import QuantReg quant = QuantReg(X, Y) qt = quant.fit(q=0.55) print(qt.summary()) 方法二:smf import statsmodels.formula.api as smf mod = smf.quantreg('Close ~ Open + High + Low', dataset) res = mod.fit(q=.5) print(res.summary ()) QuantReg Regression Results ================= Variable: Close Pseudo R-squared: 0.9842 Model: QuantReg 分位回归与线性回归的比较 不同分位数值拟合模型的一些属性值 mod = smf.quantreg('Close ~ Open', dataset) res = mod.fit(q=.5) quantiles
1.tar.gz Rcpp_1.0.2.tar.gz RcppArmadillo_0.9.700.2.0.tar.gz gtools_3.8.1.tar.gz SparseM_1.77.tar.gz quantreg 0.9.700.2.0.tar.gz R CMD INSTALL gtools_3.8.1.tar.gz R CMD INSTALL SparseM_1.77.tar.gz R CMD INSTALL quantreg
statsmodels.formula.api as smf import matplotlib.pyplot as plt data = sm.datasets.engel.load_pandas().data mod = smf.quantreg
## [73] robustbase_0.92-8 bindrcpp_0.2 nlme_3.1-129 ## [76] mime_0.5 quantreg
R包安装 BiocManager::install("ggpmisc") library(ggpmisc) library(tibble) library(dplyr) library(quantreg
如下: 「样例一」: library(ggpmisc) library(ggrepel) library(xts) library(lubridate) library(nlme) library(quantreg
如下: 「样例一」: library(ggpmisc) library(ggrepel) library(xts) library(lubridate) library(nlme) library(quantreg
PRINCOMP Procedure:主成份分析 The PRINQUAL Procedure:定质,定量,或混合数据的主成分分析(PCA) The PROBIT Procedure:probit回归 The QUANTREG
robustbase_0.92-8 bindrcpp_0.2 nlme_3.1-129 ## [76] mime_0.5 quantreg