Research Methodology:Methods and Materials

Components of a research proposal

Title Summary IntroductionObjectiveMethods and materialsEthical consideration Dissemination and utilization of findingsWork planBudgetReferencesAnnexes

2

Methods and Materials

The methods or procedures section is really the heart of the research proposal

Methods/procedures show how you will achieve the objectives and answer the research question

Indicates the methodological steps you will take to answer every question, to test every hypothesis or to address every objective

3

Methods and Materials…

• There should be a very clear link between the

methods you describe in this section and the

objectives you have previously defined.

• Be explicit in your writing and state exactly how

– the methods you have chosen will fulfil your objectives &

– It will help to deal with the needs/problems on which your

proposal is focused

Methods section may include:Study designStudy area and period PopulationsStudy variablesEligibility (Inclusion and exclusion) criteriaSample size calculation, sampling methods &

proceduresData collection techniques & toolsData quality control measuresData managementPlan for data processing and analysisOperational definitions Limitation of the studyEthical considerationsPlan for dissemination and utilization of findings

5

1. Study design

Clearly state the study design to be used

Specify the approaches to carry out the research (either quantitative, qualitative, or mixed)

Select the most appropriate and most feasible study design

6

Epidemiologic studies

• Help to answer questions:

– How big is the problem (magnitude)?– Who has the problem? When and where?– What causes the problem?– Are certain factors associated with the problem?– What will happen if the suspected factors are removed

or reduced? – What is the effect of a particular intervention on the

problem? New drug? Health education?– What are the possible solutions?

• The selection of study design depends on:• The type of problem• The current knowledge about the problem• Availability of resources• Different research questions may require different

study designs

o The selection of an appropriate study design for the study is the most important decision the investigator has to make.

2. Population

The population under consideration should be

clearly defined in terms of place, time, and other relevant criteria

In this sub-section, identify:– Source (Reference or target population) population – Study population – Sampling unit: unit measurement of source

population– Study unit: a direct source of information

Study population

Sampling unit: unit measurement of source populationStudy unit: a direct source of information

Eligibility criteria

Inclusion criteria: – identify eligible subjects for the study

Exclusion criteria: – to systematically exclude subjects

from the study population– justify why exclusion is important –Exclusion is from the domain

12

Study Variables

• A variable is a characteristic of a person, object or phenomenon, which can take on different values.

• Variables may be:– Numerical (values can be expressed in

numbers-eg. Age, income– Non-numerical characteristics

(categorical) e.g. sex, treatment outcome

Variables

• In health research we often look for associations.

• Hence, it is important to make a distinction between dependent and independent variables.

Independent variable(X) :

• Also known as predictor = explanatory

variables

• a variable that attempts to explain the

variation in dependent variable (Y).

• factor that influence the outcome variable

Dependent variable (Y)/outcome Dependent variable (Y)/outcome variable: variable:

It is the outcome It is the outcome ((response) response) of a of a

study, study, vary in relation to the independent variables, and results can be predicted

Dependent…

• Eg. Association between smoking and lung cancer

• Dependent variable= developing lung cancer (yes, No)

• Independent variable= smoking (yes, No)

»Study design

Case-controlCase-control

CohortCohort

IndividualsIndividuals

InterventionalInterventional

RetrospectiveRetrospective

ProspectiveProspective

DescriptiveDescriptive

PopulationsPopulations

AnalyticalAnalytical

ObservationalObservational

Case reports/case seriesCase reports/case series

Cross-sectional

Ecologic/correlationalEcologic/correlational

Experimental (RCT)

Types of Epidemiological Studies

Quazi-Experimental

Classical Case-controlClassical Case-control

Nested Case-controlNested Case-control

Epidemiological study design Is there comparison group?

Test hypothesis?

Epidemiological study design Is there comparison group?

Test hypothesis?

1. Descriptive Epidemiology

Describe patterns of disease occurrence within a

population in relation to person, place and time

♣ Used to identify any health problems that may exist

♣ Generates idea(s)/ hypothesis for presence of

association between risk factor and illness

♣Frequently encountered approach

1. Population as study subjecto Correlational /ecological studies

Individual as study subjects

o Case report (Single case)

o Case series (few cases)

o Cross-sectional study (survey)

Categories of descriptive statistics

2. Analytical Epidemiology

Uses comparison groups to establish an association

between risk factors and illness in the two groups

♣ Identify the cause (s) of the problem

♣ Concerned with determinants of disease,

• the reasons for low or high frequency of a disease

♣ Tests hypotheses

2.1 Observational studies = The investigator simply observes the natural course of events or an outcome of interest

o Case-control studyo Cohort study

2.2 Experimental / intervention studies = The investigator allocates the exposure and then follow the subjects for the subsequent development of disease

Categories of analytic epidemiological studies

WHO? WHERE? WHEN?

