StatP-value Lower 95% Upper 95% Lower 95.0% Upper 95.0% Intercept Bathroom Bedroom Lot(sqft) Sqft

When throw up other variables just use “Sqft”, the significant F is higher and significant F is lower. The model is more significant. The t test of “Sqft” is higher, P-value is lower. R square almost has no change. This regression model is better than before. The coefficient of x is 54.18, the intercept is So the regression model is y= 54.18x SUMMARY OUTPUT Regression Statistics Multiple R R Square Adjusted R Square Standard Error Observations19 ANOVA dfSSMSF Significanc e F Regression13.82E E-08 Residual177.91E E+08 Total184.61E+10 Coefficient s Standard Errort StatP-valueLower 95%Upper 95% Lower 95.0% Upper 95.0% Intercept Sqft E

Significance Testing and residual analysis α=0.05, α/2=0.025, t(0.025,17)=2.11, observed t is 9.05, 2.11<9.05, this regression model is adding significantly more predictive information to the no regression model. Because there are small sample sizes, so it has more inaccuracy than large sample sizes. Look at the residual plot, it seems like relatively linear The variances of the errors are about equal for each value of x, the error terms do not seems to be related to adjacent terms. Look at the normal probability plot, it indicates that the residuals are normally distributed. And this normal plot is relatively close to being a straight line, showing that the residuals are nearly normal in shape.

Model Application This model is about the relationship between “price” and “Sqft”. It shows that these two things has a positive linear relationship, which means, when “Sqft” increase, the “Price” will increase. When “Sqft” goes down, the “Price” will decrease to some extent. As a whole, if someone going to sell his house, and if the house is a big one (2000 sqft), then the selling price will be higher than a small one(1000 sqft). USING: When a hose is 2980 sqft, the forecast selling price is y=54.18* =