Third year students are in panic. Yes, that’s actually a very painful fact! We spent 2.5 years of our university life just knowing courseworks and exams, and now the final 0.5 year is spent on the longest exam ever – DISSERTATION or for the BSc people ECONOMETRICS PROJECT!
So in an attempt to help you sooth your panic, I’m posting here a few guidelines on how to ace that once in a life time exam.
For BSc student, here’s a guide on how to start thinking about your Project.
1, The Model: The model and the data are the starting points of this project. The first step in formulating a model is to select a topic of interest and to consider the model’s scope and purpose. In particular thought should be given to the objectives of the study, what boundaries to place on the topic, what hypotheses might be tested, what variables might be predicted, and what policies might be evaluated. Close attention must be paid, however, to the availability of adequate data.
So, your interest topic -> check available data -> formulate your model.
These papers are generally interested in the impact of some independent variable X on a dependent variable Y. But since there are many variables X that have influence on the variable Y, it is important to include all those variables. And as our lecturer said he would prefer if we compare between countries or commodities etc.
I think this is the hardest part of the project. I still couldn’t seem to make up my mind on what topic I want to do. I keep changing my mind without knowing exactly why. I guess, if you already have a topic in mind, you are in the lead!
2, The Data: Data should be time series. For this project it is best to avoid data sets which are too small, say less than fifteen observations. If you are dealing with yearly data, the lecturer expects at least 25 year worth of data available. The data should be examined, and if necessary, refined to make them suitable for the purposes of the model.
3, Estimation: After both the model and data have been developed, the next step is to utilize this techniques to estimate the model. Your final paper is expected to use multiple regression analysis to estimate your multivariate model and test relevant hypotheses or time series model with prediction of Y variable. You should use Excel and STATA for the statistical analysis. For this project it is best if the dependent variable is a quantitative variable.
4, The Write-Up: I guess it’s best to check your module outline for this. However, if you already lost yours, here it is:
– The project report should begin with an executive summary, giving the main features and conclusions of the study in not more than 300 words. You should pay careful attention to the clarity of this summary.
– You will have chosen a title from those suggested or have a title of your own which has been discussed with module leader. The main focus of the project is your ability to for-mulate an empirical model for a relevant and well defined economic problem, use of appro-priate econometric techniques and the interpretation of results using an econometric pack-age. You should write a clear account of what problems your project addresses.
– The economic theory behind the model should be clearly identified. In particular, if any ad-ditional assumptions are imposed on a theory with the aim to derive an empirical (estimable) model, they should be stated.
– You need to discuss the properties of data that you have collected to undertake your study, including any problems with the data and any adjustments you made to the data set. This could include, for instance, the splicing together of series measured from different base val-ues, conversion of nominal series to ‘real’ values, measurement problems, interpolations, re-liability and completeness of data sets, etc.).
– The main section of the project will be to build, estimate and apply (for forecasting and/or policy analysis) the model developed in part 3 above. The model has to be developed on the grounds of the properties of data. In particular, model specification process has to be explicitly explained. Modelling of real life data is always difficult and rarely leads to positive results; it is therefore important that students are able to look critically at their re-sults and are able to identify drawbacks and shortcomings of their findings.
– The project should always be completed by appropriate conclusions and, if relevant, policy prescriptions. These conclusions should relate to (i) the model (its ability to forecast, policy analysis, its drawbacks, advantages, consistency with the economic theory, etc) and (ii) also the economic problem. Special emphasis should be put on the transparency and clarity of conclusions.
– There should be two appendices which accompany the main text of the assignment. The first one should contain all relevant computer output (estimated parameters, statistics, etc.) and the second one should contain all original data used and details of all transformations of the variables, interpo-lations etc. Shallow and medium replicability principles have to be secured: a reader of your project should be able to obtain results identical to yours while (i) using the data you supplied (shallow rep-licability principle) and (ii) retrieving data from the sources you gave and conducting operation of the data as described in your project (medium replicability principle).
5, Length of Project: No more than 30 pages, excluding appendices, formatted as in the template. Appendices should contain full sets of original data, full data sources and relevant computer output.
So hope this hasn’t scared any prospectus or 1st and 2nd year BSc students away. And let’s pray we 3rd year could all get out of this exam in one piece. Good Luck guys!