Research Methodology

Research Methodology Dr. Sawsan Mustafa Abdalla

Associate Prof .faculty of medicineCommunity Department.

ResearchResearch

Research is Research is ““the systematic collection, the systematic collection, analysis and interpretation of data to analysis and interpretation of data to answer a certain question or to solve answer a certain question or to solve a problema problem””

Purposes of ResearchPurposes of Research

Research serves two Purposes :-Research serves two Purposes :-

1- Generates new knowledge and 1- Generates new knowledge and technologies to deal with major technologies to deal with major health problemshealth problems““ basic research basic research””

2- Identifies priority problems , 2- Identifies priority problems , evaluates polices and programs evaluates polices and programs ““applied researchapplied research””

The importance of ResearchThe importance of Research

Why do we carry out research ?Why do we carry out research ?

It is generally recognized that there is It is generally recognized that there is a wide gap between data available, a wide gap between data available, and data needed for management , and data needed for management , planning and decision making, so planning and decision making, so research is needed to bridge this gap research is needed to bridge this gap

Characteristics of researchCharacteristics of research

It demands a clear statement of the It demands a clear statement of the problem problem

It requires a plan It requires a plan It builds on existing data It builds on existing data It collects new data It collects new data

Classification of health researchClassification of health research

Bio medial research Bio medial research Clinical research Clinical research Epidemiological research Epidemiological research Health system research Health system research

11--Bio medical researchBio medical research

Bio Medical research focuses on the Bio Medical research focuses on the individual individual

It concentrates on how the body It concentrates on how the body works works i.e. Biological process , i.e. Biological process , body structure and functions , and body structure and functions , and the pathological mechanisms the pathological mechanisms occurring within the bodyoccurring within the body

Clinical researchClinical research

Clinical research focuses on the Clinical research focuses on the individual. It deals with the response individual. It deals with the response of the body to various preventive , of the body to various preventive , diagnostic or therapeutic diagnostic or therapeutic interventionsinterventions

ExampleExample:-:- The efficacy of long acting penicillin The efficacy of long acting penicillin

on tuberculous patients on tuberculous patients

Epidemiological researchEpidemiological research-:-:

Epidemiological research focuses on Epidemiological research focuses on the population , and considers the the population , and considers the frequency , distribution and frequency , distribution and determinants of diseasesdeterminants of diseases

Example:Example:-- Epidemiology of malaria in Khartoum Epidemiology of malaria in Khartoum

statestate Pattern of health problems in under Pattern of health problems in under

five children in Omdorman area .five children in Omdorman area .

Health system research (H.S.R.)Health system research (H.S.R.)

Health system research focuses on Health system research focuses on how well is the health system how well is the health system functioning , such as cost and quality functioning , such as cost and quality of health services etc of health services etc

Health system research aims to Health system research aims to provide information which improve provide information which improve the health system. the health system.

Types of Health system researchTypes of Health system research

Operational research Operational research Health policy researchHealth policy research

Operational researchOperational research

Operational research is the process Operational research is the process of identifying and solving health of identifying and solving health program problems. It is designed to program problems. It is designed to improve effectiveness and quality of improve effectiveness and quality of health services delivered by health health services delivered by health providers , and the availability , providers , and the availability , accessibility and acceptability of accessibility and acceptability of health services delivered . health services delivered .

Health policy researchHealth policy research

It looks over the policies e.g. allocation It looks over the policies e.g. allocation of resourcesof resources

CRITERIA OF CRITERIA OF A RESEARCH TOPICA RESEARCH TOPIC

11--Percived discrepancy between what is Percived discrepancy between what is existing and what is expectedexisting and what is expected

22 - -A question why this discrepancy A question why this discrepancy existsexists

33 - -More than one answer to the More than one answer to the question is expectedquestion is expected

CRITERIA FOR SELECTIONCRITERIA FOR SELECTIONA RESEARCH TOPICA RESEARCH TOPIC

The problem selected for the research should The problem selected for the research should fulfill the following criteria:fulfill the following criteria:

1.1. RELIVANCERELIVANCE:-THE PROBLEM SHOULD BE AN :-THE PROBLEM SHOULD BE AN IMPORTANT HEALTH PROBLEM.IMPORTANT HEALTH PROBLEM.

2. 2. APPLICABLEAPPLICABLE:THE PROBLEM SHOULD HAVE SOME :THE PROBLEM SHOULD HAVE SOME CHANCE OF BEING SOLVED.CHANCE OF BEING SOLVED.

3. 3. FEASIBILITYFEASIBILITY: THE RESEARCH SHOULD BE : THE RESEARCH SHOULD BE FEASIBLE WITHIN THE AVAILABLE RESOURCES.FEASIBLE WITHIN THE AVAILABLE RESOURCES.

CRITERIA FOR SELECTIONCRITERIA FOR SELECTION A RESEARCH TOPIC A RESEARCH TOPIC

4-4-Political acceptabilityPolitical acceptability The ultimate goal of a research is to The ultimate goal of a research is to

provide decision provide decision –– makers and makers and managers with results , so it is managers with results , so it is advisable to choose a topic that has advisable to choose a topic that has the interest and support of the the interest and support of the authorities . This will increase the authorities . This will increase the chance for recommendations to be chance for recommendations to be implemented . implemented .

Urgency of results needed Urgency of results needed According to the urgency needed According to the urgency needed

for data , the researcher should for data , the researcher should decide what research to be done decide what research to be done first and which can be done laterfirst and which can be done later. .

