RESEARCH METHODOLOGY
(DESIGN OF STUDY, SAMPLING, DATA COLLECTION AND
ANALYSIS, LEVEL OF EVIDENCE AND GRADES OF
RECOMMENDATION)
Dr Uttam Nepal
2nd yr Resident
MS ENT-HNS
KIST MCTH
ROADMAPS:
 Research: Introduction and its Types
 Study design: Different types of study design
 Sampling : Differnet techniques and its importance
 Methods of data collection, analysis and interpretation
 Evidence and recommendations.
If we knew what it was we were
doing, it would not be called
research, would it?
Albert Einstein
RESEARCH
RESEARCH
 French "recherche“ - to go about seeking
 Research is a quest for knowledge through diligent search or investigation
or experimentation aimed at the discovery and interpretation of new
knowledge (WHO).
 Redman and Mory defined research as a “ systematized effort to gain new
knowledge .”
 CliffordWoody : Research comprises of defining and redefining problems ,
formulating hypothesis, collecting, organising and evaluating data, making
deduction and reaching conclusions and at last carefully testing the
conclusions to determine whether they fit the formulating hypothesis
RESEARCH: NEED AND PURPOSE
 Improve existing knowledge – generate new technologies
 Identify priority problems – design and evaluate policies to deliver greatest
health benefit with available resources
 Open the new horizon for research
RESEARCH: SIGNIFICANCE
 Evidence based practice
 Treatment protocol
 Treatment of sudden sensorineural hearing loss with IV steroid
 Policy making
 Iodine supplementation in salt to prevent goiter in adolescence
 Problem identification and prioritization
 Quality of health service
 Driving force – new research
RESEARCH: IMPORTANCE
 As a postgraduate student
- To critically analyse the information
- Thesis preparation
 As future practitioner
- Evidence based practice
- Professional status
- Participate in research projects
 As an educated citizen
- To understand difference between scientifically acquired information and others
RESEARCH: FIELDS OF APPLICATION
 Useful in policy making
 Treatment protocol
 Investigation
 Sequel/Complication
 Quality of service
 Actual size of problem
 Avenue for further research
TYPES OF RESEARCH
 Basic research
 To generate new knowledge
and technologies
 In vitro / in vivo experiments
(animal experiments)
 eg. p53 gene mutation in
HNSCC
 Applied/Action research
 Involving practical application
 eg. Monoclonal antibody
therapy in HNSCC
 Discriptive research
 Eg. Prevalence of ca larynx in adult
population in Kathmandu
 Analytical research
 Eg. Role of environmental pollution
in allergic rhinitis
TYPES OF RESEARCH
 Quantitative research
o Based on the measurement of
quantity or amount
o eg. Recurrence rate of sinonasal
polyp after FESS
 Qualitative research
o Relating to quality or kind
o eg. Quality of life after surgery
for head and neck cancer
 Outcome research
o Impact of intervention on the patient
in terms of health status and health
related quality of life
o eg : Hearing outcome after butterfly
cartilage tympanoplasty
 Experimental research
o Comparing two groups on one
outcome measure to test some
hypothesis regarding causation
o eg. Comparison of dexamethasone
versus bupivacaine in reducing
early postoperative pain after
tonsillectomy in children
TYPES OF RESEARCH
 Conceptual / Empirical
 Field-setting research or laboratory research or simulation research
 Clinical or diagnostic research
 Health systems research
 Exploratory
 Historical research
HEALTH RESEARCH: TYPES
RESEARCH METHOD AND METHODOLOGY
COMPONENTS OF RESEARCH
 Conceptualizing the problem
o Statement of problem
o Research questions
o Rationale
 Literature review
 Formulating objectives
 Developing testable hypothesis
 Ethical considerations
 Workplan
SELECTION OF TOPIC
 Interest
 Relevance
o Magnitude of problem
o Severity of problem
o Population affected
 Avoidance of duplication
 Feasibility
 Political acceptability
 Applicability
 Cost effectiveness
 Ethical consideration
RESEARCH QUESTION
 “Uncertainty” about something in the population that the investigator wants
to resolve by making measurements in the study population .
 It is best to frame the research question using the PICO format
P- Population/patient/person with(or at risk of) a health problem on which
research is based.
I- Interventions
C-Comparisons
O-Outcome
Often (T) – Time frame is also added to the PICO format
RESEARCH(CONTD.)
Components of a Good Research
 Feasible- Adequate number of participants , technical expertise and
resources .
 Interesting
 Novel – Provides new information
 Ethical- Amenable to a study that ethics committee will approve
 Relevant - To the scientific world of knowledge / clinical practice/ health
policy.
STUDY DESIGN
STUDY DESIGN
STUDY DESIGN: TYPES
 Non intervention studies
 Exploratory studies
 Descriptive studies
 Comparative or analytical studies
 Cross sectional
 Case - control
 Cohort
 Intervention studies
 Experimental studies
 Quasi – experimental studies
 Parallel design
 Cross over design
 Factorial design
 Meta Analysis
NON INTERVENTION STUDIES
Exploratory Study
• To gather preliminary information that
will help define problems and suggest
hypotheses
• Helps in selection of:
• Best research design
• Data collection method
• Selection of subjects
• Audits
• E.g. Quality of discharge Summary in
different department of KISTMCTH
Descriptive study
• In-depth description of characteristic
of one or limited number of cases.
