Research Methodology
Upcoming SlideShare
Loading in...5
×
 

Research Methodology

on

  • 1,555 views

 

Statistics

Views

Total Views
1,555
Views on SlideShare
1,555
Embed Views
0

Actions

Likes
1
Downloads
120
Comments
0

0 Embeds 0

No embeds

Accessibility

Upload Details

Uploaded via as Microsoft PowerPoint

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

Research Methodology Research Methodology Presentation Transcript

  • Research Methodology Dr. Sawsan Mustafa Abdalla Associate Prof .faculty of medicine .Community Department
  • Research Research is “the systematic collection, analysis and interpretation of data to answer a certain question or to solve a problem”
  • Purposes of Research Research serves two Purposes :1- Generates new knowledge and technologies to deal with major health problems“ basic research” 2- Identifies priority problems , evaluates polices and programs “applied research”
  • The importance of Research Why do we carry out research ? It is generally recognized that there is a wide gap between data available, and data needed for management , planning and decision making, so research is needed to bridge this gap
  • Characteristics of research     It demands a clear statement of the problem It requires a plan It builds on existing data It collects new data
  • Classification of health research     Bio medial research Clinical research Epidemiological research Health system research
  • Bio medical research-1   Bio Medical research focuses on the individual It concentrates on how the body works i.e. Biological process , body structure and functions , and the pathological mechanisms occurring within the body
  • Clinical research  Clinical research focuses on the individual. It deals with the response of the body to various preventive , diagnostic or therapeutic interventions Example: The efficacy of long acting penicillin on tuberculous patients
  • :-Epidemiological research    Epidemiological research focuses on the population , and considers the frequency , distribution and determinants of diseases Example:Epidemiology of malaria in Khartoum state Pattern of health problems in under five children in Omdorman area .
  • .( Health system research (H.S.R   Health system research focuses on how well is the health system functioning , such as cost and quality of health services etc Health system research aims to provide information which improve the health system.
  • Types of Health system research   Operational research Health policy research
  • Operational research Operational research is the process of identifying and solving health program problems. It is designed to improve effectiveness and quality of health services delivered by health providers , and the availability , accessibility and acceptability of health services delivered .
  • Health policy research It looks over the policies e.g. allocation of resources
  • CRITERIA OF A RESEARCH TOPIC Percived discrepancy between what is-1 existing and what is expected A question why this discrepancy- 2 exists More than one answer to the question- 3 is expected
  • CRITERIA FOR SELECTION A RESEARCH TOPIC The problem selected for the research should fulfill the following criteria: 1. RELIVANCE:-THE PROBLEM SHOULD BE AN IMPORTANT HEALTH PROBLEM. 2. APPLICABLE:THE PROBLEM SHOULD HAVE SOME CHANCE OF BEING SOLVED. 3. FEASIBILITY: THE RESEARCH SHOULD BE FEASIBLE WITHIN THE AVAILABLE RESOURCES.
  • CRITERIA FOR SELECTION A RESEARCH TOPIC 4-Political acceptability The ultimate goal of a research is to provide decision – makers and managers with results , so it is advisable to choose a topic that has the interest and support of the authorities . This will increase the chance for recommendations to be implemented .
  • :URGENCY-5 Urgency of results needed According to the urgency needed for data , the researcher should decide what research to be done .first and which can be done later
  • Ethical acceptability-6 Ethical issues should be considered when we are trying to choose a research topic, for we may do harm on others when we are carrying out research. Acceptance of research by the study subjects is important and taking consents from them is always .important
  • Avoidance of duplication- 7  Before you decide to conduct a research, you should find out whether the suggested topic was investigated before in this area or another area with similar conditions. If the topic has been investigated the results should be reviewed to explore whether major questions need further investigations, if not this topic is not suitable for research and should be discarded. THE RESEARCH SHOULD BE COST/EFFECTIVE