55--URGENCYURGENCY::

66--Ethical acceptabilityEthical acceptability

Ethical issues should be considered Ethical issues should be considered when we are trying to choose a when we are trying to choose a research topic, for we may do harm research topic, for we may do harm on others when we are carrying out on others when we are carrying out research. Acceptance of research by research. Acceptance of research by the study subjects is important and the study subjects is important and taking consents from them is always taking consents from them is always importantimportant..

77 - -Avoidance of duplicationAvoidance of duplication Before you decide to conduct a research, you Before you decide to conduct a research, you

should find out whether the suggested topic should find out whether the suggested topic was investigated before in this area or was investigated before in this area or another area with similar conditions. If the another area with similar conditions. If the topic has been investigated the results topic has been investigated the results should be reviewed to explore whether major should be reviewed to explore whether major questions need further investigations, if not questions need further investigations, if not this topic is not suitable for research and this topic is not suitable for research and should be discarded.should be discarded.

THE RESEARCH SHOULD BE COST/EFFECTIVETHE RESEARCH SHOULD BE COST/EFFECTIVE

RATINGRATING

gradegrade

itemitem332211

RelevanceRelevanceV.RV.R..RRNotNot

DuplicationDuplicationNotNotpartiallypartiallyFullyFully

ApplicabilityApplicabilityV applicV applicApplicApplic..Not appNot app..

FeasibilityFeasibilityV.FV.F..FFNotNot

UrgencyUrgencyV. urgentV. urgentUrgentUrgentnotnot

P. acceptabilityP. acceptabilityV. acceptedV. acceptedAcceptedAcceptednotnot

Ethical accepEthical accep..NoNominorminormajormajor

TotalTotal

Definition of theDefinition of the problemproblem::

Once the researcher has decided on the Once the researcher has decided on the problem of the research, then he needs to problem of the research, then he needs to have a have a definition/descriptiondefinition/description of the problem of the problem written in a concise clear manner.written in a concise clear manner. It should contain It should contain information such asinformation such as::

Background informationBackground information concerning the health concerning the health status of the community.status of the community.

Basic descriptionBasic description of the problem.of the problem. JustificationJustification.. Mention previous studiesMention previous studies

ObjectivesObjectives

ObjectivesObjectives

The goals to be achieved by the The goals to be achieved by the research projectresearch project . .

Why should the Objectives be Why should the Objectives be developeddeveloped ? ?

11--Focus the study (Narrow it down to Focus the study (Narrow it down to essentials)essentials)

22 - -Avoid collection of unnecessary dataAvoid collection of unnecessary data

33 - -Organize the study in clearly defined Organize the study in clearly defined partsparts

TypesTypes::

General: General: Identifies in general terms, what is to Identifies in general terms, what is to

be accomplished by the research be accomplished by the research project.project.

Specific: Specific: Identifies in details the specific aims of Identifies in details the specific aims of

the research projectthe research project

ExampleExample

GeneralGeneral::

To study the reasons for low utilization of To study the reasons for low utilization of MCH Services in Khartoum State MCH Services in Khartoum State –– 2006 2006

NoteNote::

Gen. Objective is clearly related to the Gen. Objective is clearly related to the statement of the problemstatement of the problem..

SpecificSpecific- :- :

-To determine the level of utilization of -To determine the level of utilization of MCH Services in Khartoum StateMCH Services in Khartoum State

-To identify whether there are variations -To identify whether there are variations in Utilization of MCH Services andin Utilization of MCH Services and

- Seasons- Seasons

- Type of clinics- Type of clinics

Types of specific objectivesTypes of specific objectives

1. Estimation objectives1. Estimation objectives

E.g. To determine incidence rateE.g. To determine incidence rate

2. Association objectives2. Association objectives

Aims at Association between the factor of Aims at Association between the factor of interest and a particular eventinterest and a particular event

Types of specific objectives- Types of specific objectives- ContCont....

ExampleExample

To identify whether there is To identify whether there is Association of low utilization of MCH Association of low utilization of MCH clinics and mother educationclinics and mother education

3. Evaluation objectives:3. Evaluation objectives:

To evaluate the effect of an To evaluate the effect of an investigationinvestigation

E.g. the effect of H.E. on utilization of E.g. the effect of H.E. on utilization of MCH services.MCH services.

Characteristics of specific objectivesCharacteristics of specific objectives

1- 1- Simple,Simple, clearly stated & covers all the clearly stated & covers all the aspects of the problemaspects of the problem

2- 2- MeasurableMeasurable

- Using action verbs: -e.g to identity, to - Using action verbs: -e.g to identity, to comparecompare

- Avoiding non-action verbs: e.g. to - Avoiding non-action verbs: e.g. to describe, to study, to noticedescribe, to study, to notice……

Characteristics of specific objectives- Characteristics of specific objectives- ContCont..

3- 3- AttainableAttainable:: Can be achievedCan be achieved

4- 4- Realistic:Realistic: - Feasible concerning - Feasible concerning resourcesresources

5- 5- Timely:Timely: - To be conducted within - To be conducted within the allowed time frame of the study.the allowed time frame of the study.

Properly formulated specific objectives Properly formulated specific objectives will help inwill help in : :

1.1. Selection of the right type of designSelection of the right type of design

2.2. Orientation of data collection Orientation of data collection

3.3. Evaluation of the study.Evaluation of the study.

HypothesisHypothesis

A hypothesis is 'a prediction of a relation A hypothesis is 'a prediction of a relation ship between one or more factors and the ship between one or more factors and the problem under study, which can be tested.problem under study, which can be tested.

A hypothesis is a frequent goal in A hypothesis is a frequent goal in quantitative research. quantitative research.

E.g.E.g. Consumption of more than 10 cigarettes / Consumption of more than 10 cigarettes /

day for ten years is associated with Ca. day for ten years is associated with Ca. Bronchus.Bronchus.

