Preliminary Analysis Guidelines EC481
Preliminary Analysis Guidelines
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: THEend8_
Preliminary Analysis Guidelines
EC481
1. Written Preliminary Analysis
Your written submission should include the following:
1. Research question. Review the research question you submitted in the proposal, with any
necessary edits. If you have changed your topic, state the new research question. Note that
you can repeat the research question you submitted in your proposal if you are happy with it,
but please make edits if necessary to make it clearer.
2. Preliminary Literature Review. A brief review of the literature that is relevant to your
research question. Use 3-5 references (including the ones from your proposal, if you are still
using them). This will act as a start to the full literature review you will complete in your paper.
When writing this section, please avoid going paper-by-paper and summarizing each one
individually because these tend to be very tedious to read and not overly informative. Instead,
try to report the results of the literature in terms of the main findings as a whole, grouping
together papers that have similar conclusions. For examples of this, look at the literature
review sections of some of the papers you are surveying.
3. Preliminary empirical model. Write down a statistical model that you think relates your
dependent variable(s) to your independent variable(s). Provide a brief explanation for why
you chose this model. For many this will be a linear regression model, but you may be doing
something different. At this stage in the term, you will not estimate this model or explain how
to estimate it; the purpose is to guide you as you think about your descriptive analysis,
described below.
4. Descriptive Analysis of Data. In this section, state the dataset you are using, and present a
set of descriptive statistics that shows the key patterns of your data as it relates to the research
question. This typically involves a table or set of tables or graphs with the means of the key
variables of your analysis (i.e. the dependent variable(s) and main independent variable(s)), and
a table or set of tables or graphs that highlights the key relationship between your dependent
variable and main independent variables. When completing this, ask yourself what is the best
way to present your data to a reader who knows very little about the topic, so that after they
read the tables/graphs, they understand what is going on with your data and how the key
variables are related. Keep the set of tables/graphs small, and focus on the most informative
ones only.
Descriptive analyses typically do not include a regression analysis (unless you are using
regression as a descriptive tool), so do not include that in the preliminary analysis. You will
perform your regression analysis in the extended outline.
Page 2 of 2
When doing a descriptive analysis, be creative, especially with graphs. There are lots and lots
of resources on how to produce good data visualizations, some of which I will post on the
course mylearningspace page.
In terms of length, aim for about 3-5 pages of text (double spaced), not including the graphs and
tables. Again, keep the number of tables and graphs small.
2. Workshop to Discuss Preliminary Analysis
For the workshop, please prepare a slide show of what your written submission to discuss what you
have learned in your research to date. The slide show should consist of about 5-10 slides (i.e., enough
for a 7-10 minute presentation).
The slides may be different from traditional presentation slides in that the reader should be able to
understand your slides without you being there. This means that you might need to put a few more
words on the slides than you normally would.
Please submit your presentations in MyLS and Gradescope. You will each be given 7-10 minutes to
present your slides during the workshops.