Two different statisticians are evaluating the data given in...

Name: Problem 2, Chapter 14: Statistical Methods
Uploaded: 2022-10-07T22:03:40-08:00
Duration: 47 s
Channel: James Kiss
Description: Two different statisticians are evaluating the data given in Table 14.5. The first statistician uses a Kruskal-Wallis test applied to the values given in the table. The second statistician uses a Kruskal-Wallis test applied to the logarithm of the values. Both statisticians get exactly the same results. Why?

Two different statisticians are evaluating the data given in Table 14.5. The first statistician uses a Kruskal-Wallis test applied to the values given in the table. The second statistician uses a Kruskal-Wallis test applied to the logarithm of the values. Both statisticians get exactly the same results. Why?

Labs

Want to see this concept in action?

NEW

Explore this concept interactively to see how it behaves as you change inputs.

View Labs

Key Concepts

Rank Invariance in Nonparametric Tests

Rank invariance is a key property of nonparametric tests like the Kruskal-Wallis test. Since these tests rely on the order or ranks of the data rather than the actual values, applying any monotonic transformation (such as taking the logarithm) does not affect the outcome of the test. This invariance explains why both statisticians obtained the same results despite analyzing the data in different forms.

Kruskal-Wallis Test

The Kruskal-Wallis test is a nonparametric method used to determine whether there are statistically significant differences between the medians of three or more independent groups. Unlike parametric tests, it does not assume a normal distribution of the data and is based on ranking the data values rather than using the raw data. This makes it particularly useful when data do not meet the assumptions required for traditional analysis of variance (ANOVA).

Monotonic Transformation

A monotonic transformation is a mathematical function that preserves the order of the data points when applied. In other words, if one value is larger than another before the transformation, it will remain so after the transformation. The logarithmic transformation is one such example, and it does not alter the relative ranking of the data.

Please give Ace some feedback