The Kruskal-Wallis H test is a non-parametric test, which means that it does not make any assumptions about the distribution of the data. This is in contrast to the one-way ANOVA, which is a parametric test that assumes that the data is normally distributed.
The Kruskal-Wallis H test works by ranking the data from lowest to highest, and then calculating the sum of the ranks for each group. The test statistic is then calculated based on these sums of ranks.
The reason why the statement says that the variable is ordinal but is treated as continuous in the test is because the ranks of the data are treated as continuous values. This is because the test statistic is calculated based on the differences between the sums of ranks for each group.
The bar chart that is displayed in the SPSS output is simply a way of visualizing the distribution of the data. The fact that the bar chart is used does not mean that the data is treated as continuous.
Hope this helps !
------------------------------
Youssef Sbai Idrissi
Software Engineer
------------------------------
Original Message:
Sent: Wed December 28, 2022 05:43 PM
From: Clifton Hamilton
Subject: Ordinal Data as Continuous Data
Hi Rick,
When conducting a Kruskal-Wallis H test in SPSS, one component of the output is a bar chart (attached) depicting categorical field information (a count of each value of the variable in the data set). Below the chart is a statement that the variable is ordinal but is treated as continuous in the test.
I am not sure what aspect of the test treats the data as continuous, as the Kruskal-Wallis H test uses the rank sum of each group for calculations (along with n and m), and a bar chart can properly depict discrete data.
Can you explain the statement? Thanks in advance.
Cliff
#SPSSStatistics