This presentation is developed for the postgraduate students and young faculty members from economics discipline who are intending to write an empirical paper.
How to Write an Empirical Paper in Economics by W. Murad (2020)
1. A guideline for the beginners
_______________________________________________________________________________
Assistant Professor, Department of Economics
Noakhali Science and Technology University
Noakhali, Bangladesh
2. Follow the given steps sequentially:
Ø Posing a (research) question
Ø Literature review
Ø Data collection
Ø Econometric analysis
Ø Writing an empirical paper
Sunday, July 12, 2020 2
3. Posing a (research) question
§ The importance of posing a very specific question cannot be
overstated. Without being explicit about the goal of your analysis, you
cannot know where to even begin.
§ When choosing a topic, you should be reasonably sure that data
sources exist that will allow you to answer your question in the
allotted time.
§ After deciding on an area of research, there are some specific ways to
locate specific papers on the topic. For instance, the Journal of
Economic Literature (JEL) has a detailed classification system so that
each paper is given a set of identifying codes that places it within
certain subfields of economics.
Sunday, July 12, 2020 3
4. While you are formulating your question
§ It is helpful to discuss your ideas with your colleagues, mentor, and
friends. You should be able to convince people that the answer to
your question is of some interest.
§ If someone asks you about your paper and you respond with “I’m
writing a paper on the COVID-19 pandemic,” chances are you have
only decided on a general area without formulating a true question.
You should be able to say something like “I’m looking at the oil price
shocks during the COVID-19 pandemic.”
Sunday, July 12, 2020 4
5. Literature Review
All empirical papers must contain a review of literature. It is rare that
one attempts an empirical project where there is not some published
precedent.
You can search through journals or use on-line search services such as
EconLit to produce a topic.
You can search by keywords, by words in the title, by author, and so on.
You can then read abstracts of papers to see how relevant they are to
your own work.
Sunday, July 12, 2020 5
6. The Top Economic (Blue Ribbon) Journals
1. American Economic Review
2. Econometrica
3. International Economic Review
4. Journal of Economic Theory
5. Journal of Political Economy
6. Quarterly Journal of Economics
7. Review of Economic Studies
8. Review of Economics and Statistics
Sunday, July 12, 2020 6
7. Data Collection
§ Deciding on the Appropriate Data Set
§ Entering and Storing Your Data
§ Inspecting, Cleaning, and Summarizing Your Data
Sunday, July 12, 2020 7
8. Deciding on the Appropriate Data Set
You must first decide on the kind of data needed to answer your posed
question. Data sets come in a variety of forms:
• Cross-sectional data set
• Time series data set
• Pooled cross sections set
• Panel data set
Sunday, July 12, 2020 8
9. Entering and Storing Your Data
Once you have decided on a data type and have located a data source,
you must put the data into usable form. It would be convenient if you
first decide which statistical package(s) you will use for your data
analysis.
Sunday, July 12, 2020 9
10. Inspecting, Cleaning, and Summarizing Your
Data
• You need to know how missing values are coded. The best approach is to
set any numerical codes for missing values to some other character (such
as a period) that cannot be mistaken for real data.
• You must also know the nature of the variables in the data set, i.e.,
o Which are binary variables?
o Which are ordinal variables (such as a credit rating)?
o What are the units of measurement of the variables?
o Are variables representing a rate measured as a percent or a
proportion?
o If the values are in real terms, what is the base year or period?
Sunday, July 12, 2020 10
11. Inspecting, Cleaning, and Summarizing Your Data
(continued..)
o Is the variable already transformed in in certain ways, for
instance, in (natural) logarithm?
o What is the frequency of the time series data? Is it daily, weekly,
quarterly, or annually data?
o Is the time series data seasonally adjusted?
Detecting mistakes in a data set is necessary for preserving the integrity
of any data analysis. It is always useful to find minimums, maximums,
means, and standard deviations of all, or at least the most significant,
variables in the analysis.
