Handling Missing Data

Missing data can significantly affect the quality and results of research. This article discusses the importance of avoiding missing data and provides effective strategies for handling it. These strategies include proper planning, documentation, and data deletion methods.

Handling Missing Data
Institution:
Course:
Tutor:

Introduction
Missing data can be elaborated as the existence of a data value that is not entered or
stored to represent an observation of interest. The problem of missing data, as a result of
skipping or missing a variable, is very common in most instances within many of the researches
performed and significantly affects the conclusions of many researchers (Graham, 2009).
Body
The process of data analysis in itself, is a delicate one and requires the highest level of
accuracy in both data collection and input so as to obtain quality results. Missing data, during
any of the stages of data processing, substantially reduces the statistical adequacy and power of a
study and thus leads to the production of biased estimates and successively leads to the
production of inadequate and invalid conclusions (Dzuira, 2013). It is, therefore, highly crucial
that missing data is handled to avoid a loss in the overall adequacy and appropriateness of results
obtained from a research.
The most effective way of handing the existence of missing data and avoiding skipping of
data is by performing a well-planned and organized study. In order to ensure that this goal is
achieved, several activities have to be performed. To begin with, the study should be formatted
to only include participants who will be included in the study (Van den Broeck, 2013). This is
possible by reducing the number of follow-up visits and by collecting only the relevant and
essential information at each visit. It is also important that a user friendly case-report is
developed. This will ensure appropriate planning is done and the likelihood of missing some
variables will be avoided.

The process of data collection, input and editing should also be clearly highlighted in
writing. The documentation of the ways and means to perform the research process between the
investigators and participants must be properly documented. Proper documentation is essential
controlling and avoiding missing data. Compounding to the details already discussed, it is also
crucial to ensure the enrollment process of participants is well documented (Van den Broeck,
2013). A pilot study should be performed to ascertain any possible problems before pursuing the
main study.
In most cases, it is difficult to prevent missing data. However, a specific method such as
the listwise or case deletion method can be employed to avoid missing data. This method
includes deleting those instances with missing data and analyzing the remaining data set(s).
According to some researchers, litwise deletion may cause some form or bias (Catellier,2013).
However, other researchers argue that the results of listwise deletion are conclusive and do not
contain any available bias. It is however important to note that in cases where there is a large
volume of data or sample, the listwise method may not be the best strategy to use. Conversely, it
is effective in small samples of data. An example of a variable in the scholar-practitioner project
is age. The proportion of missing is around twenty percent. The possible reason for this is the
fear of participants in sharing their ages. Participant education and prior preparation is higly
crucial to avoid the occurrence and reoccurrence of this instance.
Conclusion
Missing data significantly affects the results and quality of a research and should be
avoided. The significance and applicability of a research is immensely affected.

References
Altman, D. G. (2009). Missing outcomes in randomized trials: addressing the dilemma. Open
Medicine, 3(2), e51.
Catellier, D. J., Hannan, P. J., Murray, D. M., Addy, C. L., Conway, T. L., Yang, S., & Rice, J.
C. (2005). Imputation of missing data when measuring physical activity by
accelerometry. Medicine and science in sports and exercise, 37(11 Suppl), S555.
Dziura, J. D., Post, L. A., Zhao, Q., Fu, Z., & Peduzzi, P. (2013). Strategies for dealing with
missing data in clinical trials: from design to analysis. The Yale journal of biology and
medicine, 86(3), 343.
Graham, J. W. (2009). Missing data analysis: Making it work in the real world. Annual review of
psychology, 60, 549-576.
Van den Broeck, J., Cunningham, S. A., Eeckels, R., & Herbst, K. (2005). Data cleaning:
detecting, diagnosing, and editing data abnormalities. PLoS medicine, 2(10), e267.