FORMAN CHRISTIAN COLLEGE (A CHARTERED UNIVERSITY)

1. INTRODUCTION TO BASIC CONCEPTS AND TERMINOLOGIES IN STATISTICS

1.1 Statistics
o A branch of mathematics in the past;
o The science of data;
o Deals with numbers;
o Definition: Statistics is the science of collecting, organizing, summarizing, and analyzing
information (/data) to draw conclusion (/answer questions).

1.2 The Process of Statistics

Statistics parallel the scientific method.
Statistical thinking proceeds as the following:

Identify the research objective (/planning experiment)

↓
Collect data (/information)
↓
Organize → Summarize (Descriptive Statistics)
↓
Analyze → Draw conclusions (Inferential Statistics)

1.3 Experiment
o Definition: Experiment is a planned activity whose results yield a set of data.
o An experimental unit is an object/individual (person or thing) upon which we collect data.

1.4 Population
o Definition: A population is a collection (or set) of data that describe some phenomenon of interest
to you.
o Each individual upon which we collect data from our population is our population unit.
o Number of units/elements in population are known as population size, represented by ‘N’.
o When data is to be collected only from all the members of population, it is known as Census Survey.

1.5 Sample
o Definition: A sample is a subset of data selected from a population.
o Each individual upon which we collect data from our sample is our sample unit.
o Number of units/elements in sample are known as sample size, represented by ‘n’.
o When data is to be collected only from some members of the population, it is known as Sample
Survey.

1.6 Representative Sample

o Consists of characteristics similar to those possessed by the population.
o We can say, a small enough representative part of the population would be a better sample.

Instructor: Dr. Asma Tahir, Assistant Professor, Department of Statistics, FCCU, Lahore | Page 1 of 6
1.7 Random Sample
o ‘Random’ means: made, done or happening without some pattern or conscious decision.
o Definition: A random sample or random method is one in which all the people or things involved
have an equal chance of being chosen.
o More Statistically: A random sample of n experimental units is one selected from the population in
such a way that every different sample of size n has an equal chance (/probability) of selection.
o An important benefit of simple random sampling is that it allows researchers to use statistical
methods to analyze sample results.

1.8 Non-Random Sample

o Definition: A sample drawn using certain amount of judgment or purpose → judgment or purposive
sample.
o Non-probability (/Non-random) sampling is a sampling technique where the samples are gathered
in a process that does not give all the individuals in the population equal chances of being selected.
o Disadvantage: Statistical analysis is not appropriate when non-random sampling methods are used.

1.9 Descriptive Statistics

o Definition: A branch of statistics consists of organizing and summarizing the information (data)
collected.
o Describe the information collected through numerical measurements (such as mean, median, mode
etc.), charts, graphs and tables.
o Purpose: To provide an overview of the information collected.

1.10 Inferential Statistics

o Definition: The branch of statistics concerned with using sample data to make an inference about a
population.
o Draw conclusions from the information.
o Uses methods that takes results obtained from a sample (method known as sampling), extends them
(/generalized) to the population, and measures the reliability of the result. (Note: Measures the
reliability requires proper sampling techniques).
o We can also say,
“The use of descriptive statistics to make educated guesses about something is known as
Inferential Statistics.”
o When inferential statistics is not necessary?
If the entire population is studied, inferential statistics is not necessary, because descriptive statistics
will provide all the information that we need regarding the population.

1.11 Variable Antonym – Constant:

o Definition: A characteristic (of a population or sample) which never changes.
o Example - Math/Stat: In the equation 5x - 3 = 7,
x is the variable, as it represents a number with an unknown value. 3 and 7 are the constants, as their
values remain the same no matter how the equation may be altered.
o Example - CS: Constants are quantities whose values do not change during program execution.

1.12 Variable
o Definition: A variable is a characteristic that differs/varies from one observation to the next.

Instructor: Dr. Asma Tahir, Assistant Professor, Department of Statistics, FCCU, Lahore | Page 2 of 6
 o Types:

► Nominal
► Qualitative/Categorical (non-numerical)
► Ordinal

Variable
► Discrete
► Quantitative (numerical)
► Continuous

a. Variable – Qualitative (Attributes or Characteristics): Non-numerical data that can only be

classified into one of a group of categories of qualitative data. Arithmetic operations cannot be
performed on the values of the variables.
Nominal:
o Purely descriptive.
o Imply no ordering of any kind.
o Examples: name, religion, color, area of residence.
Ordinal:
o Purely descriptive.
o Imply some kind of ordering.
o Examples: level of education, degree of severity of disease, military rank, job position.

b. Variable – Quantitative: Quantitative data are observations measured on a numerical scale.

Arithmetic operations can be performed on the values of the variables.
Discrete:
o Values obtained by counting, usually whole numbers.
o Examples: number of births, number of students in a class.
Continuous:
o Values obtained by measurements.
o Imply the measurement on a continuous scale, (a decimal fraction can be present)
o Examples: height, weight, age, time etc.

1.13 Distinguishing – Individual, Variable and Data

 An individual is an object or person for whom we wish to obtain data;
 The variables are the characteristics of the individuals; and
 The data are the specific values of the variables.

