Research and methodology 2
-
Upload
tosif-ahmad -
Category
Health & Medicine
-
view
1.638 -
download
0
Transcript of Research and methodology 2
Writing up Introduction(What have you set out to do and why?)
Introduction
Funnel Down
• General to Specific
• Historical To Latest
• International To Local
Introduce Your Research Problem
With the help of Background (Valid, Authentic References)
Finally tell what you plan to do to solve this problem (Purpose, Rationale, Significance, )
Introduction
Classic introduction should have 3 paragraphs:
1. Background information: What is the problem or issue?
2. Importance of the problem and list unresolved issues.
3. Rationale for the current study. State your research question or hypothesis.
4
• What is the problem?
• Why have you chosen that subject?
• Why do you start?
• Why is it important?
Introduction (Concept)
Writing up Materials & Methods(How will you do it?)
6
Synonyms
• Methodology
• Patients and Methods
• Volunteers and Methods
• Subjects and Methods
Materials & Methods
7
• How study is designed?
• How study will be carried out?
• How data will be collected?
• How data will be analyzed?
Materials & Methods
Material & MethodsSettingDurationStudy DesignSample SizeSampling TechniqueInclusion CriteriaExclusion CriteriaData Collection ProcedureData Analysis
9
Components of Synopsis• Supervisor Certificate• Title Page• Introduction: (Background, Problem, Rationale,
Purported Significance)• Objective: (SMART)• Operational Definition: (For all vague terms in
objectives or Title) • Hypothesis (If Any) (Give Alternate
hypothesis only)
• Material & Methods– Setting: (Short, precise)– Duration : (At least 6 months)– Study Design: (1 line only)– Sample Size: (Total subjects + Name of Groups& basis of grouping)– Sampling Technique: (Identify clearly)– Inclusion Criteria: (you have to justify them in DCP)– Exclusion Criteria: (you have to justify them in DCP)– Data Collection Procedure (DCP): (Source, How included, How
Excluded, Risk/Benefit, Informed consent, Ethical committee approval, steps of measuring variables)
– Data Analysis• References• Performa as Annexure
Components of Synopsis….
11
Study Designs
Types of Epidemiological Studies
12
Non ExperimentalObservational Studies
Experimental/Interventional Studies
Population Based
IndividualBased
Descriptive(Health Survey)
Analytic(EcologicalStudy)
DescriptiveCase reportsCase series
Analytic
RandomizedControl trial or(Clinical trial)
Non-randomizedQuasi-
ExperimentalField trial
Community Trial
Cross-sectional studyOr Prevalence study
Cohort study or Follow-up study
Case-control studyOr Case-reference
13
Descriptive Studies
Descriptive studies involve the systematic collection and presentation of data to give a clear picture of a particular situation and can be carried out on a small or large scale.
• Case Report
• Case series
• Cross Sectional Survey
14
Comparative or AnalyticalStudies
• Attempts to establish association or determine risk factors for certain problems. This is done by comparing two or more groups, with or without the outcome of interest/exposure of interest.
TypesObservationalExperimental
• A detailed report by a physician of an unusual disease in a single person.
• In 1941 Australian Ophthalmologist Greg reported a new syndrome Congenital Cataract linked to Rubella in the mother during pregnancy
15
Case Report
16
Case Report
• Classical example is that of a single case reported in Germany in late 1959 of a congenital malformation affecting the limbs and digits.
• More cases were reported in the following years. In 1961 a hypothesis was put forward that thalidomide, a sleeping pill, was responsible for congenital malformations.
• Subsequent analytic studies confirmed the link between the drug and congenital malformation.
• It was a single case report that led to formulation of hypothesis that OC use increases the risk of Venous Thromo-embolism.
• I saw a patient who reported psychotic episodes immediately after watching a TV Program “ Kaon Baney Ga Karore Pati?”
• Limitation: Only 1 individual’s experience
17
Case Report
18
Case Series
• When several unusual cases all with similar conditions are described in a published report, this is called a Case Series.
• In 1940 Alton Ochencer in US observed that virtually all patients he was operating for Lung Cancer gave history of smoking.