Review of the available literatureReview of the available literature

Review of the available literatureReview of the available literature

Why do we review LitWhy do we review Lit?.?.

11 . .Prevents duplicationPrevents duplication

22 . .Assist in refining statement of the Assist in refining statement of the problemproblem

33 . . Strengthening the argument of selection Strengthening the argument of selection of a research topic (Justification )of a research topic (Justification )

44 . .It helps to get familiar with various It helps to get familiar with various types of methodology that might be used types of methodology that might be used in your study (Design)in your study (Design)

Source of informationSource of information - ArticlesArticles- BooksBooks

- Indexes- Indexes

- Abstracts from journals- Abstracts from journals- International organization International organization

documentsdocumentse.g. e.g. (WHO,UNICEF)(WHO,UNICEF)

Source of information- contSource of information- cont..

- Reports from MOH facilities - Reports from MOH facilities - Vital statisticsVital statistics- CensusCensus- Surveillance systemSurveillance system

- Surveys- Surveys

-Computer search for international-Computer search for internationalLiteratureLiterature

-Opinions, beliefs of key persons-Opinions, beliefs of key persons (Through (Through interview)interview)

How to write lit reviewHow to write lit review??

- -Use index cardsUse index cards

- -Write in your own languageWrite in your own language..

Bias in literature reviewBias in literature review

- The presentation of the available The presentation of the available information in such away that it reflects information in such away that it reflects opinions or opinions or conclusions that does conclusions that does not represent the real situationnot represent the real situation

- Restricting Restricting references to those that references to those that support the point of view support the point of view of the of the author.author.

- Drawing far reach Drawing far reach conclusions from conclusions from shaky or Preliminaryshaky or Preliminary results results

Ethical considerations in lit. Ethical considerations in lit. ReviewReview

- -BiasBias

- Careless presentation and - Careless presentation and interpretation of datainterpretation of dataPut researcher on the wrong wayPut researcher on the wrong way

- Loss of resources.- Loss of resources.

- Wrong decisions- Wrong decisions

How to write ReferencesHow to write References

11 / /From journalsFrom journals::

Author (s). Article. Journal. Year; Author (s). Article. Journal. Year; Volume: PagesVolume: Pages

((Author : Surname followed by initialsAuthor : Surname followed by initials))

How to write ReferencesHow to write References

22 / /From a bookFrom a book

Author. Title of the book. Edition. Place: Author. Title of the book. Edition. Place: Publisher, Year: PagesPublisher, Year: Pages..

33 / /From a chapter in a bookFrom a chapter in a book

Author (s). Chapter title, In: Editors of the Author (s). Chapter title, In: Editors of the book. Edition. Title of the book. Place. book. Edition. Title of the book. Place. Publisher, Year: PagesPublisher, Year: Pages

Study VariablesStudy Variables

Study VariablesStudy Variables

A variable is a characteristic of a A variable is a characteristic of a person, object or phenomenon that person, object or phenomenon that can take different values and can be can take different values and can be measuredmeasured..

Classification of VariablesClassification of Variables

NumericalNumerical : :

Expressed in numbers, Expressed in numbers, E.g. Weight, E.g. Weight, height,height, Distance between homes and Distance between homes and

clinic etcclinic etc……

CategoricalCategorical::

Expressed in categories: E.gExpressed in categories: E.g . .

colors, ranks etccolors, ranks etc......

Classification of VariablesClassification of Variables

1- 1- Numerical variables: Numerical variables: a- Discrete: - E.g. Episodes of a- Discrete: - E.g. Episodes of

diarrhea, schist. eggs.diarrhea, schist. eggs. b- Continuous: - E.g. Weight, Heightb- Continuous: - E.g. Weight, Height2- Categorical variables: 2- Categorical variables: a- Ordinal: E.g. Doctors, soldier a- Ordinal: E.g. Doctors, soldier

ranks-ranks- b- Nominal: E.g. colors, sexb- Nominal: E.g. colors, sex

Types of variablesTypes of variables

11 \ \ Dependant variableDependant variable : :

Use to measure the problemUse to measure the problem..

22\\Independent variableIndependent variable : :

cause or influence the problemcause or influence the problem

33 \ \Confounding variablesConfounding variables : :

Variables associated with the problem Variables associated with the problem and its possible causesand its possible causes..

Confounding variablesConfounding variables

Cause EffectCause Effect Independent variable dependent variableIndependent variable dependent variable

Cigarette smoking Ca. bronchusCigarette smoking Ca. bronchus

Confounding variableConfounding variable

Confounding variablesConfounding variables : :- May affect results (Bias)- May affect results (Bias)- Must be considered - Must be considered particularly in case -control particularly in case -control studies( matching)studies( matching)

How to write variablesHow to write variables??

Expressed in a neutral wayExpressed in a neutral way

FactorFactor VariablesVariables

- -long waiting time - Waiting timelong waiting time - Waiting time

- -Absence of drugs - Drug availabilityAbsence of drugs - Drug availability

Operationalization of variablesOperationalization of variables

Determine whether the variables are Determine whether the variables are measurable or need appropriate measurable or need appropriate indicators E.g. Level of Knowledge, indicators E.g. Level of Knowledge, Nutritional status Weight/ Nutritional status Weight/ age ,Weight/ height etc... (Standard age ,Weight/ height etc... (Standard growth curve)growth curve)

Research DesignsResearch Designs

Study designsStudy designs

Intervention stud.Non intervention stud.

Exploratory stud.

Descriptive stud .

Analytical stud .

Randomized control Trials

Quazai experimental stud .

Case stud.

Surveys

Case con. Stud.

