You are on page 1of 82

Research

methodology
contents
Introduction to research
Definitions
Research
Thesis
Dissertation
Why to do a research
Categories of research
Research methods & research methodology
Procedural steps in research
Research strategy
epidemiologic studies
Introduction


 Investigation using scientific procedures, by
searching again and again to find out the
truth

 Research is the continual search for truth


using the scientific method. It is the pursuit
of the truth with the help of study,
investigation, observation, comparison and/or
definitions


Research (WHO Health research methodology, 1992, a
guide for training in research methods):

Research is a quest for knowledge through diligent search
or investigation or experimentation aimed at the discovery
and interpretation of new knowledge. Scientific method is a
systematic body of procedures and techniques applied in
carrying out investigation or experimentation targeted at
obtaining new knowledge. Here research and scientific
methods may be considered a course of critical enquiry
leading to discovery of facts or information which increases
Thesis

(according to Oxford English dictionary)


A proposition laid down as a theme to be

discussed and proved. A discussion to

maintain and prove a thesis especially

written or delivered by a candidate for

university degree- Ph.D



Dissertation:

 Dissertation means “to discuss”.

 It is an academic activity laid down by the university for the


partial fulfillment of MDS degree.

 It is an exercise to train a PG student to plan, execute, evaluate,


write and report a scientific project.

 It is an in-depth study of a particular topic which contributes


new information and knowledge in the field

 A formal, often lengthy treatise (a book or writing of some


particular subject, one containing a methodical discussion or
exposition of principles of subject) or discourse, especially one
 It is a pre-requisite or academic activity for acquiring a
masters degree or doctorial.

 To find out the truth which is hidden and which has not
been discovered yet.

 To contribute new knowledge to the existing one as the
scientific knowledge develops in increments.

 As a profession to conduct research in various aspects.

 To solve an existing health problem.

Categories of research


Empirical research and theoretical research
1.

Basic research and Applied research

Empirical

 Observational research

 Experimental research

Basic or pure research

 It is usually considered to involve the search for


knowledge without a defined goal of utility or
specific purpose.

 Eg. The microbiologist, whose expertise is the
identification of pathogenic micro organisms may
conduct research in-vitro, in a laboratory on
bacterial reproduction, growth and endotoxin
production without any direct application to clinical
dentistry. Probably, the researcher is interested in
monitoring endotoxins produced over the life cycle
of bacteria to determine a pathogenecity.
Applied research

 It is problem oriented and is directed towards a


defined and purposeful end.

 Eg. An oral health researcher investigating the


relationship between periodontal disease and
myocardial infarction may use the findings of the
microbiologist as a theoretical framework to test
the relationship between bacterial endotoxins,
periodontal disease and myocardial infarction in
animal and then in human subjects
Research
methods
 methods/ techniques that are used for conducting
research are termed as research methods or
research techniques.

 They fall into 3 groups
1.
1. Those concerned with collection of data
2.
2. Those statistical techniques which are used for
establishing relationship between the data and the
unknown
3.
Research methodology

 It is a way to systematically solve the research


problem.

 It is necessary for the researcher to design his
methodology for his problem, as the same may
differ from problem to problem i.e.
1.
2. Why a research study has been undertaken
3.
4. How the research problem has been defined
5.
6. In what way and why the hypothesis has been formed

4. What data has been collected
4.
5. What particular method has been adopted for
collection of data
5.
6. Why a particular technique of data collection
has been used

 And a host of similar questions are usually answered


when we talk of research methodology, so that research
results are capable of being evaluated either by the
researcher himself or by others
Procedural steps in research
 Selection of problem for investigation-further exploration
 Inexperienced-seek opinion –senior
 Constructing –essential starting point


Review literature
 Modern electronic research
 Abstract collection held on CD-ROMS-enables –key words
 Medline and psyclit database
 Role of systemic review grown recently-cochrane collaboration-
reviews from volunteer researchers internationally adds
them to a bank,which is open for inspection by interesting
parties.


 Specifying study design

 Selection of measures: many measure ,assessments

Eg:self report rating scales for dental
anxiety,observations,interviews,stand questionnaires


simple rating scale can be given a no.1-strongly agree

2-agree

3-undecided

4-disagree

5-strongly disgree
 May not exist for the study ,this may necessiate the
development of new scale.
 should possess Reliability and validity
 Selection of sample:
 Sampling techniques-inorder to provide information ,can be generalised
to cover the whole population.