• Between Oct 1980 & May 1981, five cases….?• A case series does not include a control group.• Useful for hypothesis formation
• A detailed report by a physician of an unusual disease in a single person.Population: unknownSelect patient: (case report)or patients (case series) with disease of interestAssessment: Describe clinical findingsAnalysis: Radiographs, lab reports, etcInterpretation: Special features of this diseaseExample: “Normal plasma cholesterol in an 88-year-old man who eats 25 eggs a day” [Kern J, NEJM 1991; 324:896–899]12
Case Reports and Case Series
Cross-sectional Study
• Data collected at a single point in time
• Describes associations
• Prevalence
• Burden of Disease A “Snapshot”
Cross-Sectional Study: Definition
• Conducted at a single point in time or over a short period of time. No Follow-up.
• Exposure status and disease status are measured at one point in time or over a period.
• Prevalence studies. Comparison of prevalence among exposed and non-exposed.
22
Cross-Sectional Surveys-Advantages
• Fairly quick and easy to perform.• Inexpensive• Useful for determining the prevalence of disease
for a defined population and can also measure factors leading to it subsequent to group formations
• Such data is of great value for Pub Health Adm in assessing health status and needs of Population for effective healthcare Planning
Cross-sectional: Disadvantages
• Difficult to separate cause from effect, because measurement of exposure and disease is conducted at the same time.
• A persons exposure status at the time of the study may have little to do with their exposure status at the time the disease began.
Cross-Sectional Studies
• Exposure and outcome status are determined at the same time
• Examples include:– Behavioral Risk Factor Surveillance System (BRFSS)
- http://www.cdc.gov/brfss/ – National Health and Nutrition Surveys (NHANES) -
http://www.cdc.gov/nchs/nhanes.htm • Also include most opinion and political polls
Cohort studies
longitudinal Prospective studiesForward looking studyIncidence study
starts with people free of disease assesses exposure at “baseline”assesses disease status at “follow-up”
25
Cohort Studies
Disease No Disease
StudyPopulation
Exposed Non-exposed
No DiseaseDisease
Exposure isself selected
Follow throughtime
Relative Risk (RR)
It is the “ratio of incidence of disease among exposed to incidence of disease among non- exposed”
Incidence among exposedRelative Risk = ----------------------------------
Incidence among not exposed
27
2 x 2 Tables
Used to summarize counts of disease and exposure in order to do calculations of association
Outcome
Exposure Yes No Total
Yes a b a + b
No c d c + d
Total a + c b + d a + b + c + d
2 x 2 Tablesa = number who are exposed and have the outcomeb = number who are exposed and do not have the outcomec = number who are not exposed and have the outcomed = number who are not exposed and do not have the outcome
*****************************************************a + b = total number who are exposedc + d = total number who are not exposeda + c = total number who have the outcomeb + d = total number who do not have the outcomea + b + c + d = total study population
a bc d
OutcomeYes No
YesExposure
No
Relative Risk
• The relative risk is the risk of disease in the exposed group divided by the risk of disease in the non-exposed group
• RR is the measure used with cohort studies
a a + b
RR = c
c + d
a b
c d
OutcomeYes No Total
YesExposure
No
a + bc + d
Risk among the exposed
Risk amongthe unexposed
Relative Risk Example
Escherichia coli?
Burger Consumed Yes No
Total
Yes 23 10 33
No 7 60 67
Total 30 70 100
a / (a + b) 23 / 33RR = = = 6.67
c / (c + d) 7 / 67
Selection of study subjects
• General population– Whole population in an area– A representative sample
• Special group of population– Select group
• occupation group / professional group (Dolls study )
– Exposure groups • Person having exposure to some physical, chemical or
biological agent, e.g. X-ray exposure to radiologists
32
Types of Cohort Studies
• Prospective:– Exposure baseline in the present– Follow-up period: present to future
• Retrospective: – Exposure baseline in the past – Follow-up period: past to present
• Historical prospective or ambispective:– Exposure baseline in the past– Follow-up period: past to present to future
33
34
Retrospective Cohort Studies
• The investigator goes back into history to define a risk
group (e.g. *those children exposed to x-rays in utero vs.
