STRATIFIED SAMPLING
Different sampling methods provide different levels of accuracy, depending on the mode the study is done (Shields, Teferra, Hapij,& Daddazio, 2015). A review is done from a research article of my choice, which entails temporal disease progression patterns in Denmark. It involves the study of the whole population. Precisely the study was focused on the chronic obstructive pulmonary disease (COPD) and gout. The disease-focused are quite common, and they are hard to mitigate. Therefore, stratified sampling is used in understanding the disease and preventing future ailments of an individual.
Stratified sampling is a highly effective method for getting high-dimensional data (Jing, Tian, & Huang, 2015). Dividing into sub-groups is very useful and is used in understanding the data in different parameters. For instance, data can be classified into age and gender. They are the most common parameter but help a lot in getting the best niche of the data collected. In terms of getting the samples, in this method, it is done in correct proportionality. The bigger the population, the bigger the sample taken and vice versa. It helps in getting more realistic and accurate data. The samples taken are carefully analyzed in terms of a specimen, and when accurately done, the data collected will represent the whole population. Despite having difficulty in choosing the characteristic to stratify, it eventually provides accurate results. Stratified sampling can be used in data with a wide range of similar traits, and finally, a well-analyzed data is created (Shields & Zhang, 2016).
In conclusion, the stratified method is a suitable method in the field of medicine. The most apparent consideration it has is in an understanding of the general subgroups that are entailed. The knowledge of the data is very essential since a clear interpretation of the data is seen.
Article title
Temporal disease trajectories condensed from population-wide registry data covering 6.2 million patients
Permalink: https://www.nature.com/articles/ncomms5022
References
Shields, M. D., Teferra, K., Hapij, A., & Daddazio, R. P. (2015). Refined stratified sampling for efficient Monte Carlo based uncertainty quantification. Reliability Engineering & System Safety, 142, 310-325.
Shields, M. D., & Zhang, J. (2016). The generalization of Latin hypercube sampling. Reliability Engineering & System Safety, 148, 96-108.
Jing, L., Tian, K., & Huang, J. Z. (2015). Stratified feature sampling method for ensemble clustering of high dimensional data. Pattern Recognition, 48(11), 3688-3702.