Which Of The Following Choices Are Responsible For Repairing Rifles And Replacing Parts As Required

Introduction

Linear Regression is however the most prominently used statistical technique in information science manufacture and in academia to explain relationships between features.

A total of ane,355 people registered for this skill test. It was particularly designed for you to exam your knowledge on linear regression techniques. If you are one of those who missed out on this skill examination, here are the questions and solutions. You missed on the real time test, merely tin can read this article to discover out how many could have answered correctly.

Hither is the leaderboard for the participants who took the test.

Overall Distribution

Below is the distribution of the scores of the participants:

You can access the scores here. More than 800 people participated in the skill test and the highest score obtained was 28.

Helpful Resources

Here are some resources to arrive depth noesis in the subject.

• v Questions which can teach you Multiple Regression (with R and Python)

• Going Deeper into Regression Analysis with Assumptions, Plots & Solutions

• seven Types of Regression Techniques you should know!

Are you a beginner in Machine Learning? Do you lot want to chief the concepts of Linear Regression and Machine Learning? Here is a beginner-friendly course to aid you in your journeying –

• Certified AI & ML Blackbelt+ Program
• Applied Motorcar Learning Class

Skill exam Questions and Answers

ane) True-Simulated: Linear Regression is a supervised motorcar learning algorithm.

A) Truthful
B) False

Solution: (A)

Yeah, Linear regression is a supervised learning algorithm because information technology uses true labels for training. Supervised learning algorithm should have input variable (x) and an output variable (Y) for each instance.

two) True-False: Linear Regression is mainly used for Regression.

A) TRUE
B) FALSE

Solution: (A)

Linear Regression has dependent variables that take continuous values.

3) True-Faux: It is possible to design a Linear regression algorithm using a neural network?

A) TRUE
B) FALSE

Solution: (A)

True. A Neural network can be used as a universal approximator, so it can definitely implement a linear regression algorithm.

4) Which of the post-obit methods do we use to find the best fit line for data in Linear Regression?

A) Least Square Error
B) Maximum Likelihood
C) Logarithmic Loss
D) Both A and B

Solution: (A)

In linear regression, we endeavor to minimize the least square errors of the model to place the line of best fit.

5) Which of the following evaluation metrics can be used to evaluate a model while modeling a continuous output variable?

A) AUC-ROC
B) Accuracy
C) Logloss
D) Mean-Squared-Error

Solution: (D)

Since linear regression gives output as continuous values, so in such case we utilise mean squared error metric to evaluate the model performance. Remaining options are use in instance of a classification problem.

six) True-False: Lasso Regularization can be used for variable selection in Linear Regression.

A) TRUE
B) FALSE

Solution: (A)

True, In case of lasso regression we apply absolute punishment which makes some of the coefficients zero.

seven) Which of the following is true nigh Residuals ?

A) Lower is better
B) Higher is better
C) A or B depend on the situation
D) None of these

Solution: (A)

Residuals refer to the error values of the model. Therefore lower residuals are desired.

8) Suppose that we have N independent variables (X1,X2… Xn) and dependent variable is Y. Now Imagine that you are applying linear regression past plumbing equipment the all-time fit line using least foursquare error on this data.

Y'all found that correlation coefficient for one of it's variable(Say X1) with Y is -0.95.

Which of the following is true for X1?

A) Relation between the X1 and Y is weak
B) Relation between the X1 and Y is potent
C) Relation between the X1 and Y is neutral
D) Correlation can't judge the relationship

Solution: (B)

The absolute value of the correlation coefficient denotes the forcefulness of the relationship. Since  absolute correlation is very high information technology means that the human relationship is strong between X1 and Y.

nine) Looking at above two characteristics, which of the post-obit option is the correct for Pearson correlation between V1 and V2?

If you are given the two variables V1 and V2 and they are following beneath two characteristics.

ane. If V1 increases then V2 as well increases

2. If V1 decreases and so V2 behavior is unknown

A) Pearson correlation will exist close to 1
B) Pearson correlation will be close to -1
C) Pearson correlation will be close to 0
D) None of these

Solution: (D)

We cannot comment on the correlation coefficient by using only statement 1.  We need to consider the both of these two statements. Consider V1 equally 10 and V2 every bit |x|. The correlation coefficient would not be close to i in such a case.

10) Suppose Pearson correlation betwixt V1 and V2 is zero. In such example, is information technology right to conclude that V1 and V2 practise non take any relation betwixt them?