Descriptive Epidemiology

Person

PlaceTime

Cases

0

5

10

15

20

25

1 2 3 4 5 6 7 8 9 10

0

200

400

600

800

1000

1200

0-4 '5-14 '15-44

'45-64

'64+

Age Group

Who? Where? When?

Descriptive Studies

Characteristics of Persons

“Who is getting the disease?” Age, sex, religion, socio-economic status, race

• Young vs old, males vs females, rich vs poor, more educated vs less educated, black vs white, etc

Characteristics of Place

“Where are the rates of disease highest/ lowest?”

• Urban vs rural, some regions more affected than others?

• National vs international?

• High altitude or low altitude?

• Polluted areas or unpolluted areas?

• Mountainous vs valley

• Adequate rainfall or little rainfall areas?

Differences in frequency of diseases are related to variations

in climate, altitude, topography, geology and in general

environment.

Characteristics of Time

“When does the disease occur commonly/ rarely?”

Was there a sudden increase over a shorter period of

time?

Is the problem greater during rainy or dry season?

“Is the frequency of the disease now different from the

corresponding frequency in the past?”

Is the problem gradually increasing/ decreasing?

Uses of Descriptive Studies

Describe the pattern of disease occurrenceDescribe the problem in terms of person, place and timeGenerate numbers of events (frequency)Help to calculate ratio, proportion and ratesProgram planning / resource allocationIdentify problems to be studied by analytic methodsGenerate hypothesis

Types of Descriptive Studies

• Ecological / Correlational studies– The unit of observation is the entire population to

compare disease frequency between different groups• During the same period of time among different

populations or in the same population at different points in time.

– Comparison of rates (morbidity or mortality) across geographical areas (or regions).

Ecologic / Correlational

• Advantages:

– useful for the formulation of hypotheses

– Quick and inexpensive

– Often use already available information (secondary

data)

Ecologic …

– Disadvantages:

• Based on averages and may miss actual contributing

factors

• Unable to link exposure with disease at individual level

• Lack of ability to control for potential confounders

• Presence or absence of correlation does not imply

valid statistical association

Types of Descriptive …Cont’d• Case report or case series

– Detailed report of a single patient (case report) or a

group of patients (case series) with a given disease

– Document unusual medical occurrences

– Gives the first clues in the identification of new disease

and adverse effects of exposures

– An important link between clinical medicine and

epidemiology

– Most common types of studies

Types of Descriptive …Cont’d

• Case reports and case series played a

role in the early recognition of AIDS

– In 1980 and 1981, five cases of Pneumocystis carini

were reported among young homosexual men in Los

Angeles. Previously, it occurred in older cancer patients

with compromised immunity

– In 1981, large number of cases of Kaposi’s sarcoma

happened in young homosexual men. Previously this

exclusively occurred in elderly men and women equally

Case reports / case series

Advantages– Simple, quick, inexpensive– Formulate hypothesis

Disadvantages– Can’t be used to test hypotheses– Based on the experience of one or few people

(small sample size), it can be coincidence – Lacks comparison group

Cross-Sectional Studies

• Often called prevalence study. E.g., KAP, DHS, etc

• Collection of data at one point in time at individual level

• Presence or absence of both exposure and disease is

assessed at the same time

• Provide “snapshot” of health experience

• Used to assess the health care status and health care

needs of a population

Cross-Sectional Studies

Advantages Disadvantages

• Quick and inexpensive• Used for planning• Initial step• Multiple factors/

outcomes• Provide early clues for

hypothesis generation

• Temporal relationship of

exposure and disease not distinguishable (whether exposure or disease came first unknown)• Bias in measuring exposure

• No incidence/ relative risk• No hypothesis testing

Why? How?

Analytical Epidemiology

Analytical Studies

• Purpose/aim

– Focus on determinants of cause

– Search for cause and effect.

– Answer questions like: Why? How?

– To test whether certain factors are associated with disease or

not

– Test hypothesis about causal relationship

• Proof

– Quantify the association between exposure and outcome

Analytical Studies

• Basic features

– Appropriate comparison group needed• Exposed Vs Control

– It is the use of comparison group that allows testing of epidemiologic hypotheses

Two types of Analytic StudiesDifference lies in the role of the

investigator

- Observational studies• The investigator simply observes the natural course of an event• The investigator measures but does not intervene.

