QUANTITATIVE TECHNIQUES

FOR BUSINESS
 Module:2 - Statistical Survey
Syllabus
❖Planning and design of enquiry
❖Statistical units
❖Executing a survey
❖Data Sources(Primary &Secondary)
❖Methods of collecting primary and secondary data
❖Sampling & Census
❖Types of sampling
❖Theoretical base of sampling
❖Statistical Laws
❖Statistical errors
❖Editing,coding,classification &Tabulation
 Statistical Survey
Survey: means a search for truth, knowledge or information
Statistics: means data
Statistical survey :A method of studying a problem by collecting numerical figures
through survey.

Stages in statistical survey:

There are many stages in an investigation which can be summarized into:
➢Planning & design of enquiry
➢Executing a statistical enquiry
 I. Planning and design of enquiry
Planning and design of enquiry is the initial phase of statistical survey. This phase
is concerned with deciding on what is to be studied and how the study is to be
carried on.
1.Defining the Problem : State very clearly the problem to be investigated.
2. Determining the Objective and Scope : Objective of the survey is clearly stated it
serves as a guide in the collection of required information.
Scope - area to be covered, the period of study, the population or items to be covered, the
type of information to be collected, etc.
3.Source of Data : Primary data & Secondary data
4. Type of Enquiry: census or sample.
5. Defining the Statistical Unit - be appropriate and be free from ambiguity, same unit
6. Degree of Accuracy: Depends upon the purpose of investigation and nature of enquiry.
7.Method of data collection: Interview method, questionnaire, schedule,
observation etc.
8. Construction of frame: “Frame means a list of all units of the population and their
description under study”

II. Execution of statistical enquiry

Putting the plan of statistical survey into action.
1. Setting up of administrative team: Based on nature and scope of enquiry
2.Designing necessary forms and questionnaires: Should be prepared before
collecting data.
3. Selection and training of field staff : Success of survey depends on efficiency of
field staff
4. Supervision of the work
5.Collection of Data: Actual collection of data. A suitable method of data collection
should be decided .
6. Editing the Data : Once the data is collected, the next step involved is the scrutiny
of the collected information.
7. Classification and Tabulation of Data : Classification is the process of arranging
the data in groups and classes according to resemblance and similarities.
Tabulation is the systematic presentation of numerical data in columns and rows in
accordance with some salient features
8. Analysis of Data : Analysis of the data through various statistical measures such as
averages, percentages, coefficients, etc.
9. Interpretation of Data: drawing inferences about the table wise classification
10. Writing the Report : A report should contain the following aspects:
The nature and purpose of survey, Area of coverage and main objective,
Method of sampling and data collection, Tools of analysis and interpretation,
Facts findings and suggestions, Guidelines for proper interpretation
 Statistical Units
Units used to express statistical data.

1) Units of enumeration/Collection: units in terms of which data are collected.

They involve either counting or measurement..Eg. Centimeter , Kg
➢ Simple units : single condition without qualification. For eg. a ton, a pound,
➢ Composite units: formed by adding a qualifying word to a simple unit. Eg. Kilowatt,
Labour hours.
➢Hypothetical Units: used for comparison. For eg. Multi specialty hospital, Multi plus
theatre etc.

ii. Units of Analysis and interpretation: units in which statistical data are analyzed
and interpreted. For eg. ratios, percentages, coefficients etc.
Units of Presentation: units by which attributes are presented.
Essentials of good statistical units : Simple & Specific , Stable, Suitable to the enquiry ,
Homogeneous, Self explanatory
 Collection of the data
Methods that are to be employed for obtaining the required information from the units
under investigation.
Types of data – Primary and Secondary Data
Primary Data : Original Data Collected from primary sources. Data collected for the first
time . Data originated directly as a result of problem under investigation.
Merits of primary data:
❑ collects data specific to the problem under study.
❑ no doubt about the quality of the data.
❑ possible to obtain additional data.
Demerits of Primary Data:
❑ Lot of time, labour, skill and money required.
❑ In some cases it is not possible to collect primary data
 Methods of collecting primary data
1. Observation Method : Data is collected with the help of observation by observer or
by personally going to the field.
Features of observation
➢ Observation is Systematic (planning) Observation is Specific:
➢ Observation is an Affair of Eyes, Definite Aim
➢ Direct method – field visit Use Only for primary data collection

