STUDY DESIGNS:OVERVIEW

1
STUDY DESIGNSOVERVIEW

• Aurmporn Oberdorfer,
• MD, PhD

2
OUTLINES

• Types of studies
• Structure
• Advantages
• Disadvantages
• Exercises

3
TYPES OF STUDIES

• Descriptive
• Analytic

4
DESCRIPTIVE STUDY

• Individual approach
• cross-sectional surveys
• case reports
• case-series
• Population approach
• ecological studies. (Population)

5
AIMS

• Describe the main design features of descriptive
  studies and to understand their uses and
  limitations.

6
CROSS-SECTIONAL

• The simplest form of an observational study.
• Both 'exposures' and 'outcomes' are measured at
  the same time.
• a 'snapshot' of the health (or other) experiences
  of the population at that particular point in
  time.

7
ADVANTAGES

• Quick and inexpensive
• First step for a cohort study
• Able to yield prevalence estimates
• Researcher has control over selection of subjects
• Researcher has control over the measurements used
• Can study several factors or outcomes at the one
  time
• Often provides early clues for hypothesis
  generation, and later, more definitive studies
• May be less prone to recall error on the part of
  the subjects

8
DISADVANTAGES

• Do not establish the true temporal sequence of
  events.
• They can only ascertain whether exposure is
  associated with a given outcome they cannot
  determine whether the exposure caused the outcome
• Potential bias in measuring exposure
• Potential sampling bias and/or survivor bias
• They are not feasible for rare conditions
• Does not yield incidence or true relative risk

9
CASE REPORT/CASE SERIES

• Case reports and case series describe the
  experience of a single patient or a group of
  patients with a similar diagnosis.

10
ECOLOGICAL STUDY

• An ecological study focuses on groups of people
  (rather than individuals) as the units of
  analysis.
• the variables include measurements taken at the
  group level e.g. infant mortality rates of
  different countries.

11
ADVANTAGES

• Quick and inexpensive.
• Use information already available.
• They may be superior to individual level studies
• Sometimes individual level exposures cannot be
  measured accurately because of large
  within-person variations, whereas ecological
  measures may accurately reflect group averages.
  (dietary measures).
• Can be used as the first step in exploring the
  relationship between an exposure and a disease
• Data can be used from populations with widely
  differing characteristics.

12
DISADVANTAGES

• Ecologic bias/fallacy. (fail to reflect the
  effect at the biological/individual level).
• Potential confounding factors cannot be readily
  controlled.
• The lack of adequate data.
• Non-differential misclassification within groups
  may lead to bias.
• Usually rely on data collected for other purpose.

13
ANALYTIC STUDY

• Cohort study
• Case-control
• Intervention/clinical trials

14
COHORT STUDIES

• an observational research design which begins
  when a group of people (a cohort) initially free
  of disease, are classified according to a given
  exposure, and then followed up over time.

15
COHORT STRUCTURE
16
TYPES OF COHORT

• 1. Prospective
• - fixed
• open or dynamic
• 2. Retrospective

17
PROSPECTIVE COHORT

• Fixed Cohort Study
• When the exposure groups in a cohort study are
  defined at the onset of the study without
  movement of individuals between exposure groups,
  the exposure groups are referred to as fixed
  cohorts. (occupational. war)

18
STRUCTURE
19
PROSPECTIVE COHORT

• Open or Dynamic Cohort Study
• The other type of prospective cohort study is the
  open or dynamic cohort study wherein individuals
  can be unexposed at one time period and unexposed
  at another time. The person-time analysis can
  take this into account in calculating incidence
  densities

20
STRUCTURE
21
RETROSPECTIVE COHORT

• The point of initial exposure occurred some time
  in the past and the experience of the population
  is followed up to the present time.

22
RETROSPECTIVE COHORT STRUCTURE
23
ADVANTAGES

• Provide strong information about the causation of
  disease.
• Provide the measurement of the risk of developing
  disease.
• Exposure can be measured without bias, because at
  that time the outcomes are not known known
  confounders can be measured (especially in a
  prospective study).
• Can be used to examine multiple outcomes.
• A range of factors that may influence the outcome
  (e.g., smoking) can be measured.
• Suitable for examining the effects of rare
  exposures because this group can be
  preferentially recruited at the baseline.
• Allows the incidence of the disease to be
  established.

24
DISADVANTAGES

• Costly and time consuming
• May be difficult to accurately define and measure
  exposure in some circumstances.
• Losses to follow-up are not uncommon and may
  introduce serious bias.
• Information bias may vary in its effect over the
  course of data collection due to sometimes subtle
  drifting of the quality of data collection.
• Use of the retrospective design is only possible
  if historical data of adequate quality are
  available.

25
CASE-CONTROL STUDY

• A case-control study is distinguished by the fact
  that subjects are selected on the basis of
  whether or not they have the disease (or other
  outcome) of interest. Cases (those with disease)
  are then compared to controls (those without
  disease) in terms of their history of exposure to
  a hypothesised causal factor.

26
STRUCTURE
27
ADVANTAGES

• Quick and inexpensive
• Valuable for studying rare or uncommon conditions
• Well suited for studying disease with long
  induction periods
• Can examine multiple etiologic factors for a
  given disease
• A relatively small number of subjects are required

28
DISADVANTAGES

• Inefficient if the exposure is very rare
• They are limited to one outcome variable
• Incidence rates or absolute risk estimates cannot
  be directly derived from them
• Do not establish the temporal sequence of events
  in some situations the temporal relationship
  between exposure and disease may thus be
  difficult to establish
• Prone to bias (selection of cases and controls
  recall, misclassification)

29
RCT

• A randomised controlled trial (RCT) is an
  experimental study design in which subjects are
  randomly allocated to groups which either do
  (treatment group) or do not (control group)
  receive a therapeutic or preventive intervention
  being evaluated.

30
STRUCTURE
31
ADVANTAGES

• A RCT provides the best chance of obtaining
  strong evidence of a cause and effect.
• Allows standardisation of the eligibility
  criteria, treatment (or other intervention) and
  outcome assessment.
• Allows the use of statistical methods which have
  few inbuilt assumptions.

32
DISADVANTAGES

• Expensive to undertake in terms of time, money
  and people.
• May be unethical for certain research questions.
• May be unsuitable because of the lack of
  cooperation of subjects or rarity of outcome.
• To a greater or lesser extent RCT tends to be an
  artificial situation as
• 1. patients who volunteer for an RCT may differ
  from those who don't and from those to whom the
  results would be applied.
• 2. patients who pass strict eligibility criteria
  to enter a trial may not be representative of the
  type of patients seen in clinical practice.
• 3. highly standardized interventions may be
  different from common practice as it is used in
  the community

33
EXERCISES

• Which design ?
• Association between CHD and alcohol
• Vitamin A and cancer
• Report of 21 cases of HIV infected children with
  P. Marneffei
• Incidence of DHF this year
• Efficacy of metronidazole to tetanus

34
YOUR STUDIES
35
MOVE ON