Pemilihan Disain Studi Observasional

download Pemilihan Disain Studi Observasional

of 44

Transcript of Pemilihan Disain Studi Observasional

  • 8/14/2019 Pemilihan Disain Studi Observasional

    1/44

    Research Design:Choosing the Study Design

    Kimberly R. BarberDirector of Research

    McLaren Regional

    Medical Center

  • 8/14/2019 Pemilihan Disain Studi Observasional

    2/44

    Yes No

    Yes No Yes No

    Exposure Outcome Exposure & OutcomeSimulteneous

    Exposure Outcome

    Assign Exposure?

    Experimental Observational

    Random allocation Comparison group

    RCT Non-RCT

    Analyticstudy

    Descripstudy

    Direction?

    Cohort Case-

    Control

    Cross-

    Section

  • 8/14/2019 Pemilihan Disain Studi Observasional

    3/44

    Design to Employ

    Dependent on the hypothesis posed.

    Is your intent to observe, associate factors, orshow cause and effect?

    Are exposure or outcome factors common or

    rare?

    Are your resources many or constrained?

  • 8/14/2019 Pemilihan Disain Studi Observasional

    4/44

    Types of Study Designs

    Observational Designs

    Descriptive Analytic

    Cross-sectional, Case-control, Cohort

    Experimental Designs

    Quasi experimentalNon randomized or non control trial

    True experimentalRandomized Controlled Trial

  • 8/14/2019 Pemilihan Disain Studi Observasional

    5/44

    Descriptive Studies

    No assignment of exposure or risk factor.

    Intent is to observe and record.

    Record events or activities. Single event or case = Case Report.

    Several events or cases = Case Series.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    6/44

    Cross-Sectional Studies

    Measurement of risk and outcome at the

    same time.

    Outcome

    Risk factor

  • 8/14/2019 Pemilihan Disain Studi Observasional

    7/44

    Cross-Sectional Design

    The only study capable

    of calculating

    prevalence. Proportion of the

    population with

    the outcome at any

    point in time.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    8/44

    Cross-Sectional Studies (cont)

    Most useful if exposure continues right up to

    time that outcome is recognized.

    Often conducted as screening and

    classification preamble to prospective studies.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    9/44

    Application Exercise:

    Cross-Sectional Study

    Design a cross-sectional study that examines

    the relationship between dietary sodium andhypertension in middle-aged men.

    What research question can we answer?

  • 8/14/2019 Pemilihan Disain Studi Observasional

    10/44

    Cross-Sectional Studies

    Advantages

    Cheap and quick studies.Data is frequently available through current

    records or statistics.

    Ideal for generating new hypothesis.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    11/44

    Cross-Sectional Studies

    Disadvantages

    The importance of the relationship between the

    cause and the effect cannot be determined. Temporal weakness:

    Cannot determine if causeprecededthe effect or

    the effect was responsible for the cause.

    The rules ofcontributory cause cannot be fulfilled.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    12/44

    Case-Control Studies

    (Retrospective)

    Case/Control Studies.

    Group subjects according to the presence orabsence of the outcome.

    Review past histories of the subjects for the

    occurrence of suspected risk factors.

    ?

    ?

    DiseaseRisk

  • 8/14/2019 Pemilihan Disain Studi Observasional

    13/44

    Case / Control Studies (cont)

    Case / Control studies have two main

    purposes:Descriptive

    Describe the risk factorprofile for an outcome.

    Analytic Analyze associations between outcome and risk

    factors.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    14/44

    Application Exercise:

    Case / Control Study

    Describe a case/control study on the

    relationship between childhood obesity,smoking history, and occurrence of

    hypertension in middle-aged men.

    What research question can we answer?

  • 8/14/2019 Pemilihan Disain Studi Observasional

    15/44

    Case / Control Studies

    Advantages

    Are good initial explanatory studies.

    Investigators can explore multiple risk factorssimultaneously for one outcome.

    Are efficient, relatively cheap, and quick. Data available through

    chart review.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    16/44

    Case / Control Studies Advantages

    (cont)

    Well suited for rare diseases.

    Since the study begins with subjects who alreadyhave the outcome, it is easier to accumulate

    enough subjects for significant results.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    17/44

    Case / Control Studies

    Disadvantages

    Data Quality

    Data with inadequate detail, questionablereliability, or use a different standard to judge

    disease severity.

    Recall bias

    Subjects who have unpleasant experiences mayrecall past differently than control subjects.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    18/44

    Retrospective Studies

    Disadvantages (cont)

    Sampling bias

    Sample usually not representative of all subjectswho could be included.

    Other Capable of studying only one outcome at a time

    Cannot calculateprevalence or incidence. Subject to confounding factors.

    Cannot prove contributory cause.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    19/44

    Cohort Studies(Prospective)

    Subjects identified according to the presence

    or absence of the risk factor.

    Followed over time until the outcome occurs

    or becomes evident.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    20/44

    Cohort Studies (cont) Subjects with and without the suspected risk

    factorare followed for the development of the

    outcome.

    The frequency of the outcome is comparedbetween the two groups.

    Disease

    ?

    ?

