|
CronoSeries
0.1.*
A fork of Cronos with a focus on being a Time Series class library.
|
| CCronoSeries.TimeSeries.Data.DirectedGraph | DirectedGraph is a collection of nodes and directed labeled (by socket) links. Each node contains a (1) an IConnectable item Each node has incoming and outgoing links. The Graph can be viewed with a DirectedGraphViewer |
| CCronoSeries.TimeSeries.Miscellaneous.DiscreteFourierTransform | |
| CCronoSeries.TimeSeries.Models.DistributionApproximation | This class keeps track of a univariate distribution by storing its quantiles in a matrix |
| CCronoSeries.TimeSeries.Models.DistributionSummary | |
| CCronoSeries.TimeSeries.Models.DurbinLevinsonPredictor | this class is used to carry out Durbin-Levinson recursions for linear time series prediction. it can use either a supplied vector containing the autocovariance, or a delegate that can compute it |
| CCronoSeries.TimeSeries.Miscellaneous.HaltonSequence | This class generates a multi-dimensional low-discrepancy sequence. See discussion at http://en.wikipedia.org/wiki/Constructions_of_low-discrepancy_sequences |
| ▼CIComparable | |
| CCronoSeries.TimeSeries.Miscellaneous.Optimizer.Evaluation | |
| ▼CCronoSeries.TimeSeries.Data.IConnectable | Connectable units have inputs and outputs. When all inputs are assigned, outputs are automatically recomputed. They also have methods that control how they are displayed. This interface is required in order to display something in a DirectedGraph |
| CCronoSeries.TimeSeries.Data.DataSource | This class provides a mechanism for connection to external sources of data. The simplest example is a connection to a .csv file, but more interesting examples could include connections by network to a broker's historical data feed, a connection to a local database of time series, etc |
| CCronoSeries.TimeSeries.Data.Longitudinal | This class represents longitudinal data, that is, a collection of time series |
| CCronoSeries.TimeSeries.Data.MVTimeSeries | |
| CCronoSeries.TimeSeries.Data.TimeSeries | |
| ▼CCronoSeries.TimeSeries.Models.Model | |
| ▼CCronoSeries.TimeSeries.Models.TimeSeriesModel | |
| ▼CCronoSeries.TimeSeries.Models.MVTimeSeriesModel | |
| CCronoSeries.TimeSeries.Models.VARModel | vector autoregressive model, fittable by method of moments only (Yule-Walker eqns) |
| ▼CCronoSeries.TimeSeries.Models.UnivariateTimeSeriesModel | This class represents a model for a univariate time series or for longitudinal data (a list of separate univariate time series) |
| CCronoSeries.TimeSeries.Models.ACFModel | This is really like an ARMA model in many respects, but you specify the square root of the variance (sigma), and the autocorrelations at lags 1...maxLag, instead of specifying autoregressive and moving average polynomials. This means that we have to fall back on the Durbin-Levinson recursions for likelihood computations, instead of using more efficient recursions from Brockwell & Davis |
| ▼CCronoSeries.TimeSeries.Models.ARMAModel | |
| CCronoSeries.TimeSeries.Models.ARMAXModel | This is just an ARMA model with exogenous inputs. The model is Phi(B) X_t = Theta(B) Z_t + Gamma U_{t-1} where Phi and Theta are standard autoregressive and moving average polynomials {U_t} is an exogenous time series. Much of the analysis is the same, we just have extra coefficients for the exogenous inputs, and to compute likelihoods, we have to adjust the observations appropriately. For now, we only allow a simple one-lag dependency on the exogenous series. Later I'll generalize this |
| CCronoSeries.TimeSeries.Models.GARCHModel | |
| ▼CCronoSeries.TimeSeries.Transforms.TimeSeriesTransformation | A TimeSeriesTransformation takes one or more univariate or multivariate inputs and creates a single univariate or multivariate output |
| CCronoSeries.TimeSeries.Transforms.AggregateTransform | |
| CCronoSeries.TimeSeries.Transforms.BindingTransformation | This transformation takes 2 or more univariate or multivariate time series and binds them together into a new multivariate time series |
| CCronoSeries.TimeSeries.Transforms.BollingerBandTransform | |
| CCronoSeries.TimeSeries.Transforms.CustomTransform | |
| CCronoSeries.TimeSeries.Transforms.DifferenceTransformation | This differencing transformation can operate on univariate, multivariate or longitudinal data |
| CCronoSeries.TimeSeries.Transforms.ExpSmoother | |
| ▼CCronoSeries.TimeSeries.Transforms.FilterTransform | |
| CCronoSeries.TimeSeries.Transforms.LagTransform | |
| CCronoSeries.TimeSeries.Transforms.ForecastTransform | |
| CCronoSeries.TimeSeries.Transforms.HubTransform | |
| CCronoSeries.TimeSeries.Transforms.IntegrateTransformation | |
| CCronoSeries.TimeSeries.Transforms.LinearCombinationTransform | |
| CCronoSeries.TimeSeries.Transforms.LogReturnTransformation | |
