Here are the enhanced explanations for the 5-mark questions with more detail:

1. Compare Poisson distribution and binomial distribution.

• Poisson Distribution:
• Used to model the number of events in a fixed interval of time or space (e.g., number of customer
arrivals per hour at a store).
• Assumes events occur independently and at a constant average rate.
• Example: Predicting the number of calls received at a call center in an hour.
• Binomial Distribution:
• Describes the number of successes in a fixed number of independent trials, where each trial has
two outcomes (success or failure).
• Example: Tossing a coin 10 times and counting the number of heads.
2. Describe the test procedure for testing the significance of the correlation coefficient.
• Steps:
1. Hypotheses:
• Null Hypothesis (H₀): There is no correlation (ρ = 0).
• Alternate Hypothesis (H₁): There is a significant correlation (ρ ≠ 0).
2. Calculate the Test Statistic: Use the formula , where  is the sample correlation coefficient and
 is the sample size.
3. Decision Making:
• Compare the t-value with the critical value or use the p-value approach.
• If the p-value is less than 0.05, reject H₀ and conclude that the correlation is significant.
3. Explain Z-test of hypothesis testing.
• The Z-test is used to test whether the sample mean is significantly different from the population
mean.
• Conditions for Z-Test:
• Large sample size (n > 30).
• Population variance or standard deviation is known.
• Steps:
1. Compute the Z-value: .
2. Find the p-value from the Z-table.
3. Compare the p-value with the significance level (e.g., 0.05).
4. Explain T-test of hypothesis testing in R.
• The T-test evaluates whether two group means are statistically different.
• Types of T-tests:
1. One-sample T-test: Compares the mean of a group to a known value.
2. Two-sample T-test: Compares means of two independent groups.
3. Paired T-test: Compares means of two related groups (e.g., before and after treatment).
• Example in R:
[Link](x, y, alternative = "[Link]")

Here, x and y are two datasets. The output includes the p-value and confidence intervals to decide if means differ
significantly.
5. Define probability. Explain any two functions of probability distribution.
• Probability:
The likelihood of an event occurring, ranging from 0 (impossible) to 1 (certain).
• Example: Rolling a 4 on a six-sided die has a probability of .
• Functions in R:
1. dbinom():
Calculates the probability of exactly k successes in a binomial experiment.
• Example:
dbinom(3, size = 10, prob = 0.5) # Probability of 3 successes in 10 trials with p = 0.5
2. pnorm():
Calculates cumulative probability for the normal distribution.
• Example:
pnorm(1.96, mean = 0, sd = 1) # Cumulative probability up to z = 1.96
6. What is linear regression? Differentiate between linear and multiple regression.
• Linear Regression:
Examines the relationship between a dependent variable (Y) and an independent variable (X). The aim is to predict
Y based on X.
• Example: Predicting house prices based on size.
• Difference:
• Linear Regression: Uses one independent variable.
• Example: Sales predicted based on advertisement spending.
• Multiple Regression: Uses two or more independent variables.
• Example: Sales predicted based on advertisement spending, pricing, and customer ratings.

7. Describe the test procedure for testing the significance of the correlation coefficient.
(Similar to Question 2—see above for details.)
8. Explain the linear discriminant analysis (LDA) model.
• Linear Discriminant Analysis (LDA):
• A classification technique that separates two or more classes by finding the line (or hyperplane)
that maximizes the separation.
• Assumption: The data for each class is normally distributed.
• Application: Commo…
Here is an in-depth explanation of the 10-mark questions:
1. Consider the employee salary database and perform all types of descriptive analysis.
Descriptive analysis involves summarizing and organizing data to make it easy to understand. For an employee salary
database, the analysis would include the following:
• Mean: The average salary provides a central tendency.
• Median: The middle salary value helps handle skewed data.
• Mode: Most frequently occurring salary, useful for understanding salary clusters.
• Range: Difference between the highest and lowest salary.
• Standard Deviation (SD): Indicates how salaries are spread around the mean.
• Skewness and Kurtosis:
• Skewness shows asymmetry in salary distribution (e.g., skewed right if a few high salaries are
pulling the average).
• Kurtosis shows the “tailedness” or concentration of salaries.
• Quartiles: Divide salaries into four equal parts (Q1, Q2, Q3) to analyze salary percentiles.
Applications: This analysis helps identify pay disparities, trends, or the need for employee compensation
adjustments.
2. Explain multiple regression with its two applications.
• Multiple Regression: A statistical technique to predict a dependent variable (Y) based on two or
more independent variables (X₁, X₂, …). It extends simple regression by considering multiple factors affecting the
target variable.
• Example: Predicting house prices based on square footage, number of bedrooms, and location.
Assumptions:
1. The relationship between dependent and independent variables is linear.
2. No multicollinearity (independent variables should not be highly correlated).
3. Residuals are normally distributed.
4. Homoscedasticity (constant variance of residuals).
Applications:
1. Marketing: Predicting sales based on advertising spend, price, and promotional offers.
2. HR: Analyzing employee performance based on training hours, experience, and education.
3. Examine ANOVA in R. State assumptions and explain one-way ANOVA in detail.
• ANOVA (Analysis of Variance): Compares means of three or more groups to determine if they are
significantly different.
• Example: Testing if three marketing campaigns generate different average sales.
Assumptions of ANOVA:
1. Groups are independent.
2. Data in each group follows a normal distribution.
3. Homogeneity of variance (equal variances across groups).

