Turn off your phones

Close the lid of your laptops

No eating during the class session
 Fundamentals of Data Analytics
MB8002 QUANTITATIVE METHODS IN MANAGEMENT

Ojelanki Ngwenyama
Global Management Studies
Basic Concepts of Quantitative Data Analysis
Different types of data
Rules for Variables and Constants
Rules for Measurement and Measures
The base ten numbering system
Powers of 10
Rounding and significant figures
Populations and Sampling
Rules for Statistical population
Rules for Statistical samples
Frequency Distributions and Percentiles
Different types of statistical procedures
Descriptive methods
Inferential methods
Basic Concepts of Quantitative Data Analysis
Rules for Variables (discrete and continuous)
Variable is a symbol that can assume a prescribed set of values
The set of values is called the domain of the variable
For example the variable x denotes students in MB8002
X can take on a value 0 to 60 (60 is maximum allowed)
This is a discrete variable because you cannot have parts of students such as 2.5 or
30.31 students
For example the variable y denotes the heights of students in MB8002
Y can take on values such as 48.25, 51.76, ..84.321 inches (and many other
possibilities
This is a continuous variable because students because there can be fractions of inches
Basic Concepts of Quantitative Data Analysis
Rules for Constants
Constants have only one value that does not change
For example:
The boiling point of water is 100C at normal temperature and pressure (NTP)
The Constant is an important concept in statistical analysis
In regression analysis it is where the line crosses the Y axis
Regression eqn. Y = mX + c (other forms: Y = a0 + a1X)
where c and m (a0 and a1 ) are the constants
m is the contribution of X to Y
Basic Concepts of Quantitative Data Analysis
Rules of Measurement
In statistical analysis all data are collected by measuring variables
Measurement is the use of a rule to assign a value to a specific
observation of a variable
For example:
On a scale of 0 to 9 indicate how much you like statistics?
Where 0 is not at all, and 9 is very much.
Validity of measurement concerns how well the rule measures the
variable under consideration than some other variable
Reliability of measurement concerns how consistent the rule is in
applying the same value for the same observation
Basic Concepts of Quantitative Data Analysis
Rules of Measures
Categorical measures (categorical variables) Nominal Scales
Observations of the same type is given the same number
Gender categories: 1= male, 2=female;
Customer value categories: 1=high, 2= medium, 3= low.
Ordinal or rank measures (ordinal or rank variables) Ordinal Scales
Observations are ordered/ranked according to magnitude
Students ranked: 1= least cooperative, 5=most cooperative
Interval equality Interval Scales
The difference between a score 1 and 2, and 4 and 5, on the cooperative scale is
always 1
Ratios Ratio Scales
Observations in relation to other observations, John is twice as tall as Mary
Basic Concepts of Quantitative Data Analysis
Powers of 10
Examples: 101= 10; 102 = 10 x 10 = 100; .. 108 1 and eight 0s
Examples: 10-1 = 1; 10-2 = .01; 10-5 = decimal point four 0s and 1
Rounding and significant figures
Example of rounding to 2 decimal places
72.157 = 72.16; 638.225 = 638.23;
72.153 = 72.15; 638.224 = 638.22;
Example of rounding to 5 decimal places
3847.256873 = 3847.25687
3847.256879 = 3847.25688
Basic Concepts of Quantitative Data Analysis
Statistical population
A statistical population is a collection (or set) of measurements of variables that
share common characteristics
Example: The set of GMAT scores for students in MB8002
Statistical populations do not consist of people
Statistical sample
A statistical sample is a subset of the scores of the statistical population
Example: A subset of the GMAT scores of the MB8002 students
A random sample is a subset of the scores of the statistical population such
that each score in the statistical population such has an equal chance of being
selected
Basic Concepts of Quantitative Data Analysis
Descriptive Statistical Methods
Used to summarize and characterize the data in samples or populations
Mean of the population or sample
Mode of the population or sample
Distribution of the population or sample
Inferential Statistical Methods
Used to make inferences about the population or sample
The likelihood that all MB8002 students will earn an A grade on the course
The likelihood that successfully completing MB8002 will lead to higher grade in MT8312
The likelihood that successfully completing MB8002 will lead to job in analytics
The likelihood that successfully completing MB8002 will lead to higher salary on
graduation
Basic Concepts of Quantitative Data Analysis
Frequency Distributions
Used to characterize data of samples and populations
Distribution of the population or sample
Inferential Statistical Methods
Used to make inferences about the population or sample
The likelihood that all MB8002 students will earn an A grade on the course
The likelihood that successfully completing MB8002 will lead to higher grade in MT8312
The likelihood that successfully completing MB8002 will lead to job in analytics
The likelihood that successfully completing MB8002 will lead to higher salary on
graduation
Basic Concepts of Quantitative Data Analysis
Basic Concepts of Descriptive Statistics
Measures of Central Tendency
Mean the average of the values of a set of observations (arithmetic and
geometric)
Use geometric mean when you have percentage data
Mode the most frequently observed value in the set of observations
Median the point at which half the observations fall to the right and left
Measures of Dispersion (Data Visualization)
Range distance between the largest and smallest values in the observations
Standard Deviation measure of how the observed values vary from the mean
Skewness & Kurtosis measures of the shape of the distribution of
observations
Basic Concepts of Quantitative Data Analysis
Basic Concepts of Descriptive Statistics
Applicability of Measures of Central Tendency (know when & where)