| CCronoSeries.TimeSeries.Transforms.LogTransform | |
| CCronoSeries.TimeSeries.Transforms.LongitudinalSampler | |
| CCronoSeries.TimeSeries.Transforms.MergeTransform | |
| CCronoSeries.TimeSeries.Transforms.MidpointTransformation | |
| CCronoSeries.TimeSeries.Transforms.OHLCAggregator | |
| CCronoSeries.TimeSeries.Transforms.OHLCBarBuilder | This transform takes a univariate price series as input, and converts it to open-high-low-close values over the specified intervals |
| CCronoSeries.TimeSeries.Transforms.PointRemoverTransform | |
| CCronoSeries.TimeSeries.Transforms.ReferenceSamplingTransform | this class allows you to sample one time series at the time points contained in another time series output can be either the sampled series or a multivariate binding of the sampled and other time series |
| CCronoSeries.TimeSeries.Transforms.RotarySwitchTransform | |
| CCronoSeries.TimeSeries.Transforms.SamplingTransformation | This class samples either a univariate or multivariate time series |
| CCronoSeries.TimeSeries.Transforms.SaturationTransform | |
| CCronoSeries.TimeSeries.Transforms.SplittingTransformation | |
| ▼CCronoSeries.TimeSeries.Data.ICopyable | |
| CCronoSeries.TimeSeries.Data.MVTimeSeries | |
| CCronoSeries.TimeSeries.Data.TimeSeries | |
| ▼CCronoSeries.TimeSeries.IExtraFunctionality | |
| CCronoSeries.TimeSeries.Transforms.ForecastTransform | |
| CCronoSeries.TimeSeries.Transforms.LongitudinalSampler | |
| CCronoSeries.TimeSeries.Transforms.RotarySwitchTransform | |
| CCronoSeries.TimeSeries.Transforms.SamplingTransformation | This class samples either a univariate or multivariate time series |
| ▼CCronoSeries.TimeSeries.Models.IMLEEstimable | |
| CCronoSeries.TimeSeries.Models.ACFModel | This is really like an ARMA model in many respects, but you specify the square root of the variance (sigma), and the autocorrelations at lags 1...maxLag, instead of specifying autoregressive and moving average polynomials. This means that we have to fall back on the Durbin-Levinson recursions for likelihood computations, instead of using more efficient recursions from Brockwell & Davis |
| CCronoSeries.TimeSeries.Models.ARMAModel | |
| CCronoSeries.TimeSeries.Models.GARCHModel | |
| ▼CCronoSeries.TimeSeries.Models.IMoMEstimable | |
| CCronoSeries.TimeSeries.Models.VARModel | vector autoregressive model, fittable by method of moments only (Yule-Walker eqns) |
| ▼CCronoSeries.TimeSeries.Models.IRealTimePredictable | |
| CCronoSeries.TimeSeries.Models.ACFModel | This is really like an ARMA model in many respects, but you specify the square root of the variance (sigma), and the autocorrelations at lags 1...maxLag, instead of specifying autoregressive and moving average polynomials. This means that we have to fall back on the Durbin-Levinson recursions for likelihood computations, instead of using more efficient recursions from Brockwell & Davis |
| CCronoSeries.TimeSeries.Models.ARMAModel | |
| CCronoSeries.TimeSeries.Data.IUpdateable | |
| CCronoSeries.TimeSeries.Data.DirectedGraph.Link | |
| CCronoSeries.TimeSeries.Miscellaneous.LogLikelihoodPenalizer | This class evaluates log-likelihood for a time series by summing up individual specified log-likelihoods. This is a rather trivial summation operation. What is useful here, however, is the consistency penalty. The idea is to look for a kind of draw-down in the partial sums of log-likelihoods and compute a penalty factor which is bad if the model is inconsistent with the data for a long sub-interval within the time range |
| CCronoSeries.TimeSeries.Models.MVDistributionSummary | |
| CCronoSeries.TimeSeries.MathNetExtensions.MVNormalDistribution | |
| CCronoSeries.TimeSeries.Data.DirectedGraph.NodeInfo | |
| ▼CCronoSeries.TimeSeries.Miscellaneous.Optimizer | |
| CCronoSeries.TimeSeries.Miscellaneous.NelderMead | |
| CCronoSeries.TimeSeries.MathNetExtensions.PrincipalComponents | |
| CCronoSeries.TimeSeries.Miscellaneous.PrincipalComponents | |
| CCronoSeries.TimeSeries.Miscellaneous.Regression | |
| CCronoSeries.TimeSeries.Models.StandardOutputs | |
| CCronoSeries.TimeSeries.Miscellaneous.StepFunction | This class keeps track of a step function mapping R -> R. It is assumed that the function only changes (has steps) in a region with compact support |
| CTests.Tests | |
| CCronoSeries.TimeSeries.Data.TimeSeriesBase< T > | |
| ▼CCronoSeries.TimeSeries.Data.TimeSeriesBase< double > | |
| CCronoSeries.TimeSeries.Data.TimeSeries | |
| ▼CCronoSeries.TimeSeries.Data.TimeSeriesBase< double[]> | |
| CCronoSeries.TimeSeries.Data.MVTimeSeries | |
| CCronoSeries.TimeSeries.Miscellaneous.VanderCorputSequence | This class generates a one-dimensional low-discrepancy sequence. See discussion at http://en.wikipedia.org/wiki/Constructions_of_low-discrepancy_sequences |
1.8.20