SPSS & Data Analytics

Judgment questions (answer "right/wrong", and if "wrong", please indicate the reason).

1. If the attributes can be derived from each other, it means that there is a meta residual problem in these data.

2. if the skewness > 0, the distribution is considered to be right skewed, i.e., the distribution has a center of gravity (head) on the right;.

3. all non-empty subsets of the frequent item set must also be frequent (correct).

4. The measure of "information content" can be based on probability. If the probability is high, the chance of occurrence is high and the uncertainty is low; conversely, the uncertainty is high.

5. the Apriori property increases the efficiency of frequent item set generation by reducing the search space ( ).

6. there is not enough evidence to disprove the original proposition, so the original proposition holds. Answer:

7. In a multiple linear regression model, the R-squared is often used to assess the goodness of fit of a linear regression model, the larger the R-squared, the better the model Answer:

8. In general, decision trees are supervised learning. Answer:

9. A subset of an infrequent item set must be infrequent. Answer:

10. Logistic regression can transform a classification problem into a continuous problem. Answer:

11. A valid rule is called a strong association rule. 12. Clustering is supervised learning. 13. The model (stream) in Demos can be modified, and another Sun