those not), and follows the group members up to the
present to see what outcome (cancer) have occurred
35
Cohort Study – Prospective
Unexposed (controls)
Exposed (cases) With outcome
Without outcome
With outcomeWithout outcome
Onset of study
Direction of study
Cohort selected for study
36
Retrospective Cohort Studies
Exposed (cases)
Unexposed (controls)
With outcome
Without outcome
With outcome
Without outcome
Direction of study
Records selected for study
Onset of study
Cohort Studies: Advantages
• Temporality: Exposure precedes outcome because the cohort is disease free at baseline
• Efficient for studying rare exposures
• May be used to study multiple outcomes
• Allows for calculation of incidence of diseases in exposed and unexposed individuals
• Minimizes recall bias
37
• Tend to be expensive (large sample size) and time consuming (long follow-up period)
• Loss to follow-up – When multiple outcomes or specific disease
incidence is the outcome of interest, it can be a serious problem
• Inefficient to study rare diseases
Cohort Studies: Disadvantages
38
• Framingham, Massachusetts population was 28,000• Study design called for a random sample of 6,500 • Enrollment questionnaire from targeted age range
30-59 years• No clinical evidence of atherosclerotic
cardiovascular disease• Cohort re-examined every two years
Framingham Study Design
39
The Framingham Study
• Exposures included: – Smoking– Alcohol use– Obesity– Elevated blood pressure– Elevated cholesterol levels– Low levels of physical activity, etc.
40
The Framingham Study• Hypotheses:
– Persons with hypertension develop CHD at a greater rate than those who are normotensive.
– Elevated blood cholesterol levels are associated with an increased risk of CHD.
– Tobacco smoking and habitual use of alcohol are associated with an increased incidence of CHD.
– Increased physical activity is associated with a decrease in development of CHD.
– An increase in body weight predisposes a person to CHD.
41
Case-Control Studies
• Study population is grouped by outcome
• Cases are persons who have the outcome
• Controls are persons who do not have the outcome
• Past exposure status is then determined
Case-Control Studies
Had Exposure No Exposure
StudyPopulation
Cases Controls
No ExposureHad Exposure
Case Control Study: Analysis
Exposure odds calculation for both case and control groups:
- exposure odds for cases =
- exposure odds for control group =
Odds Ratio (OR) =
c
a
d
b
cb
da
dbca
Odds Ratio
• In a case-control study, the risk of disease cannot be directly calculated because the population at risk is not known
• OR is the measure used with case-control studies
a x d
OR = b x c
Interpretation
Both the RR and OR are interpreted as follows:
= 1 - indicates no association
> 1 - indicates a positive association
< 1 - indicates a negative association
Odds Ratio ExampleAutism
MMR Vaccine? Yes No
Total
Yes 130 115 245
No 120 135 255
Total 250 250 500
a x d 130 x 135OR = = = 1.27
b x c 115 x 120
The odds of being exposed to the MMR vaccine were 1.27 times higher in those who had autism than in those who did not have autism.
Problems with Case Control Study Selection Bias
• In 1929, Raymond Pearl at John Hopkins, Baltimore conducted a study to test the hypothesis tuberculosis protected against cancer
• He selected 816 cases of cancer from 7500 consecutive autopsies
• He also selected 816 controls from others on whom autopsies had been carried out at John Hopkins
• Of the 816 CASES (with cancer), 6.6% had TB• Of the 816 CONTROLS (without cancer), 16.3% had TB• From the finding that the prevalence of TB was
considerably higher in the control group, Pearl concluded that TB was protective against cancer
• Was Pearl’s conclusion justified?
Problems with Case Control Studies“Pearl’s Study”
• No!! At the time of the study, TB was one of the major reasons for hospitalization at Johns Hopkins Hospital
• Pearl thought that the control group’s rate of TB would represent the level of TB in the general population; but because of the way he selected the controls, they came from a pool that was heavily weighted with TB
• The way the controls are selected is a major determinant of whether a conclusion is valid or not
04/12/2023
Problems with Case Control StudiesCoffee-drinking and Cancer of the Pancreas in Women*• Cases were white cancer patients from 11 Boston and Rhode-Island
hospitals• Controls were patients from GI Clinics• McMohan found that coffee consumption was greater in cases than
controls• Controls were patients who had reduced their coffee consumption
because of Physician’s advice• The controls level of coffee consumption was not representative of
the general population• When a difference in exposure is observed between cases and
controls we must ask “Is the level of exposure observed in the controls really the expected level in the general population.
04/12/2023
Recall Bias
• Individuals who have experienced a disease or other adverse health events tend to think about possible causes & thus are likely to recall histories of exposure differently as compared to controls.