Cohort study

Exploratory studyExploratory study


It is a small - scale study of relatively short It is a small - scale study of relatively short duration, which is carried out when little is duration, which is carried out when little is known about a situation or a problemknown about a situation or a problemExploratory studies problem is not as may Exploratory studies problem is not as may be descriptive and/ analytical. If the be descriptive and/ analytical. If the problem is not well defined , it is always problem is not well defined , it is always advisable to do an exploratory studyadvisable to do an exploratory study..


ExampleExample::

One community with high and One community with high and another with low participation in another with low participation in health activities, to identify the health activities, to identify the factors that contribute to community factors that contribute to community participationparticipation..

DESCRIPTIVE STUDYDESCRIPTIVE STUDY

DESIGNSDESIGNSThe systematic collection and The systematic collection and presentation of data to give a presentation of data to give a clear picture of a specific clear picture of a specific disease or a health related disease or a health related eventsevents

a/ Case studiesa/ Case studies

Case studiesCase studies

A case study describes in depth A case study describes in depth the characteristics of one or the characteristics of one or limited number of cases in its limited number of cases in its natural environmentnatural environment


--A case may be a patient, a health A case may be a patient, a health centre, a village etccentre, a village etc……

- -Can provide useful insight into the Can provide useful insight into the problem e.g. a new diseaseproblem e.g. a new disease

- - -Common in clinical medicine, social Common in clinical medicine, social sciences, management and sciences, management and administration etcadministration etc....

- -Associated with qualitative data and Associated with qualitative data and presentation is in a narrative waypresentation is in a narrative way


FeaturesFeatures::

- - Should be well planned and data will Should be well planned and data will be collected thorough predetermined be collected thorough predetermined questionsquestions

- - Should be flexible to deal with Should be flexible to deal with unexpected situationsunexpected situations


AdvantageAdvantage::

- - It permits a holistic approach to the It permits a holistic approach to the problem under investigationproblem under investigation

DisadvantageDisadvantage::

- - Not representativeNot representative

b/ SURVEYSb/ SURVEYS

SURVEYSSURVEYS

Use :Use :

1. To collect information on 1. To collect information on demographic characteristics. Age, demographic characteristics. Age, sex, education etcsex, education etc……

2. To study characteristics on health 2. To study characteristics on health related variables. E.g. MMR, related variables. E.g. MMR, incidence rate, etcincidence rate, etc……..

3.To study attitudes, opinions and 3.To study attitudes, opinions and beliefs beliefs

SURVEYSSURVEYSSurveys answer the following questions:Surveys answer the following questions:

- WHEN IS THE DISEASE OCCURRING?- WHEN IS THE DISEASE OCCURRING? ((TIME DISTRIBUTIONTIME DISTRIBUTION))- WHERE IS THE DISEASE OCCURRING?- WHERE IS THE DISEASE OCCURRING? ((PLACE DISTRIBUTIONPLACE DISTRIBUTION))- WHO IS AFFECTED? - WHO IS AFFECTED? (PERSON (PERSON DISTRIBUTION)DISTRIBUTION)

PROCEDUREPROCEDURE

11 - -Define the problem under Define the problem under studystudy2- DEFINE THE POPULATION 2- DEFINE THE POPULATION UNDER THE STUDY.UNDER THE STUDY.3- DESCRIBE THE DISEASE BY 3- DESCRIBE THE DISEASE BY TIME, PERSON AND PLACE.TIME, PERSON AND PLACE.4- MEASUREMENT OF THE 4- MEASUREMENT OF THE DISEASE. DISEASE. 5- COMPARING WITH KNOWN 5- COMPARING WITH KNOWN INDICES.INDICES.6- FORMULATION OF AN 6- FORMULATION OF AN AETIOLOGICAL HYPOTHESISAETIOLOGICAL HYPOTHESIS..

CROSS SECTIONAL STUDYCROSS SECTIONAL STUDY

PREVALENCE RATE STUDYPREVALENCE RATE STUDY THE RELATIONSHIP BETWEEN THE RELATIONSHIP BETWEEN

THE DISEASE & OTHER THE DISEASE & OTHER VARIABLES OF INTEREST AS VARIABLES OF INTEREST AS THEY EXIST AT ONE PARTICULAR THEY EXIST AT ONE PARTICULAR POINT OF TIME POINT OF TIME

CROSS SECTIONAL STUDY OF CROSS SECTIONAL STUDY OF HYPERTENSIONHYPERTENSION

1.1. MEASURE THE B.P. AMONG THE MEASURE THE B.P. AMONG THE STUDY POPULATION STUDY POPULATION (PREVALENCE.)(PREVALENCE.)

2.2. COLLECT DATA ON AGE, SEX, COLLECT DATA ON AGE, SEX, SOCIAL CLASS , OCCUPATION SOCIAL CLASS , OCCUPATION etc...etc...

3.3. DETERMINE HOW HYPERTENSION DETERMINE HOW HYPERTENSION IS RELATED TO THESE VARIABLES IS RELATED TO THESE VARIABLES

4.4. Compare with findings of othersCompare with findings of others5.5. Draw hypothesisDraw hypothesis

LONGITUDINAL STUDY DESIGNSLONGITUDINAL STUDY DESIGNS

OBSERVATIONS ARE REPEATED IN THE OBSERVATIONS ARE REPEATED IN THE SAME POPULATION OVER A SAME POPULATION OVER A PROLONGED PERIOD OF TIME PROLONGED PERIOD OF TIME

THESE ARE USEFUL INTHESE ARE USEFUL IN:: STUDY THE NATURAL HISTORY OF THE STUDY THE NATURAL HISTORY OF THE

DISEASE.DISEASE. IDENTIFY THE RISK FACTORS.IDENTIFY THE RISK FACTORS. DETERMINE THE INCIDENCE RATEDETERMINE THE INCIDENCE RATE. .

