7310AFE : Econometric Methods Assignment 1

Question 1 

Task Requirements

1. Present a summary statistics (1 Mark)

2. Set up suitable simple regression models and a multiple regression model (2 Marks)

3. Discuss the expected signs of each regression model coefficient (2 Marks)

4. Use scatter plots (2 Marks)

5. Present the simple and multiple regression results in the lecturer’s recommended format (3 Marks)

6. Check regression model assumptions such as heteroscedasticity (3 Marks)

7. Write a 50-word summary report on your findings (2 Marks)

Question 2

You are working as an Economist for an Australian consultancy firm. Your assignment involves investigating claims that lotteries adversely affect the poor and uneducated. Although lotteries are important for government revenue, there are concerns about disproportionate impacts.

You carried out a survey with 90 adults and collected data stored in the file Expenditure Survey.xlsx.

Claim 1: People with relatively lower education spend more on lotteries than those with higher education

• Present a simple regression model and discuss expected sign of the slope coefficient (0.5 mark).

• Provide summary measures (0.5 mark).

• Create a scatter plot (0.5 mark).

• Estimate model in EViews and interpret coefficient estimates (0.5 mark).

• Comment on suitability of model and test significance of relationship (0.5 mark).

• Test model assumptions: normality, homoscedasticity, serial correlation (1 mark).

Claim 2: Older individuals purchase more lotteries (3.5 Marks)

• Simple regression model and expected sign (0.5 mark).

• Present summary measures (0.5 mark).

• Scatter plot (0.5 mark).

• Estimate in EViews and interpret (0.5 mark).

• Comment on model suitability and significance (0.5 mark).

• Test assumptions: normality, homoscedasticity, serial correlation (1 mark).

Claim 3: People with a larger number of children spend more on lotteries (3.5 Marks)

• Simple regression model and expected sign (0.5 mark).

• Summary measures (0.5 mark).

• Scatter plot (0.5 mark).

• EViews estimation and interpretation (0.5 mark).

• Suitability and significance test (0.5 mark).

• Model assumptions testing (1 mark).

Claim 4: People with relatively lower income spend more on lotteries than higher income individuals (3.5 Marks)

• Simple regression model and expected sign (0.5 mark).

• Summary measures (0.5 mark).

• Scatter plot (0.5 mark).

• Estimate model in EViews and interpret (0.5 mark).

• Comment on suitability and test significance (0.5 mark).

• Test assumptions: normality, homoscedasticity, serial correlation (1 mark).

Multiple Regression Analysis

• Estimate a multiple regression model in EViews.

• Present results in the required reporting format.

• Interpret coefficient estimates (0.5 mark).

• Comment on suitability, test significance, and check assumptions: normality, homoscedasticity, serial correlation, multicollinearity (1 mark).

Final Analysis

• Draw inferences based on the results (1 Mark).

• Comment on findings and model assumptions.

• Prepare a 50-word media release supporting or opposing the claim about lottery spending in Australian media (3 Marks).

Question 3

Context

The State of West Bengal, India is one of the largest rice producers. Data from 44 paddy farmers are given in Rice.xlsx with variables:

• Ar: Hectares planted (land)

• Fe: Kilograms of fertiliser

• Lb: Person-days of hired and family labour

• Pd: Tonnes of freshly threshed rice

Tasks

(a) Estimate the Model

ln⁡(Pd)=β1+β2ln⁡(Ar)+β3ln⁡(Lb)+β4ln⁡(Fe)+e\ln(Pd) = β1 + β2 \ln(Ar) + β3 \ln(Lb) + β4 \ln(Fe) + eln(Pd)=β1+β2ln(Ar)+β3ln(Lb)+β4ln(Fe)+e

• Discuss expected signs of coefficients (0.5 mark).

• Present summary measures (0.5 mark).

• Use scatter plots (0.5 mark).

• Estimate in EViews and interpret coefficients (0.5 mark).

• Comment on suitability and test significance (0.5 mark).

• Test assumptions: normality, homoscedasticity, serial correlation, multicollinearity (2 marks).

(b) Hypothesis Testing – Land Elasticity (1.5 Marks)

• At 5% significance level, test if elasticity with respect to land equals elasticity with respect to labour.

(c) Returns to Scale (1.5 Marks)

• At 10% significance, test if production exhibits constant returns to scale (H0: β2 + β3 + β4 = 1).

(d) Joint Hypothesis Testing (1.5 Marks)

• At 5% significance, jointly test hypotheses in parts (b) and (c).

(e) Omitted Variable Analysis (4.5 Marks)

• Re-estimate by omitting Fe, then Lb, then Ar.

• Discuss effect of omission on estimates.

(f) RESET Test (1.5 Marks)

• For each omitted variable case, check if RESET test detects omitted variable bias.

