Introduction
Embarking on a career in data science or analytics? The interview room can be challenging, particularly regarding probability and statistics questions. Navigating these questions requires more than just theoretical knowledge; it demands a practical understanding of applying statistical concepts. In this article, we delve into key interview questions, unraveling the intricacies of probability and statistics. Whether you’re preparing for a job interview or simply seeking to enhance your, these insights will prove invaluable.
In this article you will get to learn about the probability and statistics data science interview questions that will help you to crack the interviews.
This article was published as a part of the Data Science Blogathon.
Table of contents
Probability and statistics data science interview questions
1. Which of the following relation is correct for a negative skewed distribution?
(a) Mean=Mode=Median
(b) Mean>Median>Mode
(c) Mode>Median>Mean
(d) Mean>Mode=Median
Solution:(c)
2. In the symmetric covariance matrix:
(a) Diagonal elements must be positive and other elements are always zero.
(b) Diagonal elements can never be negative and other elements are always positive.
(c) Diagonal elements can never be negative and other elements can be negative or positive.
(d) Diagonal elements can be negative and positive and other elements are always negative.
Solution: (c)
Explanation: In a covariance matrix, the diagonal entries represent covariance of the variable with itself which is equal to the variance of that variable and is calculated as the square of standard deviation. Since variance is always positive, therefore diagonal entries are always positive.
3. Presence of Outliers in a dataset not affects:
(a) Standard deviation
(b) Range
(c) Mean
(d) Inter-quartile Range(IQR)
Solution: (d)
Explanation: The IQR is essentially the range of the middle 50% of the data. Since it uses the middle 50%, therefore it is not affected by the outliers.
4. If X and Y are independent random variables, then which of the following is TRUE?
a) E(XY)=E(X)E(Y) [ E represents Expectation value ]
(b) Cov(X,Y)=0 [ Cov represents covariance between variables ]
(c) Var(X+Y)=Var(X)+Var(Y) [ Var represents variance ]
(d) All of the above
Solution: (d)
Explanation: If X and Y are independent then Cov(X,Y)=0 and Var(X+Y) = Var(X)+Var(Y) (∵ 2Cov(X, Y) = 0)
5. For a normal distribution Z, which option is TRUE?
(a) Coefficient of skewness (E(Z3))=0
(b) E(Z)=0 ; E(Z2)=Var(Z)=1
(c) Kurtosis (E(Z4))=3
(d) Its density is symmetric about the mean.
Solution: (d)
Explanation:
6. Let X and Y be normal random variables with their respective means 3 and 4 and variances 9 and 16, then 2X-Y will have normal distribution with parameters:
(a) Mean=2 and Variance=52
(b) Mean=0 and Variance=1
(c) Mean=2 and Variance=1
(d) None of the above
Solution: (d)
Hint: Var(aX + bY) = a2 Var(X) + b2 Var(Y) + 2abCov(X,Y)
7. Suppose X and Y take values {0,1} and are independent with P(X=1)=1/2 and P(Y=1)=1/3. What is the probability that P(X+Y=1)?
(a) 5/18
(b) 1/2
(c) 5/6
(d) 1/6
Solution:(b)
Explanation: P(X +Y =1) = P(X=0).P(Y=1) + P(X=1).P(Y=0) = (1/2)(1/3) + (1/2)(2/3) = 1/2.
8. Let X and Y are random variables with E(X)=μ/2 and E(Y)=μ, then which one is TRUE?
(a) g=X+Y is an unbiased estimator of μ
(b) g = X+Y is a biased estimator of μ with bias equals to μ
(c) h=X+(Y/2) is an unbiased estimator of μ
(d) h= X+(Y/2) is a biased estimator of μ with bias equals to μ/2
Solution: (c)
Explanation: E(g)= E(X+Y)= E(X) + E(Y)=3μ/2 ; Bias(g)= E(g)-μ = μ/2
E(h)= E(X+(Y/2))= E(X) + 1/2E(Y) = μ, Bias(h)= E(h)-μ = 0
9. Suppose that X takes values between 0 and 1 and has probability density function(PDF) 2x, then the value of Variance of X2 is :
(a)1/12
(b) 1/18
(c) 1/6
(d) 5/18
Solution:(a)
Hint: Use Var(X2)= E(X4) -(E(X2))2
10. For random variables X and Y, we have Var(X)=1, Var(Y)=4, and Var(2X-3Y)=34, then the correlation between X and Y is:
a) 1/2
(b) 1/4
(c) 1/3
(d) None of the above
Solution:(b)
Explanation: Var(2X-3Y) = 34
= 4Var(X)+9Var(Y)-12Cov(X, Y)
= 4(1)+9(4)-12Cov(X, Y) = 34
∴ Cov(X, Y)=1/2
11. A fair die is rolled repeatedly until a number larger than 4 is observed. If K is the total number of times that the die is rolled, then P(K=4) is equal to:
a) 16/81
(b) 8/81
(c) 8/27
(d) 16/27
Solution: (b)
Explanation: P(K=4) = (P(#less than 4 or equal))3.P({4}) = (2/3)3.(1/3) = 8/81.
12. Let X and Y be independent uniform (0, 1) random variables. Define A=X+Y and B=X-Y. Then,
a) A and B are independent random variables
(b) A and B are uncorrelated random variables
(c) A and B are both uniforms (0,1) random variables.