Analytical studiesAnalytical studies1. Case Control study1. Case Control study

Case Control studyCase Control study

In In Case Control StudyCase Control Study, the investigator , the investigator compare one group among which a compare one group among which a problem present, with another group problem present, with another group (control) where the problem is absent(control) where the problem is absent

Common featuresCommon features

1.1. Both exposure and outcome have Both exposure and outcome have occurred before the start of the occurred before the start of the studystudy

2.2. Study proceeds back from effect to Study proceeds back from effect to causecause

3.3. Presence of a control groupPresence of a control group

Basic stepsBasic steps

1.1. Selection of casesSelection of cases

2.2. Selection of controlsSelection of controls

3.3. MatchingMatching

4.4. Obtaining data on exposureObtaining data on exposure

5.5. Analysis and interpretation of Analysis and interpretation of resultsresults

Selection of casesSelection of cases

It involves two specifications:It involves two specifications:1. Diagnostic criteria1. Diagnostic criteria:: Specific diagnostic criteria of the Specific diagnostic criteria of the

disease, its staging are to be disease, its staging are to be stated clearly.stated clearly.

2. Eligibility criteria:2. Eligibility criteria: Criteria to determine who is Criteria to determine who is

allowed to be included in the allowed to be included in the study. E.g. Only newly diagnosed study. E.g. Only newly diagnosed cases rather than old ones cases rather than old ones

Sources of cases and controlsSources of cases and controls

CasesCases::- PatientsPatients- General populationGeneral population

ControlsControls::- PatientsPatients- RelativesRelatives- Neighbor hoodNeighbor hood- General populationGeneral population

MatchingMatching

Is the process by which controls are to Is the process by which controls are to be similar to the study groupbe similar to the study group

TypesTypes:: Individual matchingIndividual matching Group matchingGroup matching

AnalysisAnalysis::

1.1. The exposure rate among both the The exposure rate among both the cases and the controls.cases and the controls.

2.2. Odds ratio: This ratio can be used Odds ratio: This ratio can be used to estimate the relative risk as the to estimate the relative risk as the incidence rate can not be determined incidence rate can not be determined in case-control study design.in case-control study design.

Thus the case control study is Thus the case control study is always suggestive of the etiological always suggestive of the etiological association between two variablesassociation between two variables

status status smokingsmoking

CasesCasesControlsControlsTotalTotal

YesYes3333( ( aa))

5555( ( bb))8888( ( a+ a+ bb))

NoNo22 ( ( cc ))

2727( ( dd))2929( ( c c + d+ d))

TotalTotal3535 ( (a + ca + c) )

8282 ( (b + db + d))

117117 ((a+b+c+da+b+c+d))

Case control study of smoking and Ca. Case control study of smoking and Ca. lunglung

The exposure rate among cases= The exposure rate among cases=

a ÷ a+c = 33÷35= 0.94x100=94%. a ÷ a+c = 33÷35= 0.94x100=94%. The exposure rate among the The exposure rate among the

controls= b÷ b+ d=55 ÷82= controls= b÷ b+ d=55 ÷82= 0.67x100=67%.0.67x100=67%.

Odds ratio= a/c÷ b/d = a/c x d/ Odds ratio= a/c÷ b/d = a/c x d/ b=891÷110=8.1b=891÷110=8.1

INTERPRETATIONINTERPRETATION

From the exposure rates among the From the exposure rates among the cases & controls: Chi square test has cases & controls: Chi square test has to be used to confirm that there is to be used to confirm that there is statistical difference between the two statistical difference between the two values.values.

If the odds ratio is found to be If the odds ratio is found to be greater than one it means that there greater than one it means that there is a positive etiological association.is a positive etiological association.

Analytical studiesAnalytical studies

2. 2. Cohort studyCohort study

Cohort studyCohort study

A longitudinal a study in which a A longitudinal a study in which a group of individuals are followed up group of individuals are followed up for some time.for some time.

A cohort is a group of persons who A cohort is a group of persons who share common characteristics or share common characteristics or experience within a defined time.experience within a defined time.

FeaturesFeatures

The cohort is identified before the The cohort is identified before the appearance of the investigated appearance of the investigated diseasedisease

The study groups are observed over The study groups are observed over a period of timea period of time

The study proceeds from cause to The study proceeds from cause to effecteffect

Note: The incidence rate can be measuredNote: The incidence rate can be measured

Indications of cohort studyIndications of cohort study::

1.1. When there is strong suspicion of When there is strong suspicion of association between exposure and association between exposure and diseasedisease

2.2. When exposure is rare but the When exposure is rare but the incidence is high among the incidence is high among the exposedexposed

3.3. When the attrition of study When the attrition of study population can be minimized population can be minimized

Types of Cohort studiesTypes of Cohort studies

--Historical Cohort studyHistorical Cohort study::Starts from a point in the past to nowStarts from a point in the past to now

--ProspectiveProspective Cohort studyCohort study::

Starts from now and study goes on to the Starts from now and study goes on to the futurefuture

--Retrospective ProspectiveRetrospective Prospective Cohort Cohort studystudy::

Starts from the past, passing through now Starts from the past, passing through now and proceeds to the futureand proceeds to the future

Elements of a cohort studyElements of a cohort study

11-- Selection of a study groupSelection of a study group::From:- a. a general population orFrom:- a. a general population or

b. Special group (Such as doctors, drivers etc.. or b. Special group (Such as doctors, drivers etc.. or exposure group)exposure group)

22 - -Obtaining data on exposureObtaining data on exposure::

By review of records , medical examination, interview etcBy review of records , medical examination, interview etc……

33 - -Selection of a comparison groupSelection of a comparison group;;

--Internal comparisons: According to exposure levelInternal comparisons: According to exposure level--External comparisons: External comparisons: From out side the study groupFrom out side the study group

Elements of a cohort study- contElements of a cohort study- cont..

