Posted: April 17th, 2015

econometrics

Coursework Assignment Brief

 

Semester:	Spring 2015
Module Code:	PE208
Module Title:	Econometrics
Programme	BSc Economics
Level:	Level 5
Awarding Body:	University of Plymouth
Module Leader	Paweł Paluchowski
Format:	Report
Presentation:	No
Any special requirements:	All work should be submitted on the Student Portal along with an acceptable Turnitin Report
Word Limit:	Weekly assignments: not applicable First report: 800 words (+ or – 10%) Second report: 1,200 words (+ or – 10%)
Deadline date for submission:	Weekly assignments: 1.00pm, Friday the following week after each tutorial 5.00pm, 27 March 2015 for the first report 5.00pm, 17 April 2015 for the second report
Learning outcomes to be examined in this assessment	a) Design a simple econometric research project containing a full range of techniques b) Evaluate basic techniques of econometrics in relation to specified problems c)   Discuss the role and limitations of econometric methods in the analysis of contemporary problems.
Percentage of marks awarded for module:	Assignment 1 is worth 50% of the total marks for the module. Assignment 2 is worth 50% of the total marks for the module.
Assessment criteria	Explanatory comments on the assessment criteria	Maximum marks for each section
Content, style, relevance, originality	Content will reflect the students’ ability to understand and to analyse econometrics as taught. Answers to be based on an interpretation of class hand-outs and evidence of background reading. That is, there should be clear demonstration of focused rigorous research from recognised authoritative sources.	50%
Format, referencing, bibliography	The limit is not a guide, it is an instruction. Do not stray into tangential material. Always ask yourself – is what I’ve written relevant to the question set? Copy and Paste. Please try to refrain from doing this. Font size. Please use font size of approx.. TNR 12, Arial 12 size. Double space. Read (aloud) what you have written. If we can’t understand your argument, you will not get any credit for it. The Study Skills Handbook and Module provide detailed guidance on referencing.   Ensure you reference your citations using the Harvard method.	10 %
Constructive critical analysis, introduction, conclusion	Demonstration of a clear understanding of the issues. Use of academic models. Clear focussed understanding of a topic. Critical analysis is an important test of the student’s ability to evaluate econometric concepts. Introductions and conclusions should briefly address the issues to be discussed and discussed respectively.	40%

 

 

• Candidates must clearly label their ID Number on additional separate reference, formula or answer sheets.
• I will support Gretl for use in econometric estimation in this course, but you are welcome to use other software for estimation. However, please note Gretl is the software which is installed in the computer labs. Gretl is an open source and free software that can be downloaded and installed in PC, Mac and Linux machines.
• Please note that academic misconduct, such as collusion and ghost-writing, will NOT be tolerated. The module leader and tutors reserve the right to call the students to an informal hearing in order to query about specific details of the assignments.

 

Self-assessment sheet

 

Please fill in the form below and include it on the last page of your two individual reports.

 

Assessment categories	Criteria	Criteria are … (indicate answer with an ‘X’)
		Fully achieved		Partly achieved	Not yet achieved
Format	Title page provided
	Page numbers included
	Justified text formatting
	Grammar and spelling checked
	Charts are individual work (not copied and pasted from other sources)
	Charts and tables labelled and neatly formatted
	Charts are clearly explained in text
	Font size and text formatting make the report easy to read
Referencing, bibliography	Harvard referencing applied
	Sufficient in-text citations
	Quality citations used (no Wikipedia, Investopedia, news, etc.)
	All in-text citations are included in Bibliography
	Bibliography is neatly formatted
Content	Factual information is correct and has been double-checked
	Work is thoroughly researched
	Main issues are addressed in sufficient detail
	Answers are consistent
	Answers are supported by economic theory, factual information or external material
	Work demonstrates knowledge of subject
	Work demonstrates analytical depth (answers are not superficial)
Relevance	Answers provided directly relate to the question
	Answers are clear and focussed
	Relevant external material used
Style	Written expression conveys information clearly
	Use of academic language (colloquial expressions avoided)
	Arguments are well structured
	Arguments are supported by evidence
	Arguments are balanced
Originality	Work contains sufficient own reflection
	Evidence of critical thinking
	A wide range of material is used (Not just lecture material)

