ECNP003代做、代写R代写、代做Policy Brief、R编程设计代写

日期：2019-02-16 10:11

ECNP003 Policy Brief Assignment

Set by Danny Campbell

February 7, 2019

You are involved in a community organisation and you want to advise the local authority what local services they

should focus their efforts on. You have obtained a dataset that contains all house sales in the local area that occurred

in the previous year. The dataset contains the house prices, as well as some house features, neighbourhood characteristics

and the environmental conditions where the house is located. The independent variables are:

house_id house ID number

x_coord x coordinate

y_coord y coordinate

num_beds the number of bedrooms in the house

garage indicator variable to denote if the house has a garage (1=Yes)

house_type house type (1 = one-story; 2 = two-story; 3 = three-story)

location where the house is located (1 = city centre; 2 = suburbs; 3 = countryside)

local_crime indicator variable to denote if area has above national average crime rate (1 = high crime)

local_schools indicator variable to denote if area has above national average schools (1 = good schools)

local_health indicator variable to denote if area has above national average health care (1 = good health care)

dist_recreationpark distance to closest outdoor recreation park (in KM)

average_airqual average number of days of the year with poor air quality

windturbine_visible indicator variable to denote if wind turbines are visible from the house

flood_risk flood risk classification (1 = low risk of flood; 2 = moderate risk; 3 = high risk)

Each of you have a different dependent variable. You can work together, but note your model results will all be different.

The dependent variable (house price in ￡) you should use is indicated following your name. It is essential that

you use your specified dependent variable.

The objective of this assignment is to establish the factors that influence house price. While the data is hypothetical it

should still give you estimation practice and, importantly, the opportunity to interpret the output. Imagining the data

is real, your task is to:

1. Describe and explore the data.

2. Conduct regression analysis on the data to establish the factors influencing house price.

3. Interpret the regression model results and establish whether the hypotheses you set are confirmed or rejected.

4. Describe the (policy) implications of the results.

5. Use the results for scenario prediction (i.e., what if ... questions).

6. Write up your findings in a policy brief (up to four pages, including everything).

You will be assessed according to how well the above tasks are achieved.

1

NOTES:

1. Remember that you are undertaking this analysis and policy brief on behalf of a local organisation. So you

should be especially interested in exploring and discussing the results from this viewpoint.

2. Provide justification and discuss them in the brief.

3. In the brief, include graphs, plots, diagrams etc. where/if necessary.

4. Explore transforming and recoding some variables (this is necessary).

5. Include/exclude some variables to assess their relative importance in explaining house prices.

6. Above all, adhere to the KISS (keep it simple stupid) principle. Don’t make things even more complicated than

they have to be, especially if you feel you out of your comfort zone!

7. A technical appendix with you estimation results should also be submitted.

The deadline is 21st March 2019.

Each of you will use a different dependent variable. All the independent variables are the same.

Maureen Clezy use hp1

Christine Kinnon use hp2

Jiabin Luo use hp3

Henry Mumba use hp4

Christoph Rouhana use hp5

Christopher Sweeney use hp6

Thea Tofthagen use hp7

Some of you have said you would be keen to try doing it in R. Here I will give a demonstration.

The first thing you need to do is read the data into R. The easiest way is to follow these steps:

1. Copy and paste the data file into your chosen folder

2. Open R studio, and start a new R Script:

File -> New File -> R Script

3. Save this R Script in the same folder where you pasted the data file

4. Next, set the working directory:

Session -> Set Working Directory -> To Source File Location

5. Run the lines of code below:

houseprice.data <- read.csv("data.csv")

attach(houseprice.data)

The data should now be read in, and can be analysed in R.

I will demonstrate based on the dependent variable (hp0).