A) Truthful
B) Simulated

Solution: (B)

Pearson correlation coefficient between 2 variables might be nil even when they have a relationship between them. If the correlation coefficient is zero, it just means that that they don't move together. Nosotros can accept examples like y=|x| or y=x^2.

11) Which of the post-obit offsets, do we use in linear regression'south least square line fit? Suppose horizontal axis is contained variable and vertical centrality is dependent variable.

A) Vertical commencement
B) Perpendicular offset
C) Both, depending on the state of affairs
D) None of above

Solution: (A)

We always consider residuals as vertical offsets. We calculate the direct differences between actual value and the Y labels. Perpendicular offset are useful in instance of PCA.

12) True- False: Overfitting is more than likely when you lot accept huge corporeality of information to train?

A) True
B) Imitation

Solution: (B)

With a small training dataset, it's easier to find a hypothesis to fit the training data exactly i.due east. overfitting.

13) We tin also compute the coefficient of linear regression with the help of an analytical method called "Normal Equation". Which of the following is/are true about Normal Equation?

1. Nosotros don't have to choose the learning rate
2. It becomes slow when number of features is very large
3. Thers is no need to iterate

A) 1 and 2
B) 1 and 3
C) ii and 3
D) 1,2 and three

Solution: (D)

Instead of gradient descent, Normal Equation tin too be used to find coefficients. Refer this article for read more than about normal equation.

fourteen) Which of the following statement is truthful about sum of residuals of A and B?

Beneath graphs show ii fitted regression lines (A & B) on randomly generated data. At present, I want to detect the sum of residuals in both cases A and B.

Annotation:

1. Calibration is same in both graphs for both axis.
2. Ten centrality is independent variable and Y-axis is dependent variable.

A) A has higher sum of residuals than B
B) A has lower sum of residuum than B
C) Both have same sum of residuals
D) None of these

Solution: (C)

Sum of residuals volition e'er be nix, therefore both have same sum of residuals

Question Context fifteen-17:

Suppose you have fitted a circuitous regression model on a dataset. Now, you are using Ridge regression with penality x.

15) Choose the pick which describes bias in best manner.
A) In case of very big x; bias is low
B) In instance of very large x; bias is high
C) We can't say nearly bias
D) None of these

Solution: (B)

If the penalisation is very large it means model is less complex, therefore the bias would be loftier.

16) What will happen when you apply very large penalty?

A) Some of the coefficient volition go absolute cipher
B) Some of the coefficient will approach zero simply not absolute nada
C) Both A and B depending on the situation
D) None of these

Solution: (B)

In lasso some of the coefficient value become cypher, simply in case of Ridge, the coefficients become close to zero just not zero.

17) What volition happen when yous apply very large penalty in case of Lasso?
A) Some of the coefficient will get zippo
B) Some of the coefficient will be approaching to zero only non absolute nothing
C) Both A and B depending on the state of affairs
D) None of these

Solution: (A)

As already discussed, lasso applies absolute punishment, so some of the coefficients will become nada.

18) Which of the following statement is true about outliers in Linear regression?

A) Linear regression is sensitive to outliers
B) Linear regression is not sensitive to outliers
C) Tin't say
D) None of these

Solution: (A)

The slope of the regression line will change due to outliers in most of the cases. So Linear Regression is sensitive to outliers.

19) Suppose you lot plotted a scatter plot between the residuals and predicted values in linear regression and y'all constitute that at that place is a relationship between them. Which of the following conclusion practice you make near this situation?

A) Since the there is a relationship means our model is not skillful
B) Since the there is a relationship means our model is skillful
C) Tin can't say
D) None of these

Solution: (A)

There should not be any human relationship between predicted values and residuals. If there exists any relationship between them,information technology means that the model has not perfectly captured the information in the data.

Question Context 20-22:

Suppose that y'all take a dataset D1 and you design a linear regression model of caste 3 polynomial and you found that the training and testing fault is "0" or in another terms it perfectly fits the information.

xx) What will happen when you fit caste 4 polynomial in linear regression?
A) At that place are loftier chances that caste iv polynomial volition over fit the data
B) At that place are high chances that caste 4 polynomial will nether fit the data
C) Can't say
D) None of these

Solution: (A)

Since is more than degree iv volition be more complex(overfit the data) than the degree three model so it will once more perfectly fit the data. In such case grooming error will exist aught but exam mistake may not exist naught.

21) What will happen when you fit caste ii polynomial in linear regression?
A) It is loftier chances that degree 2 polynomial volition over fit the information
B) It is high chances that degree ii polynomial will under fit the data
C) Tin can't say
D) None of these

Solution: (B)

If a degree 3 polynomial fits the information perfectly, it's highly likely that a simpler model(caste ii polynomial) might nether fit the information.

