What is Survey? History of Survey? Why it is important? Types of Survey? How it helps in Sampling? Types of Sampling? Advantages of Survey And Disadvantages of Survey

1. Dr. Divya Bhojwani
SURVEY

2. CONTENTS
 DEFINITIONS
 INTRODUCTION
 HISTORY
 CHARACTERISITICS
 TYPES OF SURVEY
 PURPOSE OF SURVEY
 PROCEDURE IN SURVEY
 ADVANTAGES
 DISADVANTAGES

3. DEFINITION
 A Standardised stimulus designed to convert fuzzy
psychological phenomenon into hard data.
 Survey research is a type of research to collect the
data and facts about some certain situations or
issues from the target populations existing in
surroundings having relevance to the nature of
study.

4. INTRODUCTION
 In research of human subjects, a survey is a list of
questions aimed at extracting specific data from a
particular group of people.
 Survey research is often used to assess thoughts,
opinions, and feelings. Surveys can be specific and
limited, or they can have more global, widespread
goals. Psychologist and sociologists often use surveys
to analyse behaviour, while it is also used to meet the
more pragmatic needs of the media, such as, in
evaluating political candidates, public health officials,
professional organizations, and advertising and
marketing directors

5.  Surveys may be conducted by phone, mail, via the
internet, and sometimes face-to-face on busy street
corners or in malls.
 A survey consists of a predetermined set of questions
that is given to a sample.
 With a representative sample, that is, one that is
representative of the larger population of interest, one
can describe the attitudes of the population from which
the sample was drawn. Further, one can compare the
attitudes of different populations as well as look for
changes in attitudes over time.

6. HISTORY OF SURVEY RESEARCH
- Survey research methology was initially developed
during the 1920’s.
- Civil servant at trailer park, collecting census
data,Netherlands,1925
- Since the 1980’s theories and principles evolved to
create a unified perceptive on the design conduct and
evaluation of surveys i.e. survey science.

7. SURVEY RESEARCH EXAMPLES
 SOME FIELDS WHICH USE SURVEY RESEARCH
FIELD EXAMPLES
Demographics Census
Epidemiology Health survey
Marketing Customer satisfaction
Politics Polls
Psychology Attitudes, emotions
Sociology Social trends
Pharmacology Drug effects, causes

9. SURVEY RESEARCH CHARACTERSTICS
 USAGE: Surveys are widely used in the social
sciences.
 SYSTEMATIC: follow specific procedures based on
the survey science and the scientific method,
 REPLICABLE: other people using the same methods
are likely to get essentially the same results. One
aspect of the quality of the survey instrument is the
reliability of the measures on the instrument. It is
important that the measurement process be consistent

10.  TYPES: Often use interviews or questionnaires.
 IMPARTIAL SAMPLING: Units are selected from the
populations without prejudice or preference and so to be
the representative. Real world samples.
 DATA: Often quantitative but can be qualitative also.

11. TYPES OF SURVEY
 According to Span of time involved
The span of time needed to complete the survey brings us to the two different
types of surveys:
1) CROSS SECTIONAL SURVEY
2) LONGITUDINAL SURVEY

12. Cross sectional surveys
 Collecting information from the respondents at a single
period in time uses the cross sectional type of survey.
 Cross-sectional survey usually utilises questionnaires
to ask about a particular topic at one point in time.
 For instance, a researcher conducted a cross sectional
survey asking teenagers views on cigarette smoking
 Sometimes, cross sectional surveys are used to identify
the relationship between two variables as in a
comparative study.
 For example: peer pressure and cigarette smoking
among teenagers

13. LONGITUDINAL SURVEY
 When the researchers attempts to gather information
over a period of time or from one point in time up to
another, he is doing a longitudinal survey.
 The aim of longitudinal survey is to collect data and
examine the changes in the data gathered.
 Longitudinal surveys are used in cohort studies, panel
studies and trend studies.

14. CONDITIONS FOR A SURVEY
 It should answer the objectives
 Be unbiased
 Accurate
 Be generalizable
 Be ethical
 Be economical

15. PURPOSES OF SURVEY RESEARCH
 There are two broad purposes of survey based research:
INFORMATION
GATHERING
THEORY
TESTING AND
BUILTING

16. INFORMATION GATHERING
 The goal is to gather information for e.g
 Polls
 Census
 Customer satisfaction
 Attitudes
 The goal is to test and built theory for e.g habit of
smoking causes lung cancer in 89% of the populations.
 Personality and social psychology theories
THEORY TESTING AND BUILTING