Merits of Primary Data Disadvantages of Primary Data

❑ Simple and easiest Method ❑ Lack of competence of the observer
❑ Accurate and dependable ❑ Observer may lives in Different culture
❑ Does not require the willingness of ❑ Lack of clarity in conclusions
the people ❑ Observation is self interfering. - bias
❑ Mechanical devices like tape recoder, ❑ Time consuming and Costly
camera, mobile phones etc. can be ❑ Complete answer to any problem or any issue
used. cannot be obtained by observation alone.
 2. Interview method
“a two –way systematic conversation between an investigator and an
informant, intiated for obtaining information relevant to specific study”
Features
Face to face interaction Specific Object
It is Structured i.e. planned well Flexible process

Merits of interview method De-merits of interview method

➢ More information can be obtained. ➢ Expensive method
➢ Greater flexibility - opportunity to change ➢ Bias of interviewer as well as that of the
questions. respondent
➢ Personal information can obtained easily. ➢ Respondents may not be easily
➢ Non-response generally remains very low approachable for interview
➢ language of the interview can be change ➢ More-time-consuming
➢ Misinterpretations concerning questions ➢ Interviewer on the spot may over-
can be avoided. stimulate the respondent.
3. Questionnaire method
“A questionnaire is a research instrument consisting of a series of questions for the
purpose of gathering information from respondents.”
Relatively cheap, quick and efficient way of obtaining large amounts of information
Essentials of a good questionnaire:
(A)Covering Letter:
A formal request for getting co-operation - Stating the purpose of enquiry
Precautions for covering letter
➢Politely worded
➢Need and importance of the study is required to be highlighted
➢Emphasize on sincere co-operation of respondents
➢Ensuring confidentiality of information
➢ Promise that copy of the results will be sent
➢Enclosed with a self addressed envelop for convenience of the respondents to send back.
Qualities of a good questionnaire Advantages of questionnaire
❖ Limited number of questions ❖ Questionnaires are Economical
❖ Brief and Simple ❖ Quickly collect massive amounts of
❖ Logically arranged information from huge area
❖ Avoid Personal questions ❖ Replies may be received very quickly
❖ Objective type / Yes or No Questions ❖ Feel more comfortable and free to express
❖ Technical words can be avoided their view in this method.
❖ Motivate to answer all questions ❖ Uniformity
❖ Easily answerable ❖ Preliminary tool for conducting a depth
❖ Ego of respondents – not injured study later on by any other method.
❖ Few questions to Check the accuracy ❖ Easier method to plan, construct and
of answers administer.
❖ More useful and cheap, where the
repetitive information has to be collected at
regular interval.
De-merits of Questionnaire method
❖ Questionnaire cannot be used with illiterates
❖ Emotions of the respondents remain unnoticed.
❖ Respondents may misinterprets a question , Incomplete or no response.
❖ No personal contact with the respondents
❖ Difficult to verify the accuracy and reliability of information.
❖ Not a flexible method
4. Schedule method
“Schedule is a list of questions answered by the interviewer in a face to face
interaction with the respondents”
Requisites of a good schedule
❑ Questions should be clear capable reflecting the focus of study.
❑ Subjective elements in the questions should be avoided
❑ Should be capable of analysis and statistical testing
❑ Should be short , Arrange sequentially to create an interest in the respondents for
giving answers

Merits of schedule De-merits of schedule

• Proper response is ensured • Costly and Time consuming
• Clarify all doubts of the respondents • Performed well only by experts
• Flexible method • Not suitable when the area of study is large
• Chances of errors are less • Personal bias of the investigator
 Questionnaire Schedule

Indirect method of data collection Direct method of data collection

Used when geographically area is vast Used when deep information is required
Information is less reliable It supplies more reliable information
Presentation is important: i.e good paper There is no significance on presentation
,well arranged etc
No personal contact Personal contact

High chances of missing responses Low chance of missing responses

Only used among educated responded Can be used even among illiterate
respondents

Less costly More costly

Secondary Data
“Data collected from published and unpublished sources is called secondary data”
Merits of secondary data
➢ cost-efficient
➢ Available in a processed form
➢ Convenient
➢ Valid and reliable

De-merits of secondary data

➢ Quality of the data collected cannot be ensured
➢ Not capable of providing adequate information
in conducting a study
➢ May not be suitable for the study
 Basis Primary Data Secondary Data
Definition Collected for the first time. Those data which have already
been collected by some other
person.
Originality Original data - collected by the Not original - someone else has
Investigator for the first time. collected these for his own
purpose.
Nature of In the form of raw data Finished form.
data
Reliability More reliable and suitable for the It is less reliable and less suitable
enquiry

Time and Quite expensive both in time and Requires less time and money
Money money terms.
 Basic terms
Population /universe: Totality of objects under consideration
Finite: If number of units can be determined
Infinite: If number of units cannot be determined
Sample: Representative part of the population
Sampling: Process of selecting sample from a population
Sampling design: Procedure designed for selecting sample.

