Week 1

1.1. Introduction to Statistics in Business Management

Studying statistics plays a critical role in business management, providing a robust framework
for decision-making in a volatile, uncertain, complex, and ambiguous (VUCA) business
environment. This module is designed to explain why statistics is essential for businesses and
demonstrate how it contributes to informed decision-making.

Business statistics is a dynamic field with a profound impact on business profitability. By relying
on statistical methods, businesses can make decisions based on facts rather than intuition or
guesswork. Here are some core reasons why business statistics is both exciting and interesting:

Exciting: Business statistics has a direct impact on profitability, as it helps businesses make
data-driven decisions.

Interesting: The methodologies used in statistics are ingenious, providing a systematic

framework for understanding complex phenomena, making predictions, testing hypotheses, and
making informed business decisions.

Many students approach statistics with anxiety due to its mathematical nature. Additionally,
skepticism may arise regarding the relevance of theoretical approaches to practical managerial
problems. To alleviate these concerns, this course emphasizes practical applications while
de-emphasizing complex mathematics, creating a comfortable environment for learning.

1.2. Statistics in Business Management

Business statistics applies statistical methods to managerial decision-making. This involves:

Data Collection: Gathering raw data relevant to business problems. For example, a retail
business collects sales data from various locations.

Data Organization: Structuring data to make it easier to analyze. This could involve sorting sales
data by product, location, or time period.

Data Analysis: Applying statistical techniques to extract insights. For example, analyzing sales
data to identify trends or patterns in customer behavior.

Data Interpretation: Making sense of the analysis results. This might include interpreting a
correlation between product sales and promotional campaigns.

Decision-Making: Using statistical insights to guide business decisions. For instance, deciding to
increase production for high-demand products based on sales data analysis.
1.3. The Paradigms of Business Statistics

The course also introduces three key paradigms:

Statistics: A branch of mathematics focusing on data collection, organization, analysis, and

interpretation. For example, summarizing sales data with descriptive statistics or testing
hypotheses to understand customer preferences.

Data Science: A broader field that combines statistics with computer science to extract insights
from large datasets. Data science techniques are used in business analytics to process and analyze
big data.

Business Analytics: The application of data science and statistics to business problems. It often
involves using software tools to analyze business data and make informed decisions.

1.4. Business Statistics Operationalized

Here's how business statistics is operationalized in a business context:

-Data: Raw information collected from various sources. An example is customer transaction
records.

Information: Data that has been organized and processed to be meaningful. For example, a report
showing monthly sales figures.

Inference: Drawing conclusions from information. For example, inferring that a product
promotion led to increased sales.

Decision-Making: Using inferences to make business decisions. An example is deciding to

allocate more budget to marketing based on sales trends.

Data Information Inferences Decision-making

To conclude, understanding business statistics is critical for effective decision-making in

business management. By mastering the concepts and techniques in this course, you can become
a skilled or a proficient statistics practitioner, capable of applying statistical methods to solve
real-world business problems.

1.5. Branches of Statistics

i) Descriptive Statistics

ii) Inferential Statistic

iii) Predictive Statistics

 iv) Classification and Segmentation

v) Probability

1.5.1. Descriptive Statistics

Descriptive statistics are used to summarize and present data in an easily understandable way. It
includes organizing, summarizing, and graphically presenting data. Here are detailed examples:

 Charts, Graphs, and Tables

o Bar Chart: To represent the frequency of categorical data. For example, a bar chart
showing the number of employees in different departments in a company.

o Pie Chart: To represent proportions within a whole. For example, a pie chart
showing the distribution of sales across different product categories.

o Histogram: To depict the distribution of a continuous variable. For example, a

histogram displaying the distribution of ages among employees.

 Measures of Central Tendency:

o Mean: The average of a set of numbers. For example, the mean salary of
employees in a company.

o Median: The middle value when data is sorted. For example, the median score on
a test in a classroom.

o Mode: The most frequently occurring value in a dataset. For example, the mode
for the most common product size sold in a store.

 Measures of Dispersion:

o Range: The difference between the highest and lowest values. For example, the
range of ages among employees.

o Standard Deviation: A measure of data spread. For example, a higher standard

deviation in customer satisfaction scores might indicate varied experiences among
customers.

