The least-squares Monte Carlo (LSM) simulation method is a popular method for the approximation of the value of early and multiple exercise options. LSMRealOptions provides implementations of the LSM simulation method to value American option products and capital investment projects through real options analysis. LSMRealOptions values capital investment projects with cash flows dependent upon underlying state variables that are stochastically evolving, providing analysis into the timing and critical values at which investment is optimal. LSMRealOptions provides flexibility in the stochastic processes followed by underlying assets, the number of state variables, basis functions and underlying asset characteristics to allow a broad range of assets to be valued through the LSM simulation method. Real options projects are further able to be valued whilst considering construction periods, time-varying initial capital expenditures and path-dependent operational flexibility including the ability to temporarily shutdown or permanently abandon projects after initial investment has occurred. The LSM simulation method was first presented in the prolific work of Longstaff and Schwartz (2001) <doi:10.1093/rfs/14.1.113>.

Estimation of a multi-group count regression models (i.e., Poisson, negative binomial) with latent covariates. This packages provides two extensions compared to ordinary count regression models based on a generalized linear model: First, measurement models for the predictors can be specified allowing to account for measurement error. Second, the count regression can be simultaneously estimated in multiple groups with stochastic group weights. The marginal maximum likelihood estimation is described in Kiefer & Mayer (2020) <doi:10.1080/00273171.2020.1751027>.

This package provides a stochastic, spatially-explicit, demo-genetic model simulating the spread and evolution of a plant pathogen in a heterogeneous landscape to assess resistance deployment strategies. It is based on a spatial geometry for describing the landscape and allocation of different cultivars, a dispersal kernel for the dissemination of the pathogen, and a SEIR ('Susceptible-Exposed-Infectious-Removedâ ) structure with a discrete time step. It provides a useful tool to assess the performance of a wide range of deployment options with respect to their epidemiological, evolutionary and economic outcomes. Loup Rimbaud, Julien Papaïx, Jean-François Rey, Luke G Barrett, Peter H Thrall (2018) <doi:10.1371/journal.pcbi.1006067>.

This package performs the trimmed k-means clustering algorithm with lower memory use. It also provides a number of utility functions such as BIC calculations.

Useful shiny production-ready modules and helpers such as login window and visualization tools.

An adaption of the consensus clustering approach from ConsensusClusterPlus for longitudinal data. The longitudinal data is clustered with flexible mixture models from flexmix', while the consensus matrices are hierarchically clustered as in ConsensusClusterPlus'. By using the flexibility from flexmix and FactoMineR', one can use mixed data types for the clustering.

Analysis of dichotomous and continuous response data using latent factor by both 1PL LSIRM and 2PL LSIRM as described in Jeon et al. (2021) <doi:10.1007/s11336-021-09762-5>. It includes original 1PL LSIRM and 2PL LSIRM provided for binary response data and its extension for continuous response data. Bayesian model selection with spike-and-slab prior and method for dealing data with missing value under missing at random, missing completely at random are also supported. Various diagnostic plots are available to inspect the latent space and summary of estimated parameters.

Enables the generation of Laplace factor models across diverse Laplace distributions and facilitates the application of Sparse Online Principal Component (SOPC), Incremental Principal Component (IPC), Perturbation Principal Component (PPC), Stochastic Approximation Principal Component (SAPC), Sparse Principal Component (SPC) and other PC methods and Farm Test methods to these models. Evaluates the efficacy of these methods within the context of Laplace factor models by scrutinizing parameter estimation accuracy, mean square error, and the degree of sparsity.

This package provides a variety of latent Markov models, including hidden Markov models, hidden semi-Markov models, state-space models and continuous-time variants can be formulated and estimated within the same framework via directly maximising the likelihood function using the so-called forward algorithm. Applied researchers often need custom models that standard software does not easily support. Writing tailored R code offers flexibility but suffers from slow estimation speeds. We address these issues by providing easy-to-use functions (written in C++ for speed) for common tasks like the forward algorithm. These functions can be combined into custom models in a Lego-type approach, offering up to 10-20 times faster estimation via standard numerical optimisers. To aid in building fully custom likelihood functions, several vignettes are included that show how to simulate data from and estimate all the above model classes.

This package implements a logistic box-cox model. This model is fully described in Xing, L. et al. (2021) <doi:10.1002/cjs.11587>.

Computational routines for estimating local Gaussian parameters. Local Gaussian parameters are useful for characterizing and testing for non-linear dependence within bivariate data. See e.g. Tjostheim and Hufthammer, Local Gaussian correlation: A new measure of dependence, Journal of Econometrics, 2013, Volume 172 (1), pages 33-48 <DOI:10.1016/j.jeconom.2012.08.001>.