Example: In the following tables, identify the individuals, qualitative (nominal/ordinal) variables,
quantitative (discrete/continuous) variables and data:

Instructor: Dr. Asma Tahir, Assistant Professor, Department of Statistics, FCCU, Lahore | Page 3 of 6
Some STAT course students conduct a survey of in their class and get the following information:
Col. 1 2 3 4 5 6 7 8 9 10
Student Gender Age Height Blood No. of Sources use UNIV Grade No. of
(in Group Siblings to Reach 100 in Courses
cm) the FCCU Section UNIV taking in
100 the
Current
Semester
Miraal F 20 158 O 3 Car U B+ 2
Ali M 19 175 AB 1 Motorcycle H C 1
Zainab F 19 146 B 2 Bicycle A A 3
Abraham M 21 180 O 0 Walk C D 0
Haroon M 20 160 B 4 Public L A 4
transport

Group of Selected Countries and Information regarding these Countries as of July 2004:
Country Government Type Life Expectancy (years) Population (in millions)
Australia Democratic 80.26 19.9
Canada Confederation 79.96 32.5
France Republic 79.44 60.4
Morocco Constitutional Monarchy 70.35 32.2
Poland Republic 74.16 38.6
Sri Lanka Republic 72.89 19.9
United Sates Federal Republic 77.43 293.0
Source: CIA World Factbook

In a STAT class, students use Smart Phones of the current year with the following information:
Phone Weight Depth (inches) Screen Size (in Service Provider
inches)

1.14 Parameter
o Definition: A descriptive measure of a population is known as parameter.
o Definition: A numerical summary measure used to describe a characteristic of a population is known
as parameter.
o Examples: population mean, population standard deviation, and population variance.

1.15 Statistic
o Definition: A descriptive measure of a sample is known as statistic.
o Definition: A numerical summary measure used to describe a characteristic of a sample is known as
statistic.
o Examples: sample mean, sample standard deviation, and sample variance.

Instructor: Dr. Asma Tahir, Assistant Professor, Department of Statistics, FCCU, Lahore | Page 4 of 6
1.16 Census:
o Definition: When data is to be collected from each member of the population, it is known as Census
Survey.
o Census vs Sample Survey: As census is a complete enumeration (about all the members of
population), while sample survey is based on a partial enumeration (about some members of the
population).
o Advantage of census method over sampling method: It gives exact and accurate results.

1.17 Benefits of Sampling Method over Complete Enumeration:

o Speed: Less time
o Economy: Less expensive
o Adaptability: Flexibility (the quality of being able to adjust to new conditions, the capacity to be
modified for a new use or purpose)
o Scientific Approach: More dependable, less manpower, less administrative control
o Advantage of sampling method over census method: Sampling is used in infinite cases where census
cannot be measured or studied.
e.g. Inspection of a production on quality of the crop may destroy the whole field.

1.18 Statistical Data Analysis

o The goal of Statistics is to gain understanding from data.
o Any data analysis contains following steps:

(i)Begin → Objective of study/Formulation of the research problem

↓
(ii) Define population and sample
↓
(iii) Collect the data
↓
(iv) Do descriptive data analysis
while using appropriate statistical methods to solve the research problem
↓
(v) Interpret and drawing conclusions → report the result → End
__________________________________

Example 1 (Group Activity):

The Dean of CS, Math & Stat is interested in learning about

i. ___________;
ii. ___________; and
iii. ___________
of Baccalaureate students taking course STAT __________ at FCCU.
Keeping the basic statistical terminologies in mind, how will you proceed in the situation?

Hint – steps to proceed:

1. Objective of study/Formulation of the problem
2. Population
3. Population unit
4. Population units (complete list)
Instructor: Dr. Asma Tahir, Assistant Professor, Department of Statistics, FCCU, Lahore | Page 5 of 6
 5. Population size (N)
6. Sample
7. Sample size (n)
8. Sample selection method/technique (random/non-random)
9. Sample unit
10. Sample units (complete list)
11. Variable -
Think: Should your variable Qualitative (nominal/ordinal) OR Quantitative (discrete/continuous)?
12. Descriptive and Inferential Statistics – going through descriptive part i.e computing mean, median,
mode, range, variance, standard deviation etc. (whichever is required) to reach the inferential part
of the problem
13. Parameter
14. Statistic
15. Conclusion/inference

Solution:

1. Objective of study/Formulation of the problem: To know/determine the

i. _____________;
ii. _____________; and
iii. _____________
of Baccalaureate students taking course STAT_______ at FCCU.
2. The population is _____________ of Baccalaureate students taking course STAT______ at FCCU.
3. The population unit is a _____________ of Baccalaureate students taking course STAT______ at
FCCU.
4. The population units complete list: _________________.
5. Population size, N = __________________.
6. A sample is a small enough representative part of ______________ (Baccalaureate students taking
course STAT_________ at FCC).
7. The sample size, n = ___________________.
8. We select sample __________________ (randomly/non-randomly).
9. Each ____________________ is the sample unit.
10. The sample units complete list: _________________.
11. Our variable is _____________.
The variable under study is ________________ (Qualitative or Quantitative)
The variable under study is ________________ (nominal, ordinal, discrete or continuous).
12. Computing (i) mean = _________, (ii) ___________, (iii) _________ is the descriptive statistics.
13. The parameter = _______________ (𝜇, 𝜎 2 𝑜𝑟 𝜎 etc.) taken from the students in the population
(usually unkown).
14. The statistic = ______________ (𝑥̅ , 𝑠 2 𝑜𝑟 𝑠 etc.) taken from the students in the sample (known).
15. Conclusion/inference on the basis of (known) __________________ (parameter/statistic) for
unknown ________________ (parameter/statistic).

Q 1. Why did you choose a qualitative or quantitative variable to proceed?

Q 2. On the basis of your conclusion, what do you think if your sample was a good representative one?
Why/Why not?

Instructor: Dr. Asma Tahir, Assistant Professor, Department of Statistics, FCCU, Lahore | Page 6 of 6