– Interventional studies• The investigator assigns study subjects to exposure and non-

exposure, then follows to measure for disease occurrence.• The investigator manipulates the intervention or exposure.

Observational Studies

• Temporal relationship between observations of Exposure (E) and Disease (D):

• Direction– Forward: starts with E– Backward: starts with D

• Chronological relationship between onset of study and occurrence of D:

• Timing– Prospective: study onset -----> D– Retrospective: D <--------- study onset

Observational Studies

Case Control Vs Cohort

– Case-control = Both the exposure and

disease have already occurred at the time

of the study

– Cohort = Disease free exposed and non-

exposed people are followed up to measure

the outcome

Disease

No disease

Exposure

?

?

Retrospective Nature

Case-Control Studies

(Case)

(Control)

Present

Past

• Case-Control Study: – Compares people with disease (case) and without

disease (control) – to determine the exposure status by looking

backward in time.

• Data are analyzed whether exposure was different for cases and for controls

• Higher proportion of risk factor among cases than controls suggests association or lesser proportion of risk factors among case

• Very common type of epidemiologic studies

Source: partially adapted from WHO, 1993

Design of a Case-Control Study

can

Selection of cases

• Subjects selected on the basis of disease

• A case should be clearly defined with regard to

specific characteristic of disease

• Needs standard diagnostic criteria

• Sources of Cases:

– hospital setting = hospital-based case-control

– defined general population = population-based

– disease registries with complete records

Selection of Controls

• Be comparable to the cases: controls should have the same

characteristics as the cases (except for the disease of interest)

• Must have the same opportunity for exposure as a case

• Must be subject to the same inclusion and exclusion criteria as

cases

• Involves consideration of a number of issues: scientific, economic

and practical considerations

• Selection of controls may involve matching:

– Cases and controls have the same (or similar)

characteristics other than the disease

– Ensures comparability

– Age, sex, race, socio-economic status, etc.

• These factors are associated with the incidence of most

diseases

Sources of Controls

• Hospital controls: patients attending or admitted to the same

institution for other diseases

• Relatives, friends or neighborhood

• Community (population) controls: selected from the same source

population as the cases

– More expensive

Data collection

• Interviews, questionnaires and/or examination; or

surrogates (spouses or mothers of children) or from

medical records

• Should be objective or well standardized

• Better not to know cases or controls (blinding)

• Same procedure for cases and controls should be

applied

Case-Control Studies• Advantages

– Rare disease, e.g., cancer of a specific organ

– Suitable for the evaluation of diseases with long latent

periods

– Quick and inexpensive

– Relatively efficient, small sample size

– Little problem with attrition

– Can examine multiple etiologic exposures

– No ethical problems

Case-Control Studies

• Disadvantages

– Inefficient for rare exposures

– No calculation of rates and risks

– In some situations, the temporal relationship

between exposure and disease may be difficult to

establish Temporal E – D uncertainty

– Prone to selection and recall bias

– Selection of control difficult

Cohort Studies

• Disease free exposed and non-exposed people

are followed up and then outcome events are

picked up when they occur

• Measure and compare the incidence of disease

in two or more study cohorts

• Usually prospective or forward looking.

• Are also called longitudinal studies.

What is a cohort?

• A group of persons– sharing the same experience– followed for a specified period of time

• Examples– birth cohort– workers at a chemical plant– graduating university class– attendants of this course

Disease among exposed?

Disease among non-exposed?

Usually prospective

Cohort study

Populationat risk

Exposed

Not Exposed

Types of Cohort Studies

• Based on the starting point of the study– Prospective (classical)

– Retrospective (historical)

Prospective Cohort Study

+

-

+ -ill

exp+

-exp

Diseaseoccurrence

Study startsExposureoccurrence

Prospective assessment of disease

Selection based on exposure

Time

Exposureassessment

Study starts Diseaseoccurrence

Prospective Cohort Study

Time

+

-

+ -ill

exp+

-exp

Prospective assessment of exposure and disease

Selection of population

Rétrospective cohort studies

Exposure

time

Diseaseoccurrence

• Disease outbreak following a gathering• Occupational exposure in mine workers

Study starts

Rétrospective Cohort Study

Study takes place

Diseaseoccurrence

Exposureoccurrence

Retrospective assessment of exposure and disease

+

-

+ -ill

exp

• Limitations of retrospective cohort:

– All relevant variables may not be available in the original records

– Difficult to ascertain that the study population was free from the disease at the start

