Package-level declarations
Types
Serves as an abstract base class for statistical collection.
In progress...
This class automates the batching of observations that may be dependent. It computes the batch means of the batches and reports statistics across the batches. Suppose we have observations, Y(1), Y(2), Y(3), ... Y(n). This class specifies the minimum number of batches, the minimum number of observations per batch, and a maximum batch multiple. The defaults are 20, 16, and 2, respectively. This implies that the maximum number of batches will be 40 = (min number of batches times the maximum batch multiple). The class computes the average of each batch, which are called the batch means.
A class to do statistical bootstrapping. The calculations occur via the method generateSamples(). Until generateSamples() is called the results are meaningless.
This class facilitates bootstrap sampling. The originalData is sampled from, with replacement, repeatedly to form bootstrap samples from which bootstrap statistics are computed. The estimator provides the mechanism for estimating statistical quantities from the original data. From the data, it can produce 1 or more estimated quantities. Bootstrap estimates are computed on the observed estimates from each bootstrap sample. The specified stream controls the bootstrap sampling process.
Prepares the statistical quantities typically found on a box plot. This implementation uses a full sort of the data. The original data is not changed. Users may want to look for more efficient methods for use with very large data sets.
Creates a dynamically configured histogram based on an observed cache. If the amount of data observed is less than cache size and greater than or equal to 2, the returned histogram will be configured on whatever data was available in the cache. Thus, bin settings may change as more data is collected until the cache is full. Once the cache is full the returned histogram is permanently configured based on all data in the cache. The default cache size cacheSize is 512 observations.
Given some data, produce multiple estimated statistics from the data and stores the estimated quantities in the returned array. It is up to the user to interpret the array values appropriately.
This class facilitates bootstrap sampling. The estimator provides the mechanism for estimating statistical quantities from the original data. From the data, it can produce 1 or more estimated quantities. Bootstrap estimates are computed on the observed estimates from each bootstrap sample. The specified stream controls the bootstrap sampling process.
This interface represents a general set of methods for data collection. The collect() method takes in the supplied data and collects it in some manner as specified by the collector.
The default time value is 1.0
Computes the confusion matrix
There are two classes class 1 (positive) and class 0 (negative) An instance (exemplar) must be in one of the classes.
A functional interface that produces some estimate of some quantity of interest.
Tabulates the proportion and frequency for a random variable X > a(i) where a(i) are thresholds.
A data table class suitable for insertion into a database
Each statistic value separated by a comma with a corresponding header
Continually gets the value of the supplied GetValueIfc in the run() until the supplied sampling half-width requirement is met or the default maximum number of iterations is reached, whichever comes first.
A Histogram tabulates data into bins. The user must specify the break points of the bins, b0, b1, b2, ..., bk, where there are k+1 break points, and k bins. b0 may be Double.NEGATIVE_INFINITY and bk may be Double.POSITIVE_INFINITY.
Histogram Bin data suitable for a database table
This class tabulates the frequency associated with the integers presented to it via the collect() method Every value presented is interpreted as an integer For every value presented a count is maintained. There could be space/time performance issues if the number of different values presented is large. Use lowerLimit and upperLimit to limit the values that can be observed. Values lower than the lower limit are counted as underflow and values greater than the upper limit are counted as overflow.
A minimal interface to define an estimator that will produce an estimate of a population mean. We assume that the estimator has statistics available that represent the count, average, and variance of a sample. By default, the sample average is used as the estimate of the population mean; however, implementors may override this behavior by overriding the estimate() method.
A collection of Bootstrap instances to permit multidimensional bootstrapping. Construction depends on a named mapping of double[] arrays that represent the original samples. A static create method also allows creation based on a mapping to implementations of the SampleIfc.
Holds data to perform multiple comparisons Performs pairwise comparisons and computes pairwise differences and variances.
Given some data, produce multiple estimated statistics from the data and store the estimated quantities in the returned array. It is up to the user to interpret the array values appropriately.
Collects statistics for each dimension of the presented array.
Performs Ordinary Least Squares fit of the data with the response. The default is to assume that an intercept term will be estimated.
The response is an n by 1 array of the data, where n is the number of observations for a response variable. The data is an n by k matrix of the data for the regression, where k is the number of regression coefficients and n is the number of observations. This data should not include a column of 1's for estimating an intercept term. The rows of the array represent the predictor values associated with each observation. The array must be rectangular. That is, each row has the same number of columns.
A useful resource for regression can be found at (https://online.stat.psu.edu/stat501/lesson/5/5.3)
Create a state with given name and indicate usage of a Statistic object to collect additional statistics
The Statistic class allows the collection of summary statistics on data via the collect() methods. The primary statistical summary is for the statistical moments. Creates a Statistic with the given name
A statistical run is a sequence of objects that are determined equal based on a comparator. A single item is a run of length 1. A set of items that are all the same are considered a single run. The set (0, 1, 1, 1, 0) has 3 runs.
The StatisticIfc interface presents a read-only view of a Statistic
This class tabulates the frequency associated with the strings presented to it via the collect() method. For every unique string presented a count is maintained. There could be space/time performance issues if the number of different strings presented is large. Use the limit set to limit the values that can be observed. If the presented strings are not in the limiting set, then they are counted as "Other".
A data table class suitable for insertion into a database
A helper class that turns an array of time values to a supplier of times
Collects time weighted statistics that are presented to the collect() method. The property, timeGetter, must provide values for each observed value that appears in the collect method.
Makes an array look like a RandU01Ifc
Collects a basic weighted statistical summary. If the observation or the weight is infinite or NaN, then the observation is not recorded and the number of missing observations is incremented. If the observed weight is negative or 0.0, then the observation is not recorded and the number of missing observations is incremented.
If the observation or the weight is
Functions
Converts the MCB interval data to a data frame
Converts the MCB result data to a data frame
Converts the MCB interval data to a data frame
Converts the statistic data to a data frame