• Case studies: case report of
uncommon diseases
• e.g.. B/L facial nerve palsy
• Case series
CROSS SECTIONAL STUDY
 Quantifying distribution of variable in population at a point of time
 Quantify disease burden
 Useful for hypothesis generation
 Covers a sample of population
 Total population covered:- census
 E.g.. Prevalence of COM, children with OME
OUTCOME
EXPOSURE
STUDY
CROSS SECTIONAL STUDY
Advantages:
 Cheap and simple;
 Ethically safe.
Disadvantages:
 Establishes association at most, not causality;
 Confounders may be unequally distributed;
 Group sizes may be unequal.
CASE CONTROL STUDY
 Compares one group with problem to
another group without
problem(control group)
 Retrospective from outcome to
exposure
 Confounding factors
EXPOSURE STUDY DISEASE
CASE CONTROL STUDY
 Odds Ratio:
o Chances that a case was exposed
to risk factor to the odds that a
control was exposed to risk factor
o Estimation of risk & not a true
risk value
Case Ca Larynx Control Without
Ca
Smoking 33(a) 55(b)
No smoking 2(c) 27(d)
Odd Ratio: a x d/ c x d – 8.1
CASE CONTROL STUDY
Advantages:
 quick and inexpensive;
 Good for rare disorders or those with long lag between exposure and
outcome;
 fewer subjects needed than cross-sectional studies.
 Possibility of exploring multiple exposures
Disadvantages:
 reliance on recall or records to determine exposure status;
 confounders;
 selection of control groups is difficult;
 potential bias: recall, selection.
COHORT STUDY
 Group exposed to risk factor (study
group)  compared with group not
exposed (control group)
 Prospective study, Incidence
 Longer, labour intensive, expensive &
loss to follow up
EXPOSURE STUDY OUTCOME
COHORT STUDY
 Relative Risk (RR):
 Incidence among exposed/ Incidence among non exposed = a/(a+b)/c/(c+d)
 True estimate of risk,  value- strength
 Interpretation of Relative risk:
• RR =1: no association
<1: protective effect
<2 : weak association
>30: almost aetiological association
Ca Larynx No Ca Larynx Total
Smoker 60(a) 40(b) 100 (a+b)
Non smoker 30(c) 70(d) 100 (c+d)
RR:Incidence in Exposed/Incidence of non exposed-60/30-2
COHORT STUDY
Advantages:
 ethically safe;
 subjects can be matched;
 can establish timing and directionality of events;
 eligibility criteria and outcome assessments can be standardized;
Disadvantages:
 controls may be difficult to identify;
 exposure may be linked to a hidden confounder;
 blinding is difficult;
 randomization not present;
 for rare disease, large sample sizes or long follow-up necessary.
INTERVENTION STUDIES
 Experimental study
o Randomized Control Trial( RCT)
• Randomization, Control, Blinding
o Quasi- Experimental Studies
o Parallel Design
o Cross-over design
o Factorial design
 Meta analysis
RANDOMIZED CONTROLLED TRAILS(RCT)
 Can actually prove causation
o At least 2 groups (experiment or intervention & non-intervention)
 Three characteristics:
 Randomization : to allocate subjects to control & experimental group
 Control: to compare with experimental group
 Manipulation: some intervention to one group
QUASI- EXPERIMENTAL STUDY
 Study little or no control over allocation of the treatments or other factors
being studied
 The key difference : lack of random assignment  impractical or unethical
 Easier to set up, minimizes external validity
 Threat to internal validity, value of result less than RCT
PARALLEL DESIGN
 Parallel Groups
 Multiple concurrent experimental arms
o Different treatments
o Different doses
 Control arm(s)
o Placebo, active control
 Balance/imbalanced randomization
 e.g. ISSNHL :- Placebo, i.v steroid, IT steroid
CROSS OVER DESIGN
CROSS OVER DESIGN
FACTORIAL DESIGN
 Evaluates two interventions
simultaneously
 Four possible treatment combinations
 Efficient approach in some
circumstances
 Potentially more informative
approach
 Major concern: interaction of
interventions
CLINICAL TRAILS PHASES
• Phase I: Normal volunteers
• To find Maximum tolerated dose
• Phase II: Patients with Diseases
• To establish effects & side effects
• Phase III: Clinical trial
• Phase IV: Long term
surveillance
Phase I
Phase II
Phase III
Phase IV
SAMPLING
SAMPLING
 Population or Universe: a set of all individuals or
objects having common characteristics
 Sample: subset or part of the population
 Sampling: Process or technique of selecting a sample of
appropriate & manageable size for study
 Sampling unit: breakdown parts of population which are
distinct, unambiguous & non-overlapping
 e.g.. Hospitals, 15-25 yrs
SAMPLING
Advantages
 Reduces cost of study considerably
 Greater speed (less time)
 Greater accuracy
 Increase scope of study: several aspects
 Some tests not possible in population can be applied