Techniques of data collection

1. Census method: All members of the population are studied. Also called full enumeration
study
Advantages of census method Disadvantages of census method
➢ All units of the population are studied. ➢ Costly & time consuming process
➢ Greater accuracy. ➢ Cannot be applied when the population is
➢ Appropriate in case of rare events infinite or destructive in nature
2. Sample survey
Process of studying a representative group from the population
Process of sampling: Selecting the sample Collecting information from the
sample Making inference about the population

Characteristics of a good sample

➢ True representative of the population
➢ Adequate size
➢ Homogeneity in the nature of all units
➢ Selection of units should be independent
➢ Sample selected should fit the matter of study
➢ Selection should be based on experiences i.e. Past & practical
Advantages of sampling Disadvantages of sampling
➢ Time saving method ➢ Chances of bias selection
➢ Cost efficient method ➢ Difficulties in selecting a truly representative sample
➢ Flexible & Dependable ➢ Requires adequate subject specific knowledge
➢ Suitable in certain cases ➢ Changeability of units
Factors to be considered while selecting census or sampling technique:
➢ Large area : Sample survey Small area : Census method
➢ More time available : Census method Less time available: Sample survey
➢ Limited fund :survey method
➢ Higher degree of accuracy: Census method
➢ Infinite or destructive population : Only sample survey
 Basis Census method Sample method
Items studied All units Only selected samples
Suitability Area of operation is small Area of operation large
conclusion Drawn from the study of whole Drawn from the study of a
universe representative group
Time More time consuming Less time consuming
Nature of items Suitable when items are diverse Suitable when items are
homogeneous
verification Less scope for verification Verification can be made by selecting
a different group
Nature of method Old and less practical New and more practical

Number of More number Less number

enumerators
Expense More expensive Less expensive
 Sampling methods/techniques
1.Random Sampling(Probability Sampling): Each unit of the population has equal chance
of being included in the sample. Random sampling are again converted into:
Simple random sampling &Complex random sampling
i. Simple random sampling: Every item in the population has an even chance and
likelihood of being selected in the sample. Methods in simple random sampling are
Method of lottery: Each member of the population has to number
systematically and in a consequent manner by writing each number on a separate piece of
paper. These pieces of paper are mixed and put into a box and then numbers are drawn out
of the box in a random manner.
Random Number table: By using a random number table, all members in the
population will have an equal and independent chance of being selected for the sample
group.
ii. Complex Random sampling
Probability sampling under restricted sampling techniques. also called mixed
sampling. designs as they tend to combine probability and non-probability sampling
procedures during sample selection. Some of the complex sampling techniques are:
a) Stratified sampling: Total population is divided into smaller groups or strata’s
based on common characteristics. Sample are selected randomly from each strata
Merits:
➢ Representation from each strata’s
➢ Advantage of both random and purposive sampling
➢ Ensures administrative convenience
➢ It reduces time and expense
De-merits:
➢ Stratification is a difficult task
➢ Determination of size of strata is difficult
➢ If the strata’s are distributed geographically it becomes more expensive.
➢ Chances of strata’s to overlap.
b) Systematic sampling:
A probability sampling method. The researcher chooses elements from a target
population by selecting a random starting point and selects sample members after a
fixed ‘sampling interval.’
Eg. Select the first random sample from the first 20: For instance let it be 5
Select the next samples in such a manner that the second will be(
20+5=25),(25+20=45),(45+20=65),65+20=85)
Merits:
➢ Simple and easy to operate
➢ Saves a lot of time and labour
➢ Provides satisfactory results
Demerits:
➢ Needs complete and up to date frame of population which will not be available
➢ Interval selected may be unrepresentative
 C) Multistage sampling: samples are drawn stage by stage
First stage: Universe is divided into some clusters from which few clusters are selected
randomly
Second stage: Clusters selected in the first stage is again divided into some clusters from
which certain clusters are selected randomly
Third stage: Selected second stage sample is again sub divided into clusters from which
certain clusters are selected as sample
d) Cluster sampling: Researcher divide the population into multiple groups (clusters) for
research. Then select random groups with a simple random or systematic random sampling
technique for data collection and data analysis.
2. Non -Probability sampling
Researcher selects samples based on the subjective judgment of the researcher rather than
random selection. Depends heavily on the expertise of the researchers. All units of the
population do not have equal chance of being included in the sample. Methods of Non -
Probability sampling are
1.Covenience sampling: Data collection from population members who are conveniently
available to participate in study.
Demerit: Largely affected by the personal bias of investigator.
2. Judgement sampling: Judgement sampling (a type of purposive sampling) occurs
when units are selected for inclusion in a study based on the professional judgment of the
researcher.
3. Quota sampling: Whole universe is divided into parts. Each part of the population is
assigned to an investigator for whom quota of units to be examined by him is fixed in
advance according to specified characteristics such as age, gender, religion etc.
4. Snow ball sampling: Snowball sampling is where research participants recruit other
participants for a test or study. It’s called snowball sampling because (in theory) once you
have the ball rolling, it picks up more “snow” along the way and becomes larger and
larger.
5. Sequential Sampling: Researcher selects a number of sample lots are drawn one after
another in the order of sequence till a satisfactory sample lot is obtained.
6.Multi phase sampling: Some information is collected from the whole sample and
additional information is collected from sub sample.
 Theoretical Base of sampling
Sampling theory is drawn based on the two important statistical laws i.e.
Law of statistical regularity: The Law of Statistical Regularity is derived from the
mathematical theory of probability. Moderately large number of items chosen at random from
a very large group are almost sure to have the characteristics of the large group.”
A Sample selected at random could be a representative of the population.