 Writing a protocol: aims &
objectives,method,materials,sample ,procedure


 Ethical approval
 Pilot work
 Main study
 Analysis of results
 Report writing
 publication
Research strategies

 Selection of a research strategy is the


core of a research design and is
probably the single most Important
decision the investigator has to make,
i.e. whether to undertake a
descriptive, an analytical or an
experimental study.
Classification of
Epidemiologic studies
Decscriptive study

 Concerned with observing the distribution of


disease or health related characteristics in human
population
 Eg. Surveys.
 Defining population:denominator
 Defining the disease:operational definition.
 Describing disease-time,place and person

Time:
 Short term fluctuation:
1. Common source epidemics-single,continuous
2. Propagated epidemics-person to person transmission of
infectious agent---epidemics of hepatitis A and
poliomyelitis

Periodic fluctuations:
 Seasonal –communicable diseases like measles,varicella,malaria

Eg:upper Resp tract infections inc during winter and GI inf in
summer
 Cyclic trends-measles-incidence every 2-3 yrs
 Influenza occurs at intervals of 7-10 yrs

Long term fluctuation
 Changes occur over long period of time,change in frequency
encompassing sev decades

Eg:CHD,diabetes,lung cancer shows upward trend in 50 decades
and TB, typhoid downward


Place distribution:

Interanational-

National-endemic disease like goitre,flourosis

Rural-urban-lung cancer,cardiovascular accidents-urban
 Person distribution:age sex
 Measurement of disease :morbidity and mortality indicators
 Expressed in terms of incidence and prevalence
Comparing with known indices:comparision b/n different
population and subgroups of same populn-clue to etiology
 Formulation of hypothesis:relating to disease etiology

specify-population,sp cause ,expected outcome,dose-response
r/n,time-resp r/n.

Eg:smoking of 30-40 cigarettes/day causes lung cancer in 10% of
smokers after 20 yrs of exposure.

Uses:
1. magnitude and type of disease in community
2. Clues to etiology
3. contributes to research

surveys

 Surveys are methods of scientific or systematic collection


of data, compiling, presenting in order (useful manner),
analysing and evaluating them

The focus of attention must be on the following

a) Formulating the objective of the study-obj describing what


is to be measured,resources
b)
c) Designing the method of data collection eg. Questionnaires,
interviewing, examination of records or observations
d)
e) Selecting the sample
f)

a)
Collection of data through questionnaires

Questionnaire is considered as the heart of survey operation.


a)
b) General form:
 It can be either structured or unstructured.
 May be either closed or open.
d)
e) Question sequence:
 The question sequence should be clear
 First few questions are particularly important in seeking
the desired co-operation
 Questions related to personal character, wealth or memory
of the respondent should be avoided as opening
questions
 Conducting examination:
1. Obtaining approval from authorities
2. Budgeting
3. Scheduling
4. Emergency care and refferal
5. (diagnostic method)Validity and reliabilty of the data


Classification of study types-ADA(1970)

typeI: complete examination

typeII: limited examination

Type III: inspection

Type IV:screening procedures:tongue depressor


d) Analysing the data

e)Drawing the conclusion

f) Publishing the reports


Case study: it is an intensive investigation of a person,


a family, a group, a social institution or an entire


community in a natural setting

Correlational study: it is a descriptive research


technique utilized to identify consistent relationship


among variables

Analytical study


Second major type

Subject of interest –individual with in population

Object –not to formulate but test hypothesis


Can determine:

1.Statistical association between disease and suspected
factors

2.If exists--strength
Case control studies
 Design of a case-control
study Time

Direction of enquiry

Exposed

Cases
Not Exposed
Populat
ion
Exposed

Controls

Not Exposed
Defining the cases and
controls:
 Case: you have to decide a case before the start of
the study. The case has to fit in to two criteria.

1. Diagnostic criteria.
2.
3. Eligibility criteria.

only newly diagnosed cases within a specified period
of time than old cases

Selection of cases

 The criteria for inclusion in the study must


be clearly specified.
 Sources of cases:

▪ Hospitals

▪ General population
1.

Controls
 they must be as similar to the cases as possible, except for the
absence of the disease,which is under study.


 Selection of controls
 Crucial step in case-control studies

 Controls must be
▪ Be similar to the cases except for the absence of the disease under
study
▪ Equal ratio
 Sources of controls
 Hospitals:diff illness

 Relatives
Matching
 Definition:

the process by which we select controls in such a way that
they are similar to cases with regard to certain pertinent
selected variables, which are known to influence the out
come of disease and which, if not adequately matched for
comparability, could distort or confound the results.

Example: age.