44 - -Follow upFollow up::

By: a. Periodic medical examinationBy: a. Periodic medical examination

b. Review of recordsb. Review of records

c. Review of death certificatesc. Review of death certificates

d. Mailed questionnairesd. Mailed questionnaires

e. Telephone calls etce. Telephone calls etc……

55 - -AnalysisAnalysis::

a. Incidence ratea. Incidence rate

b. Relative riskb. Relative risk

AnalysisAnalysis

Relative risk:Relative risk:

This is the ratio that measures the This is the ratio that measures the strength of association between strength of association between suspected cause and effect.suspected cause and effect.

Attributable riskAttributable risk

This is the difference in incidence of This is the difference in incidence of disease or death between exposed & disease or death between exposed & non-exposed group. It is expressed as non-exposed group. It is expressed as a percentage. a percentage.

It measures the impact that removal It measures the impact that removal of a certain factor will have on the of a certain factor will have on the incidence of the disease. incidence of the disease.

SMOKING & CA. LUNGSMOKING & CA. LUNG

Smoking status

Developed Ca lung

Did not develop Ca

lung

Total

Yes 70 (a)

6930 (b)

7000 (a+b)

No 3 ©

2997 (d)

3000 (c+d)

AnalysisAnalysis

Incidence rate of Ca lung Incidence rate of Ca lung among smokers= among smokers= a/a+b=70/7000= 10/1000a/a+b=70/7000= 10/1000

Incidence rate of Ca lung Incidence rate of Ca lung among non-smokers= c/c+d= among non-smokers= c/c+d= 3/3000= 1/10003/3000= 1/1000

AnalysisAnalysis Relative riskRelative risk= =

Incidence ofIncidence of disease among exposed: disease among exposed: incidence among non-exposedincidence among non-exposed

10/100010/1000 1/1oo0.1/1oo0. Attributable riskAttributable risk= Incidence rate = Incidence rate

among exposed-incidence rate among exposed-incidence rate among non-exposed/incidence rate among non-exposed/incidence rate among exposed= 10-1x100=90%.among exposed= 10-1x100=90%.

EXPERIMENTAL STUDY EXPERIMENTAL STUDY DESIGNSDESIGNS

EXPERIMENTAL STUDY DESIGNSEXPERIMENTAL STUDY DESIGNS

In experimental studies the researcher In experimental studies the researcher manipulates a situation and measures manipulates a situation and measures its effect after thatits effect after that

TypeType::11 - -Randomized control trialsRandomized control trials

22 - -Non-randomized trialsNon-randomized trials

11 - -Randomized control trialsRandomized control trials

RANDOMIZED CONTROLLED TRIALSRANDOMIZED CONTROLLED TRIALS

Those trials are used for assessment Those trials are used for assessment of methods of treatment and of methods of treatment and prevention. prevention.

They include:They include:

- intervention - intervention

- control groups and - control groups and

- randomizationrandomization

Features ofFeatures of Randomized control trialsRandomized control trials

11 - -ManipulationManipulation::The researcher does some intervention (Example provision of The researcher does some intervention (Example provision of new drug) to one of the study groupsnew drug) to one of the study groups..

22 - -ControlControl::The researcher introduces one or more control groups to The researcher introduces one or more control groups to compare with the experimental groupcompare with the experimental group

33 - -RandomizationRandomization::Each subject have an equal chance of being Each subject have an equal chance of being allocated to either of the two groups( study and allocated to either of the two groups( study and comparison groups)comparison groups)

stepssteps-:-:

1. Drawing a protocol.1. Drawing a protocol.

2. Selecting comparison & 2. Selecting comparison & experimental groupsexperimental groups

33 . .RandomizationRandomization..

4. Manipulation (intervention).4. Manipulation (intervention).

5. Follow up.5. Follow up.

6. Assessment of the outcome.6. Assessment of the outcome.

THE PROTOCLTHE PROTOCL

One of the essential features of the One of the essential features of the randomized trials.randomized trials.

The protocol specifiesThe protocol specifies::1. The objectives.1. The objectives.2. The questions to be answered.2. The questions to be answered.3. The selection criteria.3. The selection criteria.4. The sample size.4. The sample size.5. The procedures of allocation of the 5. The procedures of allocation of the

subjects into experimental and subjects into experimental and control groups.control groups.

THE PROTOCL- contTHE PROTOCL- cont… .… .

6. The treatment applied: How, 6. The treatment applied: How, what dose etc...what dose etc...

7. The details of the scientific 7. The details of the scientific techniques and investigations. techniques and investigations.

NoteNote:: Once the protocol has been evolved, it Once the protocol has been evolved, it

should be strictly adhered to through out should be strictly adhered to through out the study. the study.

RANDOMIZATIONRANDOMIZATION

Randomization is the statistical Randomization is the statistical procedure by which the procedure by which the participants are allocated into participants are allocated into groups usually called groups usually called study & study & control groupscontrol groups to receive or not to receive or not to receive intervention or to receive intervention or therapeutic procedure .therapeutic procedure .

Randomization aims at making Randomization aims at making the groups comparable and the groups comparable and eliminate bias.eliminate bias.