    R

    i

    s

    k

  • 8/14/2019 Pemilihan Disain Studi Observasional

    21/44

    Cohort Studies (cont)

    Cohort studies have two main purposes:

    Descriptive Describe the incidence of outcome over time.

    Analytic Analyze associations between risk factors and

    outcome.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    22/44

    Historical Cohort Studies

    (Non concurrent)

    The following all happen in the past:

    Assembly of the cohort according to the presenceof absence ofrisk factors.

    Baseline measurements

    Follow-up and outcomes

    Exposure

    ?

    ?

    Disease

  • 8/14/2019 Pemilihan Disain Studi Observasional

    23/44

    Historical Cohort (cont)

    Are not retrospective studies.

    Subjects are grouped according to the presenceor absence ofrisk factors (past or present).

    Subjects in retrospective studies are grouped

    according to the presence or absence of theoutcome.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    24/44

    Cohort Studies

    Advantages

    More powerful design for defining incidence.

    Powerful design forassociating the causewith the effect. Can suggest that the cause precedes the effect.

    Data can be collected in a comprehensible and

    uniform fashion.Exception: historical cohort with same measurement

    weaknesses as the case/control.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    25/44

    Cohort Studies

    Advantages (cont)

    No recall bias.

    Cohort designs can examine many outcomesfor potential risk factors under investigation.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    26/44

    Cohort Studies

    Disadvantages

    Expensive in time, money, and number of

    patients necessary to demonstrate significant

    differences between groups.

    Less likely than retrospective studies to

    uncover new risk factors.

    Also subject to confounding.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    27/44

    Cohort Studies

    Disadvantages (cont)

    Loss of valuable information due to patient

    attrition.

    Patients may change their behaviors or risk

    factors after the initial grouping of subjects

    resulting in misclassification and studyerror.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    28/44

    Clinical Trial

    Experimental study

    Unique features: Intervention in the subjects care for the

    purposes of the study.

    Randomization of subjects.

    Control group comparison.Placebo or treatment

  • 8/14/2019 Pemilihan Disain Studi Observasional

    29/44

    Clinical Trial Design

    Randomized

    Intervention/

    Effect

    Outcome

    X

    X

  • 8/14/2019 Pemilihan Disain Studi Observasional

    30/44

    Clinical Trial (cont)

    Randomization

    Subjects are randomly assigned to control or experimental

    group.

    Groups are similar in every way except for the intervention

    under study.

    Each subject has equal probability of being placed in

    either group.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    31/44

    Clinical Trials

    Advantages

    Subject to the fewest methodological biases

    of all study designs.

    Most powerful study designed to show

    contributory cause.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    32/44

    Clinical Trials

    Disadvantages

    Is the most expensive study design in terms

    of money, time, and number of patients. Issues of patient attrition and compliance may

    invalidate the results.

    Can be problematic forethical reasons.

    Use of placeboHarm outweighing benefits

    Zero tolerance for some exposures

  • 8/14/2019 Pemilihan Disain Studi Observasional

    33/44

  • 8/14/2019 Pemilihan Disain Studi Observasional

    34/44

    Choosing the Specific Design

    Study design is highly dependent on the type

    of analysis. (3)

    Type of analysis is dependent on the

    hypothesis posed. (2)

    The hypothesis is dependent on the intent of

    your research. (1)

  • 8/14/2019 Pemilihan Disain Studi Observasional

    35/44

    1. Research Study Intent

    Know the problem.

    Determine what you

    want to conclude.

    Formulate the question.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    36/44

    Examples of Intent

    I intend to show that aspirin resistance isassociated with the severity of heart disease. I will compare levels of aspirin resistance among

    patients with differing severity of heart disease.

    I intend to show that breast feeding isprotective against allergies developing in

    infants. I will compare rates of allergies among women

    who breast feed and those who do not.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    37/44

    2. Research Hypothesis Know the question you

    want answered.

    Restate the question into

    terms of Hoand H

    a.

    Think aboutcorresponding analysis.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    38/44

    Examples of Hypotheses

    Is aspirin resistance associated with heart

    disease? Aspirin resistance increases the risk of heart

    attack.

    Is breast feeding associated with allergies?

    Breast feeding decreases the risk of allergies inbabies.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    39/44

    3. Statistical Plan of Analysis

    Correlation?

    Comparison?

    Association?

    Difference?

  • 8/14/2019 Pemilihan Disain Studi Observasional

    40/44

    Examples of Analysis

    The level of aspirin resistance is compared

    between those with heart attack and those

    without. Differences in resistance scores between two

    groups (Student T-test)

    The rate of infant allergies is comparedamong women who breast feed and those

    who do not. Relative risk association (Chi square analysis)

  • 8/14/2019 Pemilihan Disain Studi Observasional

    41/44

  • 8/14/2019 Pemilihan Disain Studi Observasional

    42/44

    Choose Appropriate Design

    Cross-sectional.

    Case-control.

    Cohort.

    Clinical Trial.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    43/44

    Apply the Best Design

    Think about the

    measures to be used.

    Know the analysis

    required.

    Rethink desired

    conclusions.

  • 8/14/2019 Pemilihan Disain Studi Observasional

    44/44

    Summary

    Study Design key to determining cause or just

    association. Each design has unique strengths &

    weaknesses.

    The design drives the conclusions.