 Confounding factor
 One which is associated both with exposure and disease;
and is distributed unequally in study and control groups
 Although associated with ‘exposure’ under investigation, it
Measurement of exposure
 Exposure can be measured by
 Interviews
 Questionnaires
 By studying past records
 Examinations
 Bias/ systematic error should be avoided while
measuring the exposure

Analysis
 Involves two steps
1. Exposure rates among cases and controls
2. Estimation of disease risk associated with exposure
(odds ratio)

1. Exposure rates
A case control study of smoking and lung cancer
cases
Smokers 33 controls
55
(a) (b)

non Smokers 2 27
(c) (d)

Total 35 82
(a+c) (b+d)

Exposure rate among cases= (a/a+c)100 = (33/35) 100 = 94.2 %


Exposure rate among controls= (b/b+d)100 = (55/82) 100 = 67 %
2.Estimation of risk
Relative risk (RR) or Risk ratio
= a/(a+b) / c/(c+d)
Relative risk = Incidence among exposed
Incidence among non exposed

Cases Controls
Smokers 33 55
(a) (b)
Non smokers 2 27
(c) (d)
Total 35 82
(a+c) (b+d)
Odds
ratio (cross product ratio)
 It is a key parameter in the analysis of case control
studies
 A measure of the strength of the association
between risk factor and outcome
 Derivation of odds ratio is based on 3 assumptions

 Disease under investigation is a rare one


 Cases are representative of those with disease
 Controls are representative of those without disease


 smokers cases
33 55 controls
(a) (b)
Non smokers 2 27
 (c) (d)

total 35 82
(a+c) (b+d)


 Odds ratio = ad/bc = 33 X27/ 55X2 = 8.1

 Smokers have a risk of having lung cancer 8.1 times that of


non smokers


 Bias in case control study
1. Bias due to confounding
2. Memory bias
3. Selection bias
4. Berksonians bias:different rates of admission to
hosp for people with diff disease
5. Interviewer’s bias
6.
advantages of …
 Relatively easy to carry out
 Rapid and inexpensive (compared with cohort studies)
 Require comparatively few subjects
 suitable to investigate rare diseases or diseases
about which little is known.
 No risk to subjects
 Allows the study of several different aetiological factors (e.g.,
smoking, physical activity and personality characteristics in
myocardial infarction)
 No attrition problems, because case control studies do not
require follow-up of individuals into the future
 Ethical problems minimal

Disadvantages of …
 High chances for bias

 Validation of information obtained is difficult or sometimes
impossible

 Selection of an appropriate control group may be difficult

 We cannot measure incidence, and can only estimate the odds
ratio but not relative risk


 Not suited to the evaluation of therapy or prophylaxis of a
disease

 Another major concern is the representativeness of cases and
Cohort studies
Usually undertaken to obtain additional evidence to

refute or support the existence of an association


between suspected cause and disease


Other names


Incidence study

Forward looking study

Longitudinal study

Prospective study

distinguishing Features of …

 Cohorts are identified prior to the appearance of

the disease under investigation

 Study groups are observed over a period of time to

determine the frequency of disease

 The study proceeds from cause to effect



 Cohort is defined as a group of people who
share a common characteristic or experience
within a defined time period
 Eg, birth cohort,age cohorts, occupational
cohorts, exposure to a drug cohorts,
marriage cohort etc.
 The comparison group may be…
 the general population from which the cohort is

drawn
Indications for …

 When there is a good evidence of an

association between exposure and disease

 When the exposure is rare but the incidence of

disease is high among exposed

 When the attrition can be minimised

 When ample funds are available


of a cohort study
Time

Direction of enquiry

Screening to
exclude those
with the Develop a
condition Disease
With the
characteristi
c Do not
S develop b
 Population A disease
free of M
P Time
condition L
E Develop c
Disease
Without the
characteristi
c
Do not d
Considerations
for selecting cohorts
 Cohorts must be free from the disease under study

 both the groups should be equally susceptible to disease under


study

 Both the groups should be comparable in respect of all possible


variables, except the assumed risk factors

 Diagnostic and eligibility criteria of the disease must be


defined beforehand.

 Inclusion and exclusion criteria should be clearly stated before


the commencement

Steps in …
 Selection of study subjects

 Obtaining data on exposure

 Selection of comparison groups

 Follow up

 Analysis
Selection of study subjects
 Cohorts can be selected from

 General population

 Special groups

▪ Select groups (eg. Doctors, lawyers, teachers, etc.)

▪ Exposure groups

Obtaining data on exposure
 Information can be obtained from
 Cohorts

 Review of records

 Medical examination or special tests

 Environmental surveys

 Information about exposure should facilitate


classification of cohort members
 According to whether or not they were exposed

 According to the degree of exposure



Selection of comparison
groups
 Internal comparisons: no outside comparision group is required

 External comparisons: when degree of exposure is not available,ext cohort .eg:smokers

and non smokers,radiologists and opthamologists.