  • RATING
  • grade item 3 2 1 Relevance .V.R R Not Duplication Not partially Fully Applicability V applic .Applic .Not app Feasibility .V.F F Not Urgency V. urgent Urgent not P. acceptability V. accepted Accepted not .Ethical accep No minor major Total
  • :Definition of the problem  Once the researcher has decided on the problem of the research, then he needs to have a definition/description of the problem written in a concise clear manner. It should contain information such as:  Background information concerning the health status of the community.    Basic description of the problem. Justification. Mention previous studies
  • Objectives
  • Objectives The goals to be achieved by the . research project Why should the Objectives be ? developed Focus the study (Narrow it down to-1 ( essentials Avoid collection of unnecessary data- 2 Organize the study in clearly defined- 3 parts
  • :Types General: Identifies in general terms, what is to be accomplished by the research project. Specific: Identifies in details the specific aims of the research project
  • Example :General To study the reasons for low utilization of MCH Services in Khartoum State – 2006 :Note Gen. Objective is clearly related to the .statement of the problem
  • : -Specific -To determine the level of utilization of MCH Services in Khartoum State -To identify whether there are variations in Utilization of MCH Services and - Seasons - Type of clinics
  • Types of specific objectives 1. Estimation objectives E.g. To determine incidence rate 2. Association objectives Aims at Association between the factor of interest and a particular event
  • ..Types of specific objectives- Cont Example To identify whether there is Association of low utilization of MCH clinics and mother education 3. Evaluation objectives: To evaluate the effect of an investigation E.g. the effect of H.E. on utilization of MCH services.
  • Characteristics of specific objectives 1- Simple, clearly stated & covers all the aspects of the problem 2- Measurable - Using action verbs: -e.g to identity, to compare - Avoiding non-action verbs: e.g. to describe, to study, to notice…
  • Characteristics of specific objectives.Cont 3- Attainable: Can be achieved 4- Realistic: - Feasible concerning resources 5- Timely: - To be conducted within the allowed time frame of the study.
  • Properly formulated specific objectives : -will help in 1. 2. 3. Selection of the right type of design Orientation of data collection Evaluation of the study.
  • Hypothesis   A hypothesis is 'a prediction of a relation ship between one or more factors and the problem under study, which can be tested. A hypothesis is a frequent goal in quantitative research. E.g. Consumption of more than 10 cigarettes / day for ten years is associated with Ca. Bronchus.
  • Review of the available literature
  • Review of the available literature .?Why do we review Lit Prevents duplication. 1 Assist in refining statement of the. 2 problem Strengthening the argument of . 3 of a research topicselection ((Justification It helps to get familiar with various . 4 types of methodology that might be (used in your study (Design
  • Source of information Articles - Books - Indexes - Abstracts from journals International organization documents - e.g. (WHO,UNICEF)
  • .Source of information- cont - Reports from MOH facilities - Vital statistics - Census - Surveillance system - Surveys -Computer search for international Literature -Opinions, beliefs of key persons (Through interview)
  • ?How to write lit review Use index cards.Write in your own language-
  • Bias in literature review - - - The presentation of the available information in such away that it reflects opinions or conclusions that does not represent the real situation Restricting references to those that support the point of view of the author. Drawing far reach conclusions from shaky or Preliminary results
  • Ethical considerations in lit. Review Bias- Careless presentation and interpretation of data Put researcher on the wrong way - Loss of resources. - Wrong decisions
  • How to write References :From journals/ 1 Author (s). Article. Journal. Year; Volume: Pages (Author : Surname followed by initials)
