Gary King

"Replication, Replication" & "Publication, Publication"

Replication, Replication

What is Replication?

  • To follow the precise path taken by a previous researcher and then review and try to improve on the data or methodology.

Why to Replicate?

  • To understand, evaluate and specially build up on existing works.

Important for Graduate Students?

  • Strengthen students' ability to learn the basics of academic research and ultimately conduct their own original research.

Publication Publication

Elements of the paper
  1. Your paper should address one problem in your field of interest and it should contain one point with several supporting points.
  2. Find an article in your field, acquire the data used in the article, and replicate the numerical results in the tables and/or figures
  3. Have an approval of professor
  4. If you decide that the conclusions of the original article are incorrect, then show why you think that but also what led the authors of the original article to have a different conclusion.
  5. Clarify with precision the extent to which you were able to replicate the author’s results.
  6. This paper should be a report and it should focus on the contribution to the collective knowledge about the world.
  7. Try to improve the presentation of the original results. See whether you can find useful, additional, or even contradictory information not discussed in the article
  8. Try to make one improvement, or the smallest number of improvements possible to produce new results, and show the results
  9. If you are able to improve or change the author’s results in some important way with the minimal change necessary, write that up separately.
  10. Look for as many observable implications as possible and check them
  11. Understand your raw data prior to statistical modeling, and help your readers do so.

Style of Replication paper

  1. Your paper should be structured and organized into sections and subsections.
  2. The overall structure of the paper, and all the key points you want to make, should make sense and aim to accomplish your goal.
  3. Follow the table of contents
  4. Do not try to hide weaknesses in your paper. If you know of a problem with your analysis that you have not solved, clearly describe the problem.
  5. The cover pager/front matters
  6. Appearance also matters
  7. Identify the specific empirical question you are interested and immediately get to it.
  8. Try to not include a section titled “literature review”
  9. If you have long technical lists of coding rules, or anything else that seems essential but distracts from your point, put it in an appendix.
  10. Be nice
  11. Math: Larger equations should be set with equation number
  12. Tables and Figures: should be included to make specific points, and to draw readers’ attention to these points.
* No one cares about numbers that even the author doesn’t want to interpret.

Problems to avoid and other suggestions

  1. Decisions about what to present should be made by you. You have been given the tools to create your own statistical models.
  2. Avoid stating the hypothesis like this
    1. Hypothesis 1: The effect of…
    2. Hypothesis 2: Instead, the effect of...

- If you want to emphasise something do it with italics

  1. Try to satisfy someone quantitative (by doing the statistics) and a smart non-quantitative type (By fully explaining things in sufficient detail).
  2. Make sure all point estimates come with some measure of their uncertainty, such as confidence intervals, or standard errors.
  3. Provide sufficient information about your analysis so that it is possible for someone who reads your paper to replicate the analysis

Recommendations for future Replications:

1. Create a replication data set
  • Include all necessary information to replicate empirical results

- Quantitative: show original data, computer program, process to obtain the data, etc.

- Qualitative: transcript of interviews, audio tapes, etc.

2. Once replication data set has been created it should be available and it should make reference to the original work (as the first footnote)
  • Make info available on request
  • Instantly available via internet – Free and easy submission

- PAVA : Public Affairs Video Archives

- ICPSR: Interuniversity Consortium for Political and Social Research