 Study can be in depth & more subtle
RELIABLE SAMPLE
 Efficient
 Representative
 Measurable
 Sizeable
 Coverage
 Goal oriented
 Representative of underlying population
 Feasible
 Economic & cost efficient
ERRORS
 Sampling errors
 Repeated sample from same population, result different
 Collection, processing, analysis
 Decrease by increasing sample size
 Non sampling errors
 Observational & defective measurement technique
 Error in editing, coding & tabulating results
 Increased by increasing sample size
TYPES OF SAMPLING
A. Probability
Each element has equal chance of being included
• Simple random
• Systematic random
• Cluster
• Stratified
B. Non-probability
Each element may not have same chance
• Convenience
• Purposive
• Quota sampling
SIMPLE RANDOM SAMPLING
 Equal chance
 Decided by law of chance
 Provides greatest number of
possible sample
 Small sample-Lottery
 Large sample-Table
SYSTEMIC RANDOM SAMPLING
• Pre determined system is followed
• Number of possible sample is greatly reduced
• Every 3rd
or 10th
• First sample is selected randomly
CLUSTER SAMPLING
 Selection made of cluster
 E.g..VDC, tole/ward; military
camp; School
 Prevalence of OME among
children in day care
STRATIFIED SAMPLING
 Population divided into different
strata
 E.g.. Religion; socioeconomic
status
 Random sampling done in each
strata proportionate sampling less
likely to miss smaller group
 e.g.. If out of 1000 in a community,
planned for 100
 Hindu = 850; sample = 85
 Muslim = 100; sample = 10
 Christian = 50, sample = 5
NON PROBABILITY SAMPLING
 Convenience:
oHaphazard, non representative
oPurpose usually for exploratory
oPatient visiting ENT OPD
 Purposive:
oPredetermined idea
oResults can not be generalized
oNatural history of AOM in immunodeficiency
 Quota sampling:
o Population divided into mutually exclusive groups and subjects or unit
selected by judgment and not randomly
PROBABILITY VS NON PROBABILITY SAMPLING
DATA COLLECTION AND
INTERPRETATION
VARIABLES
 Variable
 Any observation that can take on different values
 Attribute
 A specific value on a variable
Variable:Age,Gender
Attribute: 18/19/20,Male/Female
 Types of Variables:
o Independent Variables vs. Dependent Variables
o Qualitative Variables vs. Quantitative Variables
VARIABLES
 Qualitative / categorical
variable
Non-numerical values
o Dichotomus: Antibiotic use
–yes/no, Gender-Male/Female
o Polychotomus: Nationality
o Ordinal: Disease severity
–mild/moderate/severe
 Quantitative variable
Intrinsically numerical
o Continuous – Hearing threshold
o Discrete – Number of attacks of
tonsillitis
VARIABLES
Independent variable
 Factor that is assumed to cause / influence the problem
e.g. Smoking in the study of relationship between smoking and laryngeal
cancer
Dependent variable
 Factor that gets modified under influence of independent variable
e.g. Suffering from laryngeal cancer
SCALES OF MEASUREMENT
 Nominal
o Qualitatative data (Male, Female)
 Ordinal
o Categories are ranked
o eg . Pain - Mild, Moderate, Severe
Stage of cancer – I,II, III,IV
 Interval
o Intervals between Classes equal, zero point arbitrary
o eg. Pain scale (1-10)
IQ score (90,95,100)
 Ratio
STUDY INSTRUMENTS
Tools by which data are collected
 Questionnaire and interview schedules
 Other methods:
o Medical examination
o Laboratory tests
o Screening procedures
o Previous hospital records
o Survey
o Focus group discussion
 Designing of recording forms
 Mailing/telephone/e-mail/face to face interview
PURPOSE OF DATA COLLECTION
 Get information
 Monitor progress
 Evaluate performance & use of resources e.g. audit
 Identify gaps between knowledge & practice
 Evaluate impact of programs
 Make decision
 Utilize in planning
DATA COLLECTION: STEPS
 Identification of objective
 Listing target population
 Identification of time frame
 Selection of data collection instrument
 Development of data collection method
 Selection of proper sampling design
 Organization
 Precoding
 Pretesting
 Field survey launching
DATA ANALYSIS AND INTERPRETATION
Plan for analysis beforehand
Description should include
 Design of analysis form
 Plan for processing & coding data
 Choice of statistical method
CRITERIA IN SELECTING APPROPRIATE
ANALYTICAL METHOD
 Objectives of the study
 Design of the study
 Scale by which the variables are measured
 Sample size
 Number of variables to be analyzed
METHODS OF DATA INTERPRETATION
PRESENTATION
 Table:
o Simple
o Should be numbered
o Self explanatory title
o Heading of rows or column clear & concise
o Foot note may be given
o Presented according to size or importance
METHODS OF DATA INTERPRETATION PRESENTATION
GRAPHS:
 Methods of showing quantitative data using a coordinated system
o Arithmetic scale line
o Semi logarithm scale line
o Histogram
o Frequency polygon
o Scatter diagram
METHODS OF DATA INTERPRETATION
PRESENTATION
 Charts:
 Bar
 Pictogram
 Pie
 Geographic co-ordinate
 Flow
 Organization
METHODS OF DATA PRESENTATION
 Percentage
o no of units with certain characteristics x100
no of units in sample
o n = 50 ; M = 20 : F = 30 ; % of M = 40%
 Proportion
o Compares relation in magnitude one part of study unit to whole
o M = 2/5 : F = 3/5
 Ratio
o Relation in size between 2 or more parts
o M:F=2:3
 Rate
o Amount or degree of something measured in specific period of time
MEASUREMENTS
 Measures of central tendency
o Mean
o Median
o Mode
 Hb of patients admitted with epistaxis
(in Gm%)
13.2, 9.5, 11.7, 13.6, 10.4, 11.7, 9.9,
14.0, 12.4, 11.9, 10.3
o Mean = 11.7
o Median = 9.5, 9.9, 10.3, 10.4, 11.7,
11.7, 11.9, 12.4, 13.2, 13.6, 14.0
o Mode = 11.7
MEASUREMENTS
Measurement of dispersion
 Range:
o Difference between largest and smallest value
 Percentiles:
o Parts that divide measurements into 100 equal parts
o e.g. 3rd
percentile, 10th
percentile
 Standard deviation:
o Measure which describes how much individual measurement differs on an average
from mean
o ± 1 SD = 68.2%
o ± 2 SD = 95.4%
o ± 3 SD = 99.6%
DATA ANALYSIS
 Manually
 Using computer programs
o Excel
o Data base
o SPSS
o Epi-info
o SAS: Statistical Analysis Software
DETERMING DIFFERENCE BETWEEN GROUPS
SIGNIFICANCE TEST APPLICATION
Difference between groups
 X2
test
 Sign test
 t-test
Association between groups
 X2
test
 Odds Ratio
 Relative Risk
 Pearson’s
 Spearman's
SIGNIFICANCE TEST APPLICATION
 Chi Square test
 Criterion for using 2- test
 Data should be categorical or
qualitative one
 2- test is used to:
 Find out the significance of difference
between two proportion
Find out the association or relation
between two variables
 Students’T test
• Criterion for using t-test
 distribution should be normal
 data set may be quantitative
 sample size  30
 Z test
• Criterion for using Z-test
 Distribution should be normal
 Data set may be qualitative or quantitative
 Sample size  30
Spearmans’s rank correlation coefficient()
 = 1 - 6  d2
/ n ( n2
– 1)
Where,
d - difference of paired ordered observations &
n - number of paired observations
EVIDENCE AND
RECOMMENDATION
EVIDENCE
 Evidence
a thing or things helpful in forming
a conclusion or judgment
 Evidenced –Based Medicine
“the integration of the best
research evidence with clinical
expertise and patient value”
“conscientious, explicit and
judicious use of current best evidence
in making decisions about the care of
individual patients” sackett et al 1996
BMJ
LEVEL OF EVIDENCE
LEVEL OF EVIDENCE
 Level A: Consistent Randomized Controlled Clinical Trial, cohort study, clinical
decision rule validated in different populations.
 Level B: Consistent Retrospective Cohort, Exploratory Cohort, Ecological Study,
Outcomes Research, case-control study; or extrapolations from level A studies.
 Level C: Case-series study or extrapolations from level B studies.
 Level D: Expert opinion without explicit critical appraisal, or based on physiology,
bench research or first principles.
QUANTIFICATION OF EVIDENCE
GRADES OF RECOMMENDATION
 Grade A: Good scientific evidence suggests that the benefits of the clinical service
substantially outweighs the potential risks. Clinicians should discuss the service
with eligible patients.
 Garde B: At least fair scientific evidence suggests that the benefits of the clinical
service outweighs the potential risks. Clinicians should discuss the service with
eligible patients.
 Garde C: At least fair scientific evidence suggests that there are benefits provided
by the clinical service, but the balance between benefits and risks are too close for
making general recommendations. Clinicians need not offer it unless there are
individual considerations.
GRADES OF RECOMMENDATION
 Grade D: At least fair scientific evidence suggests that the risks of the clinical
service outweighs potential benefits. Clinicians should not routinely offer the
service to asymptomatic patients.
 Garde N : Scientific evidence is lacking, of poor quality, or conflicting, such that the
risk versus benefit balance cannot be assessed. Clinicians should help patients
understand the uncertainty surrounding the clinical service.
LEVEL OF EVIDENCE AND GRADE OF
RECOMMENDATON
SUMMARY
 Research is a quest for knowledge through diligent search or investigation or
experimentation aimed at the discovery and interpretation of new knowledge
 Research is very important aspect in medical field.