1.5.2. Inferential Statistics

Inferential statistics allow us to draw conclusions about a population based on sample data. Here
are detailed examples:

 Estimating Population Parameters:

o Election Polls: Using a sample of voters to estimate the preferences of the entire
electorate.

o Product Quality Testing: Testing a sample of products to infer the quality of a

production batch.

o Hypothesis Testing:

 T-Tests: To compare means between groups. For example, a t-test to

compare average sales before and after a marketing campaign.

 Chi-Square Tests: To test the association between categorical variables.

For example, checking if there's a relationship between gender and
product preference.

1.5.3. Predictive Methods

Predictive methods are used to forecast future outcomes based on historical data. Here's an
explanation with examples:

 Regression Analysis:

o Linear Regression: To predict a continuous outcome based on one or more

predictors. For example, predicting future sales based on past trends and
advertising spend.

o Logistic Regression: To predict categorical outcomes. For example, predicting

customer churn based on usage patterns.

o Time Series Forecasting:

 ARIMA Models: To forecast trends over time. For example, forecasting

monthly sales for the next year based on previous sales data.

 Seasonal Decomposition: Analyzing trends, seasonal patterns, and

irregularities. For example, identifying seasonal patterns in electricity
usage.
1.5.4. Classification and Segmentation

Classification methods are used to categorize data into predefined classes, while segmentation is
used to group data into distinct segments based on similarities. Here are examples for each:

 Classification:

o Supervised Learning: Algorithms learn from labeled data to predict the class of
new data points. For example, a machine learning model to classify emails as
spam or not spam.

o Decision Trees: A model to classify data based on a series of binary decisions. For
example, a decision tree to determine if a customer should receive a promotional
discount based on their purchasing history.

 Segmentation:

o Unsupervised Learning: Algorithms group data without prior labels. For example,
clustering customers into segments based on purchasing behavior.

o K-Means Clustering: A popular technique for segmentation. For example,

dividing a customer base into segments with similar shopping habits.

o Hierarchical Clustering: A method to build a tree-like structure for data. For

example, creating a hierarchy of products based on similarities in attributes.

1.5.5. Probability

Probability is a fundamental concept in mathematics and statistics, representing the measure of

the likelihood that a specific event will occur. In simpler terms, it's a way to quantify uncertainty
and make predictions about the occurrence of various events.

These are just a few examples of the many applications of the different branches of statistics.
Depending on the context and data available, data analysts choose appropriate techniques to
solve business problems, analyze trends, or make predictions.

However, the emphasis in this course will be descriptive statistics, inferential statistics,
predictive statistics and probability.

1.6. Business Statistics defined

In business management, understanding the types of data is crucial for making informed
decisions. Data serves as the foundation for analysis, interpretation, and decision-making.
Key concepts in business statistics: Below are key concepts and examples to illustrate the
importance of data in business.

 Data: Facts and figures collected for analysis and interpretation. Example: Employee
salary data, collected for compensation analysis.

 Data Set: All the data collected in a specific study or analysis. Example: Data collected
from employees, including age, grade, gender, and salary. Collection of data is data set.

 Data Point: A single observation within a data set. Example: The salary of one employee
or the gender of a specific customer.

 Features, Variables, or Factors: These are the entities or characteristics on which data are
collected. Example: In a business context, features could be sales figures, customer
demographics, or product details.

 Population: The entire group of items or individuals of interest. Example: All customers
of a retail chain.

 Sample: A subset of the population, used to make inferences about the larger group.
Example: A sample of 1,000 customers from a database of 10,000 to study purchasing
trends.

1.7. Types of Data

Statistics is an offshoot of mathematics that deal with data that are quantitative in nature.

Data in business management can be broadly categorized into different types. Understanding
these types is crucial for accurate analysis and reporting.

Personal Data: Information specific to an individual, including demographics, location, email,

etc. Companies use personal data to customize marketing and improve customer experience.
Example: Customer email addresses collected during online purchases.

Companies often collect personal data for marketing purposes. For example, social media
platforms like Facebook and Twitter collect personal data to create targeted ads.