  • How to write References From a book/ 2 Author. Title of the book. Edition. Place: .Publisher, Year: Pages From a chapter in a book/ 3 Author (s). Chapter title, In: Editors of the book. Edition. Title of the book. Place. Publisher, Year: Pages
  • Study Variables
  • Study Variables A variable is a characteristic of a person, object or phenomenon that can take different values and can be .measured
  • Classification of Variables : Numerical Expressed in numbers, E.g. Weight, height, Distance between homes and …clinic etc :Categorical . Expressed in categories: E.g ...colors, ranks etc
  • Classification of Variables 1- Numerical variables: a- Discrete: - E.g. Episodes of diarrhea, schist. eggs. b- Continuous: - E.g. Weight, Height 2- Categorical variables: a- Ordinal: E.g. Doctors, soldier ranksb- Nominal: E.g. colors, sex
  • Types of variables : Dependant variable 1 .Use to measure the problem : Independent variable2 cause or influence the problem -: Confounding variables 3 Variables associated with the problem .and its possible causes
  • Confounding variables Cause Effect Independent variable Cigarette smoking dependent variable Ca. bronchus Confounding variable
  • : -Confounding variables - May affect results (Bias) - Must be considered particularly in case -control studies( matching)
  • ?How to write variables Expressed in a neutral way Factor long waiting time Absence of drugs Variables - Waiting time- Drug availability-
  • Operationalization of variables Determine whether the variables are measurable or need appropriate indicators E.g. Level of Knowledge, Nutritional status Weight/ age ,Weight/ height etc... (Standard (growth curve
  • Research Designs
  • Study designs .Non intervention stud .Intervention stud .Exploratory stud .Case stud . Descriptive stud . Analytical stud Randomized control Trials Surveys .Case con. Stud Cohort study . Quazai experimental stud
  • Exploratory study
  • Exploratory study It is a small - scale study of relatively short duration, which is carried out when little is known about a situation or a problem Exploratory studies problem is not as may be descriptive and/ analytical. If the problem is not well defined , it is always .advisable to do an exploratory study
  • Exploratory study :Example One community with high and another with low participation in health activities, to identify the factors that contribute to community .participation
  • DESCRIPTIVE STUDY DESIGNS The systematic collection and presentation of data to give a clear picture of a specific disease or a health related events
  • a/ Case studies
  • Case studies A case study describes in depth the characteristics of one or limited number of cases in its natural environment
  • Case studies A case may be a patient, a health…centre, a village etc Can provide useful insight into theproblem e.g. a new disease Common in clinical medicine, socialsciences, management and ..administration etc Associated with qualitative data andpresentation is in a narrative way -
  • Case studies :Features Should be well planned and data will be collected thorough predetermined questions Should be flexible to deal with unexpected situations
  • Case studies :Advantage It permits a holistic approach to the problem under investigation :Disadvantage Not representative -
  • b/ SURVEYS
  • SURVEYS Use : 1. To collect information on demographic characteristics. Age, sex, education etc… 2. To study characteristics on health related variables. E.g. MMR, incidence rate, etc…. 3.To study attitudes, opinions and beliefs
  • SURVEYS Surveys answer the following questions: - WHEN IS THE DISEASE OCCURRING? (TIME DISTRIBUTION) - WHERE IS THE DISEASE OCCURRING? (PLACE DISTRIBUTION) - WHO IS AFFECTED? (PERSON DISTRIBUTION)
  • PROCEDURE Define the problem under- 1 study 2- DEFINE THE POPULATION UNDER THE STUDY. 3- DESCRIBE THE DISEASE BY TIME, PERSON AND PLACE. 4- MEASUREMENT OF THE DISEASE. 5- COMPARING WITH KNOWN INDICES. 6- FORMULATION OF AN .AETIOLOGICAL HYPOTHESIS
  • CROSS SECTIONAL STUDY   PREVALENCE RATE STUDY THE RELATIONSHIP BETWEEN THE DISEASE & OTHER VARIABLES OF INTEREST AS THEY EXIST AT ONE PARTICULAR POINT OF TIME
  • CROSS SECTIONAL STUDY OF HYPERTENSION 1. 2. 3. 4. 5. MEASURE THE B.P. AMONG THE STUDY POPULATION (PREVALENCE.) COLLECT DATA ON AGE, SEX, SOCIAL CLASS , OCCUPATION etc... DETERMINE HOW HYPERTENSION IS RELATED TO THESE VARIABLES Compare with findings of others Draw hypothesis
  • LONGITUDINAL STUDY DESIGNS  OBSERVATIONS ARE REPEATED IN THE SAME POPULATION OVER A PROLONGED PERIOD OF TIME THESE ARE USEFUL IN:    STUDY THE NATURAL HISTORY OF THE DISEASE. IDENTIFY THE RISK FACTORS. DETERMINE THE INCIDENCE RATE.
