Unit 1: Statistics and Data Analysis Foundations

1. Define mean, median, and mode with examples.

o Mean: Average of values. Example: Mean of 2, 4, 6 is (2+4+6)/3 = 4.

o Median: Middle value when sorted. Example: Median of 3, 5, 7 is 5.

o Mode: Most frequent value. Example: Mode of 2, 2, 3 is 2.

2. How do you compute variance and standard deviation?

o Variance (σ²): Average of squared differences from the mean.

o Standard Deviation (σ): Square root of variance.

3. Explain the significance of standard deviation in data analysis.

o It measures the spread or dispersion of data; low SD = data close to mean.

4. What are different types of data visualizations and when would you use each?

o Bar Chart: Comparing categories.

o Histogram: Distribution of continuous data.

o Pie Chart: Proportions of categories.

o Scatter Plot: Correlation between two variables.

5. What is the difference between PMF and PDF?

o PMF (Probability Mass Function): For discrete variables.

o PDF (Probability Density Function): For continuous variables.

6. Explain the Normal Distribution and its properties.

o Bell-shaped, symmetric about mean, area under curve = 1.

7. What is hypothesis testing? Explain with a real-world example.

o Testing a claim. Example: Testing if a new drug is more effective than existing one.

8. Differentiate between Type I and Type II errors.

o Type I: Rejecting a true null hypothesis.

o Type II: Failing to reject a false null hypothesis.

9. What is a p-value? How is it interpreted?

o Probability of getting observed results assuming H₀ is true. p < 0.05 often leads to
rejecting H₀.

10. When would you use a t-test vs a z-test?

o t-test: Small sample size, unknown population SD.

o z-test: Large sample size, known population SD.

o Population: Entire group.

o Sample: Subset of the population.

12. Explain the Central Limit Theorem and its implications.

o The sampling distribution of the sample mean approaches normality as sample size
increases.

13. What are confidence intervals? How are they useful?

o Range of values likely to include population parameter.

14. What is statistical inference?

o Drawing conclusions about a population based on a sample.

15. Explain conditional probability with an example.

o Probability of event A given B has occurred.

16. What is Bayes’ theorem? State its formula.

o [ P(A|B) = \frac{P(B|A)P(A)}{P(B)} \ ]

17. What are sampling distributions?

o Distribution of a statistic across many samples.

18. What is the role of linear algebra in statistics?

o Used in multivariate analysis, PCA, regression models.

Unit 2: Statistical Modelling

1. What is the difference between simple and multiple linear regression?

o Simple: One independent variable. Multiple: More than one.

2. Explain the assumptions of the linear regression model.

o Linearity, independence, homoscedasticity, normality, no multicollinearity.

3. What does R-squared indicate?

o Proportion of variance explained by the model.

4. Define and interpret regression coefficients.

o Show change in dependent variable for one unit change in predictor.

5. Explain the ANOVA test and its uses.

o Tests for significant differences between group means.

6. What is the Gauss-Markov theorem?

7. What does BLUE mean in the context of linear regression?

o Best Linear Unbiased Estimator.

8. Explain the concept of least squares geometrically.

o Minimizes the perpendicular distance between observed and predicted values.

9. What are orthogonal projections in linear models?

o Projections of data onto column space of X to estimate coefficients.

10. How do you identify multicollinearity in regression models?

o High VIF values, strong correlations between predictors.

11. What is residual analysis?

o Checks assumptions of model by analyzing residuals.

12. Explain influence diagnostics like Cook’s distance.

o Measures influence of individual data points on model.

13. What is the purpose of data transformation?

o To stabilize variance, make data normal, improve model fit.

14. How does the Box-Cox transformation work?

o Applies power transformation to normalize data.

15. Describe strategies for model selection.

o Stepwise, forward, backward selection; based on AIC/BIC.

16. What is AIC and BIC?

o Criteria for model selection; penalize model complexity.

17. Explain logistic regression. Where is it used?

o Predicts binary outcomes. Used in classification problems.

18. Explain Poisson regression and give a use case.

o For modeling count data. Used in call center modeling.

Unit 3: Mathematical Concepts in Data Analytics

1. What is an open set? Provide an example.

o Every point has a neighborhood within the set. Example: (0,1).

2. What is a closed set? Provide an example.

o Contains all its limit points. Example: [0,1].

o Every open cover has a finite subcover.

4. State and explain the Heine-Borel theorem.

o In ℝⁿ, compact ⇔ closed and bounded.

5. Define a metric space. Give an example in R^n.

o Set with a metric. Example: Euclidean space with d(x,y).

6. What are the properties of a metric?

o Non-negativity, identity, symmetry, triangle inequality.

7. Define a Cauchy sequence. Give an example.

o Terms get arbitrarily close. Example: 1/n in ℝ.

8. What does completeness of a metric space mean?

o Every Cauchy sequence converges in the space.

9. How is compactness different from completeness?

o Compact: All sequences have convergent subsequence. Complete: All Cauchy

10. What is connectedness in a topological space?

o Cannot be split into two disjoint open sets.

11. Use Cauchy sequence to explain convergence.

o If sequence is Cauchy and space is complete → sequence converges.

12. Provide a real-world example where compactness is important.

o Optimization problems—ensures existence of maxima/minima.

Unit 4: Advanced Linear Algebra Concepts

1. Define a vector space. What are its axioms?

o A set with operations satisfying 8 axioms (closure, associativity, identity, inverse,

2. What is a subspace? Give an example.

o Subset that is also a vector space. Example: Plane through origin in ℝ³.

3. Explain linear independence with an example.

o No vector in set is linear combination of others. Example: (1,0), (0,1).

4. Define basis and dimension of a vector space.

o Basis: Linearly independent spanning set. Dimension: Number of basis vectors.

o Check linear independence and spanning.

6. What are eigenvalues and eigenvectors?

o Ax = λx. λ is eigenvalue, x is eigenvector.

7. How do you compute eigenvalues of a matrix?

o Solve det(A - λI) = 0.

8. What is the spectral theorem?

o Real symmetric matrices can be diagonalized; eigenvectors are orthogonal.

9. Explain the importance of eigenvectors in PCA.

o Principal components are eigenvectors of covariance matrix.

10. What is diagonalization of a matrix?

o A = PDP⁻¹, where D is diagonal matrix of eigenvalues.

11. Provide a real-world application of eigenvectors.

o Face recognition, vibration analysis.

12. How do eigenvectors relate to transformation in space?

o They define invariant directions under linear transformation.