SIHR: SIHR provides functionalities for constructing confidence intervals and performing hypothesis tests for low-dimensional objectives in both one-sample and two-sample high-dimensional regression settings. Specifically, it implements inference procedures for (1) linear functionals in generalized linear regression (Cai, Cai, and Guo, 2021; Guo et al., 2020; Cai, Guo, and Ma, 2021), (2) conditional average treatment effects in generalized linear regression, (3) quadratic functionals in generalized linear regression (Guo et al., 2021). (4) inner product in generalized linear regression (5) distance in generalized linear regression.
SIHR supports different GLMs, by specifying the argument model in “linear”, “logistic”, “logistic_alternative” or “probit”. Please see the paper Rakshit, et al. (2023) for details.
CHIME: A Matlab implementation of the clustering procedure, CHIME, for high-dimensional Gaussian mixtures. Please see the paper Cai, Ma, and Zhang (2017) for details.
TestBMN: A set of R functions for differential Markov random field analysis. The multiple testing procedure is developed in the paper Cai, Li, Ma, and Xia (2017).
invalidIV: A set of R functions for linear instrumental variables analysis with potentially invalid instruments. The methods in these R functions are developed in the papers Guo, Kang, Cai, and Small (2016) and Kang, Cai, and Small (2016). Please see the papers for more details.
sisVIVE: R package that selects invalid instruments among a candidate set of potentially bad instruments. The algorithm selects potentially invalid instruments and provides an estimate of the causal effect between treatment and outcome. Please see the paper Kang, Zhang, Cai, and Small (2015) for details of the procedure.
PheWAS:
A Matlab implementation of the multiple testing procedure for phenome-wide association studies (PheWAS).
Please see the paper Cai, Cai, Liao, and Liu (2015) for details.
CAPME: R package for estimating a precision matrix while adjusting for covariates. Please see the paper Cai, Li, Liu and Xie (2013) for details of the procedure.
CLIME:
A fast and stable implementation of the CLIME estimator for sparse precision matrices proposed in Cai, Liu, and Luo (2011) can be obtained by using the flare package developed by Xingguo Li, Tuo Zhao, Lie Wang, Xiaoming Yuan and Han Liu. The R package is available here.
The original implementation of CLIME is this
R package, together with the CLIME manual.
Please see the paper Cai, Liu, and Luo (2011) for details of the method.
ssfcov: R Package for estimation of covariance function.
Please see the paper Cai and Yuan (2010) for details of the procedure.
FDR-HMM: R package for the data-driven multiple testing procedure for dependent data proposed in Sun and Cai (2009).
Here is the readme file.
Please see the paper Sun and Cai (2009) for details.
FDR: R package for the adaptive multiple testing procedure proposed in Sun and Cai (2007).
Here is the readme file.
Please see the paper Sun and Cai (2007) for details.