exam questions

Exam DP-100 All Questions

View all questions & answers for the DP-100 exam

Exam DP-100 topic 7 question 7 discussion

Actual exam question from Microsoft's DP-100
Question #: 7
Topic #: 8
[All DP-100 Questions]

You need to select a feature extraction method.
Which method should you use?

  • A. Mutual information
  • B. Pearson's correlation
  • C. Spearman correlation
  • D. Fisher Linear Discriminant Analysis
Show Suggested Answer Hide Answer
Suggested Answer: C 🗳️
Spearman's rank correlation coefficient assesses how well the relationship between two variables can be described using a monotonic function.
Note: Both Spearman's and Kendall's can be formulated as special cases of a more general correlation coefficient, and they are both appropriate in this scenario.
Scenario: The MedianValue and AvgRoomsInHouse columns both hold data in numeric format. You need to select a feature selection algorithm to analyze the relationship between the two columns in more detail.
Incorrect Answers:
B: The Spearman correlation between two variables is equal to the Pearson correlation between the rank values of those two variables; while Pearson's correlation assesses linear relationships, Spearman's correlation assesses monotonic relationships (whether linear or not).
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/feature-selection-modules

Comments

Chosen Answer:
This is a voting comment (?). It is better to Upvote an existing comment if you don't have anything to add.
Switch to a voting comment New
Mckay_
Highly Voted 2 years ago
This can be a tricky question if you did not read the case study. It says in the case study that relationship between features should be assess using non-parametric statistics. Thus, the reason for using the spearman's rank correlation.
upvoted 7 times
BTAB
1 year, 9 months ago
Thanks for the evaluation. Correct.
upvoted 1 times
...
...
XiaoQiang
Highly Voted 3 years, 10 months ago
how could 2 same questions get a different answer? bad quality
upvoted 7 times
jed_elhak
3 years, 1 month ago
Correlation analysis provides a quantitative means of measuring the strength of a linear relationship between two vectors of data. Mutual information is essentially the measure of how much “knowledge” one can gain of a certain variable by knowing the value of another variable so it can't be mututal information spearman is the right answer
upvoted 2 times
...
BrunoCavagnaro
3 years, 8 months ago
They even coment that both Pearson and Kendall are correct answers
upvoted 2 times
...
Indranee
3 years, 9 months ago
Maybe microsoft jumbles up the possible responses/answers which could appear for each test taker.
upvoted 1 times
...
...
deyoz
Most Recent 8 months, 3 weeks ago
The answer is definitely not D. But I am confused between three even after reading all the comments below. help!
upvoted 1 times
...
phdykd
1 year, 8 months ago
The question mentions "feature extraction," but the given answer choices are all feature selection methods. If the question is about feature extraction, some commonly used methods are Principal Component Analysis (PCA), Independent Component Analysis (ICA), and Non-negative Matrix Factorization (NMF). If the question is about feature selection, then the most appropriate method depends on the specific characteristics of the data and the problem at hand. Without more information about the specific characteristics of the data and the problem at hand, it is not possible to determine which method is the best choice.
upvoted 1 times
...
jed_elhak
3 years, 1 month ago
Answer is correct : they asked a non parametric pearson and fisher are parametric
upvoted 5 times
jed_elhak
3 years, 1 month ago
Correlation analysis provides a quantitative means of measuring the strength of a linear relationship between two vectors of data. Mutual information is essentially the measure of how much “knowledge” one can gain of a certain variable by knowing the value of another variable so it can't be mututal information spearman is the right answer
upvoted 1 times
...
...
levm39
3 years, 4 months ago
Note: Both Spearman's and Kendall's can be formulated as special cases of a more general correlation coefficient, and they are both appropriate in this scenario.
upvoted 2 times
...
rabbie
3 years, 5 months ago
pearson's correlation is not a non-parametric method
upvoted 1 times
rabbie
3 years, 5 months ago
MY BAD, IT'S SPEARMAN
upvoted 2 times
...
...
prashantjoge
3 years, 5 months ago
Pearson is linear while spearman and kendall are monotonic. Pearson does not work well with outliers but there is not indication that the medianvalue and AvgRoomsInHouse columns have outliers. Fisher linear discriminant (FLD) analysis is not a valid option (fisher score is) See links for difference https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/fisher-linear-discriminant-analysis https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/filter-based-feature-selection The answer I think is Pearson's correlation.
upvoted 1 times
...
saurabhk1
3 years, 7 months ago
The answer should be Fisher Linear Discriminant Analysis, as this is the only method in the given options, that is used for extracting features in low dimensions.
upvoted 3 times
deyoz
8 months, 3 weeks ago
Fisher LDA is definitely not the answer as it is used in classification problems not regression.
upvoted 1 times
...
...
Community vote distribution
A (35%)
C (25%)
B (20%)
Other
Most Voted
A voting comment increases the vote count for the chosen answer by one.

Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.

SaveCancel
Loading ...
exam
Someone Bought Contributor Access for:
SY0-701
London, 1 minute ago