Law of inertia of large numbers: Law of Inertia of Large Numbers states, “Other things
being equal, as the sample size increases, the results tend to be more reliable and
accurate.”
 Statistical errors
Difference between a value obtained from a data collection process and the 'true' value for
the population. Statistical errors can be classified as :
Sampling Error: Arising as a result of unrepresentativeness of sample taken. Sampling
errors are of two types:
a)Biased sampling error: Sample is chosen in a way that makes some individuals less
likely to be included in the sample than others. arises if there is bias in selection of sample
b)Unbiased sampling error: The investigator has not intentionally tampered with the
sample and that the difference between the population and sample have occurred by chance
1. Non sampling errors: Errors arising in statistical investigation not because of sampling. It
occurs at the planning stage, fieldwork stage as well as at tabulation and computation
stage. Measurement of errors
1.Standard Error / Absolute Error: Difference between true value and estimated value
Absolute error = Actual value- Estimated value
2.Relative error: Relative Error is the percentage/ ratio of the estimated error.
Relative error = Absolute error/ Estimated value
Editing of data
Detection of errors or irregularities in collected data and their elimination.
a) Editing of primary data
Primary data is raw data characterized by in accuracy, heterogeneity, inconsistency,
incompleteness etc. Therefore editing is necessary to make the data Accurate,
Consistency, Adequacy , Completeness and Homogeneity.
b) Editing of secondary data
Editing is done to figure out in consistencies, probable errors and omissions. IT makes the
data suitable for the purpose of present investigation.
Secondary data is edited to ensure Reliability, Suitability, Adequacy, Accuracy and to
identify Unit of measurement and analysis. Reliability of data can be ensured by verifying
the source from which data is collected.
Coding of data: “Coding is the process of assigning numbers or letters or combination
of both to the data collected for the purpose of purpose of proper identification and
presentation in a secret manner.”
Classification of data
“ Process of arranging data in groups or classes according to resemblances and
similarities is technically called classification”
Features of classification
❑ Exhaustiveness: Each and every item of data must be presented in any of one class.
❑ Mutually Exclusive: Each item of data must be presented in one class only
❑ Flexibility: Possible to make adjustments to new situation and circumstance
❑ Homogeneous : Variables included in all classes must be homogeneous
❑ Suitability: Suited for the purpose and object of the study
❑ Stability: It should be stable
❑ Accuracy: Ensure accuracy of data
❑ Clarity: It presents data in a simple and clear form
❑ Condensation: It helps in shortening the huge mass of data
❑ Presentation and analysis: It is essential for presentation of data and application of
tools of analysis.
 Methods of classification
➢ Geographical classification: Data classified according to the geographical differences.
Data are classified on the basis of states , districts , villages, zones etc
➢ Chronological classification: When data are collected for a number of period and arranged
chronologically. Data are classified on the basis of year, month, week, day etc.
➢Qualitative classification: Classified on the basis of presence or absence of an attribute.
a) Two fold or Dichotomous classification : Classification on the basis of one attribute
leads to creation of two groups. Eg. on the basis of literacy data can be divided into two
literate and illiterate
b) Manifold classification: Classification on the basis of more than one attribute
Eg. When population is divided on the basis of gender and literacy there can be four
groups: Male literate , Male illiterate, Female literate, Female illiterate
➢Quantitative Classification: Classification on the basis of measurable characteristics.
Variable: Variable is a value that can change depending on conditions.
Attributes: Qualitative Characteristics like gender, education etc.
Statistical series
systematic arrangement of the items into some logical orders. The data so arranged is called
a statistical series. Types of statistical series:
Statistical series can be classified according to their general characteristic into:
1. Time series: When data are arranged on the basis of time or chronologically.
year 2015 2016 2017 2018 2019 2020
Sales 200 500 600 700 900 1000
2.Spatial series: When data are arranged or presented in relation to place
Town A B C D E F
Population 20 15 23 45 55 16
3. Condition series: When data are presented with reference to some conditions
Division of sector Private sector Public sector Joint sector
Productive capital 4800 6200 700
On the basis of their construction :
1. Individual series: In individual series the items are listed singly , showing the observation
relating to them
Marks: 20 30 40 56 25 88 96 63