22) In terms of bias and variance. Which of the following is true when you fit caste 2 polynomial?

A) Bias will exist high, variance will exist high
B) Bias volition be depression, variance volition be high
C) Bias will be loftier, variance will exist low
D) Bias volition be depression, variance will be depression

Solution: (C)

Since a degree 2 polynomial volition be less complex as compared to degree three, the bias will be high and variance will exist low.

Question Context 23:

Which of the following is true about below graphs(A,B, C left to correct) between the cost function and Number of iterations?

23) Suppose l1, l2 and l3 are the three learning rates for A,B,C respectively. Which of the following is true almost l1,l2 and l3?

A) l2 < l1 < l3

B) l1 > l2 > l3
C) l1 = l2 = l3
D) None of these

Solution: (A)

In case of high learning charge per unit, step will be high, the objective role volition decrease chop-chop initially, but it volition not find the global minima and objective function starts increasing after a few iterations.

In case of depression learning charge per unit, the step will exist pocket-sized. So the objective part will decrease slowly

Question Context 24-25:

We have been given a dataset with n records in which nosotros have input attribute as x and output attribute as y. Suppose we use a linear regression method to model this data. To examination our linear regressor, we split the information in training set and examination set randomly.

24) At present we increase the training set size gradually. As the preparation set size increases, what do you expect volition happen with the mean grooming error?

A) Increase
B) Decrease
C) Remain constant
D) Tin can't Say

Solution: (D)

Training error may increase or decrease depending on the values that are used to fit the model. If the values used to train contain more than outliers gradually, and then the mistake might just increase.

25) What do you look will happen with bias and variance as you increase the size of preparation information?

A) Bias increases and Variance increases
B) Bias decreases and Variance increases
C) Bias decreases and Variance decreases
D) Bias increases and Variance decreases
E) Tin can't Say False

Solution: (D)

As we increase the size of the training data, the bias would increase while the variance would subtract.

Question Context 26:

Consider the following data where ane input(Ten) and i output(Y) is given.

26) What would exist the root hateful square training error for this data if you run a Linear Regression model of the form (Y = A0+A1X)?

A) Less than 0
B) Greater than zero
C) Equal to 0
D) None of these

Solution: (C)

We can perfectly fit the line on the following data then mean error will be zero.

Question Context 27-28:

Suppose you have been given the post-obit scenario for training and validation error for Linear Regression.

Scenario	Learning Charge per unit	Number of iterations	Preparation Error	Validation Error
1	0.1	g	100	110
2	0.ii	600	90	105
3	0.3	400	110	110
4	0.4	300	120	130
5	0.4	250	130	150

27) Which of the following scenario would give you the right hyper parameter?

A) 1
B) two
C) 3
D) 4

Solution: (B)

Selection B would exist the amend pick because it leads to less grooming too equally validation mistake.

28) Suppose you got the tuned hyper parameters from the previous question. Now, Imagine you want to add a variable in variable space such that this added feature is important. Which of the following thing would you observe in such instance?

A) Preparation Error will decrease and Validation error volition increment

B) Training Fault volition increment and Validation error will increase
C) Training Mistake volition increment and Validation fault will decrease
D) Training Error volition subtract and Validation error will decrease
East) None of the above

Solution: (D)

If the added feature is important, the training and validation fault would decrease.

Question Context 29-thirty:

Suppose, you lot got a situation where you find that your linear regression model is under fitting the data.

29) In such situation which of the post-obit options would you consider?

1. Add more variables
2. Start introducing polynomial degree variables
3. Remove some variables

A) ane and two
B) 2 and iii
C) ane and 3
D) i, 2 and 3

Solution: (A)

In case of under fitting, y'all need to induce more than variables in variable space or you tin add some polynomial degree variables to brand the model more complex to be able to fir the data meliorate.

30) Now state of affairs is same every bit written in previous question(under fitting).Which of following regularization algorithm would y'all prefer?

A) L1
B) L2
C) Whatever
D) None of these

Solution: (D)

I won't use any regularization methods because regularization is used in case of overfitting.

Terminate Notes

I tried my best to make the solutions equally comprehensive every bit possible simply if yous have any questions / doubts delight drop in your comments beneath. I would love to hear your feedback about the skilltest. For more such skilltests, check out our electric current hackathons.

Source: https://www.analyticsvidhya.com/blog/2017/07/30-questions-to-test-a-data-scientist-on-linear-regression/

Posted by: reedalind1967.blogspot.com

Share this post