Sunday, July 12, 2020 11
12. Econometric Analysis
§ Ordinary least squares (OLS) or weighted least squares (WLS)?
In order to justify OLS, you must also make a convincing case that the
key OLS assumptions are satisfied for your model.
§ When specifying your model you must also make functional form
decisions.
o Should some variables appear in logarithmic form?
oShould some variables be included in levels and squares, to
possibly capture a diminishing effect?
oIs there any specification error?
oIs there any measurement error?
Sunday, July 12, 2020 12
17. Writing An Empirical Paper
“Do not be discouraged if you find writing an empirical paper difficult; most
professional researchers have spent many years learning how to craft an empirical
analysis and to write the results in a convincing form.” – Jeffrey M. Wooldridge
Outline of an empirical paper:
• Introduction
• Literature Review
• Theoretical Framework
• Econometric Models and Estimation Methods
• The Data
• Result Discussion
• Conclusions (and Policy Recommendation)
Sunday, July 12, 2020 17
18. Guidelines for Writings
• Stay focused. If some material is irrelevant to these points, it should
probably be cut.
• Keep sentences short.
• Present tense is preferable.
• Cite prior works according to the author’s guidelines.
• Try to avoid contractions or abbreviations. For example, write ‘that is’
in the place of ‘i.e.’.
• Good writers avoid the passive voice.
• Positive statements are more convincing than normative statements.
• Avoid jargon.
Sunday, July 12, 2020 18
19. Guidelines for Writings (cont.)
• Revise wordy sentences. For example, in most cases, change “in order
to” to “to”, “whether or not” to “whether” and “is equal to” to
“equals”.
• Keep your writing self-contained. Frequent references to other works,
or to things that have come before or will come later, can be
distracting.
• Put details and digressions in footnotes.
• Remember two basic rules of economic usage:
o “Long run” (without a hyphen) is a noun. “Long-run” (with a
hyphen) is an adjective. Same with “short(-)run.”
Sunday, July 12, 2020 19
20. Guidelines for Writings (cont.)
• Buy a copy of Strunk and White’s Elements of Style. Also, William
Zinsser’s On Writing Well. Read them—again and again and again.
• Keep it simple. Think of your reader as being your college roommate
who majored in English literature. Assume he has never taken an
economics course, or if he did, he used the wrong textbook.
• Be your own worst enemy. If you are not, someone else will be!!
Sunday, July 12, 2020 20
21. Introduction
• Basic objectives
• Why we should care about this study. Is it a controversial theoretical
result? An important policy question? Why should we care from an
economic perspective?
• A good idea is to surprise or puzzle the reader’s intuition in this
section so that he or she would be curious to read the rest of your
paper.
• Presenting simple statistics or graphs that reveal a seemingly
paradoxical relationship is a useful way to introduce the paper’s topic.
Sunday, July 12, 2020 21
22. Review of the Literature
Review of the literature, indicating what has been done and how previous
work can be improved upon.
• Since your main contribution will be in economics discipline, try to relate
your study mostly to previous economics papers.
• Citation of more research is better than less.
• Keep in mind that you should cover only those works that are directly
relevant to your research.
Sunday, July 12, 2020 22
23. Review of the Literature (cont.)
• The first objective of the literature survey is to
o demonstrate your familiarity with scholarly work on your topic
o trace the development of important themes
o draw out any tensions in the prior studies.
• The second objective of the literature survey is to
o lay the foundations for your paper
o provide your motivation
o explore the issues you intend to raise, the approach you will take
with referencing to previous (scholarly) research.
Sunday, July 12, 2020 23
24. Review of the Literature (cont.)
Where should I write the literature review?
Some like to have a separate section called “literature review,” while
others like to include the literature review as part of the introduction.
This is largely a matter of taste, although an extensive literature review
probably deserves its own section.
Sunday, July 12, 2020 24
25. Theoretical Framework
This is the section where you describe the general approach to
answering the question you have posed. It can be formal economic
theory, but in many cases, it is an intuitive discussion about what
conceptual problems arise in answering your question.
