Definition of Statistics:

“It is the science that examinesthe methods of collecting, presenting, analyzing, and
interpreting data.” Statistics, by this definition, is a unified, systematic, logical method that
deals with issues and characteristics that can be expressed numerically.
As for statistics, they are the numerical data related to a specific subject organized (in
tables or graphs) about a certain activity or sector within a country. For example, we say:
 Population statistics are used to express a set of specific data related to
thepopulation in a country (total number of population, distribution of population by
age or sex, geographical distribution of population by regions/ states).
 Foreign trade statistics.
 Agriculture statistics.
 Higher education statistics.
Therefore, statistics is the primary material that is used in the field of statistics.
Stages (methodology) of statistical research:
Based on the previous definition of statistics, it is evident that it involves several stages
that the researcher must follow. These stages are summarized as follows:
I. Precise determination of the statistical objective:
Wemean by that, determining the type of information to be collected, which is translated
into questions to be included in a special document called a form. It requires proper
organization and clearness of the questions, and the statistical objective is deduced from
the general objective of the statistical study.
 Example: We want to conduct a statistical study on the standard of living family in
Algeria (the general objective).
Determining the statistical objective: family income - number of individuals in the family -
type of housing - size of housing (number of rooms).
II. statistical data collection:
Statistical data is collected in different ways, depending on the study’sobjective and the
method of analysis used. Among the methods used for data collection, we mention the
following:
A- The Direct Method and the Indirect Method:
A-1-The direct method:This method means that the researcher collects statistical
information personally from primary sources. For example, asking questions directly to
families by moving to their locations.
- One of the advantages of this method: the exactmatching between the research
objectives and the data collected the precise definition of the concepts and termsrelated
to the study...
Among the disadvantagesof this method: the high cost, fieldwork complexities and
difficulties, relativelylong timeto obtain the final study results...
A-2- The indirect method:
It is also known as the secondary data method, and it includes all the available
statistical data and information from statistical documents, publications, and reports
issued by various bodiesand organizations, as well as different international bodies.
One of the main advantages of this method is that the greatlysavings time and
expenses.Among its shortcomings draw backs: the mismatch of many data with the
desired study objectives.
- Lack of accuracy as well as the amountquantity of data itself.
- The statistical unit used may not match the research plan.
B- Comprehensive inventory method and sampling method:
B-1- Comprehensive inventory method:
According to this method, all statistical units that make up the statistical community under
study are counted.
One of the advantages of this method is that it provides us a comprehensive and
detailed picture of the statistical community, characterized by required accuracy.
The disadvantages of this method are the difficulty of execution, the high costs, and
the need for a large and specialized statistical apparatus.
B-2-The statistical sampling method:
Where only a subset of the statistical population is studied, by taking a random sample
from the community, studying its characteristics and extracting the necessary information
from it, then generalisedto the entire population. from which it was taken.
 Among its advantages: easy implementation, low costs, quick accessto results, it is
the only considered method in many studies in which a comprehensive inventory is not
possible or impossible.
GraphicRepresentation
Graphic representation isused to compare the values of a phenomenon according
to location or its development according to time, and itenables the comparison of multiple
phenomena at the same time.
The use of graphic representation makes the statistical information more clear and
understandable, which helps to take a comprehensive and quick idea of the studied
phenomenon, i.e. in contrast to the tabular presentation. Among the most important
methods of graphic presentation, we mention: bar charts,pie charts, and broken lines
model.
4-2-2 Analysis of Statistical Data:
This stage involves studying, arranging and analyzing statistical information, breaking it
down into its primary elements and revealing the relationship among them. The analysis
processincludes the following steps:
 Arranging and classifying statistics. The arrangement can be according to type
or quantity, such as classifying the population as single, married, divorced and
widowed. The arrangement can also be geographical, such as distributing the
population in Algeria according to states, districts and municipalities.

 Calculating the central values of the data sets and studying the dispersion and
curving chart in it.
 Exploring the correlations between the factors of the statistical community.
 Eliciting estimates or predictions indicated by the study.