  • Analytical studies 1. Case Control study
  • Case Control study In Case Control Study, the investigator compare one group among which a problem present, with another group (control) where the problem is absent
  • Common features 1. 2. 3. Both exposure and outcome have occurred before the start of the study Study proceeds back from effect to cause Presence of a control group
  • Basic steps 1. 2. 3. 4. 5. Selection of cases Selection of controls Matching Obtaining data on exposure Analysis and interpretation of results
  • Selection of cases It involves two specifications: 1. Diagnostic criteria: Specific diagnostic criteria of the disease, its staging are to be stated clearly. 2. Eligibility criteria: Criteria to determine who is allowed to be included in the study. E.g. Only newly diagnosed cases rather than old ones
  • Sources of cases and controls :Cases - Patients General population :Controls - Patients Relatives Neighbor hood General population
  • Matching Is the process by which controls are to be similar to the study group :Types   Individual matching Group matching
  • :Analysis 1. 2.  The exposure rate among both the cases and the controls. Odds ratio: This ratio can be used to estimate the relative risk as the incidence rate can not be determined in case-control study design. Thus the case control study is always suggestive of the etiological association between two variables
  • Case control study of smoking and Ca. lung Cases status smoking Yes No Total (a c Controls Total )33 (b ( )55 a+ (d )27 c )2 35 (a + c) 82 (b + d) (b )88 )29 (+ d 117 (a+b+c+d)
  •    The exposure rate among cases= a ÷ a+c = 33÷35= 0.94x100=94%. The exposure rate among the controls= b÷ b+ d=55 ÷82= 0.67x100=67%. Odds ratio= a/c÷ b/d = a/c x d/ b=891÷110=8.1
  • INTERPRETATION   From the exposure rates among the cases & controls: Chi square test has to be used to confirm that there is statistical difference between the two values. If the odds ratio is found to be greater than one it means that there is a positive etiological association.
  • Analytical studies 2. Cohort study
  • Cohort study   A longitudinal a study in which a group of individuals are followed up for some time. A cohort is a group of persons who share common characteristics or experience within a defined time.
  • Features    The cohort is identified before the appearance of the investigated disease The study groups are observed over a period of time The study proceeds from cause to effect Note: The incidence rate can be measured
  • :Indications of cohort study 1. 2. 3. When there is strong suspicion of association between exposure and disease When exposure is rare but the incidence is high among the exposed When the attrition of study population can be minimized
  • Types of Cohort studies :Historical Cohort studyStarts from a point in the past to now :Prospective Cohort studyStarts from now and study goes on to the future Retrospective Prospective Cohort:study Starts from the past, passing through now and proceeds to the future
  • Elements of a cohort study :Selection of a study group -1 From:- a. a general population or b. Special group (Such as doctors, drivers etc.. or (exposure group :Obtaining data on exposure- 2 …By review of records , medical examination, interview etc ;Selection of a comparison group- 3 Internal comparisons: According to exposure levelExternal comparisons: From out side the study group-
  • .Elements of a cohort study- cont :Follow up- 4 By: a. Periodic medical examination b. Review of records c. Review of death certificates d. Mailed questionnaires …e. Telephone calls etc :Analysis- 5 a. Incidence rate b. Relative risk
  • Analysis Relative risk: This is the ratio that measures the strength of association between suspected cause and effect.
  • Attributable risk This is the difference in incidence of disease or death between exposed & non-exposed group. It is expressed as a percentage. It measures the impact that removal of a certain factor will have on the incidence of the disease.
  • SMOKING & CA. LUNG Smoking status Developed Ca lung 70 (a) Did not develop Ca lung 6930 (b) Yes No Total 7000 (a+b) 3 © 2997 (d) 3000 (c+d)
  • Analysis Incidence rate of Ca lung among smokers= a/a+b=70/7000= 10/1000  Incidence rate of Ca lung among non-smokers= c/c+d= 3/3000= 1/1000 