2.Discrete series: When the exact measurement of various items are shown along with their
corresponding frequencies(numbers)
Marks 50 60 40 55 65 89 90 89 78
Numbers 10 12 15 15 20 18 5 15 0
3. Continuous series: When approximate measurements are shown as class intervals along
with their corresponding frequencies.

Class 0-10 10-20 20-30 30-40 40-50 50-60 60-70 70-80

interval
numbers 25 12 18 20 5 30 40 5
➢ Class interval: Difference between two approximated end within which data item is to
appear: These approximated ends are called class limits &
The highest end is called upper limit
The lowest end is called lower limit
➢ Frequency distribution:
Frequency : Number of times each value of a variable occurs is known as frequency
Frequency Distribution: Orderly arrangement of data along with frequency.
Univariate frequency distribution: Frequency distribution with one variable
Multivariate Frequency distribution: Frequency distribution with more than one variable
Tabulation : Tabulation can be defined as “ Systematic arrangement of data in columns
and rows”. Method of placing organised data into a tabular form is called as tabulation.
Major Objectives Of Tabulation:
➢ To Bring Essential Features of the Data
➢ To Simplify the Complex Data:
➢ It indicate the trend and pattern of the data.
➢ To remember the data
➢ It helps in dictating errors and omissions.
➢ To Facilitate Comparison:
➢ Unnecessary details are avoided , economy
➢ To Facilitate Statistical Analysis
of space can be achieved.
Types of tabulation
1. Hand tabulation : Hand tabulation is done by tally sheets
2. Machine tabulation: Used when the amount of data is large, mechanical devices are used
for tabulating
3. Electronic Computers: Computer software's perform tabulation work within a fraction of
time
Tables: A systematic arrangement of Classified data
Essential parts of a table
1. Table Number: Identification and reference in future
2. Title of Table: Written on the top of the table. It should describe the contents of the table
3. Head note: Statement given below the title and enclosed in brackets. like ( in crores)
4. Captions: These are column headings. Need to be self explanatory
5. Stubs: These are row headings
6. Body of the table: Actual data appears here
7. Foot note: Explanation or elaboration regarding any time in the table
8. Source Note: Depicts the source from which data is collected
 Rules for Tabulation:
❑ Table should be simple and compact
❑ Captions and stubs should be arranged systematically
❑ Table should suit the purpose of the study
❑ Unit of measurement should be clearly defined, Figures should be rounded off
❑ Miscellaneous column should be added to include important items
❑ It should be complete and self explanatory
❑ Attractive to draw attention of readers
❑ Abbreviations should be avoided, Proper lettering should be followed
Types of tables
1. Simple Table: Table containing data relating to one characteristics
Eg. Table showing number of students in 1 st year B.com class
Class Number of students
1st B.com Taxation 50
1st B.com Co-operation 30
1st B.com Computer Application 60
2. Cross Tabulation (Complex Table): contains data relating to more than one
characteristics. It may be two way three way or manifold tables
Example : Distribution of employees on the basis of age, gender and nature of work

Age Male Female Total

Skilled Unskilled Total Skilled unskilled Total Skilled Unskilled Total
20-30 16 35 51 10 42 52 26 77 103
30-40 35 69 104 21 68 89 56 137 193
40-50 32 65 97 16 49 65 48 114 162
50-60 10 24 34 16 36 52 26 60 86
Total 93 193 286 63 195 258 156 388 544
 Classification Tabulation
Process of arranging data in groups Process of presentation of data
Basis for tabulation Based on classification
Data is divided into classes and sub Data is presented in rows and columns
classes
Not a mechanical function Mechanical function