It is good scientific practice to make your data available so that others may replicate your work. (This goes back to the methodology of the scientific method.) At a minimum, this means explaining your “Sources and Methods,” i.e. providing clear citations for exactly where you got the raw data, and how you manipulated the raw data to put it in the form you actually used. Better yet, is to provide a copy of the exact data you used, in addition to documenting where it came from (and how).
To that end, please create a data appendix in the form of a Word document, including data for all the variables you plan to use in your research project. (I understand that ultimately these data may change, but do the best you can for now. Think of this as a first draft of the data appendix for your final paper.)
Your data appendix should include the following:
- A title; e.g. Data Appendix
- A one-line equation that states your model: e.g. Income = f[ Age, Education, Father’s education, IQ, Gender ]
- Note: It is good practice to use meaningful variable names. For example, instead of X1, X2, X3, and X4, use Q, C, I, and G.
- The complete definition of each variable that is included in the equation listed in number one. For example:
* Income – annual income in nominal terms for the year 1997 for each individual
* Age – age in years of each individual in the data set
* Education – total number of years of education completed for each individual
* Parent’s education – total number of years of education completed by father
* IQ – results of IQ test for each individual
* Gender – sex of individual, male = 1, female = 0
- A table listing the observations for each variable, appropriately formatted and labeled. You may wish to create your dataset as an excel spreadsheet. You can then insert the spreadsheet as a table in your data appendix (which is a word document).
- For each variable, list the exact source where you found the data. Don’t just list sources. Make sure you specify which variables came from which sources. Explain any manipulations you did to the source data to obtain the values you present in your appendix. The documentation should be sufficiently detailed so that any reader can find the exact data you include with a minimum of effort.
- Please include graphs of all the variables, appropriately formatted and labeled, and be sure to visually examine all data series to identify any obvious problems (e.g. typos, outlying data points which may need to be fixed, etc.)
You can see a good example of a data appendix HERE: