This function performs a robust an initial Guided Analysis for parameter testing and
controlband extraction (iGATE) for a categorical target variable by repeatedly running
categorical.igate and only returning those parameters that are selected more often than a
certain threshold.
robust.categorical.igate(df, versus = 8, target, best.cat, worst.cat,
test = "w", ssv = NULL, outlier_removal_ssv = TRUE,
iterations = 50, threshold = 0.5)Data frame to be analysed.
How many Best of the Best and Worst of the Worst do we collect? By default, we will collect 8 of each.
Target variable to be analysed. Must be categorical.
Use igate for continuous target.
The best category. The versus BOB will be selected randomly from this
category.
The worst category. The versus WOW will be selected randomly from this
category.
Statistical hypothesis test to be used to determine influential
process parameters. Choose between Wilcoxon Rank test ("w", default)
and Student's t-test ("t").
A vector of suspected sources of variation. These are the variables
in df which we believe might have an influence on the target variable and
will be tested. If no list of ssv is provided, the test will be performed
on all numeric variables.
Logical. Should outlier removal be performed for each ssv (default: TRUE)?
Integer. How often should categorical.igate be performed? A message about how many iterations
have been perfermed so far will be printed to the console every 0.1*iterations iterations.
Between 0 and 1. Only parameters that are selected at least floor(iterations*threshold)
times are returned.
A data frame with the summary statistics for those parameters that were selected
at least floor(iterations*threshold) times:
Causes |
Those ssv that have been found to be influential to the target variable. |
median_count |
The median value returned by the counting method for this parameter. |
median_p_value |
The median p-value of the hypothesis test performed, i.e. either of the
Wilcoxon rank test (in case test = "w") or the t-test (if test = "t"). |
median_good_lower_bound |
The median lower bound for this Cause for good quality. |
median_good_upper_bound |
The median upper bound for this Cause for good quality. |
median_bad_lower_bound |
The median lower bound for this Cause for bad quality. |
We collect the Best of the Best and the Worst of the Worst
dynamically dependent on the current ssv. That means, for each ssv we first
remove all the observations with missing values for that ssv from df.
Then, based on the remaining observations, we randomly select versus
observations from the the best category (<U+201C>Best of the Best<U+201D>, short BOB) and
versus observations from the worst category
(<U+201C>Worst of the Worst<U+201D>, short WOW). By default, we select 8 of each. Since this selection
happens randomly, it is recommended to use robust.categorical.igate over categorical.igate.
After the selection we compare BOB and WOW using the the counting method and the specified
hypothesis test. If the distributions of the ssv in BOB and WOW are
significantly different, the current ssv has been identified as influential
to the target variable. An ssv is considered influential, if the test returns
a count larger/ equal to 6 and/ or a p-value of less than 0.05.
For the next ssv we again start with the entire dataset df, remove all
the observations with missing values for that new ssv and then select our
new BOB and WOW. In particular, for each ssv we might select different observations.
This dynamic selection is necessary, because in case of an incomplete data set,
if we select the same BOB and WOW for all the ssv, we might end up with many
missing values for particular ssv. In that case the hypothesis test loses
statistical power, because it is used on a smaller sample or worse, might
fail altogether if the sample size gets too small.
For those ssv determined to be significant, control bands are extracted. The rationale is:
If the value for an ssv is in the interval [good_lower_bound,good_upper_bound]
the target is likely to be good. If it is in the interval
[bad_lower_bound,bad_upper_bound], the target is likely to be bad.
# NOT RUN {
robust.categorical.igate(mtcars, target = "cyl",
best.cat = "8", worst.cat = "4", iterations = 50, threshold = 0.5)
# }
Run the code above in your browser using DataLab