Assessment Requirements

The assignment is divided into three major questions:

Question 1

• Present summary statistics.

• Build simple regression models and a multiple regression model.

• Discuss expected signs of coefficients.

• Use scatter plots for visualization.

• Present results in lecturer’s recommended format.

• Check assumptions such as heteroscedasticity.

• Write a 50-word summary report of findings.

Question 2

• Investigate lottery expenditure behaviour using survey data (Expenditure Survey.xlsx).

• Test four specific claims using simple regressions:

  1. Lower education leads to higher lottery spending.

  2. Older individuals purchase more lotteries.

  3. Larger number of children leads to higher lottery spending.

  4. Lower income individuals spend more on lotteries.

• For each claim:

  • Build regression model and explain expected sign.

  • Provide summary measures and scatter plot.

  • Estimate model in EViews and interpret coefficients.

  • Comment on suitability and test significance.

  • Test assumptions: normality, homoscedasticity, serial correlation.

• Extend to multiple regression analysis with checks for multicollinearity.

• Draw final inferences, comment on findings, and prepare a 50-word media release.

Question 3

• Analyse productivity of rice farmers in West Bengal using log-linear regression:

  ln⁡(Pd)=β1+β2ln⁡(Ar)+β3ln⁡(Lb)+β4ln⁡(Fe)+e\ln(Pd) = β1 + β2 \ln(Ar) + β3 \ln(Lb) + β4 \ln(Fe) + eln(Pd)=β1+β2ln(Ar)+β3ln(Lb)+β4ln(Fe)+e

• Tasks include:

  • Discuss expected signs of coefficients.

  • Provide summary measures and scatter plots.

  • Estimate model in EViews, interpret coefficients, and test assumptions (normality, homoscedasticity, serial correlation, multicollinearity).

• Hypothesis testing:

  • Test equality of land and labour elasticities.

  • Test for constant returns to scale.

  • Conduct joint hypothesis testing.

• Omitted variable analysis: exclude Fe, Lb, and Ar one by one and discuss results.

• Conduct RESET test for omitted variable bias.

Mentor’s Step-by-Step Guidance

Step 1: Understanding the Scope

The mentor explained that the assignment blends theory, application, and interpretation. Students were advised to balance statistical computation with clear economic reasoning and reporting.

Step 2: Approaching Question 1

• Generate descriptive statistics (mean, median, standard deviation).

• Develop simple and multiple regression models in EViews.

• Predict expected signs using economic reasoning.

• Plot scatter graphs to visualize relationships.

• Present results using the lecturer’s format.

• Test residuals for heteroscedasticity.

• Summarize findings in a concise 50-word report.

Step 3: Approaching Question 2

• Break down the task into four claims and set up individual regressions.

• Formulate hypotheses on expected signs before estimation.

• Present descriptive measures and scatter plots for each claim.

• Estimate models in EViews and interpret coefficients, significance, and fit.

• Run diagnostic tests: normality, homoscedasticity, serial correlation.

• Extend analysis to multiple regression, check for multicollinearity, and refine results.

• Prepare inferences based on evidence.

• Draft a short media release in a professional, policy-focused tone.

Step 4: Approaching Question 3

• Understand log-log model and elasticity interpretation.

• Predict signs for land, labour, and fertiliser variables.

• Use descriptive measures and scatter plots to support assumptions.

• Estimate regression, interpret coefficients, and test assumptions thoroughly.

• Perform hypothesis testing: land vs labour elasticity, returns to scale, and joint testing.

• Re-estimate models by omitting variables and examine the impact.

• Conduct RESET test for specification errors.

Final Outcome

By following this approach:

• The student generated well-structured regression models.

• Learned to connect statistical results to economic meaning.

• Applied diagnostic tests to validate models.

• Practiced hypothesis testing and communicating policy insights.

• Achieved learning objectives: applying econometric tools, interpreting real-world data, and producing professional reports.

Get Access to Assignment Solutions the Right Way

Looking for guidance on your academic task? You can download the available sample solution provided on this page to understand the correct structure, formatting, and approach. Please note: this sample is strictly for reference purposes only. Submitting it as your own work may lead to plagiarism issues and academic penalties.

For students who want to secure higher grades with confidence, we recommend ordering a fresh, plagiarism-free assignment solution written by our team of professional academic writers. With a custom-written solution, you’ll get:

• 100% original, plagiarism-free work

• Tailored answers aligned with your university guidelines

• Expert support from subject specialists

• On-time delivery with guaranteed quality

Don’t risk your academic success with copied content — let our experts create a unique solution just for you.

Disclaimer: The sample file is for learning and reference only. Do not submit it as your final work.

[Download Sample Solution] [Order Fresh Assignment]