This project is worth 85% of your final mark

Deadline: Monday 21st April 2023 12 noon

Project Outline

The aim is to devise a causal research question and research design, find data and demonstrate application and understanding of the methods from the course by writing a “letter” style paper on any applied economics question. The question will be your choice (and you may want to do something related to your PhD research) but remember the “rules” of what makes a good research question, and choose something that you can (partially) answer with data.

My advice is to keep the question simple and don’t try to do anything too ambitious or try to cover too much. The project is more about showing your understanding of what a good research design and how to devise an identification strategy, and demonstrating you can choose appropriate empirical methods and apply some of the methods taught. It may be that in the end you are unable to achieve convincing causal estimates or find fully appropriate data in time; this is not a problem so long as you show understanding of why this was not possible, and what would have been needed to obtain causal estimation.

It is recommended you start think about/working on the project as early as possible (as early as week 1 of the module!), to give you time to develop your question, devise an identification strategy and source some appropriate data. Starting early will also mean as you learn about methods you can consider if they would be appropriate for your identification strategy to answer your question.

Statistical Software Use

We will predominately use the statistical package Stata in the module but you will also see a bit of the package R. You are welcome to use any software package you prefer so long as you provide the code used e.g., a Stata do-file or alternative software equivalent.

Project Structure

The aim is to keep the write up concise and write a short piece in the style of the letters journal e.g. economics letters, applied economic letters – have a look at some of the papers in these journals. Below I provide a guide to some suggested project sections (you do not have to stick to these headings or keep the same order; or include everything mentioned).

Title page and Abstract (100-120 words; this will not count towards the final word count)

Title, JEL codes  keywords (normally a list of three to five terms). An abstract will typically include the aims of the research, a basic overview of the approach (data, sample, methods) used, your main findings and any key conclusions/implications. 

Introduction (guide 500-700 words)

The introduction should provide some context and state a clear research question(s) /hypothesis(es). Briefly state why the question/topic is important and/or interesting, and your contributions. A formal literature review is not required but you should make critical reference to relevant literature and/or economic theory to help develop/motivate your question(s). Often researchers preview what they will do (your identification strategy) and their key findings

Methods (guide 300-500 words)

Explain what your identification strategy is (convince the reader!) and methods you will use to answer/test your research question/hypotheses and why they are appropriate. Be concise (details can be left to an appendix) but the reader should be able to understand what you have done, why, and have enough information to be able to replicate your results. You should provide references

Data (guide 200-400 words)

Describe the dataset and sample: why is it appropriate to help answer your research questions/test your hypotheses? Are there any data limitations?

[Note if you do not have enough time to source all of the necessary data that is okay so long as you explain what additional data would be needed and why, and you have made an attempt to work with the data you managed to source]

Empirical results and discussion  (guide 1,000-1,500)

This is a key section.  Talk the reader through and explain your results. Remember you are trying to answer a research question and you want to convince the reader your effects are causal. You should explain how you have ruled out other explanations (i.e. your sensitivity/robustness checks). Tables of results should be formatted and presented to an academic standard and not directly copied from Stata.  

[Note if your identification strategy has not worked and hence you have not had time to devise another and/or you do not have all the necessary data that is okay, you just need to show your have attempted to apply your chosen methods and then explain why your results are not causal and steps that would be needed to obtain causal results].

Conclusions (guide 200-400 words)

Summarise key findings and provide answers to research questions. You can discuss any policy implications if not already discussed. State any limitations and avenues for future research.

References

References should be cited correctly. It does not matter which reference system you use so long as you are consistent. For more guidance, please see the library guide on citing reference.

Appendices (a copy of your do-file or must be included in your appendix)

There is no set number of tables but it would be expected you’d have at least 1 table of statistics and at least 1 table of regression results (most likely more). I would not expect more than 5 tables/figures in the text as you want to present your results efficiently and not overload the reader. However, you may include extra tables/figures and other additional information in your appendix. All appendices should be referred to at some point in the main text. You must paste a copy of your do-file or equivalent (if not using Stata) into the appendix (you do not need to refer to it) or if you are using an alternative software to Stata a list of commands used.

The suggested word count is 2,000-3,000 words (excluding abstract, tables and figures, references and appendices)

Data sources

Part of the project involves you identifying appropriate sources of data to answer your chosen question (although it is understood that it may not be possible to source all the data you need in the time you have to do the project). Please do have a look at the library guide which will give you some starting points but available and appropriate data sources will really depend on your specific context so another good place to start is to see what datasets related empirical studies have used.

Marking and Assessment Criteria:

Please see the marking rubric at the end which provides details on the marking criteria (and their weights in the final project mark) but the key things I am looking for is:

· A clear and focused research question

· A well thought out and convincing identification strategy

· Appropriately used and well-executed empirical strategy/methods

· Good depth of analysis and independent thought

· Excellent presentation and style: where relevant use of equations; results, tables and other figures well formatted and presented to an academic standard; consistent and accurate referencing

The project is to be submitted electronically through Turnitin (details provided under assignment submission) by Monday 24th April 2023 12 noon. You can only submit a single document  and don’t forget to paste a copy of your do-file or equivalent if you are using another software into your appendix

Students are reminded of the University’s penalty for late submission of work:

The Support Centres will apply the following penalties for work submitted late:

· where the piece of work is submitted after the original deadline (or any formally agreed extension to the deadline): 10% of the total marks available for that piece of work will be deducted from the mark for each working day (or part thereof) following the deadline up to a total of five working days;

· where the piece of work is submitted more than five working days after the original deadline (or any formally agreed extension to the deadline): a mark of zero will be recorded.

The University policy statement on penalties for late submission can be found at: http://www.reading.ac.uk/web/FILES/qualitysupport/penaltiesforlatesubmission.pdf
You are strongly advised to ensure that coursework is submitted by the relevant deadline. You should note that it is advisable to submit work in an unfinished state rather than to fail to submit any work.