 RCTs are regularly done trails in medical field
 Sampling and its different methods are used for minimizing error
 Mean, mode and median are used for measuring central tendency ; Range,
percentile and SD are used for measuring dispersion
 X2
is used for measuring association and difference between groups
 Level of evidence and Grade of Recommendation are associated with each other
REFERENCES:
 Scott-Brown’s Otorhinolaryngology, Head and Neck Surgery, 8th
edition
 Park’s Text book of social and preventive medicine ,21st
edition
Thank
you

Research Methodology and study design.pptx

  • 1.
    RESEARCH METHODOLOGY (DESIGN OFSTUDY, SAMPLING, DATA COLLECTION AND ANALYSIS, LEVEL OF EVIDENCE AND GRADES OF RECOMMENDATION) Dr Uttam Nepal 2nd yr Resident MS ENT-HNS KIST MCTH
  • 2.
    ROADMAPS:  Research: Introductionand its Types  Study design: Different types of study design  Sampling : Differnet techniques and its importance  Methods of data collection, analysis and interpretation  Evidence and recommendations.
  • 3.
    If we knewwhat it was we were doing, it would not be called research, would it? Albert Einstein
  • 4.
  • 5.
    RESEARCH  French "recherche“- to go about seeking  Research is a quest for knowledge through diligent search or investigation or experimentation aimed at the discovery and interpretation of new knowledge (WHO).  Redman and Mory defined research as a “ systematized effort to gain new knowledge .”  CliffordWoody : Research comprises of defining and redefining problems , formulating hypothesis, collecting, organising and evaluating data, making deduction and reaching conclusions and at last carefully testing the conclusions to determine whether they fit the formulating hypothesis
  • 6.
    RESEARCH: NEED ANDPURPOSE  Improve existing knowledge – generate new technologies  Identify priority problems – design and evaluate policies to deliver greatest health benefit with available resources  Open the new horizon for research
  • 7.
    RESEARCH: SIGNIFICANCE  Evidencebased practice  Treatment protocol  Treatment of sudden sensorineural hearing loss with IV steroid  Policy making  Iodine supplementation in salt to prevent goiter in adolescence  Problem identification and prioritization  Quality of health service  Driving force – new research
  • 8.
    RESEARCH: IMPORTANCE  Asa postgraduate student - To critically analyse the information - Thesis preparation  As future practitioner - Evidence based practice - Professional status - Participate in research projects  As an educated citizen - To understand difference between scientifically acquired information and others
  • 9.
    RESEARCH: FIELDS OFAPPLICATION  Useful in policy making  Treatment protocol  Investigation  Sequel/Complication  Quality of service  Actual size of problem  Avenue for further research
  • 10.
    TYPES OF RESEARCH Basic research  To generate new knowledge and technologies  In vitro / in vivo experiments (animal experiments)  eg. p53 gene mutation in HNSCC  Applied/Action research  Involving practical application  eg. Monoclonal antibody therapy in HNSCC  Discriptive research  Eg. Prevalence of ca larynx in adult population in Kathmandu  Analytical research  Eg. Role of environmental pollution in allergic rhinitis
  • 11.
    TYPES OF RESEARCH Quantitative research o Based on the measurement of quantity or amount o eg. Recurrence rate of sinonasal polyp after FESS  Qualitative research o Relating to quality or kind o eg. Quality of life after surgery for head and neck cancer  Outcome research o Impact of intervention on the patient in terms of health status and health related quality of life o eg : Hearing outcome after butterfly cartilage tympanoplasty  Experimental research o Comparing two groups on one outcome measure to test some hypothesis regarding causation o eg. Comparison of dexamethasone versus bupivacaine in reducing early postoperative pain after tonsillectomy in children
  • 12.
    TYPES OF RESEARCH Conceptual / Empirical  Field-setting research or laboratory research or simulation research  Clinical or diagnostic research  Health systems research  Exploratory  Historical research
  • 13.
  • 14.
  • 15.
    COMPONENTS OF RESEARCH Conceptualizing the problem o Statement of problem o Research questions o Rationale  Literature review  Formulating objectives  Developing testable hypothesis  Ethical considerations  Workplan
  • 16.
    SELECTION OF TOPIC Interest  Relevance o Magnitude of problem o Severity of problem o Population affected  Avoidance of duplication  Feasibility  Political acceptability  Applicability  Cost effectiveness  Ethical consideration
  • 17.
    RESEARCH QUESTION  “Uncertainty”about something in the population that the investigator wants to resolve by making measurements in the study population .  It is best to frame the research question using the PICO format P- Population/patient/person with(or at risk of) a health problem on which research is based. I- Interventions C-Comparisons O-Outcome Often (T) – Time frame is also added to the PICO format
  • 18.
    RESEARCH(CONTD.) Components of aGood Research  Feasible- Adequate number of participants , technical expertise and resources .  Interesting  Novel – Provides new information  Ethical- Amenable to a study that ethics committee will approve  Relevant - To the scientific world of knowledge / clinical practice/ health policy.
  • 19.
  • 20.
  • 21.
    STUDY DESIGN: TYPES Non intervention studies  Exploratory studies  Descriptive studies  Comparative or analytical studies  Cross sectional  Case - control  Cohort  Intervention studies  Experimental studies  Quasi – experimental studies  Parallel design  Cross over design  Factorial design  Meta Analysis
  • 22.
