Missing data within a quantitative research study: How to assess it, treat it, and why you should care.
Autor: | Bannon W Jr; William Bannon Associates, Inc, Brooklyn, New York. |
---|---|
Jazyk: | angličtina |
Zdroj: | Journal of the American Association of Nurse Practitioners [J Am Assoc Nurse Pract] 2015 Apr; Vol. 27 (4), pp. 230-2. Date of Electronic Publication: 2015 Feb 11. |
DOI: | 10.1002/2327-6924.12208 |
Abstrakt: | Missing data typically refer to the absence of one or more values within a study variable(s) contained in a dataset. The development is often the result of a study participant choosing not to provide a response to a survey item. In general, a greater number of missing values within a dataset reflects a greater challenge to the data analyst. However, if researchers are armed with just a few basic tools, they can quite effectively diagnose how serious the issue of missing data is within a dataset, as well as prescribe the most appropriate solution. Specifically, the keys to effectively assessing and treating missing data values within a dataset involve specifying how missing data will be defined in a study, assessing the amount of missing data, identifying the pattern of the missing data, and selecting the best way to treat the missing data values. I will touch on each of these processes and provide a brief illustration of how the validity of study findings are at great risk if missing data values are not treated effectively. (©2015 American Association of Nurse Practitioners.) |
Databáze: | MEDLINE |
Externí odkaz: |