04/12/2023
Advantages
1. only realistic study design for uncovering etiology in rare diseases2. important in understanding new diseases3. commonly used in outbreak investigation4. useful if induction period is long5. relatively inexpensive
Disadvantages 1. Susceptible to bias if not carefully designed
(and matched)2. Especially susceptible to exposure misclassification3. Especially susceptible to recall bias4. Restricted to single outcome5. Incidence rates not usually calculable6. Cannot assess effects of matching variables
Experimental Study• Only type of study design that can actually prove
causation
• Individuals are randomly allocated to at least two groups. One group is subjected to an intervention, while the other group(s) is not.
• The outcome of the intervention (effect of the intervention on the dependent variable) is obtained by comparing the two groups.
04/12/2023
55
Interventional / Experimental Studies
• The researcher manipulates a situation and measures the effects of the manipulation amongst two groups, one in which the intervention takes place (e.g. treatment with a certain drug) and another group that remains "untouched" (e.g., treatment with a placebo) .
Experimental Study Examples
• Randomized clinical trial to determine if giving magnesium sulfate to pregnant women in preterm labor decreases the risk of their babies developing cerebral palsy
• Randomized community trial to determine if fluoridation of the public water supply decreases dental cavities
SamplingA sample is a sub set of the population, with all its inherent qualities. Inferences about the populationcan be made from the measurements taken from a sample, if the sample is truly representative of the population. Since a sample is expected to represent thewhole population, the sampling procedure has to follow three fundamentals:
1. Should be representative.2. Large enough.3. The selected elements should have been properly approached, included and interviewed.
Samples can be studied more quickly than populations. Speed can be important if a physician needs to determine something quickly, such as a vaccine or treatment for a new disease.
A study of a sample is less expensive than a study of an entire population because a smaller number of items or subjects are examined. This consideration is especially important in the design of large studies that require a long follow-up.
A study of the entire population is impossible in most situations.
Reasons for Using Samples
Steps in Sampling1. Definition of the population
We first need to identify the population we wish to draw the sample, from and do so somewhat formally because any inferences we draw are really only applicable to that population
2. Construction of a sampling frame (or thinking of an alternate)
The list of all possible units that might be drawn in a sample.
3. Selection of a sampling procedure
This is a critical decision about how to collect the sample. We will look at some different sampling procedure in the following slides.
TWO MAJOR TYPES OF SAMPLING PROCEDURES:
PROBABILITY Each element has the same chance of being included in the sample like:
1. Simple random2. Systematic3. Cluster4. Stratified
NON-PROBABILITY There is no assurance that each element will have the same chance of being included in the sample:
1. Consecutive2. Convenience3. Purposive
Convenience
TYPES OF SAMPLING METHODS
Sampling
Non-Probability Sampling
Consecutive Purposive
Probability Sampling
Simple Random
Systematic
Stratified
Cluster
Simple Random Sampling PREREQUISITES
1. Sampling frame a unique number is assigned to each element
2. Elements are selected into the sample randomly by 3 means:
Table of Random Numbers Lottery Method Computer Generated Numbers
64
Systematic Sampling
PREREQUISITES
1. Sampling frame (If available ) if not then too systematic sampling can be undertaken. What is required is an estimate of population size and required sample size.
SYSTEMATIC SAMPLING
• Decide on sample size: n
•Determine population size = N
• Divide population of N individuals into groups of k individuals: k = N/n
• Randomly select one individual from the 1st group.• Select every k-th individual thereafter.
N = 64
n = 8
k = 8
First Group
STRATIFIED SAMPLINGOne of the main purposes of stratified sampling is to compare different strata, which may not be possible with simple random sampling alone.
Pre requisite: Sampling frame The population is first divided into groups of elements called
strata. Each element in the population belongs to one and only one
stratum. Best results are obtained when the elements within each
stratum are as much alike as possible (i.e. homogeneous group).
A simple random sample is taken from each stratum.
CLUSTER SAMPLING
When a list of the entire area is not available and it is not physically possible to visit the entire area (e.g. the city, or country) one can divide the area into several equal size clusters or units.E.g.: Mohallas, Apartment Buildings, Villages, SchoolsOne can select (randomly) only a few cluster,
number all the units within it and draw either:
1. A random sample or2. A systematic sample
NONPROBABILITY SAMPLING
Non-probability sampling design are often more practical than probability designs for some clinical research. Because statistical significance test are based on the assumption that a probability sample has been used, the objective in non-probability sampling is to produce a facsimile, for the search question at hand of the probability sample.