Sunday, July 12, 2020 25
26. Econometric Models and Estimation Methods
You must restate your theoretical framework in an econometric model. Suppose
you are inclined to estimate the long-run relationship and short-run dynamics
between demand for money and interest rate, then you may follow the
following estimation methods:
o Unit Root Test
o Cointegration Test
o Error Correction Mechanism (ECM)
You are supposed to explicitly present the estimation methods in detail.
Sunday, July 12, 2020 26
27. Econometric Models and Estimation Methods (cont.)
Things to be noted before estimating specific strategy:
• Be aware of a naïve estimate.
• Describe comparison groups and give intuition/justification for this
comparison.
• Use subheadings to lead the reader through the different levels of
your analysis.
• Generally, you will estimate more than one regression model. Present
your results in the conventional format.
Sunday, July 12, 2020 27
28. The Data
Enough information should be presented so that a reader could, in principle, obtain the
data and redo your analysis.
• Public data sources should be included in the references.
• Short data sets can be listed in an appendix.
• If you have conducted a field survey, a copy of the questionnaire should be presented
in an appendix.
• Discuss limitations of the data. For example, missing variables/observations, small
sample size or survey response.
• Let the reader know why your data is most relevant to your research.
Sunday, July 12, 2020 28
29. The Data (cont.)
It is also very informative to present a table of summary statistics, such as
minimum and maximum values, means, and standard deviations for each
variable. For binary variables, the only necessary summary statistic is the
fraction of ones in the sample. For trending variables, things like means
are less interesting.
For time series data sets, identify the years that you are using in the
analysis, including a description of any special periods in history (such as
World War II).
Sunday, July 12, 2020 29
30. How to Present the Results
• Present enough information in detail so that one can replicate your
results.
• Report standard errors in the parentheses underneath the
coefficients (instead of t-statistics or p-value).
• Be careful. Don’t make your paper like a “kitchen sink”!!
• Don’t include every parameter estimated from every regression. A
good general rule is to present only those parameter estimates that
speak directly to your topic. For example, see the following tables:
(Table 3 is from Currie and Neidell, 2005 and Table 4 is from Chay and
Greenstone, 2003)
Sunday, July 12, 2020 30
33. Result Discussion
§ Keep theory in mind when interpreting results.
§ If only a few equations are estimated, you can present the results in
equation form with standard errors in parentheses below estimated
coefficients.
§ If your model has several explanatory variables and you are
presenting several variations on the general model, it is better to
report the results in tabular rather than equation form.
Sunday, July 12, 2020 33
34. Result Discussion (continued..)
The most important thing is to discuss the interpretation and strength
of your empirical results.
§ Do the coefficients have the expected signs?
§ Are they statistically significant?
§ If a coefficient is statistically significant but has a counterintuitive sign,
why might this be true?
§ Describe the magnitudes of the coefficients on the major explanatory
variables. Often there are one or two policy variables that are central
to the study. Their signs, magnitudes, and statistical significance
should be addressed in detail.
Sunday, July 12, 2020 34
35. Result Discussion (cont.)
If you have used at least two different methods—such as OLS and 2SLS,
or levels and differencing for a time series, or pooled OLS versus
differencing with a panel data set—then you should comment on any
critical differences. In particular, if OLS gives counterintuitive results,
did using 2SLS or panel data methods improve the estimates?
Provide enough information for a reader to decide whether they find
your results convincing or not.
Sunday, July 12, 2020 35
36. Result Discussion (cont.)
• Compare your results to others in the literature.
• Draw a conclusion even if it is a negative one! This is still worth
reporting.
Sunday, July 12, 2020 36
37. Conclusions (and Policy Recommendation)
• Conclusion should be short and sweet.
• Remember your reader wants to know your facts not your opinions.
• Focus your contribution in detail.
• Summarizes your findings.
§ Discuss caveats of your study.
§ It might even suggest directions for further research.
§ It may propose some policy recommendation regarding the findings of the
study.
Sunday, July 12, 2020 37