Computing statistical hypothesis testing for loading in principal component analysis (PCA) (Yamamoto, H. et al. (2014) <doi:10.1186/1471-2105-15-51>), orthogonal smoothed PCA (OS-PCA) (Yamamoto, H. et al. (2021) <doi:10.3390/metabo11030149>), one-sided kernel PCA (Yamamoto, H. (2023) <doi:10.51094/jxiv.262>), partial least squares (PLS) and PLS discriminant analysis (PLS-DA) (Yamamoto, H. et al. (2009) <doi:10.1016/j.chemolab.2009.05.006>), PLS with rank order of groups (PLS-ROG) (Yamamoto, H. (2017) <doi:10.1002/cem.2883>), regularized canonical correlation analysis discriminant analysis (RCCA-DA) (Yamamoto, H. et al. (2008) <doi:10.1016/j.bej.2007.12.009>), multiset PLS and PLS-ROG (Yamamoto, H. (2022) <doi:10.1101/2022.08.30.505949>).

Routines for fitting Logic Regression models. Logic Regression is described in Ruczinski, Kooperberg, and LeBlanc (2003) <DOI:10.1198/1061860032238>. Monte Carlo Logic Regression is described in and Kooperberg and Ruczinski (2005) <DOI:10.1002/gepi.20042>.

Supervised learning techniques designed for the situation when the dimensionality exceeds the sample size have a tendency to overfit as the dimensionality of the data increases. To remedy this High dimensionality; low sample size (HDLSS) situation, we attempt to learn a lower-dimensional representation of the data before learning a classifier. That is, we project the data to a situation where the dimensionality is more manageable, and then are able to better apply standard classification or clustering techniques since we will have fewer dimensions to overfit. A number of previous works have focused on how to strategically reduce dimensionality in the unsupervised case, yet in the supervised HDLSS regime, few works have attempted to devise dimensionality reduction techniques that leverage the labels associated with the data. In this package and the associated manuscript Vogelstein et al. (2017) <arXiv:1709.01233>, we provide several methods for feature extraction, some utilizing labels and some not, along with easily extensible utilities to simplify cross-validative efforts to identify the best feature extraction method. Additionally, we include a series of adaptable benchmark simulations to serve as a standard for future investigative efforts into supervised HDLSS. Finally, we produce a comprehensive comparison of the included algorithms across a range of benchmark simulations and real data applications.

Implementations of Hurst exponent estimators based on the relationship between wavelet lifting scales and wavelet energy of Knight et al (2017) <doi:10.1007/s11222-016-9698-2>.

Several service functions to be used to analyse datasets obtained from diallel experiments within the frame of linear models in R, as described in Onofri et al (2020) <DOI:10.1007/s00122-020-03716-8>.

This package contains data sets to accompany the book: Lazic SE (2016). "Experimental Design for Laboratory Biologists: Maximising Information and Improving Reproducibility". Cambridge University Press.

Modifying a load shape to match specific peak and load factor is a fundamental component for various power system planning and operation studies. This package is an efficient tool to modify a reference load shape while matching the desired peak and load factor. The package offers both linear and non-linear method, described in <https://rpubs.com/riazakhan94/load_shape_match_peak_energy>. The user can control the shape of the final load shape by regulating certain parameters. The package provides validation metrics for assessing the derived load shape in terms of preserving time series properties. It also offers powerful graphics, that allows the user to visually assess the derived load shape.

This is for code management functions, NLP tools, a Monty Hall simulator, and for implementing my own variable reduction technique called Feed Reduction. The Feed Reduction technique is not yet published, but is merely a tool for implementing a series of binary neural networks meant for reducing data into N dimensions, where N is the number of possible values of the response variable.

For fitting Bayesian joint latent class and regression models using Gibbs sampling. See the documentation for the model. The technical details of the model implemented here are described in Elliott, Michael R., Zhao, Zhangchen, Mukherjee, Bhramar, Kanaya, Alka, Needham, Belinda L., "Methods to account for uncertainty in latent class assignments when using latent classes as predictors in regression models, with application to acculturation strategy measures" (2020) In press at Epidemiology <doi:10.1097/EDE.0000000000001139>.

The leader clustering algorithm provides a means for clustering a set of data points. Unlike many other clustering algorithms it does not require the user to specify the number of clusters, but instead requires the approximate radius of a cluster as its primary tuning parameter. The package provides a fast implementation of this algorithm in n-dimensions using Lp-distances (with special cases for p=1,2, and infinity) as well as for spatial data using the Haversine formula, which takes latitude/longitude pairs as inputs and clusters based on great circle distances.

Perform pairwise likelihood inference in latent autoregressive count models. See Pedeli and Varin (2020) for details.

This package provides a statistical learning method that tries to find the best set of predictors and interactions between predictors for modeling binary or quantitative response data in a decision tree. Several search algorithms and ensembling techniques are implemented allowing for finetuning the method to the specific problem. Interactions with quantitative covariables can be properly taken into account by fitting local regression models. Moreover, a variable importance measure for assessing marginal and interaction effects is provided. Implements the procedures proposed by Lau et al. (2024, <doi:10.1007/s10994-023-06488-6>).

This package implements the letter value boxplot which extends the standard boxplot to deal with both larger and smaller number of data points by dynamically selecting the appropriate number of letter values to display.