 

 

 

 

 

1) Assignment block 1 (Weekly tasks and report 1):

(This assignment consists of two components and has a combined weight of 50% of the overall module mark. The weekly tasks make up 40% and the individual report 60% of the total assignment 1 mark. You have to complete both parts of assignment 1 in one semester. A non-submission of one of the components will be counted as 0 marks.)

 

1a) Weekly assignments

 

Every week’s tutorial contains 10 short applied questions that you will have to answer within a week (submission deadline is always Friday, the following week at 1.00pm). Late submissions count as non-submissions.

Each weekly assignment question bears 10 points so having answered all questions correctly will give you the maximum weekly mark of 100. The questions have to be typed into the specifically designed tutorial applications (only Windows support; contact module leader to discuss other options). Once you provided your answers, the application will ask for your student ID and your official gsm email account and then submit your results automatically. You can submit several times but only the last submission will be taken into account. This can be useful if you find a mistake before the submission deadline. Once the deadline passed, you will receive an email to your gsm account confirming your weekly score.

There will be 9 tutorials in total. The final weekly assignments mark is the average mark of the 7 highest marked submissions. The example below demonstrates how the overall mark for the weekly assignments is calculated:

Assume a student submitted 8 out of 9 weekly assignments receiving the following scores: 70, 100, 90, 100, 40, 80, 100, 100. Hence, the average for the 7 highest marked submissions can be calculated as follows:

 

You are strongly encouraged to attend the tutorials as you will receive in-class support with your weekly assignment from you lecturer. Of course, you can complete the assignments at home as well. Please note, that you will not be able to copy results from other students.

Each student be provided with individualised data sets based on the student ID number. A specifically designed program (only Windows support – if you rely on other operating systems, please contact the module leader) will be distributed that will generate your data sets. You can only use your unique data sets for the assignments. While all data sets have an identical structure, their values and case numbers vary. Hence, results of the data analysis will differ in almost all cases.

 

Learning outcomes assessed: a

 

 

 

1b) Report 1 (30 marks)

(This assignment comprises 50% of the final mark for this module)

 

• Question 1 (30 marks)

 

1. The following chart shows a scatter plot of two variables. What is the goodness of fit (R-squared) of the corresponding regression line? Please briefly explain your answer (5 marks).
2. Using the same data as above (Question 1a)), a researcher runs a regression model. The researcher is quite surprised to find that the output does not show a figure for the p-value as it usually would. Please briefly explain why the model cannot provide a p-value in this specific case (5 marks).

 

1. The following chart shows the distribution of a variable. Briefly explain why it will be problematic to use the variable as a dependent variable in a standard OLS regression (5 marks).

 

 

1. Assume that you run a regression with 223 observations. The dependent variable is ‘annual salary’ and there are 3 independent variables ‘work experience in years’, ‘education duration in years’ and ‘number of employees in company’. The regression yields following result for the variable ‘number of employees in company’:

 

Coefficient estimate: 150.3 ; standard error: 98.4

 

Calculate the p-value (two-tailed) and briefly discuss whether employees in larger companies earn significantly higher salaries (5 marks).

 

 

1. A researcher wants to find out whether age has an effect on how happy people are. The researcher runs a regression with the dependent variable ‘happiness score’ (0 to 10 with 10 being extremely satisfied) and the independent variable ‘age’ (in years). The modelling results show that age is not significant. You also have a look at the residual plot (shown below). Please explain why the residual plot indicates that the regression generated by the researcher is misleading. Discuss what relationship you expect between age and happiness. Outline how you could work this into the initial regression model and hence, improve it (10 marks).

