SEER - Using Multiple Imputation to Enhance the Utility of the SEER Summary Stage for Comparative Effectiveness Research Project

The aims of this study are as follows: 1. Understand the coding rules for the SEER Summary Stage 1977, 2000 and CS, and how unknown stage is defined for lung and liver cancer. 2. Determine which SEER variables are associated with known SEER Summary stage values as well as variables that predict unknown SEER summary stage values. 3. Utilize several Multiple Imputation techniques/statistical packages to impute the SEER Summary Stage, and examine which factors will affect the analysis. 4. Examine if using the Multiple Imputation techniques will generate disparate results in data analysis when compared to use of the common statistical method (complete case method). 5. Examine whether the different software packages that implement Multiple Imputation procedures will generate similar or disparate results in data analysis.