– Loss of records, incomplete data

Data collection for Cohort Studies

• Interview with follow-up

• Medical records monitored over time

• Medical examinations and laboratory testing

• Apply equally to exposed and non-exposed

Advantages of cohort studies• Directly measure relative risk or rate

• Measures of effect have clear meaning and are easily

understandable

• Temporal relationship between exposure & disease is clear

• Prospective cohort studies less susceptible to selection bias

because outcome not known

• Well suited to rare exposures

• Several outcomes can be examined in one study

Disadvantages of cohort studies

• Large sample size• Inefficient for disease with latency period• Loss to follow-up• Exposure can change over time• Multiple exposures = difficult• High cost • Time consuming

Summary

• Cohort studies allow measure of risk• Case-control studies are rapid, but not

measure risk; only estimate RR• In the ideal world: prefer cohort to case-

control study• In the real world: case-control studies usually

do the job

Experimental/Intervention Studies

o Investigator assigns subjects to exposure and non-exposure and makes follow up to measure for the occurrence of a disease.

o It is usually prospective.o Provides high quality datao Random allocation

o Assign E randomly, follow for D

Source: partially adapted from WHO, 1993

Design of an Experimental Study

Investigator determinesexposure status throughRandom allocation

When to choose an experimental design?

• Generally reserved for relatively "mature” research

questions

• A lot has to be done before embarking on an

experimental study

When to choose an experimental design?• When:

– the research question cannot be answered by observational studies

– earlier observational studies have not answered the research question

– existing knowledge is not sufficient to determine clinical or public health policy

– an experiment is likely to provide an important extension of this knowledge

Types of Experimental Studies

• Randomized Clinical Trial (RCT)• Community Intervention Trial (CIT)

Randomized Clinical Trial (RCT)• Randomization is done on individuals

– Each patient is given an equal chance of being assigned to either group (e.g., treatment vs. placebo)

• Blinding (masking) possible:– Double-blind = Neither the patients nor the investigators

responsible for outcome assessment know what treatment she/he is getting

– Single-blind = The investigator alone is aware of the group to which a participant has been assigned

– Un-blinded = Both the investigator and patient are aware of the treatment assignment.

• Most common

Direction of inquiry

Manipulation

Community Intervention Trials (CITs)

• Randomization is done on groups or communities rather than individuals– E.g., New drug or vaccine testing (some communities receive vaccine others

placebo through random assignment)

• Blinding not possible• Contaminations and co-interventions serious

problems

Problems of Intervention Studies• More difficult to design and conduct• Ethical issues

– Withholding– Exposing

• Feasibility– Very large sample size required

• Cost – Very expensive

Advantages of Intervention Studies

• GOLD STANDARD = Randomized, placebo controlled, blinded clinical trials

• The ability to assign exposure

• The ability to control confounding

• Findings can be replicated = Generalizability

The hierarchy of epidemiological research

Summary Points on Study Designs• Two types of epidemiological studies

– Descriptive– Analytic

• Descriptive– Case reports/Case series– Ecological– Cross-sectional

• Analytical– Observational: Case-control & Cohort– Experimental

Operational definition

For some variables it is sometimes not possible to find meaningful categories unless the variables are made operational with one or more precise indicators

Operationalizing variables means that you make them measureable

81

Operational Versus standard definition

Standard definitions are widely/universally accepted definitions of the variable E.g. “Obesity”-excessive fatness”,

“overweight”

However, operational definition is heavily influenced by considerations of practicability during measuring

82

In general, operational definitions of variables are used in order to:– Avoid ambiguity– Make the variables to be more measurable

Justification is needed for setting cut-off points

Example: Knowledge

83

Sample size and sampling techniques

Describe how the sample size is determined

Describe the methods of sample selection

If needed, use diagrams to simplify the sample selection process (sampling procedures)

84

Sample size and sampling...con’d

The key reason for being concerned with sampling is validity (internal and external validity)

The key word in sampling is representativeness

A representative sample has all the important characteristics of the population from which it is drawn

A sample is a representative of the population under study

85

SAMPLE SIZEDepending on:

1) Variability in the target population. (If unknown, assume maximum variability)

2) Desired precision in the estimate

3) Desired confidence in the estimate

4) Feasibility

and Confidence Level

The significance level of a test: the probability of rejecting the null hypothesis when it is true (or the probability of making a Type I error). It is usually 5% (0.05)

Confidence level: The probability that an estimate of a population parameter is within certain specified limits of the true value;

(commonly denoted by “1-”, and is usually 95%).

