1. A simple linear regression model

The project is accompanied by data showing the square meter price of housing for one hundred properties in the state of Florida. We take a look of two variables in the database, price (e. Price) and size (e. Size), and thus begin to present a regression model which describes real estate prices that depend on the size of the property.

a) Estimate a simple linear regression model that describes real estate price of housing (Y, e. Price) as a function of size of housing (X, e. Size). Present the estimated model, the regression equation that describes how the variable Size has effect on price (e. Price) b) State a 95% confidence interval for the bar Size at the independent variable Size (housing size) in the model. Interpret value of the bar.

c) Does the size of housing have a statistically significant effect on property price? Justify by referring to the confidence interval from point b). Use the significance requirement =0.05.

d) State the coefficient of variation of the model (r2) and interpret in context of the variables being worked with, i.e. price properties and their size.

2. Multiple linear regression model

A model that takes into account more variables than just the size of the house. The data also includes the following variables: Taxes on the house, Beds, Baths.

a) Estimate a multivariate regression model with four independent variables (ie four explanatory variables). Model which describes the price of housing as a function of size the housing (e. Size), real estate taxes (e. Taxes) which therefore follow, number of bedrooms (e. Beds) and number bathroom (e. Baths).

b) Use an F-test to check whether the model in Example 2a describes real estate prices better than the model from Example 1a. The ticket at the significance requirement =0.05.

c) Is the number of bathrooms statistically significant effect on real estate prices, including the model from point 2a)? Who are effect of additional bathroom on property value? (ie if the variable Baths increases by 1)