 Comparison with general population:mortality experience of exposure group is compared

with mortality experience of general populationin same geographic area



Follow up
 Periodic medical examination of each member

 Reviewing physician and hospital records

 Routine surveillence of morbidity and mortality

records

 Mailed questionnaires, telephone interviews, periodic

home visits

Analysis
 Data is analysed interms of

i. Incidence rates of outcome among exposed and non-

exposed

ii. Estimation of risk

▪ Relative risk

▪ Attributable risk
Incidence rates
 Incidence can be Cigarett Lung No lung Total
measured directly e cancer cancer
smoking

 Incidence rate among
smokers = 70/7000 Yes 70 6930 7000
a b a+b
= 10 per
thousand
No 3 2997 3000
 c d c+d
 Incidence rate among
non-smokers=
3/3000 =
1 per 1000
Relative risk
Cigarett Lung No lung Total
 Relative risThe ratio of e cancer cancer
incidence smoking

among exposed and

incidence among Yes 70 6930 7000

non-exposed a b a+b
 InAlso
cid ecalled
n ce a m‘risk
o n g ratio’
e x p o=se d
In cid e n ce a m o n g n o n - e x p o se d No 3 2997 3000
 c d c+d
10 / 1 = 10

 RR=

 RR is the direct RR-i= no assossiation


RR > 1= positive assossiation
measure of strength
of association
Attributable risk
 The difference in incidence rates between exposed
and non-exposed groups

 Also called risk difference




Incident rate among exposed – incidence rate among non-exposedX 100
 Incident rate among exposed
 (10-1/10) X 100 = 90%
of lung cancer was due to their smoking
 It indicates to what extent disease can be
attributed to the exposure
 Suggests the amount of disease that might be
Relative risk X Attributable risk


Relative risk Attributable risk

 Etiological enquiries  Gives a better idea of


 Larger the RR, the impact of a
stronger the successful
association between intervention might
risk factor and have in reducing the
outcome problem
 Does not reflect the 
potential public
health importance


Advantages of cohort
studies
 Allow the possibility of measuring directly
the relative risk of developing the condition for those
who have the characteristic, compared to those who do
not
 Allows for a conclusion of cause-effect relationship

 Because the presence or absence of the risk factor is


recorded before the disease occurs, there is no chance
of bias

 Cohort studies are capable of identifying other


diseases that may be related to the same
risk factor.
 Unlike case-control studies, cohort studies
provide the
possibility of estimating attributable risks,
thus indicating the absolute magnitude of
Disadvantages of cohort
studies
 Not always feasible.
 Relatively inefficient for studying rare conditions.
 They are very costly in time, personnel, space and patient
follow-up.
 Sample sizes required for cohort studies are extremely large,
especially for infrequent conditions; it is usually difficult to
find and manage samples of this size.
 The most serious problem is that of attrition, which can affect
the validity of the conclusion, if it renders the samples less
representative, or if the people who become unavailable are
different from those actually followed up. The higher the
proportion lost (say beyond 10-15%) the more serious the
potential bias.
 There may also be attrition among investigators
who may
lose interest, leave for another job, or become
involved
in another project.

 Over a long period, many changes may occur in the


environment, among individuals or in the type of
intervention, and these may confuse the issue of
association and attributable risk.


Case control study
cohort study
 Proceeds from effect to cause  Proceeds from "cause to effect".
 Starts with the disease  Starts with people exposed to
 Tests whether the suspected risk factor or suspected
exposure occurs more frequently cause.
in those with the disease than  Tests whether disease occurs
among those without the more frequently in those
disease. exposed, than in those not
 Involves fewer number of similarly exposed.
subjects  Involves larger number of
 Yields relatively quick results subjects
 Suitable for the study of rare  Long follow-up period often
diseases needed, involving delayed
 Generally yields only estimate results.
of RR (odds ratio)  Inappropriate when the disease
 Cannot yield information about or exposure under
diseases other than that investigation is rare.
selected for study  Yields incidence rates, RR as
 Relatively inexpensive well as AR.
  Can yield information about
more than one disease
outcome.
 Expensive.
Experimental studies

 Study of epidemics among colonies of experimental animals


such as rats and mice .
 AIMS
 To provide scientific proofs of etiological factors
 To provide a method of measuring the effectiveness and
efficiency of health services
 has all adv and disadv of cohort study and also ethics,cost
and feasibility
 Animal studies: important application

Advantages
1. Bred in lab,and can manipulated easily
2. They multiply rapidly

Disadvantages:
1. Not all human diseases can be reprodeuced
Human studies:


To investigate disease etiology and to evaluate the
preventive ,therapeutic measures

1747-john lind-scurvy

1796-Edward Jennar-cowpox

1. Ethical and logistic considerations,benefits weighed


againsts the risks involved
2. Volunteers –made fully aware of the experiment
3. WHO (1980)-strict code of practice

Randomised controlled trials
Experimental studies
Non-randomized trials

 Randomised controlled trials:


Involves some action,interventionor manipulation such as deliberate application


or withdrawl of suspected cause.


