The objective of this course is to provide the student with the knowledge in nonparametric inference and methodsthe objective of this course is to provide the student with knowledge in nonparametric inference and methods
無母數分析和傳統的母數分析最大的差別在於在做無母數分析時，不需對於母體的分佈做很多限制性大的假設，因此適用的範疇相當的廣，但也因相同的原因使得統計結論的品質較為粗糙。
本系所受之無母數分析包含下列三大範疇：(1)根據二項式分佈所做的無母數分析，如sign test, tolerance limit等。(2)根據二維列聯表所做之無母數分析，如相關性分析。(3)根據排序(rank)所做之無母數分析，如Mann-Whitney test, Friedman’s test。
The biggest difference between mother-free analysis and traditional mother-number analysis is that when doing mother-free analysis, there is no need to make many restrictive assumptions about the distribution of the mother. Therefore, the applicable scope is quite wide, but also for the same reason. This makes the quality of statistical conclusions rougher.
The mother-free analysis accepted by this department includes the following three categories: (1) Mother-free analysis based on binomial distribution, such as sign test, tolerance limit, etc. (2) Parentless analysis based on two-dimensional contingency tables, such as correlation analysis. (3) Mother-free analysis based on ranking, such as Mann-Whitney test, Friedman’s test.
Nonparametric Statistical Inference (fifth edition)
by J. D. Gibbons and S. Chakraborti
nonparametric statistical inference (fifth edition)
| 評分項目 Grading Method | 配分比例 Grading percentage | 說明 Description |
|---|---|---|
| midtermmidterm midterm |
50 | |
| finalfinal final |
50 |