Transactional Data: Data generated from transactions or user interactions. This includes data on
purchases, website visits, ad clicks, etc. Example: The number of times a product is purchased in
a day, used for inventory management. Businesses use transactional data to understand customer
behavior and track sales performance. For example, analyzing website clicks to determine which
products are most popular.
Web Data: Data collected from the internet, not necessarily generated by the company. This
can include public information from websites, social media, etc. Example: Collecting data from
online reviews to assess customer sentiment. Web data is valuable for competitive analysis and
market research. For example, tracking mentions of a company's products on social media to
gauge brand perception.

Personal or transactional or web data may be categorical and numeric in nature. This means
personal or transaction or web data could be either categorical or numeric data

Categorical Data: Categorical data is non-numeric and represents categories or labels. Business
management often uses categorical data for segmenting customers, classifying products, and
more.

Examples of Categorical Data: Gender, used to understand customer demographics. Product

categories used to organize inventory. customer loyalty levels used to segment customers for
targeted marketing.

 Encoding Categorical Data: Although categorical data is not numerical, it can be

encoded with numbers for analysis and making it compatible for the application of
statistical analysis. Remember, statistics is an offshoot of mathematics and hence,
numbers are used with statistical methods. Hence, categorical data that are textual in
nature are number-coded. For example, Assigning "1" to male and "2" to female in a
customer demographic study.

Numerical Data

Numerical data represents quantifiable information and can be discrete or continuous. Businesses
rely on numerical data for calculations, comparisons, and trend analysis. Even at the collection
stage, they are collected as numbers.

 Discrete Data: Arises from a process of counting, with countable distinct values.
Example: The number of units sold in a month or the number of employees in a
department.

Business applications include tracking inventory, calculating employee headcount, or

assessing production output.

 Continuous Data: Arises from a process of measuring, with infinitely uncountable

values within an interval. Example: The height of employees, the weight of products, or
the revenue generated each quarter.

Continuous data is often used in quality control, financial analysis, and performance
tracking.
1.8. Using Data for Business Decisions

In business management, properly organized data helps decision-makers extract reliable

information for intelligent decision-making. The ability to transform raw data into actionable
insights is a critical skill.

Data Visualization: Charts and graphs help business managers visualize data trends and
patterns. Example: A line graph to show revenue growth over time, aiding strategic planning.
Bar charts and pie charts are used to summarize categorical data, while histograms and scatter
plots are used for numerical data.

Data Analysis: Businesses use data analysis techniques to uncover insights and trends.
Example: Using regression analysis to identify relationships between marketing spend and sales.

Data analysis allows businesses to make evidence-based decisions, reducing guesswork and
improving outcomes.

To conclude, understanding the types of data and their applications in business management is
essential for effective decision-making. By categorizing, visualizing, and analyzing data,
business leaders can gain valuable insights that drive success and competitiveness in the market.
1.9. Descriptive Statistics

Descriptive statistics focus on organizing, summarizing, and presenting data in a convenient and
informative way. This involves various techniques to make raw data more accessible and
interpretable. Let's explore some methods and business management examples to illustrate the
importance of organizing data effectively.

Data Arrays: A data array arranges values in ascending or descending order, providing a simple
way to organize data. This method helps identify the lowest and highest values, recognize
repetition, and observe distances between successive data points. In business, data arrays are
useful for understanding distributions and spotting trends.

Example: A retail business collects data on daily sales for 30 days. By creating a data array in
ascending order, the business can easily identify the lowest and highest sales days. This
organization allows for quick insights, such as identifying the best sales days for promotions.

Problem 1

Transmission Fix-It stores recorded the number of service tickets submitted by each of the 20
stores last month as follows:

823 648 321 634 752 669 427 555 904 586

722 360 468 847 641 217 588 349 308 766

The company believes that a store cannot really hope to break even financially with fewer than
475 service actions a month. It is also company policy to give a financial bonus to any store
manager who generates more than 725 service actions a month.

(Source: Levin, R.I., Rubin, D,S., Rastogi, S., Siddiqui, M,H. (2013). Statistics for Management.
7th edn. Pearson: India)

Solution

To construct the data array, organise the data In ascending order as follows

217 308 321 349 360 427 468 555 586 588
634 641 648 669 722 752 766 823 847 904

Count the number of stores that doesn‟t generate 475 service action. It is seen that 7 stores
don‟t generate 475 service action and hence, 7 stores don‟t not breaking even.

