为什么在R和Java中对于简单线性回归会得到不同的截距值？

我有用R编写的线性回归代码，我必须用Java做同样的事情。我用图书馆来做这个。我在R代码和Java代码中使用了相同的数据，但截取值不同。我不知道我在代码中做了什么蠢事

R代码：

test_trait <- c( -0.48812477 , 0.33458213, -0.52754476, -0.79863471, -0.68544309, -0.12970239,  0.02355622, -0.31890850,0.34725819 , 0.08108851)

geno_A <- as.factor(c("Sub_0001"=1, "Sub_0002"=0, "Sub_0003"=1, "Sub_0004"=2, "Sub_0005"=0, "Sub_0006"=0, "Sub_0007"=1, "Sub_0008"=0, "Sub_0009"=1, "Sub_0010"=0))

geno_B <- as.factor(c("Sub_0001"=0, "Sub_0002"=0, "Sub_0003"=0, "Sub_0004"=1, "Sub_0005"=1, "Sub_0006"=0, "Sub_0007"=0, "Sub_0008"=0, "Sub_0009"=0, "Sub_0010"=0) )

fit <- lm(test_trait ~ geno_A*geno_B)
fit

package linearregression;
import org.apache.commons.math3.stat.regression.SimpleRegression;
public class LinearRegression {
    public static void main(String[] args) {

        double[][] x = {{1,0},
                        {0,0},
                        {1,0},
                        {2,1},
                        {0,1},
                        {0,0},
                        {1,0},
                        {0,0},
                        {1,0},
                        {0,0}
        };

        double[]y = { -0.48812477,
                       0.33458213,
                      -0.52754476,
                      -0.79863471,
                      -0.68544309,
                      -0.12970239,
                       0.02355622,
                      -0.31890850,
                       0.34725819,
                       0.08108851
        };
        SimpleRegression regression = new SimpleRegression(true);
        regression.addObservations(x,y);

        System.out.println("Intercept: \t\t"+regression.getIntercept());

    }
}

Intercept:      -0.08732359363636362

Java代码：

test_trait <- c( -0.48812477 , 0.33458213, -0.52754476, -0.79863471, -0.68544309, -0.12970239,  0.02355622, -0.31890850,0.34725819 , 0.08108851)

geno_A <- as.factor(c("Sub_0001"=1, "Sub_0002"=0, "Sub_0003"=1, "Sub_0004"=2, "Sub_0005"=0, "Sub_0006"=0, "Sub_0007"=1, "Sub_0008"=0, "Sub_0009"=1, "Sub_0010"=0))

geno_B <- as.factor(c("Sub_0001"=0, "Sub_0002"=0, "Sub_0003"=0, "Sub_0004"=1, "Sub_0005"=1, "Sub_0006"=0, "Sub_0007"=0, "Sub_0008"=0, "Sub_0009"=0, "Sub_0010"=0) )

fit <- lm(test_trait ~ geno_A*geno_B)
fit

package linearregression;
import org.apache.commons.math3.stat.regression.SimpleRegression;
public class LinearRegression {
    public static void main(String[] args) {

        double[][] x = {{1,0},
                        {0,0},
                        {1,0},
                        {2,1},
                        {0,1},
                        {0,0},
                        {1,0},
                        {0,0},
                        {1,0},
                        {0,0}
        };

        double[]y = { -0.48812477,
                       0.33458213,
                      -0.52754476,
                      -0.79863471,
                      -0.68544309,
                      -0.12970239,
                       0.02355622,
                      -0.31890850,
                       0.34725819,
                       0.08108851
        };
        SimpleRegression regression = new SimpleRegression(true);
        regression.addObservations(x,y);

        System.out.println("Intercept: \t\t"+regression.getIntercept());

    }
}

Intercept:      -0.08732359363636362

Java输出：

test_trait <- c( -0.48812477 , 0.33458213, -0.52754476, -0.79863471, -0.68544309, -0.12970239,  0.02355622, -0.31890850,0.34725819 , 0.08108851)

geno_A <- as.factor(c("Sub_0001"=1, "Sub_0002"=0, "Sub_0003"=1, "Sub_0004"=2, "Sub_0005"=0, "Sub_0006"=0, "Sub_0007"=1, "Sub_0008"=0, "Sub_0009"=1, "Sub_0010"=0))

geno_B <- as.factor(c("Sub_0001"=0, "Sub_0002"=0, "Sub_0003"=0, "Sub_0004"=1, "Sub_0005"=1, "Sub_0006"=0, "Sub_0007"=0, "Sub_0008"=0, "Sub_0009"=0, "Sub_0010"=0) )

fit <- lm(test_trait ~ geno_A*geno_B)
fit

package linearregression;
import org.apache.commons.math3.stat.regression.SimpleRegression;
public class LinearRegression {
    public static void main(String[] args) {

        double[][] x = {{1,0},
                        {0,0},
                        {1,0},
                        {2,1},
                        {0,1},
                        {0,0},
                        {1,0},
                        {0,0},
                        {1,0},
                        {0,0}
        };

        double[]y = { -0.48812477,
                       0.33458213,
                      -0.52754476,
                      -0.79863471,
                      -0.68544309,
                      -0.12970239,
                       0.02355622,
                      -0.31890850,
                       0.34725819,
                       0.08108851
        };
        SimpleRegression regression = new SimpleRegression(true);
        regression.addObservations(x,y);

        System.out.println("Intercept: \t\t"+regression.getIntercept());

    }
}

Intercept:      -0.08732359363636362

---

我将非常感谢你的帮助。谢谢

Java正在做一个简单的回归，只解释第一个变量和数字

> test_trait <- c( -0.48812477 , 0.33458213, -0.52754476, -0.79863471, -0.68544309, -0.12970239,  0.02355622, -0.31890850,0.34725819 , 0.08108851)
> geno_A <- c("Sub_0001"=1, "Sub_0002"=0, "Sub_0003"=1, "Sub_0004"=2, "Sub_0005"=0, "Sub_0006"=0, "Sub_0007"=1, "Sub_0008"=0, "Sub_0009"=1, "Sub_0010"=0)
> fit <- lm(test_trait ~ geno_A)
> fit$coef[1]
(Intercept) 
-0.08732359 

>test\u trait geno\u A fit$coef[1]
（截取）
-0.08732359 

+1获得清晰、详细的示例感谢您的回答，它在某种程度上有所帮助。你知道我如何让java同时考虑到

geno_A

和

geno_B

？