75590 - Statistics Order 6 Pages within 48 hrs

Project #1: Regression Analysis – Residential Real Estate.

REE 6935 - Spring 2019 – Dr. Beracha

This real estate regression analysis project involves compiling and analyzing real world real

estate data. You are asked to analyze residential real estate data to determine the effect of

school quality on residential real estate. Specifically, you will determine whether purchase

prices and rent prices are affected by school quality and whether these affects are dependent on

whether the properties are occupied by renters or owners.

The goal of this assignment is to examine your ability to analytically answer relevant real estate

questions using a linear regression. After you successfully complete this project you will be

tooled to analytically answer many other relevant questions, given an appropriate dataset is

available.

You will be working on this assignment in a group of five students (+/- one). A project

submitted by a group that doesn’t include 4-6 students will incur a grade penalty of 10%. The

assignment is due on or before Feb 12th at 11:55 p.m. EST. By that time you should submit an

electronic copy (via Canvas not via email) of your assignment. If you turn your assignment

late, 10% will be deducted from your grade for every calendar-day delay.

Before you begin working on this project, one representative from each group must email me

with the names of the group members and I will assign you the county for your analysis.

Your complete assignment should read and look like a professional report and include the

following sections:

1. Short introduction: Describe the questions you are attempting to answer; Tell the reader what you expect to find (your hypothesis/hypotheses) and why.

2. Data preparation and description: Before you begin with your analysis, your dataset must be fitted to answer your research questions. To prepare your dataset, you will need

to do the following:

- Define a range for a few property characteristics and exclude all observations that do not meet your defined ranges. This allows you to work with more a

homogeneous set of observations and eliminates some of the errors embedded

within the original dataset. You will define ranges for SQFT, Bedrooms, Bathrooms

(full and half) and Age based on the segment of the market that you would like to

explore (the same characteristic ranges should be applied to your rent and purchase

datasets).

- Report your defined ranges. - Report the initial number of observations in each dataset (before the characteristic

ranges were applied).

- Report the final number of observations in each dataset (after the characteristic ranges were applied).

- Create a variable that serves as a proxy for school quality and explain how this variable is defined.

- For each of the two datasets, create a table that provides some basic statistics (average, min, max and SD) for selected key variables.

3. Regression analysis: Apply each of the models below to each of your two datasets (rent and purchase) and report your regression results within a table.

1) 𝑃𝑟𝑖𝑐𝑒 = 𝛽0 + 𝛽1𝑆𝑄𝐹𝑇 + 𝛽2𝐵𝑒𝑑𝑟𝑜𝑜𝑚𝑠 + 𝛽3𝐵𝑎𝑡ℎ𝑟𝑜𝑜𝑚 + 𝛽4𝐴𝑔𝑒 + 𝛽5𝐷𝑢𝑚2012 + 𝛽6𝑆𝑐ℎ𝑜𝑜𝑙_𝑄𝑡𝑦

2) 𝐿𝑁_𝑃𝑟𝑖𝑐𝑒 = 𝛽0 + 𝛽1𝐿𝑁_𝑆𝑄𝐹𝑇 + 𝛽2𝐵𝑒𝑑𝑟𝑜𝑜𝑚𝑠 + 𝛽3𝐵𝑎𝑡ℎ𝑟𝑜𝑜𝑚 + 𝛽4𝐿𝑁_𝐴𝑔𝑒 + 𝛽5𝐷𝑢𝑚2012 + 𝛽6𝑆𝑐ℎ𝑜𝑜𝑙_𝑄𝑡𝑦

4. Interpretation of the regression analysis and estimations: In this section you will provide answers to the following questions:

- Are all the coefficients you report in part 3 consistent with your expectations? If not, which coefficients are inconsistent?

- Using the 1st regression model, what is the average estimated rent price in 2012 for a 2100 sqft, 3-bedroom, 2-bath, 18-year-old property that is associated with average

school quality? Show your work!

- Using the 1st regression model, what is the average estimated purchase price in 2012 for a 2100 sqft 3-bedroom, 2-bath, 18-year-old property that is associated with

average school quality? Show your work!

- According to regression models (1) and (2), what is the effect of school quality on rent prices?

- According to regression models (1) and (2), what is the effect of school quality on purchase prices?

5. Discussion: Briefly discuss your results. Are your results consistent with your initial hypotheses?

6. Limitations: Point out some limitations of your analysis and the possible issues or problems that may prove your results to be inaccurate.

7. Conclusion: Conclude your report using two-three paragraphs.

Deliverables:

- ONE Excel file including your modified data and the outputs of your regressions. - ONE Word file including text and tables. The Word file should be organized as a

complete and well flowing report. The total length of the report must not exceed 7

pages (single space, font size 12 and default size margins). Your assignment files

should be named: “THE SENDER’S NAME – REE6935_Proj1_Excel” and “THE

SENDER’S NAME – REE6935_Proj1_Word”

Grading criteria:

Following the project guidance: 10%

Please make sure that your report follows the description provided above, including the

name of file submitted, submission via Blackboard and the material included in each

section.

Professionalism, clarity and conciseness: 10%

Margins, spacing, and fonts have been chosen to make the document attractive and easy

to read. Tables, figures and graphs have been used to summarize data and effectively

illustrate points. Headings are used judiciously to help reader find key sections in longer

reports. It should look like a professional report. Contains few typographical errors and

is well-printed.

Be brief and clear! The total length of the report must not exceed 7 pages.

Section 1: 10%

Section 2: 10%

Section 3: 15%

Section 4: 18%

Section 5: 12%

Section 6: 10%

Section 7: 5%