 

1. You want to know whether people with higher incomes are happier. Your friend has run a survey in their company and run a regression on the data. The dependent variable is ‘happiness score’ (0 to 10 with 10 being extremely satisfied). There is only one independent variable: ‘monthly income’ (in £). Your friend sends you the gretl output of the regression via email. Unfortunately, the file got corrupted and only the critical F-value is legible (see below). Using this output, show that ‘monthly income’ is indeed highly significant (provide p-value and explain calculation). Can you tell whether workers with higher incomes are significantly happier? (10 marks)

 

 

Model 1: OLS, using observations □□□□

Dependent variable: happiness_score

 

Coefficient	Std. Error	t-ratio	p-value
Const	□□□□	□□□□	□□□□	□□□□□□□□
Monthly_income	□□□□	□□□□	□□□□	□□□□□□□□

 

Mean dependent var	□□□□		S.D. dependent var	□□□□
Sum squared resid	□□□□		S.E. of regression	□□□□
R-squared	□□□□		Adjusted R-squared	□□□□
F(1, 198)	13.44598		P-value(F)	□□□□
Log-likelihood	□□□□		Akaike criterion	□□□□
Schwarz criterion	□□□□		Hannan-Quinn	□□□□

 

• Question 2 (40 marks)

Using sample data for height (in inches) and weight (in pounds/lbs) of major baseball league players in the United States, a researcher has generated following model:

 

Model 1: OLS, using observations 1-83

Dependent variable: weight_pounds

 

Coefficient	Std. Error	t-ratio	p-value
const	−158.102	58.8343	-2.6872	0.00874	***
height_inches	4.84271	0.800029	6.0532	<0.00001	***

 

Mean dependent var	197.8072		S.D. dependent var	22.77218
Sum squared resid	29278.58		S.E. of regression	19.01221
R-squared	0.311463		Adjusted R-squared	0.302963
F(1, 81)	36.64081		P-value(F)	4.22e-08
Log-likelihood	−361.2014		Akaike criterion	726.4028
Schwarz criterion	731.2405		Hannan-Quinn	728.3463

 

 

1. Interpret the modelling results with specific focus on goodness of fit, the coefficient estimates and significance (10 marks).

 

1. Please write the model results in equation form and calculate the predicted weight of a player who is 73 inches tall (5 marks).

 

The researcher generates a second model, now including data for age in years. The modelling results are shown below.

 

Model 2: OLS, using observations 1-83

Dependent variable: weight_pounds

 

Coefficient	Std. Error	t-ratio	p-value
const	−211.373	62.1572	-3.4006	0.00105	***
height_inches	5.11238	0.790125	6.4703	<0.00001	***
age	1.17307	0.523714	2.2399	0.02787	**

 

Mean dependent var	197.8072		S.D. dependent var	22.77218
Sum squared resid	27550.74		S.E. of regression	18.55759
R-squared	0.352097		Adjusted R-squared	0.335899
F(2, 80)	21.73759		P-value(F)	2.89e-08
Log-likelihood	−358.6771		Akaike criterion	723.3542
Schwarz criterion	730.6107		Hannan-Quinn	726.2694

 

1. Has the inclusion of age improved the initial model? Briefly explain your answer (5 marks)

 

1. Please write the revised model in equation form and predict the weight of a baseball player who is aged 27 years and is 70 inches tall. How accurate is this prediction? (10 marks)

 

1. According to the second model, how much does the weight of a baseball player change within 10 years? Why would a time series model be better to estimate this? (5 marks)

 

1. Outline how the second model could be further improved (5 marks).

Learning outcomes assessed: b, c

 

• Question 3 (20 marks)

Considering data on fuel consumption (G) and price of fuel per litre (Pg) for 36 years, per capita disposable income (Y), a price index for new cars (Pnc), and a price index for public transportation (Ppt), a researcher has estimated the following model.

