main content

假设检验 -凯发k8网页登录

t 检验、f 检验、卡方拟合优度检验等

statistics and machine learning toolbox™ 提供参数化假设检验和非参数化假设检验,帮助您确定样本数据是否来自具有特定特征的总体。

分布检验(如 anderson-darling 检验和单样本 kolmogorov-smirnov 检验)可以检验样本数据是否来自具有特定分布的总体。双样本 kolmogorov-smirnov 检验可以检验两组样本数据是否具有相同的分布。

位置检验(如 z 检验和单样本 t 检验)可以检验样本数据是否来自具有特定均值或中位数的总体。双样本 t 检验或多重比较检验可以检验两组或多组样本数据是否具有相同的位置值。

散度检验(如卡方方差检验)可以检验样本数据是否来自具有特定方差的总体。双样本 f 检验或多样本检验可以比较两个或多个样本数据集的方差。

通过交叉表分析和随机性游程检验确定样本数据的其他特征,并确定假设检验的样本大小和幂。

函数

anderson-darling test
chi-square goodness-of-fit test
cross-tabulation
durbin-watson test with residual inputs
fisher’s exact test
jarque-bera test
one-sample kolmogorov-smirnov test
two-sample kolmogorov-smirnov test
lilliefors test
run test for randomness
friedman’s test
kruskal-wallis test
multiple comparison test
wilcoxon rank sum test
sample size and power of test
wilcoxon signed rank test
sign test
单样本和配对样本 t 检验
双样本 t 检验
z 检验
ansari-bradley test
bartlett’s test
sample size and power of test
chi-square variance test
two-sample f-test for equal variances
multiple-sample tests for equal variances
one-sample or two-sample effect size computations
gardner-altman plot for two-sample effect size

检测漂移

detect drifts between baseline and target data using permutation testing

访问测试结果

diagnostics information for batch drift detection

检查测试结果

summary table for driftdiagnostics object
compute empirical cumulative distribution function (ecdf) for baseline and target data specified for data drift detection
compute histogram bin counts for specified variables in baseline and target data for drift detection
plot p-values and confidence intervals for variables tested for data drift
plot empirical cumulative distribution function (ecdf) of a variable specified for data drift detection
plot histogram of a variable specified for data drift detection
plot histogram of permutation results for a variable specified for data drift detection

主题


  • hypothesis testing is a common method of drawing inferences about a population based on statistical evidence from a sample.


  • all hypothesis tests share the same basic terminology and structure.


  • different hypothesis tests make different assumptions about the distribution of the random variable being sampled in the data.


  • view hypothesis tests of distributions and statistics.

网站地图