RANDOMIZATIONRANDOMIZATION

Randomization ensures that the Randomization ensures that the investigator has no control over the investigator has no control over the allocation of the participants to either the allocation of the participants to either the study or control group, thus eliminating study or control group, thus eliminating the selection bias.the selection bias.

Every individual has an equal chance of Every individual has an equal chance of being allocated into either group.being allocated into either group.

Randomization is best done by using Randomization is best done by using statistical random table. statistical random table.

MANIPULATIONMANIPULATION

Manipulation or intervention is usually Manipulation or intervention is usually done by application or withdrawal of the done by application or withdrawal of the suspected factor e.g. drugs, vaccine or suspected factor e.g. drugs, vaccine or dietary factor.dietary factor.

This manipulation creates an independent This manipulation creates an independent variable (drug, vaccine or new procedure) variable (drug, vaccine or new procedure) which effect is then determined by the which effect is then determined by the measurement of the final outcome which measurement of the final outcome which constitutes the dependent variable e.g. constitutes the dependent variable e.g. incidence of disease, recovery.incidence of disease, recovery.

FOLLOW UPFOLLOW UP

This includes examination of the This includes examination of the study & control groups subjects at study & control groups subjects at defined intervals of time in standard defined intervals of time in standard manner under the same conditions in manner under the same conditions in the same time frame till the final the same time frame till the final assessment.assessment.

The main difficulties encountered in The main difficulties encountered in the follow up process include:the follow up process include:

Attrition from:- death, migration, Attrition from:- death, migration, displacement and loss of interest etcdisplacement and loss of interest etc

ASSESSMENTASSESSMENT

The final assessment of the trial is carried in terms of:The final assessment of the trial is carried in terms of: Positive results: Positive results: These include the benefits of the experimental study These include the benefits of the experimental study

such as reduced incidence of the disease or severity such as reduced incidence of the disease or severity of the disease, cost of health services or other of the disease, cost of health services or other appropriate outcome.appropriate outcome.

Negative results: Negative results: These include the severity & frequency of side-These include the severity & frequency of side-

effects and complications.effects and complications. The incidence of positive/negative results is The incidence of positive/negative results is

compared in both groups and the differences are compared in both groups and the differences are tested statistically. tested statistically.

22 - -Non-randomized trialsNon-randomized trials

a. QUASI-EXPERIMENTAL STUDY DESIGNSa. QUASI-EXPERIMENTAL STUDY DESIGNS

At least one of the characteristics of the At least one of the characteristics of the true experiment is missing true experiment is missing (RANDOMIZATION OR CONTROL GROUP) (RANDOMIZATION OR CONTROL GROUP)

QUASI-EXPERIMENTAL STUDY DESIGNS QUASI-EXPERIMENTAL STUDY DESIGNS ALWAYS INCLUDES MANIPULATION ( ALWAYS INCLUDES MANIPULATION ( INTERVENTION)INTERVENTION)

22 . .Non-randomized trialsNon-randomized trials

b. Before and after study:b. Before and after study:- Includes intervention- Includes intervention

- No control group - No control group

- No randomization- No randomization

- Observation before and after the - Observation before and after the interventionintervention

- Test ( analysis)- Test ( analysis)

Bias in experimental studiesBias in experimental studies

Bias is the systematic difference between Bias is the systematic difference between observed results and the actual resultsobserved results and the actual results..

Sources of bias:Sources of bias: 1. Participant1. Participant’’s bias:s bias: The participants report subjectively that The participants report subjectively that

they feel better or improved if they knew they feel better or improved if they knew that they were receiving new treatment.that they were receiving new treatment.

BIAS – contBIAS – cont.. ... .

2.2.ObserverObserver’’s bias:s bias: The influence of the investigator measuring The influence of the investigator measuring

the outcome of the trial if he knew the outcome of the trial if he knew beforehand the particular procedure to beforehand the particular procedure to which the patient has been subjectedwhich the patient has been subjected. .

How to reduce the sources of biasHow to reduce the sources of bias??

1. Randomization. 1. Randomization. 2. Blinding2. Blinding. .

Blinding is carried in three ways:Blinding is carried in three ways:1. Single blind trial1. Single blind trial: : The trial is so planned The trial is so planned

that the participant is not aware whether he that the participant is not aware whether he belongs to the study or control group.belongs to the study or control group.

2. Double blind trial:2. Double blind trial: The trial is so planned The trial is so planned that nether the doctor nor the participant is that nether the doctor nor the participant is aware of the group allocation and treatment aware of the group allocation and treatment receivedreceived. .

How to reduce the sources of bias? How to reduce the sources of bias? ContCont……

3. Triple-blind trial:3. Triple-blind trial:

The trial is so planned that the The trial is so planned that the participant, the investigator& the participant, the investigator& the person analyzing the data are all person analyzing the data are all blind. blind.

This is the ideal but double-blinding is the This is the ideal but double-blinding is the most commonly used. most commonly used.

DISADVANTAGES OF EXPERIMENTAL DISADVANTAGES OF EXPERIMENTAL STUDIESSTUDIES

They are costly.They are costly. Ethical problems.Ethical problems. Feasibility is difficult.Feasibility is difficult.