17. PROCEDURES IN SURVEYING
 Conducting a survey appears easy, however without
careful planning and thought, the data collected may
not provide the information needed.
 A survey research project should follow the scientific
process that is used in any research project.
 Defining the study purpose clearly and narrowing is
essential. It is also important to conduct a literature
search to determine research that has been previously
done.
 There are four main characteristics when conducting a
survey:

18. 1) SAMPLING
2) DATA COLLECTION
3) SURVEY INSTRUMENT DESIGN
4) DATAANALYSIS AND REPORTING
SAMPLING
SURVEY
INSTRUMENT
DESIGN
DATA
COLLECTION DATA
ANALYSIS

19. SAMPLING
 Sampling is the selection of population to represent the
entire population. The study population includes all those
of interest from which a sample can be selected.
 Selecting a sample to represent a population should be done
with careful thought.
 The study populations includes all those of interest from
which a sample can be selected. Before defining a
populations and selecting a sample, the sampling unit
should be determined.
 Often the sampling unit is an individual person(patient or
physician). However, the sampling unit may be pharmacies,
families, household, clinics hospital may be grouping.

21.  Once the population and sampling unit have been
determined, a sample frame can be developed. The sample
frame is the operational definition of the population that is
used to select the sample.
 After the sampling is defined, a sample can be selected.
SAMPLING DESIGN
 The part of research plan that details that how the sample
can be selected is the sample design. Both probability and
non probability designs can be used for sampling.
Probability sampling
Non- probability sampling

22. PROBABILITY SAMPLING
 Probability sampling means that each sampling unit has a
known probability of being included in the sample.
Because there is a known probability of being included,
the laws of mathematical probability can be used to make
inferences about the population, and the results can be
generalized to the study population.
 The types of probability sampling are as follows:
• RANDOM SAMPLING
 STRATIFIED SAMPLING
 CLUSTER SAMPLING

23. RANDOM SAMPLING
Random sampling means each sampling unit is randomly
selected to participate. In simple random sampling, each
sampling unit has a known and equal chance of
participating in the survey. To select a simple random
sample, a random number generator or a table of random
numbers can be used to select the sample from the
sample frame.
The list of sampling units can be generated in many
ways, such as an alphabetical list of employees or a
sequential list of patients admitted to a ward. Then after
selecting a random starting point, every Nth name is
selected from the list of sampling units

25. STRATIFIED SAMPLING
 Stratified sampling refers to grouping a study
population according to some demographic
characteristic.
 The populations to be sampled is to be divided into
groups called “strata”, such that each group is
homogenous in its characteristics.
 For example, hospital employees can be grouped by
department, and then within each group, five
employees can be randomly selected.
 This method ensures more representativeness provide
greater accuracy and can concentrate on a wider
geographical area.

27. CLUSTER SAMPLING
 Cluster sampling refers to selecting participants
randomly who are naturally grouped by either
geographic location, natural groups or time.
 Within cluster sampling, there are single-stage
clustering. In single-stage clustering, the pharmacy
researcher may randomly select clusters and then
survey all sampling units within the clusters.
 For example, villages, wards, or children of the school.
 This method is simpler and involves less time and cost
but gives a high standard error.

29. NON-PROBABILITY SAMPLING
 Nonprobability sampling means there is not a known
probability of being included in the sample. Although
confidence intervals and sampling error can be computed
from a nonprobability sample, these statistics would be
technically invalid.
 However, there are times when a nonprobability
sampling technique is acceptable because of the purpose of
the study or because it is the only way to select participants
for a study.
 For example, it may be best to use a nonprobability
sampling technique when surveying hard-to-identify groups
(e.g., patients who are homeless or individuals who abuse
drugs) or specific groups (e.g., patients who live in a
hospice facility).

30.  Convenience Sampling/Accidental sampling
Convenience sampling is when a researcher
selects a group of individuals from the study population
who are easily accessible to participate in the study. For
example, shoppers in a single mall.
 Snowball Sampling
Snowball sampling is selecting people to
participate and then asking these participants to supply
names of other potential participants i.e. the friend also
refers a friend . But the give people with more social
connection an unknown but higher chances of selection.

32.  Quota Sampling/ Ad hoc quotas
Quota sampling divides the population into
groups or strata, such as by race, age, or gender, and
determines how many sampling units per strata are
needed .Then the researcher selects anyone in the
population to fill the quotas at his or her discretion.
Example: 100 smokers or 10 males.
• Judgmental sampling/purposive sampling
The researcher chooses the sample based on who they
think would be appropriate for the study. This is used when
there is a limited number of people that have expertise in the
area of being researched.

