Oh No! They Cut My Funding! Using “Post Hoc” Planned Missing Data Designs to Salvage Longitudinal Research

Planned missing designs are becoming increasingly popular, but because there is no consensus on how to implement them in longitudinal research, we simulated longitudinal data to distinguish between strategies of assigning items to forms and of assigning forms to participants across measurement occasions. Using relative efficiency as the criterion, results indicate that balanced item assignment coupled with assigning different forms over time most often yields the optimal assignment method, but only if variables are reliable. We also address how practice effects can bias latent means. A second simulation demonstrates that (a) assigning different forms over time diminishes practice effects and (b) using planned-missing-data patterns as predictors of practice can remove bias altogether.

Download Full-text

Planned missing data designs in psychological research.

Psychological Methods ◽

10.1037/1082-989x.11.4.323 ◽

2006 ◽

Vol 11 (4) ◽

pp. 323-343 ◽

Cited By ~ 238

Author(s):

John W. Graham ◽

Bonnie J. Taylor ◽

Allison E. Olchowski ◽

Patricio E. Cumsille

Keyword(s):

Missing Data ◽

Psychological Research ◽

Planned Missing Data ◽

Planned Missing

Download Full-text

Reflection on modern methods: planned missing data designs for epidemiological research

International Journal of Epidemiology ◽

10.1093/ije/dyaa042 ◽

2020 ◽

Vol 49 (5) ◽

pp. 1702-1711 ◽

Cited By ~ 1

Author(s):

Charlie Rioux ◽

Antoine Lewin ◽

Omolola A Odejimi ◽

Todd D Little

Keyword(s):

Missing Data ◽

Gold Standard ◽

Epidemiological Research ◽

Missing Data Treatments ◽

Planned Missing Data ◽

Missing Completely At Random ◽

Modern Methods ◽

Missing Items ◽

Data Design ◽

Planned Missing

Abstract Taking advantage of the ability of modern missing data treatments in epidemiological research (e.g. multiple imputation) to recover power while avoiding bias in the presence of data that is missing completely at random, planned missing data designs allow researchers to deliberately incorporate missing data into a research design. A planned missing data design may be done by randomly assigning participants to have missing items in a questionnaire (multiform design) or missing occasions of measurement in a longitudinal study (wave-missing design), or by administering an expensive gold-standard measure to a random subset of participants while the whole sample is administered a cheaper measure (two-method design). Although not common in epidemiology, these designs have been recommended for decades by methodologists for their benefits—notably that data collection costs are minimized and participant burden is reduced, which can increase validity. This paper describes the multiform, wave-missing and two-method designs, including their benefits, their impact on bias and power, and other factors that must be taken into consideration when implementing them in an epidemiological study design.

Download Full-text