About 10 years ago, when I first started consulting, I had a client, Linda, who had a lot of data missing from her data set for her master’s thesis. She had a pretty big model–about 15 predictors. And while no one variable was missing more than 5 or 10% of the data, in combination, listwise deletion was getting rid of more than half the cases. She wasn’t getting any significant results because of the huge loss of power, and with that many dropped cases, it wasn’t clear that she still had a random sample that gave her unbiased results.
At that point, modern approaches to dealing with missing data did exist, but they were just beginning to become available in specialized software. Neither Linda nor I had learned about them in statistics classes, because they just hadn’t hit the mainstream yet. With a lot of research and a lot of learning some frustrating software, we were able to hobble together a reasonable solution.
But Missing Data is one area of statistics that has just blossomed in the past 10 years. Good solutions that give unbiased results for most missing data problems are now available in mainstream software–SPSS, SAS, Stata, R. There isn’t a reason (or an excuse) to keep struggling with (or defaulting to) listwise deletion.
But these approaches do require some solid understanding. They can be used in different situations, and some are much simpler and faster to implement well. Like most statistical techniques, you have to know what you’re doing. A little knowledge can be dangerous.
My upcoming Dealing with Missing Data without Biasing your Results workshop will give you: the solid understanding of the four main approaches to dealing with Missing Data; the advantages, disadvantages, issues, and appropriate situations for using each; the step-by-step process of how to diagnose your missing data and choose an approach; a full session each on multiple imputation and maximum likelihood approaches.
The webinar workshop is a convenient, inexpensive, and supportive way to learn. Attend three 90-minute sessions and a 60-minute Q&A session through your own computer. Ask questions during the workshop and in our online forum between sessions. You have full access to all the video recordings to watch again and again (or if you miss a session); the example data and all my SPSS and SAS programs to try things on your own; and the option to purchase the written transcripts for easy reference.
If you’re ready to understand modern approaches to Missing Data, how to figure out which one to use, and how to implement it, come join me. It begins this Thursday, May 21.
Register and get more information at http://www.theanalysisfactor.com/learning/MD/MD-registration.html