Power and β

Power: The probability of correctly rejecting the null hypothesis when it is false; commonly denoted by “1- β”.

β : The probability of failing to reject the null hypothesis when it is false (or the probability of making a Type II error).

Null hypothesis

Precision

A measure of how close an estimate is to the true value of a population parameter.

It may be expressed in absolute terms or relative to the estimate.

It is denoted by d in sample size determination

SAMPLE SIZESample Size Required for Estimating Population Mean

• The objective in interval estimation is to obtain narrow intervals with high reliability

• The width of the interval is determined by the magnitude of the quantity

Sample Size Required for Estimating Proportions

• The formula requires the knowledge of p, the proportion in the population possessing the characteristic of interest.

– A pilot or preliminary sample. Observations used in the pilot can be counted as part of the final sample

– Estimates may be available from previous studies and the upper bound of p can be used in the formula

– If impossible to come with a better estimate, set p = 0.5 in the formula to yield the maximum value of n

Sample Size Required for Estimating Proportions

Assuming random sampling and approximate normality in the distribution of p,

Where q = 1 – p

nZα/2 P q

2

2d

Finite Population Correction

• Finite Population Correction (FP)

• – N = population size– n = sample size

• Can be ignored when sample size is small in comparison with the population size

• Use when n / N .05

Finite Population Correction

N n n/N (N-n)/(N-1) nFPC

100000 384 0.00384 0.996 383 50000 384 0.00768 0.992 381 20000 384 0.0192 0.981 377 10000 384 0.0384 0.962 369 5000 384 0.0768 0.923 355 1000 384 0.384 0.617 237

Definition of sampling

Procedure by which some members of the population are selected as representatives of

the entire population

Why sampling?

• Due to the variability of characteristics among items in the population, researchers apply scientific sample designs in the sample selection process to reduce the risk of a distorted view of the population, and they make inferences about the population based on the information from the sample survey data.

Advantages of sampling:• Feasibility: Sampling may be the only feasible method of

collecting the information.• Reduced cost: Sampling reduces demands on resource such as

finance, personnel, and material.• Greater accuracy: Sampling may lead to better accuracy of

collecting data• Sampling error: Precise allowance can be made for sampling

error• Greater speed: Data can be collected and summarized more

quickly

Disadvantages of sampling:

• There is always a sampling error.• Sampling may create a feeling of

discrimination within the population.• Sampling may be inadvisable where every unit

in the population is legally required to have a record.

Errors in sampling• i) Sampling error: • Errors introduced due to errors in selection of a

sample.• They cannot be avoided or totally eliminated.

ii) Non sampling error:‐ ‐ Observational error ‐ Respondent error ‐ Lack of preciseness of definition ‐ Errors in editing and tabulation of data

Concept of representativity

• Time• Seasonality• Day of the week• Time of the day

• Place• Urban• Rural

• Persons• Age• Sex• Other demographic characteristics

Definition of sampling terms

• Sampling unit– Basic sampling unit (bsu) around which sampling

is planned

• Sampling frame – Any list of all the sampling units in the population

• Sampling scheme– Method of selecting sampling units from

sampling frame

Why do we sample populations?

• Get information from large populations• Study efficiency• Obtain more accurate information

Type of samples

• Non-probability samples– Convenience samples

• Biased• Best or worst scenario

– Subjective samples • Based on knowledge• Time/resources constraints

• Probability samples– Only sampling method that allows to draw valid

conclusions about population

Probability sampling:• It is a sample obtained in a way that ensures

that every member of the population has a known, non zero probability of being included in the sample.

• Probability sampling involves the selection of a sample from a population, based on chance.

• Probability sampling is more complex, more time consuming and usually more costly than ‐non probability sampling.‐

Probability samples

• Random sampling• Removes possibility of bias in selection of

subjects• Each subject has a known probability of

being chosen • Allows application of statistical theory to

results

Sampling error• No sample is a perfect mirror image of the

population• Magnitude of error can be measured in probability

samples • Expressed by standard error

– of mean, proportion, differences, etc

• Function of– sample size– amount of variability in measuring factor of interest

Methods used in probability samples

• Simple random sampling• Systematic sampling• Stratified sampling• Cluster sampling• Multistage sampling

Simple random sampling

• Principle– Equal chance for each statistical unit

• Procedure– Number all units– Randomly draw units

• Advantages– Simple– Sampling error easily measured

• Disadvantages– Need complete list of units– Does not always achieve best representatively when there is minority

Example: Simple random sampling1 Albert D.2 Richard D.3 Belle H.4 Raymond L.5 Stéphane B.6 Albert T.7 Jean William V.8 André D.9 Denis C.10 Anthony Q.11 James B.12 Denis G.13 Amanda L.14 Jennifer L.15 Philippe K.16 Eve F.17 Priscilla O.18 Frank V.L.19 Brian F.20 Hellène H.21 Isabelle R.22 Jean T.23 Samanta D.24 Berthe L.

