How to avoid the warning “Cannot compute exact p-value with ties” while perform correlation test for Spearman’s correlation in R?

When the variables are not continuous but could be ranked then we do not use pearson correlation coefficient to find the linear relationship, in this case spearman correlation coefficient comes into the scene. Since the spearman correlation coefficient considers the rank of values, the correlation test ignores the same ranks to find the p-values as a result we get the warning “Cannot compute exact p-value with ties”. This can be avoided by using exact = FALSE inside the cor.test function.

Example

Consider the below vectors and perform spearman correlation test to check the relationship between them −

 Live Demo

x1<-rpois(20,2)
y1<-rpois(20,5)
cor.test(x1,y1,method="spearman")

Output

   Spearman's rank correlation rho
data: x1 and y1
S = 1401.7, p-value = 0.8214
alternative hypothesis: true rho is not equal to 0
sample estimates:
   rho
-0.05390585
Warning message:
In cor.test.default(x1, y1, method = "spearman") :
Cannot compute exact p-value with ties

Here, we have the warning for ties, this can be avoided by using exact=FALSE as shown below −

Example

cor.test(x1,y1,method="spearman",exact=FALSE)

Output

   Spearman's rank correlation rho
data: x1 and y1
S = 1401.7, p-value = 0.8214
alternative hypothesis: true rho is not equal to 0
sample estimates:
   rho
-0.05390585

Let’s have a look at some more examples −

Example

 Live Demo

x2<-sample(1:100,500,replace=TRUE)
y2<-sample(1:50,500,replace=TRUE)
cor.test(x2,y2,method="spearman")

Output

   Spearman's rank correlation rho
data: x2 and y2
S = 20110148, p-value = 0.4387
alternative hypothesis: true rho is not equal to 0
sample estimates:
   rho
0.03470902
Warning message:
In cor.test.default(x2, y2, method = "spearman") :
Cannot compute exact p-value with ties

Example

cor.test(x2,y2,method="spearman",exact=FALSE)

Output

   Spearman's rank correlation rho
data: x2 and y2
S = 20110148, p-value = 0.4387
alternative hypothesis: true rho is not equal to 0
sample estimates:
   rho
0.03470902

Example

 Live Demo

x3<-sample(101:110,5000,replace=TRUE)
y3<-sample(501:510,5000,replace=TRUE)
cor.test(x3,y3,method="spearman")

Output

   Spearman's rank correlation rho
data: x3 and y3
S = 2.0642e+10, p-value = 0.5155
alternative hypothesis: true rho is not equal to 0
sample estimates:
   rho
0.009199129
Warning message:
In cor.test.default(x3, y3, method = "spearman") :
Cannot compute exact p-value with ties

Example

cor.test(x3,y3,method="spearman",exact=FALSE)

Output

   Spearman's rank correlation rho
data: x3 and y3
S = 2.0642e+10, p-value = 0.5155
alternative hypothesis: true rho is not equal to 0
sample estimates:
   rho
0.009199129

Nizamuddin Siddiqui

Updated on 08-Sep-2020 14:45:45

• Related Questions & Answers
• How to extract correlation coefficient value from correlation test in R?
• How to find p-value for correlation coefficient in R?
• How to find the correlation matrix with p-values for an R data frame?
• How to change the size of correlation coefficient value in correlation matrix plot using corrplot in R?
• How to round correlation values in the correlation matrix to zero decimal places in R?
• How to create correlation matrix plot in R?
• How to find the groupwise correlation matrix for an R data frame?
• How to extract the p-value from t test in R?
• How to find the group-wise correlation coefficient in R?
• How to convert a correlation matrix into a logical matrix based on correlation coefficient in R?
• How to find the correlation matrix for rows of an R data frame?
• Find the combination of columns for correlation coefficient greater than a certain value in R
• How to deal with missing values to calculate correlation matrix in R?
• How to find the correlation matrix of groups for a data.table object in R?
• How to find the significant correlation in an R data frame?