0% found this document useful (0 votes)
13 views2 pages

Advanced Business Analytics Assignment Answers

The document covers key concepts in advanced business analytics, including levels of measurement in data, characteristics of Big Data, and the importance of normalization. It explains nominal, ordinal, interval, and ratio scales, along with their analytical methods. Additionally, it discusses univariate and bivariate analysis, emphasizing their applications and significance in data preparation.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
13 views2 pages

Advanced Business Analytics Assignment Answers

The document covers key concepts in advanced business analytics, including levels of measurement in data, characteristics of Big Data, and the importance of normalization. It explains nominal, ordinal, interval, and ratio scales, along with their analytical methods. Additionally, it discusses univariate and bivariate analysis, emphasizing their applications and significance in data preparation.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Course Name: Advanced Business Analytics Using R &

Python

Home Assignment 1 - Answers

CO1

Question 1: Explain the levels of measurement in data and illustrate them with examples.
Answer:

1 1. Nominal scale: Categorical labels without intrinsic order (e.g., gender, product category). Analysis:
mode, contingency tables, chi-square tests.

2 2. Ordinal scale: Categories with a meaningful order but unknown distance between levels (e.g., customer
satisfaction: low/medium/high). Analysis: median, percentiles, non-parametric tests like Mann-Whitney.

3 3. Interval scale: Ordered numeric scales with equal intervals but no true zero (e.g., temperature in
Celsius). Analysis: mean, standard deviation, correlation, regression (with caution on ratios).

4 4. Ratio scale: Numeric with meaningful zero allowing ratios (e.g., income, weight). Analysis: all arithmetic
operations valid including geometric means and coefficient of variation.

Question 2: What is Big Data? Discuss its characteristics and relevance in business contexts.
Answer:

1 1. Definition: Big Data refers to datasets that are large, fast-moving, or complex such that traditional data
processing tools are inadequate. Big Data often requires distributed storage and parallel processing.

2 2. Key characteristics (the Vs): Volume (massive scale), Velocity (speed of generation and processing),
Variety (structured, unstructured, semi-structured), Veracity (uncertainty and quality), and Value
(extractable insights).

3 3. Business relevance: Enables improved customer segmentation, real-time analytics (fraud detection,
recommendation systems), operational optimization (IoT sensor data), and data-driven product innovation.
Discuss governance, privacy, and infrastructure considerations when deploying Big Data solutions.
CO2

Question 1: Write a short note on univariate and bivariate analysis with suitable examples.
Answer:

1 1. Univariate analysis: Examination of a single variable to summarize its distribution and central tendency
(e.g., mean, median, mode, variance). Example: Analyzing monthly sales distribution using histogram and
descriptive statistics.

2 2. Bivariate analysis: Analysis of relationship between two variables (e.g., scatterplot, correlation,
cross-tabulation). Example: Assessing relationship between advertising spend and sales using scatterplot
and Pearson correlation; for categorical pairs use chi-square tests.

Question 2: Explain normalization and its importance in preparing data.


Answer:

1 1. Normalization definition: Scaling numeric features to a common range (e.g., 0–1) or transforming to have
zero mean and unit variance (standardization).

2 2. Common methods: Min-max scaling: x' = (x - min) / (max - min); Standardization (Z-score): x' = (x - µ) / σ.

3 3. Importance: Improves numerical stability, helps gradient-based optimization converge faster, prevents
features with large scales from dominating distance-based models (k-NN, SVM, K-means), and ensures
meaningful regularization penalties.

You might also like