(d) None of these
Solution: (b)
Explanation: Cov(X+Y, X-Y) = Cov(X, X) – Cov(X, Y) + Cov(Y, X) – Cov(Y ,Y) ⇒ Var(X) – Var(Y) = 0
13. If g is a point estimator of X, then Mean Square error(MSE) for g is:
(a) Variance(g) + Bias(g)
(b) Variance(g) + Bias(g2)
(c) Variance(g) + (Bias(g))2
(d) Variance(g2) + Bias(g)
Solution: (c)
Explanation: MSE(g) = E[ (g-X)2 ] = Var(g-X) + (E[ g-X ])2 = Var(g) + (Bias(g))2
14. Let X and Y be two random variables and let a, b, c, d be real numbers, then which one of the following is FALSE?
(a) Cov(X+b, Y+d) = Cov(X, Y)
(b) Cov(aX, cY) = ac*Cov(X, Y)
(c) Cov(aX+b, cY+d) = ac*Cov(X, Y)
(d) Corr(aX+b, cY+d) = ac*Corr(X, Y) for a,c>0
Solution: (d)
Explanation: Corr(aX+b, cY+d) = Corr(X, Y)
15. Let X and Y be jointly(bivariate) normal with Var(X) = Var(Y), then:
(a) X+Y and X-Y are jointly normal
(b) X+Y and X-Y are uncorrelated
(c) X+Y and X-Y are independent
(d) All of the above
Solution: (d)
Explanation: If X and Y be the bivariate normal distribution, then any linear combination of X and Y is also normally distributed.
16. Let X1, X2, X3, ——-, Xn be a random sample from a distribution with E(Xi)=μ and Var(Xi)=.σ2 Now, consider two estimators:
g1=X1 g2=X’=(X1+X2+X3+————-Xn)/n
Which of these estimator has high mean squared error(MSE)?
(a) g1
(b) g2
(c) Same for both g1 and g2
(d) None of the above
Solution: (a)
Explanation: MSE(g1)=E[(g1-μ)2] = E[(X1-E(X1))2] = Var(X1) = σ2
MSE(g2)=E[(g2-μ)2]= E[(X’-μ)2] = Var(X’-μ) + (E[X’-μ])2 = Var(X’) = σ2/n
17. A random sample of n=6 taken from the population has the elements 6, 10, 13, 14 ,18, 20. Then, which option is False?
(a) Point estimate for population mean is 13.5
(b) Point estimate for population standard deviation is 4.68
(c) Point estimate for population standard deviation is 3.5
(d) Point estimate for standard error of mean is 1.91
Solution: (c)
Explanation: Population mean(X’) = (Σ Xi/n ) = 13.5
Population standard deviation(S) = sqrt( (Σ Xi2/n) – (Σ Xi/n)2 ) = 4.68
Standard error of mean = S/sqrt(n) = 4.68/sqrt(6) = 1.91
Section-2
18. True or False: If the Pearson’s correlation between 2 variables is zero, then they are necessarily independent.
Solution: False
Explanation: Correlation is a measure of linear dependence between the variables.
19. True or False: Let g be an unbiased estimator of X and U be a random variable with zero means, then h=g+U is also unbiased for X.
Solution: True.
Explanation: E(h) =E(g) + E(U) = 0+0 =0( ∵ E(g)=0 due to unbiased estimator)
20. True or False: Let X and Y be two independent standard normal random variables and T=XY2+X+1 and P=X-3, then Cov(T, P)=1
Solution: False.
Hint: Use properties mentioned in Question-14.
21. True or False: Let X has a normal distribution with parameters μ and σ2, then X2 follows a chi-square distribution with parameter 1.
Solution: False.
Explanation: For the given statement to be True, X should be Standard normal distribution(μ=0, σ2=1)
22. True or False: If the characteristic function of a random variable exists, then its expectation and variance will also exist.
Solution: False.
Hint: Moment Generating Function(MGF)
23. True or False: Let X has uniform distribution U(a, b) such that E(X)=2 and Var(X)=3/4, then P(X<1)=1/6.
Solution: True.
Explanation: E(X) = (a+b)/2 = a+b=4 ; Var(X) = (b-a)2/12 = (b-a)=3 ⇒ X~ U(0.5, 3.5)
24. True or False: The correlation coefficient between X+Y and X-Y, where X and Y are independent random variables with variances 36 and 16 respectively is 6/13.
Solution: False.
Explanation: Corr(X+Y, X-Y) = Cov(X+Y, X-Y)/ Std(X+ Y).Std(X-Y) [Std= Standard Deviation]
25. True or False: In interval estimation, As the confidence level increases the margin of error decreases.
Solution: False.
Explanation: The Confidence Interval is defined as X ± Z(s/√n)
Conclusion
In summary, probability and statistics form the backbone of informed decision-making in our data-driven world. From predicting trends to guiding research, these concepts are indispensable. To deepen your mastery, explore our Blackbelt AI/ML program. Equip yourself with essential statistical skills crucial for success in data science. Join today to unlock the power of understanding and navigating the complexities of statistical data.
Hope u understand and get the understanding of probability and statistics data science interview questions that will help you for the preparation of interviews.
Something not mentioned or want to share your thoughts? Feel free to comment below And I’ll get back to you.
Thanks for reading!
ace your data science interviewblogathonprobabilityprobability statistics interview questionsstatistics
I am a B.Tech. student (Computer Science major) currently in the pre-final year of my undergrad. My interest lies in the field of Data Science and Machine Learning. I have been pursuing this interest and am eager to work more in these directions. I feel proud to share that I am one of the best students in my class who has a desire to learn many new things in my field.
