spark.kstest {SparkR}R Documentation

(One-Sample) Kolmogorov-Smirnov Test


spark.kstest Conduct the two-sided Kolmogorov-Smirnov (KS) test for data sampled from a continuous distribution.

By comparing the largest difference between the empirical cumulative distribution of the sample data and the theoretical distribution we can provide a test for the the null hypothesis that the sample data comes from that theoretical distribution.

Users can call summary to obtain a summary of the test, and print.summary.KSTest to print out a summary result.


spark.kstest(data, ...)

## S4 method for signature 'SparkDataFrame'
  testCol = "test",
  nullHypothesis = c("norm"),
  distParams = c(0, 1)

## S4 method for signature 'KSTest'

## S3 method for class 'summary.KSTest'
print(x, ...)



a SparkDataFrame of user data.


additional argument(s) passed to the method.


column name where the test data is from. It should be a column of double type.


name of the theoretical distribution tested against. Currently only "norm" for normal distribution is supported.


parameters(s) of the distribution. For nullHypothesis = "norm", we can provide as a vector the mean and standard deviation of the distribution. If none is provided, then standard normal will be used. If only one is provided, then the standard deviation will be set to be one.


test result object of KSTest by spark.kstest.


summary object of KSTest returned by summary.


spark.kstest returns a test result object.

summary returns summary information of KSTest object, which is a list. The list includes the p.value (p-value), statistic (test statistic computed for the test), nullHypothesis (the null hypothesis with its parameters tested against) and degreesOfFreedom (degrees of freedom of the test).


spark.kstest since 2.1.0

summary(KSTest) since 2.1.0

print.summary.KSTest since 2.1.0

See Also

MLlib: Hypothesis Testing


## Not run: 
##D data <- data.frame(test = c(0.1, 0.15, 0.2, 0.3, 0.25))
##D df <- createDataFrame(data)
##D test <- spark.kstest(df, "test", "norm", c(0, 1))
##D # get a summary of the test result
##D testSummary <- summary(test)
##D testSummary
##D # print out the summary in an organized way
##D print.summary.KSTest(testSummary)
## End(Not run)

[Package SparkR version 2.4.7 Index]