Rank order outlier (ROO) plots to detect possible outliers in unreplicated 2k completely randomized factorial designs: numerical example
Two-level unreplicated factorial design is very common in manufacturing industries. The design can be used to save cost since it usually needs less experimental run. But, problem appears when the experiment is done without any replication. In such kind of experiment, there are problems in identifyin...
保存先:
| 主要な著者: | , |
|---|---|
| フォーマット: | 論文 |
| 言語: | English |
| 出版事項: |
Asian Research Publishing Network
2016
|
| オンライン･アクセス: | http://psasir.upm.edu.my/id/eprint/53723/1/Rank%20Order%20Outlier%20%28ROO%29%20plots%20to%20detect%20possible%20outliers%20in%20unreplicated%202k%20completely%20randomized%20factorial%20designs.pdf http://psasir.upm.edu.my/id/eprint/53723/ http://www.arpnjournals.com/jeas/volume_18_2016.htm |
| タグ: |
タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
|
| 要約: | Two-level unreplicated factorial design is very common in manufacturing industries. The design can be used to save cost since it usually needs less experimental run. But, problem appears when the experiment is done without any replication. In such kind of experiment, there are problems in identifying significant terms as well as to identify possible outlier in the data. This article discusses about the use of Pareto plot to identify significant terms for unreplicated two-level factorial experiments through numerical example. Meanwhile, the numerical example is also used to clearly describe how to create and interpret both Rank Order Outlier (ROO) and iterative ROO plot in identifying possible outlier in the experimental data. |
|---|