stat841

Course Note for Sept.30th (Classfication_by Liang Jiaxi)

1.

2. Classification
Classification is a function between two random varialbe

3. Error data
Definition:
True error rate of a classifier(h) is defined as the probability that the prediction of Y from X does not exactly equal to Y, namely, [math]\displaystyle{ \, L(h)=P(h(X) \neq Y) }[/math].
Empirical error rate(training error rate) of a classifier(h) is defined as the frequency of event that Y predicted from X does not equal to Y in totally n prediction. The mathematical defition is as below:
[math]\displaystyle{ \, L_{h}= \frac{1}{n} \sum_{i=1}^{n} I(h(X_{i} \neq Y_{i})) }[/math], where [math]\displaystyle{ \,I }[/math] is an indicator that [math]\displaystyle{ \, I= }[/math].

4. Bayes Classifier