25 Monique Q.26 Régine D.27 Lucille L.28 Jérémy W.29 Gilles D.30 Renaud S.31 Pierre K.32 Mike R.33 Marie M.34 Gaétan Z.35 Fidèle D.36 Maria P.37 Anne-Marie G.38 Michel K.39 Gaston C.40 Alain M.41 Olivier P.42 Geneviève M.43 Berthe D.44 Jean Pierre P.45 Jacques B.46 François P.47 Dominique M.48 Antoine C.

Systematic sampling

• Principle– A unit drawn every k units– Equal chance of being drawn for each unit

• Procedure– Calculate sampling interval (k = N/n)– Draw a random number ( k) for starting– Draw every k units from first unit

• Advantages– Ensures representativity across list– Easy to implement

• Disadvantages– Dangerous if list has cycles

Example: Systematic samplingExample: systematic sampling

Stratified sampling

• Principle– Classify population into homogeneous subgroups (strata)– Draw sample in each strata– Combine results of all strata

• Advantage– More precise if variable associated with strata– All subgroups represented, allowing separate conclusions about

each of them

• Disadvantages– Sampling error difficult to measure– Loss of precision if very small numbers sampled in individual strata

Example: Stratified sampling

• Determine vaccination coverage in a country• One sample drawn in each region• Estimates calculated for each stratum• Each strata weighted to obtain estimate for

country

Cluster sampling

• Principle– Random sample of groups (“clusters”) of units– In selected clusters, all units or proportion of units included

• Advantages– Simple as no list of units required– Less travel/resources required

• Disadvantages– Imprecise if clusters homogeneous

(large design effect)– Sampling error difficult to measure

CLUSTER SAMPLING

The sampling unit is not a subject, but a group (cluster)of subjects. It is assumed that the variability among clustersis minimal, while within each cluster is representing thegeneral population

1. Define the number of clusters to be included

2. Compute a cumulative list with the populations per each unit and a grand total

3. Divide the grand total by the number of clusters and obtain the sampling interval

CLUSTER SAMPLE

6. By repeating the same procedure, identify all the clusters

7. In each cluster select a random sample using a sampling frame of subjects (e.g. residents) or households.

4. Choose a random number and identify the first cluster

5. Add the sampling interval and identify the second cluster

Advantage: easy to perform

Disadvantage: design effect

CLUSTER SAMPLING in EPI

Procedure: list of all villages (areas) with total population

village inhabitants Cumulative1 34 342 60 943 30 1244 76 2005 315 515.. 4,715

divide the cumulative total by 30 clusters we wish to select

4,715 : 30= 157.1

EPI CLUSTER SAMPLING

choose from the cumulative distribution the clustersby adding 157 (sampling interval)

4 124 124 * 1st cluster5 76 200 6 315 515 ** 2nd 123+157=280

3th 280+157=437..

in each village (area) choose 7 children

Total sample 30 X 7= 210

find a random number with three digits (= sampling interval) e.g. 123

Design effect

Global variance

p(1-p) Var srs = ----------

n

Cluster variance

p= global proportionpi= proportion in each stratumn= number of subjectsk= number of strata

Σ (pi-p)²Var cluster = -------------

k(k-1)

Design effect = ------------------Var srs

Var clust

Example: Cluster sampling

Section 4

Section 5

Section 3

Section 2Section 1

Multistage sampling

• Principle– Several chained samples– Several statistical units

• Advantages– No complete listing of population required– Most feasible approach for large populations

• Disadvantages– Several sampling lists– Sampling error difficult to measure

Data collection techniques and tools

Describe: What are data collection techniques

and tools?Who will collect the data?Who will supervise the data collection

process?How long will take the data collection?

etc…

123

Data quality control measures

Be aware of possible sources of error to which your design exposes you

You will not produce a perfect, error free design (no one can!)