Similarly, count the number of store managers that generate more than 725 service actions. It is
seen from the table that 5 store managers generate more than 725 service actions. Hence, 5
store managers are eligible for bonus.

Frequency distribution

Few terminologies related to frequency need to be understand before we step into construction of
frequency distribution table

Frequency count involves counting the number of times a specific value or category is repeated
in a dataset. This technique helps gauge how common or rare a particular observation is.

Example: An e-commerce company counts the frequency of returns for different product
categories. This count helps identify which products have higher return rates, guiding quality
control and customer service efforts.

A frequency distribution summarizes how often each value or category appears in a dataset. It
can be used to create various types of charts and graphs to visualize data trends.

Example: A clothing store creates a frequency distribution of shirt sizes sold in a month. The
data show counts for each size: Small (30), Medium (50), Large (70), Extra Large (40). This
distribution helps the store optimize inventory by ordering more popular sizes.

Absolute Frequency is the straightforward count of occurrences of specific values or categories.

Example: A restaurant records the absolute frequency of dishes ordered in a week. If "Spaghetti
Carbonara" is ordered 120 times, the absolute frequency for that dish is 120. This data can
inform menu planning and help determine which dishes to promote.

Relative Frequency represents the proportion or fraction of the total number of observations that
belong to a specific class. This is useful for comparing frequencies across different categories or
data sets.

Example: A survey asks customers to rate their experience with customer service on a scale from
1 to 5, with 200 responses. If 60 people rate it 5, the relative frequency for a 5 rating is (60 /200
= 0.30, or in percentage 30%). This information helps the business understand customer
satisfaction and identify areas for improvement.
Cumulative Relative Frequency is the accumulation of relative frequencies, showing the
proportion of observations less than or equal to a specific value.

Example: A car dealership has a database of 1,000 customer records. To find the cumulative
relative frequency of customers with incomes of $60,000 or less, the dealership calculates the
relative frequencies for income brackets up to $60,000 and then sums them. If the relative
frequencies are 0.10, 0.15, and 0.25, the cumulative relative frequency is (0.10 + 0.15 + 0.25 =
0.50 in proportions or fractions, or 50% in percentages).

Constructing a Frequency Distribution table

A frequency distribution organizes data into classes or groups of values, describing a

characteristic of the data. This is useful for identifying trends and patterns within a dataset.

Example: A manufacturing company collects data on the number of defects in products across
different production runs. Constructing a frequency distribution helps identify runs with higher
defect rates, guiding quality control efforts.

Constructing a frequency distribution involves several steps:

1. Determine Class Intervals: Decide the number of classes and their width.

Sturges' rule suggests 1 + 3.3log(n), where „n‟ is the sample size.

2. Sort Data into Classes: Assign data points to their respective classes based on their value.

3. Count Frequencies in Each Class: Tally the number of data points in each class.

Example: A software development company records the time taken to resolve customer issues.
To construct a frequency distribution, they might use class intervals of 1.0 hour, sorting the data
into these intervals and counting the frequency in each class. If the distribution shows a
significant number of issues taking over 6 hours to resolve, it indicates a performance problem
that needs attention.

Inclusive and Exclusive Classification

Classification methods determine how class intervals are defined:

Inclusive Classification: Both the lower and upper values of the class interval are included in the
same class.

Exclusive Classification: The upper value of the class interval is included in the next class, where
it becomes the lower value.

Problem 2
(Source: Levin, R.I., Rubin, D,S., Rastogi, S., Siddiqui, M,H. (2013). Statistics for Management.
7th edn. Pearson: India)

The number of hours taken by transmission mechanics to remove , repair and replace
transmissions in one of the Transmission Fix-It stores one day last week is recorded as follows:

4.3 2.7 3.8 2.2 3.4 3.1 4.5 2.6 5.5 3.2

6.6 2 4.4 2.1 3.3 6.3 6.7 5.9 4.3 3.7

Construct a frequency distribution with intervals of 1.0 hour from these data. What
conclusions can you reach from the productivity of mechanics from this distribution? If the
company believes that more than 6.0 hours is evidence of unsatisfactory performance, does it
have a major or minor problem with performance in this particular store?

