This page has advice and practically-focused getting started resources for those who need help getting started with a project.
Some thoughts from Charlie Kufs, the writer of Stats For Cats
What can go wrong AND what you should do about it.
Some thoughts from Karen Grace-Martin at The Analysis Factor
It takes time to collect good data, from designing and pilot testing the questionnaire to recruiting a large and representative sample. If you are doing a data analysis project in one semester, time is the one thing you don't have. Thus, you will probably be doing convenience sampling, which restricts generalizability.
If you are doing a longer project and need to collect data, check out our longer Collect Data with a Survey guide.
Data + Design: A Simple Introduction to Preparing and Visualizing Information
by
See our recommended video tutorials for Learning Qualtrics. Tutorials from the company require you to sign in first.
Experienced data collectors produce the cleanest and easiest to use data files. Always download and read the documentation that comes with it to find variables of interest (note the variable name) and to learn about the population that was surveyed. Also, look for information about how missing or implausible values are represented.
Expect to take several hours to complete.
See also Data Skills module videos on the Data Service YouTube Channel
Interactive text and video tutorials
These suggest completing the surveys module first.
If you are doing a practice project and do not have a pre-existing research question, be nice to yourself and use a dataset provided by your professor (if possible) or from one of the sources listed on the Find Data & Statistics InfoGuide, such as these sources of small-ish datasets on interesting topics:
Multivariable Analysis
by
Now in its third edition, this highly successful text has been fully revised and updated with expanded sections on cutting-edge techniques including Poisson regression, negative binomial regression, multinomial logistic regression and proportional odds regression. As before, it focuses on easy-to-follow explanations of complicated multivariable techniques. It is the perfect introduction for all clinical researchers. It describes how to perform and interpret multivariable analysis, using plain language rather than complex derivations and mathematical formulae. It focuses on the nuts and bolts of performing research, and prepares the reader to set up, perform and interpret multivariable models. Numerous tables, graphs and tips help to demystify the process of performing multivariable analysis. The text is illustrated with many up-to-date examples from the medical literature on how to use multivariable analysis in clinical practice and in research.
(Software-independent) A Question-and-Answer format helps make this book a great reference for those who need to do multiple or other multivariate regression, especially those doing clinical research or biostatistics. It also includes chapters on Propensity scores and Correlated observations.