    NON INTERVENTION STUDIES ExploratoryStudy • To gather preliminary information that will help define problems and suggest hypotheses • Helps in selection of: • Best research design • Data collection method • Selection of subjects • Audits • E.g. Quality of discharge Summary in different department of KISTMCTH Descriptive study • In-depth description of characteristic of one or limited number of cases. • Case studies: case report of uncommon diseases • e.g.. B/L facial nerve palsy • Case series
  • 23.
    CROSS SECTIONAL STUDY Quantifying distribution of variable in population at a point of time  Quantify disease burden  Useful for hypothesis generation  Covers a sample of population  Total population covered:- census  E.g.. Prevalence of COM, children with OME OUTCOME EXPOSURE STUDY
  • 24.
    CROSS SECTIONAL STUDY Advantages: Cheap and simple;  Ethically safe. Disadvantages:  Establishes association at most, not causality;  Confounders may be unequally distributed;  Group sizes may be unequal.
  • 25.
    CASE CONTROL STUDY Compares one group with problem to another group without problem(control group)  Retrospective from outcome to exposure  Confounding factors EXPOSURE STUDY DISEASE
  • 26.
    CASE CONTROL STUDY Odds Ratio: o Chances that a case was exposed to risk factor to the odds that a control was exposed to risk factor o Estimation of risk & not a true risk value Case Ca Larynx Control Without Ca Smoking 33(a) 55(b) No smoking 2(c) 27(d) Odd Ratio: a x d/ c x d – 8.1
  • 27.
    CASE CONTROL STUDY Advantages: quick and inexpensive;  Good for rare disorders or those with long lag between exposure and outcome;  fewer subjects needed than cross-sectional studies.  Possibility of exploring multiple exposures Disadvantages:  reliance on recall or records to determine exposure status;  confounders;  selection of control groups is difficult;  potential bias: recall, selection.
  • 28.
    COHORT STUDY  Groupexposed to risk factor (study group)  compared with group not exposed (control group)  Prospective study, Incidence  Longer, labour intensive, expensive & loss to follow up EXPOSURE STUDY OUTCOME
  • 29.
    COHORT STUDY  RelativeRisk (RR):  Incidence among exposed/ Incidence among non exposed = a/(a+b)/c/(c+d)  True estimate of risk,  value- strength  Interpretation of Relative risk: • RR =1: no association <1: protective effect <2 : weak association >30: almost aetiological association Ca Larynx No Ca Larynx Total Smoker 60(a) 40(b) 100 (a+b) Non smoker 30(c) 70(d) 100 (c+d) RR:Incidence in Exposed/Incidence of non exposed-60/30-2
  • 30.
    COHORT STUDY Advantages:  ethicallysafe;  subjects can be matched;  can establish timing and directionality of events;  eligibility criteria and outcome assessments can be standardized; Disadvantages:  controls may be difficult to identify;  exposure may be linked to a hidden confounder;  blinding is difficult;  randomization not present;  for rare disease, large sample sizes or long follow-up necessary.
  • 31.
    INTERVENTION STUDIES  Experimentalstudy o Randomized Control Trial( RCT) • Randomization, Control, Blinding o Quasi- Experimental Studies o Parallel Design o Cross-over design o Factorial design  Meta analysis
  • 32.
    RANDOMIZED CONTROLLED TRAILS(RCT) Can actually prove causation o At least 2 groups (experiment or intervention & non-intervention)  Three characteristics:  Randomization : to allocate subjects to control & experimental group  Control: to compare with experimental group  Manipulation: some intervention to one group
  • 33.
    QUASI- EXPERIMENTAL STUDY Study little or no control over allocation of the treatments or other factors being studied  The key difference : lack of random assignment  impractical or unethical  Easier to set up, minimizes external validity  Threat to internal validity, value of result less than RCT
  • 34.
    PARALLEL DESIGN  ParallelGroups  Multiple concurrent experimental arms o Different treatments o Different doses  Control arm(s) o Placebo, active control  Balance/imbalanced randomization  e.g. ISSNHL :- Placebo, i.v steroid, IT steroid
  • 35.
  • 36.
  • 37.
    FACTORIAL DESIGN  Evaluatestwo interventions simultaneously  Four possible treatment combinations  Efficient approach in some circumstances  Potentially more informative approach  Major concern: interaction of interventions
  • 38.
    CLINICAL TRAILS PHASES •Phase I: Normal volunteers • To find Maximum tolerated dose • Phase II: Patients with Diseases • To establish effects & side effects • Phase III: Clinical trial • Phase IV: Long term surveillance Phase I Phase II Phase III Phase IV
  • 39.
  • 40.
    SAMPLING  Population orUniverse: a set of all individuals or objects having common characteristics  Sample: subset or part of the population  Sampling: Process or technique of selecting a sample of appropriate & manageable size for study  Sampling unit: breakdown parts of population which are distinct, unambiguous & non-overlapping  e.g.. Hospitals, 15-25 yrs
  • 41.
