QC_Violations {ggQC}

Calculate QC Violations

Description

function that calculates QC violations on sequentially ordered data based on the following 4 rules:

• Violation Same Side: 8 or more consecutive, same-side points

• Violation 1 Sigma: 4 or more consecutive, same-side points exceeding 1 sigma

• Violation 2 Sigma: 2 or more consecutive, same-side points exceeding 2 sigma

• Violation 3 Sigma: any points exceeding 3 sigma

Usage

QC_Violations(data, value = NULL, grouping = NULL, formula = NULL,
  method = NULL, ...)

Arguments

data

vector or dataframe, as indicated below for each chart type

• Individuals: vector of values;

• Studentized Charts: dataframe

value

Studentized Charts: numeric vector in dataframe with values of interest

grouping

Studentized Charts: single factor/variable to split the dataframe "values" by

formula

Studentized Charts: a formula, such as y ~ x1 + x2, where the y variable is numeric data to be split into groups according to the grouping x factors/variables

method

string, calling the following methods:

• Individuals Charts: XmR,

• Studentized Charts: xBar.rBar, xBar.rMedian, xBar.sBar, xMedian.rBar, xMedian.rMedian

...

further arguments passed to or from other methods.

Value

a dataframe, with the following columns

• data: The input data if XmR, mean or median by group for Studentized methods

• z_score: z-score for the data point

• Index: number, indicating the order of the input data

• Violation_Result: description of the type of test being run.

  • Violation Same Side: 8 or more consecutive, same-side points

  • Violation 1 Sigma: 4 or more consecutive, same-side points exceeding 1 sigma

  • Violation 2 Sigma: 2 or more consecutive, same-side points exceeding 2 sigma

  • Violation 3 Sigma: any points exceeding 3 sigma

• Index: boolean, does the data point violate the rule?

Note

If using the formula argument do not use value and group arguments.

References

Wheeler, DJ, and DS Chambers. Understanding Statistical Process Control, 2nd Ed. Knoxville, TN: SPC, 1992. Print.

Examples

#####################################
#  Example 1: XmR Check Violations  #
#####################################
# Load Libraries ----------------------------------------------------------
 require(ggQC)

# Setup Data --------------------------------------------------------------

    set.seed(5555)
    QC_XmR <- data.frame(
    data = c(c(-1, 2.3, 2.4, 2.5),                        #Outlier Data
          sample(c(rnorm(60),5,-5), 62, replace = FALSE), #Normal Data
          c(1,-.3, -2.4,-2.6,-2.5,-2.7, .3)),             #Outlier Data
    Run_Order = 1:73                                      #Run Order
    )

   QC_Vs <- QC_Violations(data  = QC_XmR$data, method = "XmR")

#######################################
#  Example 2: Xbar Check Violations   #
#######################################

# Setup Some Data ------------------------------------------------------------
     QC_xBar.rBar <- do.call(rbind, lapply(1:3, function(X){
       set.seed(5555+X)                                   #Loop over 3 seeds
       data.frame(
         sub_group = rep(1:42),                           #Define Subgroups
         sub_class = letters[X],
         c(
          c(runif(n = 5, min = 2.0,3.2)),                 #Outlier Data
          sample(c(rnorm(30),5,-4), 32, replace = FALSE), #Normal Data
          c(runif(n = 5, min = -3.2, max = -2.0))         #Outlier Data
         )
      )
     }
   )
)

colnames(QC_xBar.rBar) <- c("sub_group","sub_class", "value")
QC_Vs <- QC_Violations(data  = QC_xBar.rBar,
                       formula = value~sub_group,
                       method = "xBar.rBar")