Interpretation of Statistical Data:
Branches of Statistics: The science of statistics is divided into:
a- Descriptive Statistics:
It is that part of statistics that is concerned with summarizing statistical data into a limited
number known as statistical measures or in an easy-to-readstatistical table or in graphs.
The purpose of all of this is to give a preliminary description of the studied phenomenon
without in-depth analysis.
 b- Inferential statistics:
It is based on the idea of selecting a part of the population called the sample, in an
appropriate scientific way, in order to use the data of this sample to reach results that can
be generalized to the study community.
This is called inferring the characteristics of the community based on the characteristics
of the sample, and this is the opposite of deduction, which means extracting the part (the
sample) based on the characteristics of the whole.
c- General Statistical Terms and Concepts:
3-1- The statistical unit
It is the single entity or the fundamental cell that is the subject to statistical study,
meaning that the questions of the formare centred around this unit, whether the object is
a human being, an animal, or something, like: a person, a cow, a car,...etc.
Examples:
- A statistical study on the standard of living population in Algeria, the statistical unit is
the single family.
- Surveying opinions about the political and social conditions in Algeria. The statistical
unit is an individual in Algeria (a man or a woman) aged 18 years and over.
- A statistical study on the spread of the white worm in agricultural lands in a state
province. The statistical unit is 1 m2 of agricultural land that couldbe infected by this
pest in the concerned province.
3-2- The statistical population:
It is the sum of the statistical units to be studied, which is accuratelydefined, that share
the fundamental characteristic of interest to the researcher, as a population of students,
families, institutions.
Examples:
- A statistical study on the standard of living population in Algeria. The statistical
community is all Algerian families on a specific date.
- Surveying opinions about the political and social conditions in Algeria. The statistical
community is all individuals in Algeria (men or women) aged 18 years and over.
- A statistical study on the spreadof the white worm in agricultural lands in a province.
The statistical community is all agricultural lands that could be affected by this pest in the
concerned province.
  3-3- Statistical variable:
 3-3-1- Definition of the statistical variable:
It is the common element of all statistical units that make up the statistical population,
like: height, age, educational qualificationlevel, production,…etc.
 3-3-2- Types of Statistical Variables:
Statistical variables are divided into two types:
A- Qualitative variables: are those variables that cannot be measured, andcan be
further divided into two types:
A-1- Ordinal qualitative variables: such as the level of educational qualification, ... etc.
A-2- Nominal qualitative variables: such as nationality, sex, family status, colour,..etc.
B- Quantitative variables: These are the variables that can be measured, and they are
the most widely used variables as the language of statistics is the language of numbers,
and quantitative variables are in turn divided into two types:
B-1- Discrete Quantitative Variables: These are those variables that take valid
valuesthat cannot be subdivided, such as the number of children in one family, the
number of produced spare parts...etc.
B-2- Continuous quantitative variables: They are those variables that take any
possible values of the field of study, and due to the infinite number of these values, we
divide the field of study into partial fields called categories, for example height, age,
weight, ... etc.
-4- The statistical sample:
It is a part of the statistical population that is extracted by certain statistical methods in
order to be the best representative of the statistical population, and it is relied upon in the
study instead of the entire community for the following reasons:
A- The large seize of population.
B - time, effort and cost saving.
B- The examination may be harmful or damaging to the units.
Exercise 1:
Define: the statistical unit, the statistical population, the statistical variable and
its type in the following:
1- Distribution of a sample of 30 economic establishments according to their
annual turnover.
2- The number of rooms in one dwelling for a sample of 50 dwellings in the
municipality of Sétif.
3- Distribution of 360 marriages cases in a city according to the wife age.
4- Distribution of monthly wages in DZD for 65 workers in a company.
5- Distribution of a sample of 40 individuals from the Maghreb community in
France according to the country of origin.
6- Distribution of a sample of 50 individuals according to educational
qualification in a given municipality.

Exercise 2:
For the purpose of identifying the needs of Sétif habitant of semolina and bread
(ready for bakers), the Food Industries Company in the province decided to
conduct a statistical study about this topic:
1- What is the general aim of the study?
2- What are the characteristics or statistical variables studied for each type of
consumption (semolina and readymade bread)?
3- describe the nature of each variable?
4- What is the statistical unit and the statistical community in this study?
5- What is the appropriate method for collecting data in such a study?
Justify?

Solution to the first exercise:

 Determine each of the following: the statistical unit, the statistical population, the
statistical variable and its type.
Statistical population Statistical unit Statistical variable Type
30 enterprise A single enterprise Annual turnover Continuous quantitative
50 dwelling A single dwelling Rooms numbers Discrete qualitative
360 wedding The single wedding Wife age continuous quantitative
65 worker The single worker Monthly wage continuous quantitative
40 expatriate in France Single person Origin country Non ordinal qualitative

50 individuals from a Single person Scientific qualification Ordinal qualitative

municipality

Solution to the 2ndexercise:

1- The general objective of the study is to find out the extent to which the population
atSétif province needs for semolina and bread.
2- The statistical characteristics or variables studied for each type of consumption
(semolina and bread):
The 1st variable: the quantity of semolina in kilograms.
The 2nd variable: the number of bread loaves.
3- The nature of each variable:
Quantity of semolina in kilograms: Continuous quantitative variable. Number of bread
loaves: Discrete quantitative variable.
4- The statistical unit and the statistical population in this study:
Statistical unit: single family.
Statistical community: All families residing in Setif province during the study period.
5- The appropriate method for collecting data for this study:
The direct method: since it requires a field visits and direct interviews with the study
units.
- The sampling method: due to the large size of the population (difficulty in conducting a
comprehensive inventory), as well as a profit of time, effort and money.