  • Analysis  Relative risk= Incidence of disease among exposed: incidence among non-exposed 10/1000 1/1oo0.  Attributable risk= Incidence rate among exposed-incidence rate among non-exposed/incidence rate among exposed= 10-1x100=90%.
  • EXPERIMENTAL STUDY DESIGNS
  • EXPERIMENTAL STUDY DESIGNS In experimental studies the researcher manipulates a situation and measures its effect after that :Type Randomized control trials- 1 Non-randomized trials- 2
  • Randomized control trials- 1
  • RANDOMIZED CONTROLLED TRIALS Those trials are used for assessment of methods of treatment and prevention. They include: - intervention - control groups and - randomization
  • Features of Randomized control trials :Manipulation- 1 The researcher does some intervention (Example provision of .new drug) to one of the study groups :Control- 2 The researcher introduces one or more control groups to compare with the experimental group :Randomization- 3 Each subject have an equal chance of being allocated to either of the two groups( study and (comparison groups
  • :-steps 1. Drawing a protocol. 2. Selecting comparison & experimental groups .Randomization. 3 4. Manipulation (intervention). 5. Follow up. 6. Assessment of the outcome.
  • THE PROTOCL One of the essential features of the randomized trials. The protocol specifies: 1. The objectives. 2. The questions to be answered. 3. The selection criteria. 4. The sample size. 5. The procedures of allocation of the subjects into experimental and control groups.
  • . …THE PROTOCL- cont 6. The treatment applied: How, what dose etc... 7. The details of the scientific techniques and investigations. :Note Once the protocol has been evolved, it should be strictly adhered to through out the study.
  • RANDOMIZATION   Randomization is the statistical procedure by which the participants are allocated into groups usually called study & control groups to receive or not to receive intervention or therapeutic procedure . Randomization aims at making the groups comparable and eliminate bias.
  • RANDOMIZATION    Randomization ensures that the investigator has no control over the allocation of the participants to either the study or control group, thus eliminating the selection bias. Every individual has an equal chance of being allocated into either group. Randomization is best done by using statistical random table.
  • MANIPULATION   Manipulation or intervention is usually done by application or withdrawal of the suspected factor e.g. drugs, vaccine or dietary factor. This manipulation creates an independent variable (drug, vaccine or new procedure) which effect is then determined by the measurement of the final outcome which constitutes the dependent variable e.g. incidence of disease, recovery.
  • FOLLOW UP   This includes examination of the study & control groups subjects at defined intervals of time in standard manner under the same conditions in the same time frame till the final assessment. The main difficulties encountered in the follow up process include: Attrition from:- death, migration, displacement and loss of interest etc
  • ASSESSMENT The final assessment of the trial is carried in terms of:  Positive results: These include the benefits of the experimental study such as reduced incidence of the disease or severity of the disease, cost of health services or other appropriate outcome.  Negative results: These include the severity & frequency of sideeffects and complications. The incidence of positive/negative results is compared in both groups and the differences are tested statistically.
  • Non-randomized trials- 2
  • a. QUASI-EXPERIMENTAL STUDY DESIGNS   At least one of the characteristics of the true experiment is missing (RANDOMIZATION OR CONTROL GROUP) QUASI-EXPERIMENTAL STUDY DESIGNS ALWAYS INCLUDES MANIPULATION ( INTERVENTION)
  • Non-randomized trials. 2 b. Before and after study: - Includes intervention - No control group - No randomization - Observation before and after the intervention - Test ( analysis)
  • Bias in experimental studies   Bias is the systematic difference between observed results and the actual results. Sources of bias: 1. Participant’s bias: The participants report subjectively that they feel better or improved if they knew that they were receiving new treatment.
  • . ..BIAS – cont 2.Observer’s bias: The influence of the investigator measuring the outcome of the trial if he knew beforehand the particular procedure to which the patient has been subjected.