33. SURVEY INSTRUMENT DESIGN
1) Questionnaires:
Typically a question is “paper and pencil instrument”
that is administered to the respondents. The usual questions
found in questionnaires are closed ended questions, which are
followed by response options.
Questionnaires have been developed over the years.
Today, questionnaires are utilised in various survey methods
according to how they are given. These methods include the
self administered, the group administered and the household
drop off.
Among this the self administered method is often used by
researcher nowadays.

35.  A questionnaire is a research instruments consisting of a
series of questions and other prompts for the purpose of
gathering information's from respondents.
The questions framed to be answered by the sample class
should be:
 Short and concise
 Open questions
 Multiple choice
 Yes/no
 Phrasing of questions is critical
 Avoid vague, nebulous questions
Eg: what do you think about abortions?

36.  Avoid double- barred questions(compound questions)
Eg: Do you think that students should have more
classes about pharmacology and
anatomy?
• Avoid loaded language (push polling)
E.g. don’t you think that…?
Emotionally charged words like gang members,
welfare mothers.
• Avoid slang, jargon, abbreviations and acronyms
• Avoid or minimize negative wordings

37.  Questions must be clear, unambiguous
Good example: which of the following statements
best represents your attitudes toward abortions in first
trimester?
Conduct a readable analysis.
• Avoid lengthy questions; keep questions short
example: how many times to you smoke daily?

38.  OPEN ENDED/CLOSED ENDED
An open ended questions asks the respondents to
formulate his/her own answers, whereas the closed ended
questions has the respondents pick an answer from the given
number of options.
 Open ended allows subjects more leeway flexibility
example: what is your primary cultural background?
 Close ended or forced-choices ties respondents hands
somewhat easy to code the data.
example: choose your favourite ice-cream?
a) strawberry b) choclate
c) vanilla d) pista

40.  ADVANTAGES:
Ideal for asking closed ended questions,
effective for market or consumer research.
• DISADVANTAGES:
Limit the researcher understanding of the
respondent answer, requires budget for reproduction of
survey questionnaires.

41. INTERVIEWS
 Between the two broad types of survey, interviews are
more personnel and probing.
 Questionnaires do not provide the freedom to ask
follow up questions to explore the answers of the
respondents, but interviews do.
 An interview includes two persons-the researcher as
the interviewer and the respondent who is interviewed.
 These are the personnel or face to face interview, the
phone interview and more recently the online
interview.

43.  ADVANTAGES:
-follow up questions can be asked
- provide better understanding of the answers of
the respondents.
• DISADVANTAGES:
- Time-consuming
- many target respondents have no public listed
phone numbers or contacts.

44. METHODS OF DATA COLLECTION
 There are several ways of administering a survey.
Within a survey different methods are used for
different parts.
 The choice between administration modes is
influenced by several factors including:
 - costs
 -coverage of the target populations
 - flexibility of asking questions
 - respondents; willingness to participate
 -response accuracy

45. MOBILE SURVEY
 MOBILE DATA collection or mobile survey is an
increasingly popular method of data collections.
 Over 50% of surveys todays are opened on mobile devices.
The survey from app or collection tool is on the mobile
devices such as smart phone or tablet.
 These data offer innovate ways to gather data and eliminate
the laborious “data entry” which delays data analysis and
understanding.
 SMS survey can reach any handset in any language in any
country. As they are not dependant on internet access and
the answers can be sent when its convenient
 Apart from high mobile phone penetration, further
advantages are quicker response times and; possibility to
reach previously hard to reach target group ups.

47. ONLINE SURVEY
 Online survey are becoming an essential research tool
for a variety of research fields including marketing.
 According to data ,online survey research accounted
for 20% of global data collection expenditure.
 Online consumers panel are also extremely used for
carrying out survey but the quality is considered
inferior because the plane list tend to be fatigued.
 Advantages are they are faster, simpler and cheaper.
 The entire data collection period is significantly
shortened as all the data collected and processed in
little more than a month.

49. TELEPHONE
 Use of interviewers encourages sample person to
respond, leading to higher response rates
 Interviewer can increase comprehension of questions
by answering respondents questions.
 Fairly cost effective depending on local calls charge
structure.
 Good for large national sampling frames.
Three types:
 Traditional telephone interviews
 Computer assisted telephone dialling
 Computer assisted telephone interviewing.

50. MAIL
 The questionnaires may be handed to the respondents
or mailed to them but in all cases they are returned to
the researchers via mail.
 An advantage is that its cost is very low, since bulk
postage is cheap in most countries.
 Not suitable for issues that may require clarifications.
 No interviewer bias
 Large amount of information can be obtained.

51. FACE TO FACE
 Suitable for locations where telephones or mailed are
not developed remote areas.
 Potential for interviewer bias
 Easy to manipulate by completing multiple times to
skew results.