Data Type Measures of Central Tendency

Nominal, Categorical Mode
Ordinal Median and Mode
Interval Mean, Median and Mode
Ratio Mean, Median and Mode
Basic Concepts of Quantitative Data Analysis
Basic Concepts of Descriptive Statistics
Applicability of Measures of Dispersion (know when & where)

Data Type Measures of Dispersion

Nominal, Categorical none
Ordinal Range
Interval Standard Deviation and Range
Ratio Standard Deviation and Range
Basic Concepts of Quantitative Data Analysis
In-class experiment on applying the concepts to analyze data
The Problem To Be Analyzed:
In 2017 the Ted Rogers School of Management, Ryerson University launched
an MBA Specialization in Business Analytics. The director of the MBA program
Dr. Kim Bates is interested in finding out some information about the 2020
cohort of applicants, those admitted and those who accepted entry into our MBA
Analytics degree program.
The data currently available for this analysis is contained in an EXCEL data
sheet MB8002 In-Class-Experiment-Day-01
Dr. Bates asks a very simple question: Using these data what can you tell me
about the 2020 MBA class on Business Analytics?
The General Problem Solving Method of Data Analytics

Potential
Entry point Understand Your Breakdowns
Problem (questions and
data)

Reflect on what you did; Decide plan of attack &

Challenge your results Choose a method
(use counterfactual (Critical understanding the
analysis) conceptual foundations of method)

Apply method and concepts

systematically
Basic Concepts of Quantitative Data Analysis
Step 1: Understand The Problem:
What type of question is Dr. Bates asking?
Using these data what can you tell me about the 2020 MBA class on Business
Analytics? It is a descriptive question
What type of data do we have?
Interval and discrete
What are the appropriate descriptive analysis methods for these data?
Mean, Median, Mode and Standard Deviation
What exactly can I learn from the data by using these methods?
How do I apply the methods of analysis and interpret the results?
Basic Concepts of Quantitative Data Analysis
Step 1a: Differentiate between population and sample
Data: The set of GMAT scores for applicants, admitted and accepted to MBA
Analytics 2020
Which is the population and which is the sample?
Statistical population
A statistical population is a collection (or set) of measurements of variables that
share common characteristics
Statistical sample
A statistical sample is a subset of the scores of the statistical population
A random sample is a subset of the scores of the statistical population such
that each score in the statistical population has an equal chance of being
selected
Basic Concepts of Quantitative Data Analysis
Step 1 b: Data Validation
Satisfying Rules of Measurement
Are the data collected by measuring variables
Validity: Are GMAT scores valid measures
Reliability: Are GMAT scores consistently measured across the population