However, you should anticipate possible sources of error and attempt to overcome them or take them into account in the analysis

124

Data quality…con’d

Describe/provide:Selection and training of field staffsTranslation of the data collection tool to

the local language Pre testing the research methods and toolsStandardization and/or calibration of data

collection toolsStrict supervision of field staffsClarify the purpose of study to respondentsDouble data entry Re-interviewing of randomly (e.g. 5%)

etc…125

Pretesting Versus Pilot study

Describe where the pretesting will be conducted

How many study subjects will be included in the pretesting

Will that be undertaken in the same area and/or the same population.

If the collected data is going to be analysed or included in the study.

126

Data management

Data processing refers to:– data entry onto a computer, and – data checks and corrections

The aim of this process is to produce a relatively ‘clean’ data set

127

Data management… con’d

Data coding:In general computers are at their best

with numbers

Some statistical packages cannot analyze alphabetic codes, some cannot understand open ended responses

128

Data management… con’d

Coding is assigning a separate (non-overlapping) numerical code for separate answers and missing values

Example: Instead of using ‘Male’ and ‘Female’ for

the variable sex, it can be indicated as 1=Male & 2= Female

129

Data management… con’d

Data Cleaning:

Once data have been gathered, they need to be entered into a computer data file and checked for errors

No matter how carefully the data have been entered some errors are inevitable

The aim of this process is to produce a clean set of data for statistical analysis

130

Plan for data processing and analysis

A plan for data analysis should include the following information:

Identification of the analysis tasks to be completed– Z test, Chi-square test , t-test, correlation,

regression…– Confidence interval (CI) and P-value

A schedule or work plan for the analysis of the data

Identification of the statistical software to be used for the analysis

131

Limitation of the study

State anticipated and inevitable limitations of the study be methodological and/or logistical

132

Ethical consideration Professional obligation to safeguard the

safety of study subjects

Describe potential ethical concerns and mechanisms to minimize harm and maximize benefits

Every research can potentially cause ethical concerns!

Research Ethics principles

Respect person

Benefit /no harm

Justice 133

Plan for dissemination and utilization of findings

Briefly describe the dissemination plan:– Feedback to the community– Feedback to local authorities– Identify relevant agencies that need to be

informed– Scientific publication in a reputable journal– Presentation in meetings/conferences/ symposium

Briefly describe how the study findings can be best translated into application

134

Work plan

The work plan is the timeline that shows when specific tasks will have been accomplished

A work plan informs the reader how long it will take to achieve the objectives/answer the questions

135

Work plan …con’d

It is a schedule, chart or graph that summarizes the different components of a research proposal and how they will be implemented in a coherent way within a specific time-span

Work plan includes:– Tasks to be performed– When these tasks will be performed– Who will perform the task

136

Work plan …con’d

The GANTT Chart

It is a planning tool which depicts graphically the order in which various tasks must be completed and their duration of activity

A typical Gantt chart includes the following information:

The tasks to be performedWho is responsible for each taskThe time each task is expected to take

137

A work plan can serve as:

A management toolA tool for monitoring and evaluationA visual illustration of the sequence of

the project operations

138

GANTT Chart

Budget

To conduct research, it is necessary to obtain funding for the research project

When drawing up a budget, be realistic!

Do no attempt to be too economical to demonstrate how cheaply you can run the project

At the same time, do not be too expensive so as not to discourage the fund providers

140

Budget …con’d

How should a budget be prepared?

It is necessary to use the work plan as a starting point

Specify, for each activity in the work plan, what resources are required

Determine for each resource needed the unit cost and the total cost

141

Budget …con’dThe budget format and justification

The type of budget format to be used may vary

Most donor organizations have their own special project forms, which include a budget format

Include 5%-10% contingency fund for market inflation

142

AnnexesAnnexes may include the following:

Data collection tools and procedures Consent form and information sheetDummy table Conceptual frame workSampling procedure Map of the study areaLetter of support (cooperation letter) Copy of the ethical approval letter, etc…Curriculum vitae (CV) of the principal

investigator 147

Referencing

Referencing is a standard way of acknowledging the sources of information

It is important to be consistent when you are referencing

149

Major sources of literatures

–Books – Journals –Report paper–Conference paper–Website etc...

150

Methods of citations in preparing LR:

Vancouver system Harvard system

151

The Vancouver system

In the Vancouver style, citations within the text of the essay/paper are identified by Arabic numbers in round brackets or Arabic numbers in superscript.

Example: Although an increasing number of countries have

succeeded in improving the health and well being of mothers and children, some countries with the highest burden of mortality made little progress during the 1990s (1). More than 10 million children die each year, most from preventable causes and almost all in poor countries, but the causes of death may differ from one country to another (2).