One-Way ANOVA:
Used when there is one independent variable with multiple groups.
• Example: Analyzing the effect of different fertilizers (Fertilizer A, B, C) on crop yield.
1. Null Hypothesis (H₀): All group means are equal.
2. Alternate Hypothesis (H₁): At least one group mean is different.
3. F-Statistic: Compares the variability between groups to within groups.
4. P-value: If < 0.05, reject H₀, indicating significant differences among groups.
Benefits: Identifies which interventions (e.g., campaigns, treatments) work best without requiring multiple
pairwise comparisons.
5. Describe the procedure of one-way ANOVA with an example.
(Refer to Question 3 above for details on One-Way ANOVA.)
6. Discuss the Normal Distribution and its applications in statistical analysis.
• Normal Distribution: A bell-shaped curve where most data points cluster around the mean. It is
symmetric, with equal probabilities on both sides of the mean.
• Characteristics:
1. Mean = Median = Mode.
2. About 68% of data lies within ±1 standard deviation, 95% within ±2, and 99.7% within ±3.
Applications:
1. Quality Control: Analyzing defects in a manufacturing process to identify if products are within
acceptable ranges.
2. Finance: Modeling stock market returns or investment risks.
3. Education: Evaluating test scores to identify outliers or student performance.
7. What is ANOVA in R? Explain one-way ANOVA and state its limitations.
(See Question 3 for details on ANOVA and One-Way ANOVA.)
Limitations:
1. Assumes equal variance and normality, which might not hold for all data.
2. Only tests if at least one group differs but doesn’t indicate which groups differ (requires post-hoc
testing).
3. Sensitive to outliers, which can distort results.

8. How to perform step-by-step logistic regression?

• Logistic Regression: Predicts categorical outcomes (e.g., Yes/No) based on independent variables.
• Steps:
1. Define the dependent variable (e.g., purchase decision: 1 for yes, 0 for no).
2. Identify independent variables (e.g., age, income).
3. Fit the logistic regression model.
4. Interpret coefficients: A positive coefficient increases the likelihood of the outcome.
5. Use the model for predictions (e.g., classify a new customer as a buyer or non-buyer).
Real-Life Example: Predicting loan approval based on applicant features (income, credit score, employment status).
9. Describe factor analysis. What are the types and examples?
• Factor Analysis: Reduces many variables into fewer factors based on their correlation.
Types:
1. Exploratory Factor Analysis (EFA): Identifies hidden structures in the data.
• Example: Grouping survey responses into themes like “customer satisfaction” and “product
quality.”
2. Confirmatory Factor Analysis (CFA): Tests a pre-defined structure based on hypotheses.
• Example: Validating if test questions measure specific skills (e.g., reading comprehension).
Applications:
1. Marketing: Reducing customer attributes into factors like “loyalty” and “price sensitivity.”
2. HR: Identifying key traits in employee performance reviews.
10. Write down the step-by-step procedure for building a linear regression model.
• Steps:
1. Define the Problem: Identify dependent (Y) and independent (X) variables.
2. Explore Data: Check for missing values, outliers, and correlations between variables.
3. Split Data: Divide into training and testing sets (e.g., 80%-20%).
4. Fit the Model: Use the training set to find the line that best fits the data (minimizing errors).
5. Evaluate the Model: Check metrics like R², Mean Squared Error (MSE), and residual plots.
6. Make Predictions: Apply the model to the testing set or new data.
Example: Predicting house prices based on square footage and location.
11. Describe descriptive analysis in R. Explain any three functions of descriptive analysis.
• Descriptive Analysis: Summarizes data characteristics like central tendency, dispersion, and
distribution.
Functions:
1. Summary(): Provides statistics like mean, median, and quartiles.
2. Table(): Creates frequency tables for categorical variables.
3. Quantile(): Computes percentiles (e.g., Q1, Q3).
12. Explain the concept of time series analysis. State any four types with examples.
• Time Series Analysis: Analyzes data points collected over time (e.g., monthly sales, daily stock
prices).
Types:
1. Trend Analysis: Long-term increase or decrease (e.g., rising housing prices).
2. Seasonal Analysis: Regular patterns over time (e.g., ice cream sales peak in summer).
3. Cyclic Analysis: Fluctuations without fixed periodicity (e.g., economic cycles).
4. Stationary Analysis: Removing trends to analyze consistent patterns (e.g., ARIMA models).
Principal Component Analysis (PCA)
Definition:
PCA is a dimensionality reduction technique that identifies new uncorrelated variables (principal components) from
the original features, capturing maximum variance in fewer components.
Applications:
1. Image Compression: Reduces pixel data while retaining essential image features.
2. Customer Segmentation: Simplifies customer data to key traits for better marketing strategies.
3. Finance: Simplifies stock data to identify major trends or market factors.

Limitations:
1. Loss of Interpretability: Principal components are linear combinations, making them hard to
interpret.
2. Linear Assumption: Assumes the relationships between features are linear.
3. Sensitive to Scaling: Requires standardized data to perform effectively.
4. Information Loss: Some data variance is inevitably lost in the process.
Linear Discriminant Analysis (LDA)
Definition:
LDA is a supervised machine learning method that reduces dimensions while focusing on class separation. It
maximizes the distance between different classes in the data.
Applications:
1. Fraud Detection: Helps classify transactions as fraudulent or legitimate.
2. Medical Diagnosis: Differentiates patients based on disease characteristics.
3. Face Recognition: Separates features to improve identification accuracy.
Limitations:
1. Assumes Gaussian Distribution: Works best when data follows a normal distribution.
2. Overfitting Risk: May not generalize well with small datasets.
3. Linear Separability: Performs poorly if the classes are not linearly separable.
4. Class Imbalance: Struggles when one class dominates the dataset.