J*y
发帖数: 271 | 1 Linear regression line 是通过 minimizes the sum of the SQUARE of the
vertical distances from the points to the line.
为什么不是那条 Sum of the vertical distances 最小的线？
谢谢 |
f**e
发帖数: 350 | 2 Linear regression by default uses least sqaures.
If you use the second criterion, this is called the least absolute deviation
estimator, which is more difficult to minimize. |
J*y
发帖数: 271 | 3 谢谢。也就是说为了计算容易一点。
其实minimize sum of squared distances 的同时，也 minimize sum of distances.
我可不可以说regression line 就是那条sum of vertical distances from points to
fitted line is the smallest.
deviation
【在 f**e 的大作中提到】
: Linear regression by default uses least sqaures.
: If you use the second criterion, this is called the least absolute deviation
: estimator, which is more difficult to minimize.
|
f**e
发帖数: 350 | 4 你的解释不对，minimize sum of squared distances 不等于minimize sum of
distances，很容易找个反例。 |
J*y
发帖数: 271 | 5 明白了，谢谢。
【在 f**e 的大作中提到】
: 你的解释不对，minimize sum of squared distances 不等于minimize sum of
: distances，很容易找个反例。
|
m****i
发帖数: 875 | 6 都可以吧，有的人用2-norm，有的人用1-norm |
