网站首页
知道智慧树答案 
1、单选题：
Information analytics include:
选项：
A: Data organization
B: Data interpretation
C: Data visualization
D: All of above.
答案: 【 All of above.】
2、单选题：
Which one of the following categories does the age of a student (e.g., 19) belong to?
选项：
A: Nominal
B: Ordinal
C: Interval
D: Ratio
答案: 【 Interval】
3、单选题：
Which one of the following categories does the gender of a student (e.g., female) belong to?
选项：
A: Nominal
B: Ordinal
C: Interval
D: Ratio
答案: 【 Nominal】
4、单选题：
Which one of the following categories does the average score of a course (e.g., 85.2) belong to?
选项：
A: Nominal
B: Ordinal
C: Interval
D: Ratio
答案: 【 Ratio】
5、单选题：
Which one of the following categories does the ranking of a student’s score (e.g., 2) belong to?
选项：
A: Nominal
B: Ordinal
C: Interval
D: Ratio
答案: 【 Ordinal】
1、单选题：
What is the ultimate purpose of data analysis?
选项：
A: To build a model to perform simulation
B: To gain insights and help with decision making
C: To make a descriptive analysis and visualize the data
D: To build a model to perform simulation
答案: 【 To gain insights and help with decision making】
2、判断题：
When optimizing a model, we should always consider a trade-off between model interpretation and model accuracy.
选项：
A: 正确
B: 错误
答案: 【 正确】
3、填空题：
We will use Python, R and ____ in this class.
答案: 【 Stata】
4、填空题：
The stages of data analytics usually include feature selection, modeling and testing, model evaluation and .
答案: 【 optimization】
1、单选题：
Which of the following terminology is the same as reproducibility
选项：
A: Validity
B: Fair
C: Useful
D: Reliability
答案: 【 Reliability】
2、单选题：
Normalization with z-value can be used for
选项：
A: Normally distributed data
B: Symmetric but not normally distributed data
C: Uniformly distributed data
D: Exponentially distributed data
答案: 【 Normally distributed data】
3、填空题：
An indicator is a mathematical expression that can be applied to ________ data.
答案: 【 numerical】
1、单选题：
Which of the following indices can represent the degree of collaboration
选项：
A: 
B: 
C: 
D: 
答案: 【 】
2、判断题：
According to this figure, we can argue that collaboration enhances productivity.
选项：
A: 正确
B: 错误
答案: 【 错误】
1、单选题：
The first h articles ranked by the citation counts in descending order form the h-core, then h-tail is
选项：
A: all the other articles outside the h-core
B: the last h articles by the same ranking
C: randomly picked h articles
D: another h articles right following the h-core by the order
答案: 【 all the other articles outside the h-core】
2、单选题：
Read the following table and answer questions 2-4
The h index of this author is .
选项：
A: 4
B: 5
C: 6
D: 7
答案: 【 5】
3、单选题：
The h-core consists publication
选项：
A: A, B, C
B: A, B, C, D
C: A, B, C, D, E
D: A, B, C, D, E, F
答案: 【 A, B, C, D, E】
4、单选题：
The extended h-core including publications
选项：
A: A, B, C
B: A, B, C, D
C: A, B, C, D, E
D: A, B, C, D, E, F
答案: 【 A, B, C, D, E, F】
1、单选题：
Which of the following characteristics of the h-index is not correct
选项：
A: Simple
B: Relatively stable
C: Independent of productivity
D: Time-dependent
答案: 【 Independent of productivity】
2、单选题：
Which of the following has no chances to affect the value of the h-index?
选项：
A: Increasing the number of publications alone
B: Increasing the number of co-authors
C: Calculation errors
D: Increasing the number of citations
答案: 【 Increasing the number of co-authors】
3、判断题：
Does the h-index measure how GOOD a scientist is?
选项：
A: 正确
B: 错误
答案: 【 错误】
4、填空题：
One potential flaw of the h-index is that publications and citations are not _____ on each other.
答案: 【 independent】
1、单选题：
Choose the mathematical formula for density indicator in a directed network
选项：
A: 
B: 
C: 
D: 
答案: 【 】
2、单选题：
The closeness centrality can measure the _______ of a network.
选项：
A: activeness
B: efficiency
C: control over the flow
D: density
答案: 【 efficiency】
3、填空题：
The betweenness centrality is the number of times a node needs a given node to reach another node, which means it is the number of paths that pass through a given node.
答案: 【 shortest】
1、单选题：
Which of the following concepts is not relevent to the diversity indicators
选项：
A: Variety
B: Balance
C: Modularity
D: Disparity
答案: 【 Modularity】
2、单选题：
Which of the followings can lead to a larger diversity
选项：
A: higher disparity
B: lower disparity
C: less balanced distribution
D: less variety
答案: 【 higher disparity】
3、判断题：
Balance describes the number of distinctive categories.
选项：
A: 正确
B: 错误
答案: 【 错误】
4、判断题：
Variety is a function of fractions summing up to one.
