is a data-mining technique used for classifying a set of observations into predefined classes.

Question

BlackTom AI · Accepted Answer

Discriminant analysis separates predefined groups by finding one or more linear combinations of predictor variables that best discriminate between the classes.

Relevant concepts:
- Supervised classification: assigning observations to known classes based on predictors.
- Discriminant functions: linear (LDA) or quadratic (QDA) combinations of predictors that maximize between-class separation relative to within-class variation.
- Key assumptions of classical LDA: multivariate normality and (for LDA) equal covariance matrices across classes.

Step-by-step reasoning and method (mathematical form):
1. For each class k compute the class mean vector μ_k and the pooled within-class covariance matrix S_w = Σ_k Σ_i (x_i - μ_k)(x_i - μ_k)^T.
2. Compute the between-class scatter S_b = Σ_k n_k (μ_k - μ)(μ_k - μ)^T, where μ is the overall mean and n_k are class sizes.
3. Solve the generalized eigenvalue problem S_b w = λ S_w w; for two classes this simplifies to w ∝ S_w^-1 (μ_1 - μ_2). This w is the discriminant vector.
4. Project an observation x onto w: y = w^T x. Classify x by comparing y to a threshold (often based on class priors and projected class means).
These steps show how discriminant analysis constructs explicit decision boundaries to classify observations into predefined groups.

Why the correct answer is correct:
- Discriminant analysis is explicitly designed to classify observations into known categories by maximizing separation between classes; it provides discriminant functions and decision rules directly tied to predefined classes.

Why other options are not correct:
- Logistic regression: also a classification technique modeling class probabilities via a logit link; but the question asks specifically for the data-mining technique conventionally described as classifying via discriminant functions—“Discriminant analysis” is the textbook answer. Logistic regression differs in approach (probability modeling rather than discriminant functions) and is not named “discriminant analysis.”
- k-Nearest Neighbors: a non-parametric instance-based classifier; it assigns class by neighborhood voting rather than constructing discriminant functions, so it’s not what the phrase typically denotes.
- Linear regression: predicts continuous outcomes, not classification into predefined classes, so it’s incorrect.

Conclusion: The correct choice is Discriminant analysis, as given.

is a data-mining technique used for classifying a set of observations into predefined classes.单项选择题

类似问题

You own a bond that pays $64 in interest annually. The face value is $1,000 and the current market price is $1,021.61. The bond matures in 11 years. What is the yield to maturity?

Which of the following statements is CORRECT?

It will cost $9,600 to acquire an ice cream cart that is expected to produce cash inflows of $3,600 a year for three years. After the three years, the cart is expected to be worthless. What is the payback period?

更多留学生实用工具

智能学习助手

风格化写作助手

论文查重助手

文献引用助手

课堂转译助手

课堂笔记助手

Quiz搜索助手

学校历年真题

智能刷题助手

智能匹配练习

希望你的学习变得更简单