    SAMPLING Advantages  Reduces costof study considerably  Greater speed (less time)  Greater accuracy  Increase scope of study: several aspects  Some tests not possible in population can be applied  Study can be in depth & more subtle
  • 42.
    RELIABLE SAMPLE  Efficient Representative  Measurable  Sizeable  Coverage  Goal oriented  Representative of underlying population  Feasible  Economic & cost efficient
  • 43.
    ERRORS  Sampling errors Repeated sample from same population, result different  Collection, processing, analysis  Decrease by increasing sample size  Non sampling errors  Observational & defective measurement technique  Error in editing, coding & tabulating results  Increased by increasing sample size
  • 44.
    TYPES OF SAMPLING A.Probability Each element has equal chance of being included • Simple random • Systematic random • Cluster • Stratified B. Non-probability Each element may not have same chance • Convenience • Purposive • Quota sampling
  • 45.
    SIMPLE RANDOM SAMPLING Equal chance  Decided by law of chance  Provides greatest number of possible sample  Small sample-Lottery  Large sample-Table
  • 46.
    SYSTEMIC RANDOM SAMPLING •Pre determined system is followed • Number of possible sample is greatly reduced • Every 3rd or 10th • First sample is selected randomly
  • 47.
    CLUSTER SAMPLING  Selectionmade of cluster  E.g..VDC, tole/ward; military camp; School  Prevalence of OME among children in day care
  • 48.
    STRATIFIED SAMPLING  Populationdivided into different strata  E.g.. Religion; socioeconomic status  Random sampling done in each strata proportionate sampling less likely to miss smaller group  e.g.. If out of 1000 in a community, planned for 100  Hindu = 850; sample = 85  Muslim = 100; sample = 10  Christian = 50, sample = 5
  • 49.
    NON PROBABILITY SAMPLING Convenience: oHaphazard, non representative oPurpose usually for exploratory oPatient visiting ENT OPD  Purposive: oPredetermined idea oResults can not be generalized oNatural history of AOM in immunodeficiency  Quota sampling: o Population divided into mutually exclusive groups and subjects or unit selected by judgment and not randomly
  • 50.
    PROBABILITY VS NONPROBABILITY SAMPLING
  • 51.
  • 52.
    VARIABLES  Variable  Anyobservation that can take on different values  Attribute  A specific value on a variable Variable:Age,Gender Attribute: 18/19/20,Male/Female  Types of Variables: o Independent Variables vs. Dependent Variables o Qualitative Variables vs. Quantitative Variables
  • 53.
    VARIABLES  Qualitative /categorical variable Non-numerical values o Dichotomus: Antibiotic use –yes/no, Gender-Male/Female o Polychotomus: Nationality o Ordinal: Disease severity –mild/moderate/severe  Quantitative variable Intrinsically numerical o Continuous – Hearing threshold o Discrete – Number of attacks of tonsillitis
  • 54.
    VARIABLES Independent variable  Factorthat is assumed to cause / influence the problem e.g. Smoking in the study of relationship between smoking and laryngeal cancer Dependent variable  Factor that gets modified under influence of independent variable e.g. Suffering from laryngeal cancer
  • 55.
    SCALES OF MEASUREMENT Nominal o Qualitatative data (Male, Female)  Ordinal o Categories are ranked o eg . Pain - Mild, Moderate, Severe Stage of cancer – I,II, III,IV  Interval o Intervals between Classes equal, zero point arbitrary o eg. Pain scale (1-10) IQ score (90,95,100)  Ratio
  • 56.
    STUDY INSTRUMENTS Tools bywhich data are collected  Questionnaire and interview schedules  Other methods: o Medical examination o Laboratory tests o Screening procedures o Previous hospital records o Survey o Focus group discussion  Designing of recording forms  Mailing/telephone/e-mail/face to face interview
  • 57.
    PURPOSE OF DATACOLLECTION  Get information  Monitor progress  Evaluate performance & use of resources e.g. audit  Identify gaps between knowledge & practice  Evaluate impact of programs  Make decision  Utilize in planning
  • 58.
    DATA COLLECTION: STEPS Identification of objective  Listing target population  Identification of time frame  Selection of data collection instrument  Development of data collection method  Selection of proper sampling design  Organization  Precoding  Pretesting  Field survey launching
  • 59.
    DATA ANALYSIS ANDINTERPRETATION Plan for analysis beforehand Description should include  Design of analysis form  Plan for processing & coding data  Choice of statistical method
  • 60.
    CRITERIA IN SELECTINGAPPROPRIATE ANALYTICAL METHOD  Objectives of the study  Design of the study  Scale by which the variables are measured  Sample size  Number of variables to be analyzed
  • 61.
    METHODS OF DATAINTERPRETATION PRESENTATION  Table: o Simple o Should be numbered o Self explanatory title o Heading of rows or column clear & concise o Foot note may be given o Presented according to size or importance
  • 62.
    METHODS OF DATAINTERPRETATION PRESENTATION GRAPHS:  Methods of showing quantitative data using a coordinated system o Arithmetic scale line o Semi logarithm scale line o Histogram o Frequency polygon o Scatter diagram
  • 63.