152

Vancouver…con’d

Example:

Human ascariasis occurs both in temperate and tropical environments. The prevalence is low in arid climates, but high where conditions are wet and warm as these conditions are ideal for egg survival and embryonation. In addition, crowding, low socioeconomic status, poor environmental hygiene, and water supply contribute to the increased risk of infections due to helminthes (3-6).

153

Vancouver…con’d

The original number assigned to the reference is reused each time the reference is cited in the text, regardless of its previous position in the text

154

Vancouver…con’d

For a book

Author(s)’ Surname followed by initials. Title of book. Place: Publisher; Year, Edition.

Example:

Abramson H. Survey methods in community Health. Edinburgh: Churchill Livingstone ; 1990, 4th ed.

155

Vancouver…con’d

For a chapter in a book:

Author(s) of chapter (Surname(s) followed by initials. Chapter title. In: Editor(s) of book, (Surname(s) followed by initials) (eds). Title of book. Place: Publisher, Year: Page numbers of chapter.

Example:

Jennifer D. Epidemiological methods. In: Ng’weshemi J, Boerma T, Bennett J and Schapink D (eds). HIV prevention and AIDS care in Africa; A district level approach. Amsterdam: KIT Press, 1997: 51-68.

156

Journal:

Author(s) Family name and initials. Title of article. Title of journal abbreviated Publication year, month, day (month and day if available); volume(issue): pages.

Example:

Paul K. Maternal mortality in Africa from1980-87. Social Science and Medicine 1993;37(2):745-52.

157

Two Authors

Example Haile A, Enqueselassie F. Influence of

women's autonomy on couple's contraception use in Jimma town, Ethiopia. Ethiop. J. Health Dev 2006;20(3):145-151.

158

More than Six authors:

Write the first three authors, and et al.

Example:

Tsega E, Mengesha B, Nordenfelt E, et al. Serological survey of HIV infection in Ethiopia. Ethiop Med J 1998;26(4):179-84.

159

Reports and other organizational publications

Author(s). Title of report. Place of publication: Publisher; Date of publication (year and month if applicable).

Example:

WHO. Lay Reporting of Health Information. Geneva, Switzerland: World Health Organization; 1978.

160

Conference papers

Author(s) of paper – Family name and initials. Title of paper. In: Editor(s) Family name and initials, editor(s). Title of conference; Date of conference; Place of conference. Place of publication: Publisher’s name; Year of publication.

Example: Kimura J, Shibasaki H. Recent advances in clinical

neurophysiology. Proceedings of the 10th International Congress of EMG and Clinical Neurophysiology; 1995 Oct 15-19; Kyoto, Japan. Amsterdam: Elsevier; 1996.

161

Websites

Example World Health Organization. Deployment at

community level of artemether-lumefantrine and rapid diagnostic tests, Raya Valley, Tigray, Ethiopia. 2009. (http://apps.who.int/malaria/docs/diagnosisandtreatment/RapportTigrayLowres.pdf) (Accessed October 15, 2009).

162

The Harvard System

In other journals and books it is common to put the year, between brackets, straight after the name of the author(s)

If this system of citation is used, the references at the end of the proposal, should be listed in Alphabetical order

In Harvard System, put the surname of the author, year of publication and number(s) of page(s) referred to between brackets, (E.g. Shiva 1998)

163

Harvard…con’d

Example :

Many patients with malaria have limited access to the new recommended first-line treatment because of poor communication, lack of knowledge, as well as distance and transport costs to reach the health services (Whitty et al. 2008).

164

Harvard…con’d

Thus, WHO recommends combination therapies, preferably those including an artemisinin derivative, as treatment for uncomplicated P. falciparum malaria for achieving a rapid cure, reducing parasiteinfectivity (WHO 2008) and countering the threat of resistance to P. falciparum (CDC 2006).

165

Harvard…con’d

Name of the author(s) (year). Title. Place of Publication: Publisher

Example: Abramson JH (1990), 4th ed. Survey methods in

community medicine. Edinburgh: Churchill Livingstone.

World Health Organization (1963). Terminology of Malaria and of Malaria Eradication. Columbia University Press, New York.

166

Tips!When you use the Vancouver system, you will

use consecutive numbers in the text to indicate your references

At the end, you will then list your references in that order, using the format described above

In Harvard system, put the surname of the author , year of publication and number(s) of page(s) referred to between brackets

If this system of citation is used, the references at the end of the proposal, should be listed in alphabetical order of the authors name

167

Student project work:

Develop health research proposal!

168

Thank you!Be healthy graduate!!!