选项：
A: 正确
B: 错误
答案: 【 错误】
1、单选题：
Which of the following statement of classical analysis and EDA is not true:
选项：
A: In classical analysis, we build models before analysis
B: In EDA, we estimate the model directly after preparing data
C: In classical analysis, we spend most of our time estimating and testing hypothetical models
D: In EDA, we focus more on the true distribution of data and emphasize the visualization of data
答案: 【 In EDA, we estimate the model directly after preparing data】
2、单选题：
Which one of the following does not belong to the descriptive statistics of one quantitative variable:
选项：
A: Maximum
B: Average
C: 40 percentiles
D: Distribution
答案: 【 Distribution】
3、单选题：
If the following figure is the PDF plot, then _ is the CDF plot.
选项：
A: 
B: 
C:
D:
答案: 【 】
4、填空题：
The Matthew effect is examplified in this lecture as: a limited number of papers have a __ number of citations:
答案: 【 large##%_YZPRLFH_%##big##%_YZPRLFH_%##great】
1、单选题：
Which of the following cannot be used for bivariate data analysis:
选项：
A: Scatter plot
B: Pearson’s correlation coefficient
C: One-dimensional distribution
D: Regression analysis
答案: 【 One-dimensional distribution】
2、单选题：
In situation _, we will use Pearson’s correlation coefficient.
选项：
A: Continuous, normally distributed, linear data
B: Continuous, normally distributed data
C: Two sequential data
D: Continuous, uniformly distributed, linear data
答案: 【 Continuous, normally distributed, linear data】
3、单选题：
In the example about confidence interval in this lecture, why do we draw samples for 1000 times?
选项：
A: Decrease the negative effect from unusual data points
B: Avoid Matthew effect
C: Increase sample size to facilitate aggregate variable
D: Provide enough data for regression analysis
答案: 【 Decrease the negative effect from unusual data points】
4、单选题：
Which of the following is not a method used for multivariate data analysis:
选项：
A: Bubble plot
B: Pairwise analysis
C: Single scatter plot
D: Regression analysis
答案: 【 Single scatter plot】
1、单选题：
Which of the following value shows a positive correlation:
选项：
A: 1.0
B: 1.5
C: -1.0
D: -1.5
答案: 【 1.0】
2、单选题：
We usually use _ to test Pearson correlation coefficient.
选项：
A: z-test
B: t-test
C: Normalization
D: Chi-square test
答案: 【 t-test】
3、单选题：
We usually use __ to test Spearman rank order correlation coefficient.
选项：
A: z-test
B: t-test
C: Normalization
D: Chi-square test
答案: 【 z-test】
4、单选题：
Which of the following statements of Spearman rank order correlation coefficient and Kendall rank correlation coefficient is true?
选项：
A: We change original data to rank pair of data in Spearman rank order correlation coefficient to eliminate the influence of outliers.
B: For categorical variables, we need to use Spearman rank order correlation coefficient.
C: For two sequential measurement variables, we need to use Kendall rank correlation coefficient.
D: For continuous, normally distributed, linear variables, we need to use Spearman rank order correlation coefficient.
答案: 【 We change original data to rank pair of data in Spearman rank order correlation coefficient to eliminate the influence of outliers.】
1、单选题：
Which of the following statement about regression analysis is not true?
选项：
A: Regression method analyzes the quantitative causal relationship between the independent variable and the dependent variable.
B: Regression analysis can be divided to quantitative variable regression and classified variable regression.
C: Regression analysis can be classified depending on the number of variables.
D: Regression analysis is omnipotent.
答案: 【 Regression analysis is omnipotent. 】
2、单选题：
In the following equation 
, 
is __.
选项：
A: residual
B: fitted value
C: real independent variable
D: estimated parameter
答案: 【 residual】
3、单选题：
According to the rule of OLS, the __ needs to be the smallest.
选项：
A: total sum of squares
B: residual sum of squares
C: explained sum of squares
D: regression
答案: 【 residual sum of squares】
4、单选题：
Which of the following statement for goodness of fit test for OLS is not true.
选项：
A: Goodness of fit test is used to describe the volatility of Yi relative to its fitted value.
B: TSS = ESS + RSS
C: 
D: The larger 
is, the better regression line fits.
答案: 【 Goodness of fit test is used to describe the volatility of Yi relative to its fitted value.】
1、单选题：
Based on what you have learned about types of regression, which of the following statement is true?
选项：
A: PLS regression can be used for several quantitative dependent variables.
B: Logistic regression can be used when the independent variable and the dependent variable are not linear.
C: Polynomial regression can be used when the dependent variables are categorized.
D: Multiple linear regression can be used for several quantitative dependent variables.
答案: 【 PLS regression can be used for several quantitative dependent variables.】
2、单选题：
This is a matrix multiplication for multiple linear regression, 
,if n is the number of independent variables and 
is an n×1 column vector, p is the number of observations, then which of the following statement is true?
选项：
A: 
is a p×1 vector of parameters.
B: 
is an (n+1)×1 vector of random errors.
C: 
is an n×(p+1) matrix.
D: 
答案: 【 is an n×(p+1) matrix. 】
3、单选题：
Which of the following describes the estimated parameter of multiple linear regression?
选项：
A: 
B: 
C: 
D:
备案号：冀ICP备20010840号 2020-2099辉辉网络科技 All Rights Reserved