Exclusive way of classification

Class 2.0 - 3.0 3.0 – 4.0 4:0 – 5.0 5.0·- 6.0 6.0 – 7.0

Frequency 5 6 4 2 3

Inclusive way of classification

Class 2.0 – 2.9 3.0 – 3.9 4:0 – 4.9 5.0·- 5.9 6.0 – 6.9

Frequency 5 6 4 2 3

Almost all of the jobs are done in under six hours, and fully 75% of them are done in five hours
or less. Since 15% take more than 6.0 hours, there is a minor productivity problem here that
merits some attention.

Exclusive way of classification is a method where the upper limit value of a class interval is
fixed in the next class interval where it is the lower limit value

Inclusive way of classification the upper limit as well as the lower limit values are included in
the same class interval

In summary, descriptive statistics play a critical role in organizing data for business analysis.
Properly structured data allows businesses to gain insights, make informed decisions, and
address issues effectively.
Problem 3

(Source: Levin, R.I., Rubin, D,S., Rastogi, S., Siddiqui, M,H. (2013). Statistics for Management.
7th edn. Pearson: India)

Sarah Anne Rapp, the president of Baggit, Inc., has just obtained some raw data from a
marketing survey that her company recently conducted. The survey was taken to determine the
effectiveness of the new company slogan, “When you‟ve given up on the rest, Baggit!” To
determine the effect of the slogan on the sales of Luncheon Baggits, 20 people were asked how
many boxes of Luncheon Baggits per month they bought before and after the slogan was used in
the advertising campaign. The results were as follows:

Before 4 4 1 3 5 2 6 6 5 3 5 2 6 8 3 8 1 4 5 2
After 3 6 5 7 5 1 9 7 8 6 6 7 8 4 5 10 3 3 7 2

a) Create both frequency and relative frequency distributions for the “Before” responses
using as classes 1-2, 3-4, 5-6, 7-8, 8-9 and 9-10

b) Work part (a) for the “After” responses

c) Give the most basic reason why it makes sense to use the same classes for both the
“before” and “after” responses

d) For each pair of “Before / After” responses, subtract the “Before” responses from the
“After” response to get the number that we will call “Change” (Example: 3-4 =-1), and
create frequency and relative frequency distributions for “Change” using classes -5 to -4,
-4 to -3, -2 to -1, -1 to 0, 1 to 2, 3-4, and 5-6

e) Based on your analysis, state whether the new slogan has helped sales, and give one or
two reasons to support your conclusion

Solution

a)

“Before” Frequency Relative Cumulative

Classes Frequencies relative
frequency
1 to 2 5 .25 25
3 to 4 6 .30 55
5 to 6 7 .35 90
7 to 8 2 .10 100
9 to 10 0 .05
20 1.00
 b)
“After” Classes Frequency Relative
Frequencies
1 to 2 2 .10
3 to 4 4 .20
5 to 6 6 .30
7 to 8 6 .30
9 to 10 2 .10
20 1.00

c) In order to be able to make comparisons of the frequency distributions

d)

“Change” Frequency Relative Cumulative

Classes Frequencies relative
frequencies
5 to 4 1 .05 5
3 to 2 0 .00 5
1 to 0 5 .25 30
1 to 2 8 .40 70
3 to 4 5 .25 95
5 to 6 1 .05 100
20 1.00

e) Sales appear to have increased, but the apparent increase could be due to other factors we
don't know about, so we can't say for sure that the new slogan has helped.

Problem 4

(Source: Levin, R.I., Rubin, D,S., Rastogi, S., Siddiqui, M,H. (2013). Statistics for Management.
7th edn. Pearson: India)

Here are the ages of 30 people who bought video recorders a Symphony Music Shop last week:

26 37 40 18 14 45 32 68 31 37
20 32 15 27 46 44 62 58 30 42
22 26 44 41 34 55 50 63 29 22

a) From looking at the data just as they are, what conclusions can you come to quickly
about Symphony‟s markst

b) Construct a 6-category closed classification. Does having this enable you to conclude
anything more about Symphony‟s market
a) It is hard to tell anything from the raw data.
b) Class 10-19 20-29 30-39 40-49 50-59 60-69
Frequency 3 7 7 7 3 3
Most video recorders are bought by people between 20 and 50, so marketing efforts
should be aimed at that age group.