When we compare our control with another group, the t-test could fit our goal very well. But when we need to compare it into more than 1 group, 3 groups for example, the t-test could only give the random false positive independently. That means three false positives in three comparisons. This would cause a problem. Because the false positive we need to consider now is at least one false positive in three comparisons. It means we need to adjust the p-value and apply a rigorous method to achieve a more reliable result. For doing that, ANOVA was introduced and applied.

XGBoost (Extreme Gradient Boosting) is a popular open-source machine learning library used for classification and regression tasks. It is designed to improve upon the performance of traditional gradient boosting algorithms by adding additional regularization and optimizing the gradient descent algorithm. It is widely used in industry and has won several machine learning competitions. Who said this?

Calculating logistic function with R| logistic regression| 逻辑斯蒂曲线

Calculating regression function by R

Some machine learning codes for R

Calculating response surface Methodology in R

Plot a Words Cloud

Tricks for Data cleaning in R

XGBoost codes