The class estimate.pin is a blueprint of S4 objects
that store the results of the different PIN functions: pin(), pin_yz(),
pin_gwj(), and pin_ea().
# S4 method for estimate.pin
show(object)an object of class estimate.pin
success(logical) takes the value TRUE when the estimation has
succeeded, FALSE otherwise.
errorMessage(character) contains an error message if the PIN
estimation has failed, and is empty otherwise.
convergent.sets(numeric) returns the number of initial parameter
sets at which the likelihood maximization converged.
algorithm(character) returns the algorithm used to determine the set
of initial parameter sets for the maximum likelihood estimation.
It takes one of the following values:
"YZ": Yan and Zhang (2012)
"GWJ": Gan, Wei and Johnstone (2015)
"YZ*": Yan and Zhang (2012) as modified by Ersan and Alici (2016)
"EA": Ersan and Alici (2016)
"CUSTOM": Custom initial parameter sets
factorization(character) returns the factorization of the PIN
likelihood function as used in the maximum likelihood estimation.
It takes one of the following values:
"NONE": No factorization
"EHO": Easley, Hvidkjaer and O'Hara (2010)
"LK": Lin and Ke (2011)
"E": Ersan (2016)
parameters(list) returns the list of the maximum likelihood
estimates (\(\alpha\), \(\delta\), \(\mu\), \(\epsilon\)b, \(\epsilon\)s)
likelihood(numeric) returns the value of (the factorization of)
the likelihood function evaluated at the optimal set of parameters.
pin(numeric) returns the value of the probability of informed
trading.
pin.goodbad(list) returns a list containing a decomposition
of PIN into good-news, and bad-news PIN components. The decomposition has
been suggested in Brennan2016;textualPINstimation. The list
has two elements: pinG, and pinB are the good-news, and bad-news
components of PIN, respectively.
dataset(dataframe) returns the dataset of buys and sells used
in the maximum likelihood estimation of the PIN model.
initialsets(dataframe) returns the initial parameter sets used
in the maximum likelihood estimation of the PIN model.
details(dataframe) returns a dataframe containing the estimated
parameters by the MLE method for each initial parameter set.
runningtime(numeric) returns the running time of the estimation
of the PIN model in seconds.