52. MIXED MODE SURVEYS
 Researchers can combine several above methods for
the data collections.
 With the introduction of computers survey mode now
included combinations of different approaches or
mixed mode designs.
 Computer assisted personnel interviewing(CAPI):
the computer displays the questions on screen, the
interviewer reads them to the respondents and enter the
respondents answer.

54.  Audio-computer-assisted self interviewing (audio CASI):
the respondents operates the computer
display the questions on the screen and plays the
recoding of the questions to the respondents who
then enters his/her answers.
• Interactive voice response(IVR):
the computers plays recordings of the
questions to respondents over the telephone who
then respond by using the keyboard of the
telephone or speaking their answers aloud.

56. CHARACTERSTICS OF TYPES OF
SURVEYS
TYPE OF
SURVEY
OBTAINING
SAMPLE
COOPERATION
RATE
COST PER
RESPONDEN
T
ADVANTAGES
IN PERSON DIFFICULT MEDIUM HIGH INTERVIEWER
RAPPORT
TELEPHONE EASY HIGH MEDIUM FAST
MALL
INTERCEPT
EASY MEDIUM MEDIUM FAST,IN
PERSON
MAIL EASY LOW LOW EXPENSIVE
COMPUTER
ASSISTED
EASY HIGH LOW AUTOMATIC
DATA ENTRY

57. VALIDITY OF SURVEY
 Validity is defined as “THE ACCURACY OR
THRUTHFULLNESS OF A MEASUREMENT”
 This is an simple concept but very difficult to determine if a
measure is valid.
 The definition that rely here is that, that a survey
represents what it intends and claims to represent.
 There are two types of validity: Internal and External
validity
 External validity refers to the validity of the survey beyond
study that is its generalizability both to the populations and
across context.
 Internal validity refers to rigours of measurement that the
concepts one sets to measure are actually measured.
•

58. WHY TO MEASURE VALIDITY
 LIMITED COVERAGE
 LACK OF SAMPLING FRAME
 LOW RESPONSE RATES
 CONTROLLING ACCESS
 INTERVIEWER EFFECTS
 DISPLAY EFFECTS

59. MODES OF VALIDITY
 CONTENT VALIDITY:
this approach measures the degree to which
the test item represent the domain being measured.
In order to measure the content validity of a
measuring instrument the researcher must identify
the overall content to be represented. Items must
be randomly chosen from this content that will
accurately represent the information of the areas.

60.  CONSTRUCT VALIDITY:
construct validity must be investigated
whenever no criterion is accepted as entirely
adequate to define the quality to be measured.
There are two parts of the construct validity first
and foremost the theory underlying the construct
must be constructed. Secondly, the adequacy of
the test in measuring the construct is evaluated.
• CRITERION –RELATED VALIDITY:
this approach is concerned with detecting the
presence and absence of one or more criteria to
represent domain

61. DATA PROCESSING AND ANALYSIS
 After the data have been collected, they have to be
processed and analyzed to provide results. Although data
processing will vary slightly depending on the data
collection method, the basic principles are the same.
 DATA RECEIPT AND CODING:
Most survey responses need to be recorded in
numerical form, rather than words; therefore, surveys need to be
coded. If computer technology is used and the responses are
entered directly into a software program, the survey is coded
before data collection. If the question asks for a numerical
answer or has a linear-type scale with a numerical value, the
number response is recorded. However, if categories are listed,
then each category response is given a numeric code. Codes are
given to missing data. A codebook can be generated that
provides the code for each question so that all data entry clerks
are using the same codes.

62.  DATA ANALYSIS:
When a sample is surveyed, statistical
analysis is conducted so that inferences can be made to
the population. Statistical analysis allows the researcher
to compute the probability that the values obtained from
the sample are within a specific range of those for the
population. Statistical analysis helps the researcher
describe the population, identify trends, and identify
relationships.
After statistical analysis, the pharmacy
researcher should interpret the results and report the
findings through publication or presentation.

63. ADVANTAGES OF SURVEY
 Ecological validity
 Access to wide range of participants
 Potentially large amounts of data
 May be more ethical than experiments.
 Relatively easy to administer
 Can be developed in less time
 Cost effective
 Can be administer remotely
 A broad range of data can be collected

64. DISADVANTAGES OF SURVEY
 Lack of control
 Less internal validity
 Data may be superficial
 Can be costly to obtain representative data
 Self report data only
 Potentially low compliance rates
 Respondents may not feel encouraged to provide
accurate honest answers.
 Customised surveys can run the risk of containing
certain types of errors.