semester

semester - Semester Project SYA 6305 See the Data...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Semester Project SYA 6305 See the ‘Data Management in Stata’ document. Part I Hypotheses § Present appropriate hypotheses to guide your project. Project folder § Keep all of the data and files for this, or any, project in its own exclusive folder. § Save a backup copy of the original (‘master’) data set. o Never save changes made to the original (‘master’) data set, but rather make the changes by means of do-files and save the changes as new, working versions of the data sets (see below on nested do-files). Log file, command file, and do-file § Make a log file, command file, and do-file for every step. o Nest the do-files: nested, shorter do-files are more manageable than long do-files (see ‘Nested Do-Files’). § Every step you do must be documented and replicable. If helpful, restrict the working version of the data set to the variables that are relevant to your project (including variables that will help you explore the data). § Log, command, and do files are necessary for this step, as well as for all of the other steps. § help keep; help drop The Stata commands ‘inspect’ and ‘codebook’ provide excellent overviews of potential problems. Part II § Key questions to answer about the data o Who funded the collection of the data, and who collected the data and for what objectives? Do your answers suggest any possible biases in the data? o Who do the data represent, how were the data collected, and how many observations are there? In view of these questions, to what extent are the data adequate or not for your study? o What are the data’s variables? In view of your study’s purpose, are potentially important variables not included? If so, what variables are absent, and why are they important? o How are each of the variables defined and measured? To what extent are the definitions and measurements valid or not, and to what extent are the measurements likely to be reliable (if you have some way of judging) (see, e.g., Babbie, The Practice of Social Research , on ‘validity’ and ‘reliability’)? Insofar as the operationalization could be improved, are there mitigating circumstances, and if there are, what are they? Are there ways that you might be able to improve the operationalization of the
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 07/11/2011 for the course SYA 6305 taught by Professor Tardanico during the Fall '08 term at FIU.

Page1 / 5

semester - Semester Project SYA 6305 See the Data...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online