    METHODS OF DATAINTERPRETATION PRESENTATION  Charts:  Bar  Pictogram  Pie  Geographic co-ordinate  Flow  Organization
  • 64.
    METHODS OF DATAPRESENTATION  Percentage o no of units with certain characteristics x100 no of units in sample o n = 50 ; M = 20 : F = 30 ; % of M = 40%  Proportion o Compares relation in magnitude one part of study unit to whole o M = 2/5 : F = 3/5  Ratio o Relation in size between 2 or more parts o M:F=2:3  Rate o Amount or degree of something measured in specific period of time
  • 65.
    MEASUREMENTS  Measures ofcentral tendency o Mean o Median o Mode  Hb of patients admitted with epistaxis (in Gm%) 13.2, 9.5, 11.7, 13.6, 10.4, 11.7, 9.9, 14.0, 12.4, 11.9, 10.3 o Mean = 11.7 o Median = 9.5, 9.9, 10.3, 10.4, 11.7, 11.7, 11.9, 12.4, 13.2, 13.6, 14.0 o Mode = 11.7
  • 66.
    MEASUREMENTS Measurement of dispersion Range: o Difference between largest and smallest value  Percentiles: o Parts that divide measurements into 100 equal parts o e.g. 3rd percentile, 10th percentile  Standard deviation: o Measure which describes how much individual measurement differs on an average from mean o ± 1 SD = 68.2% o ± 2 SD = 95.4% o ± 3 SD = 99.6%
  • 67.
    DATA ANALYSIS  Manually Using computer programs o Excel o Data base o SPSS o Epi-info o SAS: Statistical Analysis Software
  • 68.
  • 69.
    SIGNIFICANCE TEST APPLICATION Differencebetween groups  X2 test  Sign test  t-test Association between groups  X2 test  Odds Ratio  Relative Risk  Pearson’s  Spearman's
  • 70.
    SIGNIFICANCE TEST APPLICATION Chi Square test  Criterion for using 2- test  Data should be categorical or qualitative one  2- test is used to:  Find out the significance of difference between two proportion Find out the association or relation between two variables  Students’T test • Criterion for using t-test  distribution should be normal  data set may be quantitative  sample size  30  Z test • Criterion for using Z-test  Distribution should be normal  Data set may be qualitative or quantitative  Sample size  30 Spearmans’s rank correlation coefficient()  = 1 - 6  d2 / n ( n2 – 1) Where, d - difference of paired ordered observations & n - number of paired observations
  • 71.
  • 72.
    EVIDENCE  Evidence a thingor things helpful in forming a conclusion or judgment  Evidenced –Based Medicine “the integration of the best research evidence with clinical expertise and patient value” “conscientious, explicit and judicious use of current best evidence in making decisions about the care of individual patients” sackett et al 1996 BMJ
  • 73.
  • 74.
    LEVEL OF EVIDENCE Level A: Consistent Randomized Controlled Clinical Trial, cohort study, clinical decision rule validated in different populations.  Level B: Consistent Retrospective Cohort, Exploratory Cohort, Ecological Study, Outcomes Research, case-control study; or extrapolations from level A studies.  Level C: Case-series study or extrapolations from level B studies.  Level D: Expert opinion without explicit critical appraisal, or based on physiology, bench research or first principles.
  • 75.
  • 76.
    GRADES OF RECOMMENDATION Grade A: Good scientific evidence suggests that the benefits of the clinical service substantially outweighs the potential risks. Clinicians should discuss the service with eligible patients.  Garde B: At least fair scientific evidence suggests that the benefits of the clinical service outweighs the potential risks. Clinicians should discuss the service with eligible patients.  Garde C: At least fair scientific evidence suggests that there are benefits provided by the clinical service, but the balance between benefits and risks are too close for making general recommendations. Clinicians need not offer it unless there are individual considerations.
  • 77.
    GRADES OF RECOMMENDATION Grade D: At least fair scientific evidence suggests that the risks of the clinical service outweighs potential benefits. Clinicians should not routinely offer the service to asymptomatic patients.  Garde N : Scientific evidence is lacking, of poor quality, or conflicting, such that the risk versus benefit balance cannot be assessed. Clinicians should help patients understand the uncertainty surrounding the clinical service.
  • 78.
    LEVEL OF EVIDENCEAND GRADE OF RECOMMENDATON
  • 79.
    SUMMARY  Research isa quest for knowledge through diligent search or investigation or experimentation aimed at the discovery and interpretation of new knowledge  Research is very important aspect in medical field.  RCTs are regularly done trails in medical field  Sampling and its different methods are used for minimizing error  Mean, mode and median are used for measuring central tendency ; Range, percentile and SD are used for measuring dispersion  X2 is used for measuring association and difference between groups  Level of evidence and Grade of Recommendation are associated with each other
  • 80.
    REFERENCES:  Scott-Brown’s Otorhinolaryngology,Head and Neck Surgery, 8th edition  Park’s Text book of social and preventive medicine ,21st edition
  • 81.