I will give a sample below of how my data is organized but every time I run Friedman's using frieman.test(y =, groups = , blocks= ) it gives me an error that my data is not from an unreplicated complete block design despite the fact that it is.
| score | treatment | day |
|---|---|---|
| 10 | 1 | 1 |
| 20 | 1 | 1 |
| 40 | 1 | 1 |
| 7 | 2 | 1 |
| 100 | 2 | 1 |
| 58 | 2 | 1 |
| 98 | 3 | 1 |
| 89 | 3 | 1 |
| 40 | 3 | 1 |
| 70 | 4 | 1 |
| 10 | 4 | 1 |
| 28 | 4 | 1 |
| 86 | 5 | 1 |
| 200 | 5 | 1 |
| 40 | 5 | 1 |
| 77 | 1 | 2 |
| 100 | 1 | 2 |
| 90 | 1 | 2 |
| 33 | 2 | 2 |
| 15 | 2 | 2 |
| 25 | 2 | 2 |
| 23 | 3 | 2 |
| 54 | 3 | 2 |
| 67 | 3 | 2 |
| 1 | 4 | 2 |
| 2 | 4 | 2 |
| 400 | 4 | 2 |
| 16 | 5 | 2 |
| 10 | 5 | 2 |
| 90 | 5 | 2 |
library(readr)
sample_data$treatment <- as.factor(sample_data$treatment) #setting treatment as categorical independent variable
sample_data$day <- as.factor(sample_data$day) #setting day as categorical independent variable
summary(sample_data)
friedman3 <- friedman.test(y = sample_data$score, groups = sample_data$treatment, blocks = sample_data$day)
summary(friedman3)
the code above gives me the error I described earlier.
However when I convert the csv data to a matrix, Friedman's works but the answer seems wrong as SPSS gives a different result for the degrees of freedom.
sample_data$treatment <- as.factor(sample_data$treatment) #converting to categorical independent variable
sample_data$day <- as.factor(sample_data$day) #converting to categorical independent variable
data = as.matrix(sample_data)
friedman.test(data)
friedman2 <- friedman.test(y = data$score, groups = data$treatment, blocks = data$day)
summary(friedman2)
Any idea what I am doing incorrectly?
I am aware that Friedman's gives me chi-square but I am also wondering how can I get the test statistic instead of the chi-square value.
I am using Rstudio and I am new to R. And I want to know how to specify groups as treatment and day as blocks.
CodePudding user response：
We could summarise the data by taking the mean of the 'score' and then use that summarised data in friedman.test
sample_data1 <- aggregate(score ~ ., sample_data, FUN = mean)
friedman.test(sample_data1$score, groups = sample_data1$treatment,
blocks = sample_data1$day)