Advantages and disadvantages of the planned missing data design method in field research are discussed.
We utilized a planned missing data design to assess weight status and a broad range of psychological flexibility components in a nationally representative sample of Americans (N=7884; 3748 males, 4136 females; age: M=47.9, SD=16).
Due to the large number of items, we implemented a planned missing data design with three booklets to evaluate our instrument (cf. Frey et al. 2009; Graham et al. 2006).
The method involves using a planned missing data design to randomly allocate participants a reduced selection of items using multiple imputation to replace the missing data and produce a complete dataset, thus retaining the full range of items across the studied population.
No imputation for missing data was planned or performed.
No replacement of missing data was planned as part of the analysis of the primary endpoint.
However, their effects could not be analyzed in this study due to the high proportion of missing data; we plan to test the effects of these variables on breast cancer stage in a future study.
With the recent guidelines and exhortations to more appropriately handle missing data (including planning and prevention), we hypothesized that the amount of missing data would have decreased and current approaches would have improved.
Knapp [ 41] noted that the best way to handle missing data is to plan in advance how to prevent the data from being missing.
In addition, this risk will be minimised by careful handling of the data, involvement of two independent statisticians in data analysis, having a unified plan for management of missing data, and the plan for open discussions to resolve any issues regarding any conflicting information.
Finally, the paper illustrates ways that researchers can use intentional, or planned, missing data to enhance their research designs.