SamplingSampling

SamplingSampling

A sample is a selection of a A sample is a selection of a number of study units from a number of study units from a defined study populationdefined study population

Questions to be askedQuestions to be asked

- Study population:- Study population:- Population from whom the sample is to be takenPopulation from whom the sample is to be taken

- Sample frame:Sample frame: A list of all units of study population from which the A list of all units of study population from which the

sample is to be drawnsample is to be drawn- Sample sizeSample size- Method of selection of the sampleMethod of selection of the sample NoteNote The sample should be representative, i.e. it should The sample should be representative, i.e. it should

carry the characteristics of the study populationcarry the characteristics of the study population

Sampling methodsSampling methods

Divided according to the way of selection:Divided according to the way of selection:- Probability samplingProbability sampling- Non-probability samplingNon-probability sampling

11 - -Probability sampleProbability sample

It is a random selection procedures It is a random selection procedures that every unit of the study that every unit of the study population has an equal chance of population has an equal chance of being selected in the samplebeing selected in the sample

TypesTypes

1.1. Simple random samplingSimple random sampling

2.2. Systematic random samplingSystematic random sampling

3.3. Stratified samplingStratified sampling

4.4. Multistage samplingMultistage sampling

5.5. Cluster sampling Cluster sampling

11 - -Probability samplingProbability sampling

1. Simple random sampling1. Simple random sampling

1.1. Give number to all the subjects Give number to all the subjects (List)(List)

2.2. Determine the sample sizeDetermine the sample size

3.3. Select the sample using;Select the sample using;

- A lottery or- A lottery or

- A table of random selection - A table of random selection

11 - -Probability sampling Probability sampling 2. 2. Systematic random samplingSystematic random sampling

Used when there is a sample frame e.g. a Used when there is a sample frame e.g. a class, doctors in a hospital etcclass, doctors in a hospital etc

StepsSteps::

- - Determine the sample frameDetermine the sample frame

- - Determine the sample sizeDetermine the sample size

- - Determine the intervalDetermine the interval

= = Sample frame/ Sample sizeSample frame/ Sample size

NoteNote

First unit should be taken randomlyFirst unit should be taken randomly

11 - -Probability samplingProbability sampling3. 3. Stratified samplingStratified sampling

Used when the characteristics are not Used when the characteristics are not equally distributed in the population equally distributed in the population and the researcher is interested in and the researcher is interested in these characteristics to appear in the these characteristics to appear in the analysisanalysis

E.gE.g..

Age, sex, religions etcAge, sex, religions etc....

11 - -Probability samplingProbability sampling 4.4. Multistage samplingMultistage sampling

Used when the population is divided into subgroups Used when the population is divided into subgroups e.g. In a study of HIV/AIDS prevalence in the Sudan, e.g. In a study of HIV/AIDS prevalence in the Sudan, the sample may be taken as followsthe sample may be taken as follows::

- - Take three states out of the 25 statesTake three states out of the 25 states - - Take two localities from each selected stateTake two localities from each selected state

- - Take towns and villages from each selected localityTake towns and villages from each selected locality

- - Take individuals from each town and villageTake individuals from each town and village localitylocality

NoteNote Multistage sampling usually involves more than one methodsMultistage sampling usually involves more than one methods

11 - -Probability samplingProbability sampling 5. 5. Cluster samplingCluster sampling

Cluster samplingCluster sampling is is the selection of study the selection of study groups instead of individualsgroups instead of individuals..

Used when there is no complete sampling Used when there is no complete sampling frame, or there is some logistic difficulties frame, or there is some logistic difficulties e.g. the population is composed of a large e.g. the population is composed of a large number of scattered villagesnumber of scattered villages . .

NoteNote Multistage sampling usually involves more than one Multistage sampling usually involves more than one

methodmethod

Advantages of multistage and cluster Advantages of multistage and cluster samplingsampling

A sampling frame is not requiredA sampling frame is not required The sample is easy to select The sample is easy to select

Disadvantage of cluster sampling:Disadvantage of cluster sampling:-The sample may not be representative-The sample may not be representativeNote:Note: Take more clusters and so big sample to Take more clusters and so big sample to

avoid this problemavoid this problem

Bias in samplingBias in sampling

1.1. Improper sampling procedureImproper sampling procedure

2.2. Study of registered patients only Study of registered patients only

3.3. studying volunteers onlystudying volunteers only

4.4. Tarmac bias: Study accessible areas Tarmac bias: Study accessible areas onlyonly

22 - -Non-probability samplingNon-probability sampling

22 - -Non-probability samplingNon-probability sampling1. Convenience sample1. Convenience sample

- - Samples in which randomization is absent, Samples in which randomization is absent, and so subjects have no equal chances of and so subjects have no equal chances of being selected.being selected.

- For convenience, only those units which are - For convenience, only those units which are accessible at the time are taken. accessible at the time are taken.

- Used when there is no sample frame- Used when there is no sample frame - - Many clinical based studies are from this type. Many clinical based studies are from this type.

Problem:Problem:

Not representativeNot representative

22 - -Non-probability samplingNon-probability sampling2. Quota sample2. Quota sample

The population is divided into The population is divided into categories and a quota is to be categories and a quota is to be surveyed from each categorysurveyed from each category

ProblemProblem::


22 - -Non-probability samplingNon-probability sampling3. Purposive sample3. Purposive sample

The researcher selects specific subjects in The researcher selects specific subjects in the population and includes them in the the population and includes them in the samplesample

ProblemProblem::


Sample sizeSample size

For descriptive studyFor descriptive study:: 22 22

n= z . p q/ dn= z . p q/ d

n = Sample sizen = Sample size z = Standard normal deviate = 1.96z = Standard normal deviate = 1.96 p = Proportion of the characteristic p = Proportion of the characteristic

under study estimated in the target under study estimated in the target populationpopulation

q = 1-pq = 1-p d = Error allowed = 0.05d = Error allowed = 0.05

22 - -Non-probability samplingNon-probability sampling4.Volunteer sample4.Volunteer sample

Sample involves only those who are Sample involves only those who are accepting to introduce the studyaccepting to introduce the study

ProblemProblem::


Health & Medicine

Research Methodology