1. Drawing up a protocal
2.
3. Selecting reference and experimental population
4.
5. Randomization
6.
7. Blinding
8.
9. Manipulation or intervention
D Select population
(Reference or target population)
E
s
Select suitable sample
i (Experimental or study population)
G Selection by defined criteria

N Potential participants Non-participants


(Meet selection criteria) (do not meet selection criteria)

o Invitation to participate Non-participants


(do not give consent)
F
Participants

a Randomization &
Experimental group Manipulation,
Follow up
N double blinding
Control group &
Assessment
 Positive results: benefit of exp measure----reduced incidence or
severity of disease or other appropriate outcomes of study.

 Negative results: severity and frequency of side effects and


complications ,if any death


Blinding:
 Randomization cannot guard against these sorts of bias nor the size of
the sample.the technique known as blinding is adopted which can be
done in

Single blind trial:
 here the participant is not aware whether he belongs to study group or
control group.

Double blind trial;
 Here neither the doctor nor the participant is aware of the group
Ethics in research
 First important code of ethics was the NURENBURG
CODE of 1947. “No research could proceed in
human subjects without voluntary consent.”

 Declaration of Helsinki code of ethics on principles


of ethical behaviour was established in HELSINKI-
I in 1975.

 The term “clinical research” to “biomedical research”
was revised in HELSINKI- II in 1975
institutional ethics committee or institutional review
board

 Institutions undertaking clinical trials have to


constitute an Institutional Ethics Committee (IEC)
or Institutional Review Board (IRB).

 It is mandatory that each dissertation research
proposal (synopsis) involving humans (irrespective
of type of study, including questionnaire based
surveys) or animals should be accompanied by a
clearance letter from IEC.

ethics and its
principles


 The science of ideal human character and behavior in
situations where distinction must be made between
right and wrong, duty must be followed and good
inter-personal relations maintained.

 When considering the ethical aspect of health
research the following principles should also be
kept in mind. (Helsinki declaration)

Ethical principles

1. Non-malificence
2. Benificience
3. Veracity or truthfulness
4. Autonomy
5. Justice
6. Confidentiality

submitted to the ethics
committee in the following
manner
1. Clear research objectives and rationale for
undertaking the investigation in human subjects in
the light of existing knowledge.
2.
3. Subject recruitment procedures.
4.
5. Inclusion and exclusion criteria for entry of subjects
in the study.
6.
7. Precise description of methodology of the proposed
research, including intended dosage of drugs,
5. A description of plans to withdraw or withhold
standard therapies in the course of research.
6.
7. The plans for statistical analysis of the study.
8.
9. Procedure for seeking and obtaining informed consent
with sample of patient information sheet and
informed consent forms in English and regional
languages.
10.
11.Safety of proposed intervention and any drug or
9. For research carrying more than minimal risk, an account
of plans to provide medical therapy for such risk or
injury or toxicity due to over dosage should be
included.
10.Proposed compensation and reimbursement of incidental
expenses.
11.
12.Storage and maintenance of all data collected during the
trial.
13.
14.Plans for publication of results- positive or negative- while
maintaining the privacy and confidentiality of the
study participants.
Considerations to be kept in
mind while conducting research:
In any research on human beings, each subject must
be adequately informed of the aim, methods,
anticipated benefits and potential hazards of the
study and the discomfort it may entail.

When obtaining informed consent, we should be
cautious if the subject has a dependent relationship
to us. No pressure or threat should be exercised.

In case of legal incompetence informed consent
should be obtained from the legal guardian in
accordance with the existing legislation.

references
 Behavioural sciences for dentistry. G.Humphris & M.S.Ling.
Churchill Livingstone.2000.

 Health research methodology- a guide for training in


research methods. WHO 1992

 Critical thinking; understanding and evaluating dental


research. D.M.Brunette. Quintessence publishing. 1996.

 Dentistry, dental practice and community. 5th edition. B.A.


Burt & S.A.Eklund. WB Saunders company.

 Park’s text book of preventive and social medicine. 19th


edition. K.Park. Bhanot publishers. 2007.
TH
A
N
K
YO
U