CONSECUTIVECONSECUTIVE
CONVENIENCECONVENIENCE
PURPOSIVEPURPOSIVE
Three major types of nonprobability sampling are
CONSECUTIVE SAMPLING
– It involves taking every patient who meets the selection criteria over a specified time interval or number of patients.
– It is the best of the nonprobability techniques and one that is very often practical.
CONVENIENCE SAMPLING
1. It is the process of taking those members of the accessible population who are easily available.
2. Sample is selected in a haphazard fashion.
3. It is widely used because of its obvious advantages in cost and logistics, however this type of sampling technique in fraught with biases.
Purposive Sampling • Judgemental Sampling• done on the basis of some pre determined idea
(clinical knowledge)• Specific targets interviewed, as they posses the
desired information.• Experimenter exercises deliberate subjective choice
in drawing what he regards as the representative sample
• Personal prejudices / lack of knowledge• e.g. All Hypertensive patients of a certain age
04/12/2023
Quota Sampling
• Strata Identified• Researcher determines proportion of
elements needed from sub groups• No yard stick to measure representativeness • e.g. Male and Female population –
researcher decides the percentage
04/12/2023
Snowball Sampling • Technique where existing study subjects recruit
future subjects from among their acquaintances thus the sample group appears to grow like a snowball.
• Used for hidden populations difficult for researchers to access
• Examples would be ?• commercial sex workers, one would be able to get
information on more subjects by getting their contacts from those initially interviewed.
04/12/2023
INTRODUCTION TO BIOSTATISTICS
Statistics refers to numerical facts.
Field of statistics – how data are · presented· calculated· analysed· interpreted
When the data we use are biological, medical or health related the subject is called Biostatistics
•Set or group of discrete observations of attributes or events that carry little meaning when considered alone. •Data is the raw material for any research
•Data (plural) – Singular ? – Singular for Data is ‘Datum’
•Comprises of observations made on VARIABLES
April 12, 2023
IT ALL STARTS WITH DATA
•A characteristic that takes different values in different persons, places or things or different values in the same person at different times:
– Heights of adult males– Weight of preschool children– RBCs / ml of blood– Age of patients in a medical OPD
•Any quantity that varies.April 12, 2023
WHAT IS A VARIABLE
Independent Variable
The variables that are used to describe or measure the factors that are assumed to cause or at least to influence the problem are called the INDEPENDENT (exposure) variables. e.g. Smoking
April 12, 2023
Dependent Variable
April 12, 2023
–The variable that is used to describe or measure the problem under study (outcome) is called the DEPENDENT variable.–e.g Lung cancer
Categorical(Qualitative)
April 12, 2023
Numerical(Quantitative)
Nominal Ordinal Discrete Continuous
VARIABLE / DATA CLASSIFICATION
•The characteristic which can’t be expressed numerically like sex, ethnicity , healing etc.•Types
– Nominal
– Ordinal
April 12, 2023
CATEGORICAL / QUALITATIVE VARIABLES
Presentation of Data•Data once collected should be presented in a such a way as to be easily understood. The style of presentation depends, of course, on type of data.
•Data can be presented in as frequency tables, charts, graphs, etc. Here we would discuss some of the important means of presentation.
April 12, 2023
FREQUENCY TABLES
•In a FREQUENCY TABLE data is presented in a tabular form. It gives the frequency with which (or the number of times) a particular value appears in the data.
Blood Pressure of patients coming to a tertiary care hospital OPD
Distribution Frequency Relative Cumulative Relative
Below 100 6 0.10 0.10
100 – 120 9 0.15 0.25
121 – 140 24 0.40 0.65
141 – 160 15 0.25 0.90
Above 160 6 0.10 1.00
Bar charts
•Bar charts are used for nominal or ordinal data.
Years
No.
of
ciga
rett
es
Cigarette consumption of persons 18 years of age or older, United States, 1900 - 1990
Pie chart•Pie charts can also be used to display nominal or ordinal data.
April 12, 2023
Gender distribution
Histogram
A histogram depicts a frequency distribution for ContinuousHistogram showing distribution of Age (years)