 

Model 1: OLS, using observations 1960-1995 (T = 36)

Dependent variable: G

 

Coefficient	Std. Error	t-ratio	p-value
const	-105.521	12.3137	-8.5694	<0.00001	***
Pg	-12.5788	2.29866	-5.4722	<0.00001	***
Y	0.0402417	0.00142279	28.2835	<0.00001	***
Pnc	4.60283	14.2292	0.3235	0.74850
Ppt	-6.73255	3.9671	-1.6971	0.09970	*

 

Mean dependent var	226.0944		S.D. dependent var	50.59182
Sum squared resid	978.4683		S.E. of regression	5.618140
R-squared	0.989078		Adjusted R-squared	0.987668
F(4, 31)	701.8009		P-value(F)	6.41e-30

 

1. Interpret and fully discuss the modelling results with specific reference to economic theory (10 marks).
2. You want to know whether it is possible that the true coefficient of Pg is actually above -10. Build a 99% confidence interval to test this (10 marks).

 

Learning outcomes assessed: b, c

Total marks for assignment: 100

2) Assignment block 2: Report 2

(This assignment comprises 50% of the final mark for this module; you will receive the data during Week 8, and you will be submitting during Week 10. There will be a dedicated data set for each question. In analogy to the tutorial data, the data sets for report 2 are going to be personalised)

 

• Question 1 (50 marks)

The supermarket group ‘Dodo’ is concerned as their stores have been recording falling profits in London in two consecutive years. They have hired you to conduct an analysis of their stores and identify factors that positively and negatively affect profits. You will use these results to make recommendations for store optimisation and location. Dodo has given you a data set (q1_data) of annual profits (revenues minus costs) of their shops and their characteristics.

1. Dodo is primarily interested in maximising profits per workers. Create the variable profits per worker and provide a short discussion of descriptives for the variable. Thereby, include a summary statistics table, a frequency plot, another interesting chart of your choice (e.g. scatterplot with another interesting variable) (15 marks)

 

1. Estimate a multiple regression model for profits per worker as dependent variable. Outline and interpret the modelling results. Debate potential implications of your findings for store optimisation and location (20 marks).

 

1. Run tests for multicollinearity and heteroscedasticity and discuss their results. Discuss the implications for your modelling results (10 marks).

 

1. Dodo would like you to conduct more analysis in the future. Identify additional variables that you would like to obtain from Dodo in the consecutive round in order to improve your research (5 marks).

Learning outcomes assessed: a, b, c

• Question 2 (50 marks)

Another company, ‘Walrus’, has been impressed with your work for Dodo and would like you to conduct an analysis for them. Walrus is an online bicycle store that sells mainly one product, their ‘tBike’. Another online bicycle store, ‘Shifty’, has recently announced a lasting and substantial reduction in their prices for the next year and Walrus would like to know whether this is likely to significantly affect their sales of tBikes. Walrus has provided you with monthly data of their sales (q2_data).

1. Generate a simple multiple OLS regression including the variables in your data set. The variable ‘tBike_sales’ is going to be your dependent variable. Briefly describe the modelling results (10 marks).

 

1. Why are your modelling results likely to be affected by autocorrelation? Provide an adequate time series chart to support your answer (5 marks).

 

1. Run tests for autocorrelation and discuss the results (10 marks).

 

1. Apply a solution to get rid of the autocorrelation issue (You new approach should also address potential seasonality – you have a look at your dependent variable and choose appropriate time period dummies). Estimate the new model and provide the modelling output. Interpret the regression results. Thereby, address whether Walrus can expect a decrease in their tBike sales revenue when Shifty lowers their prices in the following year. Use the modelling findings to make recommendations for Walrus’ sales strategy. (Additional instructions: Your answers should be written in report format, not only a list of loosely connected bullet points. Imagine you are writing this report for Walrus) (25 marks).

Learning outcomes assessed: a, b, c

Total marks for assignment: 100