  • ?How to reduce the sources of bias 1. Randomization. 2. Blinding. Blinding is carried in three ways: 1. Single blind trial: The trial is so planned that the participant is not aware whether he belongs to the study or control group. 2. Double blind trial: The trial is so planned that nether the doctor nor the participant is aware of the group allocation and treatment received.
  • How to reduce the sources of bias? …Cont 3. Triple-blind trial: The trial is so planned that the participant, the investigator& the person analyzing the data are all blind. This is the ideal but double-blinding is the most commonly used.
  • DISADVANTAGES OF EXPERIMENTAL STUDIES    They are costly. Ethical problems. Feasibility is difficult.
  • Sampling
  • Sampling A sample is a selection of a number of study units from a defined study population
  • Questions to be asked - Study population:Population from whom the sample is to be taken - Sample frame: A list of all units of study population from which the sample is to be drawn - Sample size Method of selection of the sample Note The sample should be representative, i.e. it should carry the characteristics of the study population
  • Sampling methods Divided according to the way of selection: Probability sampling Non-probability sampling
  • Probability sample- 1 It is a random selection procedures that every unit of the study population has an equal chance of being selected in the sample
  • Types 1. 2. 3. 4. 5. Simple random sampling Systematic random sampling Stratified sampling Multistage sampling Cluster sampling
  • Probability sampling- 1 1. Simple random sampling 1. 2. 3. Give number to all the subjects (List) Determine the sample size Select the sample using; - A lottery or - A table of random selection
  • Probability sampling - 1 2. Systematic random sampling Used when there is a sample frame e.g. a class, doctors in a hospital etc :Steps Determine the sample frame Determine the sample size Determine the interval Sample frame/ Sample size = Note First unit should be taken randomly
  • Probability sampling- 1 3. Stratified sampling Used when the characteristics are not equally distributed in the population and the researcher is interested in these characteristics to appear in the analysis .E.g ..Age, sex, religions etc
  • Probability sampling- 1 4. Multistage sampling Used when the population is divided into subgroups e.g. In a study of HIV/AIDS prevalence in the Sudan, :the sample may be taken as follows Take three states out of the 25 states Take two localities from each selected state Take towns and villages from each selected locality Take individuals from each town and village locality Note Multistage sampling usually involves more than one methods
  • Probability sampling- 1 5. Cluster sampling Cluster sampling is the selection of study .groups instead of individuals Used when there is no complete sampling frame, or there is some logistic difficulties e.g. the population is composed of a large . number of scattered villages Note Multistage sampling usually involves more than one method
  • Advantages of multistage and cluster sampling   A sampling frame is not required The sample is easy to select Disadvantage of cluster sampling: -The sample may not be representative Note: Take more clusters and so big sample to avoid this problem
  • Bias in sampling 1. 2. 3. 4. Improper sampling procedure Study of registered patients only studying volunteers only Tarmac bias: Study accessible areas only
  • Non-probability sampling- 2
  • Non-probability sampling- 2 1. Convenience sample - Samples in which randomization is absent, and so subjects have no equal chances of being selected. - For convenience, only those units which are accessible at the time are taken. - Used when there is no sample frame - Many clinical based studies are from this type. Problem: Not representative
  • Non-probability sampling- 2 2. Quota sample The population is divided into categories and a quota is to be surveyed from each category :Problem Not representative
  • Non-probability sampling- 2 3. Purposive sample The researcher selects specific subjects in the population and includes them in the sample :Problem Not representative
  • Sample size :For descriptive study 2 2 n= z . p q/ d n = Sample size z = Standard normal deviate = 1.96 p = Proportion of the characteristic under study estimated in the target population q = 1-p d = Error allowed = 0.05
  • Non-probability sampling- 2 4.Volunteer sample Sample involves only those who are accepting to introduce the study :Problem Not representative