开发者:上海品职教育科技有限公司 隐私政策详情

应用版本:4.2.11(IOS)｜3.2.5(安卓)APP下载

返回

游得过 · 2024年04月21日

normalization.为什么不选？

  1. CFA II
  2. Quantitative

* 问题详情，请 查看题干

NO.PZ202208300200000604

问题如下：

The method of scaling that Khan will use on Dataset 1 is most likely:

选项：

A.winsorization. B.normalization. C.standardization.

解释：

Solution

C is correct. Standardization is the process of both centering and scaling the variables. In this case, each temperature value will be standardized against the historical mean temperature for the geographic area. Standardization requires that the data be normally distributed, and the resulting standardized variable will have an arithmetic mean of 0 and a standard deviation of 1.

A is incorrect. Winsorization is a process of handling outliers that replaces extreme values and outliers with the maximum (for large-value outliers) and minimum (for small-value outliers) values of data points that are not outliers.

B is incorrect. Normalization is the process of rescaling numeric values in the rage of [0, 1], which is not the case for determining variation against historical temperature. Normalization can be used when the distribution of data is not known but treatment of outliers is necessary.

normalization.为什么不选？

添加评论
1 个答案

袁园_品职助教 · 2024年04月21日

嗨，努力学习的PZer你好：


题干说，接下来，Khan 假设在地区层面上呈正态分布的历史温度数据，并开始缩放这些数据，以确定每个区域的温度变化与平均温度的差异。

标准化（Standardization）：

  • 标准化是一种中心化（减去平均值）和缩放（除以标准差）变量的过程。在这个案例中，每个温度值将针对该地理区域的历史平均温度进行标准化。
  • 这种方法要求数据呈正态分布，结果得到的标准化变量将具有0的均值和1的标准差。
  • 这个选项是正确的，因为它直接关联到了问题描述中提及的“确定变化与每个区域的平均温度的差异”的任务。

归一化（Normalization）：

  • 归一化是一种重新缩放数值范围到[0, 1]的过程。
  • 这个选项不正确，因为问题描述中提到的是确定相对于历史平均温度的变化，而不是将数据缩放到[0, 1]的范围内。


----------------------------------------------
努力的时光都是限量版，加油！

  • 1

    回答

  • 0

    关注

  • 191

    浏览
相关问题

NO.PZ202208300200000604 问题如下 The methoof scaling thKhwill use on taset 1 is most likely: A.winsorization. B.normalization. C.stanrzation. SolutionC is correct. Stanrzation is the process of both centering anscaling the variables. In this case, eatemperature value will stanrzeagainst the historicmetemperature for the geographic areStanrzation requires ththe ta normally stribute anthe resulting stanrzevariable will have arithmetic meof 0 ana stanrviation of 1.A is incorrect. Winsorization is a process of haning outliers threplaces extreme values anoutliers with the maximum (for large-value outliers) anminimum (for small-value outliers) values of ta points thare not outliers.B is incorrect. Normalization is the process of rescaling numeric values in the rage of [0, 1], whiis not the case for termining variation against historictemperature. Normalization cusewhen the stribution of ta is not known but treatment of outliers is necessary. 没找到答案中显示的能表示标准化的题干句子

2024-06-25 14:22 1 · 回答