Quantitative Research

advertisement
Quantitative Research
Richard Peacock, Clinical Librarian
Archway Healthcare Library
Ziba Nadimi, Outreach and Information Skills Librarian
Camden Primary Care Trust
Definition
A study that aims to quantify attitudes or
behaviours, measure variables on which they
hinge, compare, and point out correlations. It
is most often conducted via a survey on a
sampling that must be representative so that
the results can be extrapolated to the entire
population studied. It requires the
development of standardised and codifiable
measurement instruments (structured
questionnaires).
Ipsos- A Market Research Co.
Quantitative Data Collection
• Requires a specific protocol
• Protocol is specified in advance of data
collection
• Population and sample should be large.
The larger the better
Data Analysis
• Statistical analysis
• Describes trends, compares groups,
relates variables
• Compares your results with past research
The Anatomy of a Research Paper
•
•
•
•
Introduction
Methods
Results
Discussion
The Anatomy of a Research Paper
cont.
• The introduction summarises the
background to the study
• The methods helps to understand if you are
critically appraising a paper
• The results reports findings objectively
without speculation or interpretation
• In the discussion the authors interpret the
findings in light of the study design and other
research
Levels of Evidence
Systematic Review
• Identifies an intervention for a specific disease or
other problem in health care
• Determines whether or not this interventions works
• Authors locate, appraise and synthesise evidence
from as many relevant scientific studies as possible
• They summarise conclusions about effectiveness
• They provide a collation of the known evidence on a
given topic
• Statistical methods (meta-analysis) may or may not
be used to analyse and summarise the results
Advantages of Systematic Reviews
• Adhere to a strict design, therefore minimise
the chance of bias
• Provide a scientific rather than subjective
summarisation of literature
• Large amounts of information can be
assimilated quickly by healthcare providers,
researchers, and policymakers
• Compare results of different studies to
establish generalisability of findings and
consistency of results
Disadvantages of Systematic Reviews
• Experts may select only supportive evidence
• Papers with more interesting result more
likely to be published
• SRs may be biased due to exclusion of
relevant studies and inclusion of inadequate
studies
• SRs include an element of judgement,
whatever method is used e.g. authors of tobacco
industry affiliated reviews are more likely to conclude
that passive smoking is not harmful
Randomised Controlled Trials- RCTs
• Two or more interventions are compared by
being randomly allocated to participants
• Includes a control intervention or no
intervention
• If possible should be single/ double/ triple
blinded
Blinding in RCTs
• Preventing those involved in a trial from
knowing to which comparison group, i.e.
experimental and control, a particular
participant belongs
• The risk of bias is minimised
• Participants, caregivers, outcome assessors
and analysts can all be blinded
• Blinding of certain groups is not always
possible, e.g. surgeons in surgical trials
• Single, double and triple blind are in common
use
Cohort Studies
• An observational study
• A defined group of people (the cohort) is
followed over time
• Outcomes are compared to examine people
who were exposed or not exposed to a
particular intervention
• A retrospective cohort study identifies subjects
from past records and follows them to the present
• A prospective cohort study assembles
participants and follows them into the future
Case Control Studies
• Compares people with a specific disease or
outcome of interest (cases) to people from
the same population without that disease or
outcome (control)
• Seeks associations between the outcome
and prior exposure to particular risk factors
e.g. one group may have been exposed to a
particular substance that the other was not
• They are usually retrospective
Case Series
• A study reporting observations on a series of
individuals, usually all receiving the same
intervention, with no control group.
Odds-Ratio Diagram (Blobbogram)
Odds-Ratio Diagram
Cont.
• Included in CDSR and other good systematic
reviews
• Presents complicated results and concepts in
a clear visual format
• For each individual trial, the odds-ratio result
is represented by a box
• The vertical line is an odds-ratio of one
known as “line of no effect”
• The horizontal line is the “confidence interval”
for that result
Odds-Ratio Diagram
Cont.
• Confidence Interval - the range in which we
are 95% or 99% confident that the ‘real’ result
of the study lies when is extrapolated to the
whole of the population sampled in the study
• The diamond is called meta analysis – the
statistical method of combining the results of
different RCTs for the same intervention
Odds-Ratio Diagram
Cont.
• Results to the left of the line of no effect =
less of the outcome in the experimental
group
• Results to the right of the line of no effect =
more of the outcome in the experimental
group
• It is important to note whether the outcome is
good or bad
Odds-Ratio Diagram
Cont.
• If CI crosses line of no effect = inconclusive
results
• Longer CI = smaller study (less confident of
results)
• Shorter CI = bigger study (more confident of
results)
P Values
• P for probability (ranging from zero to one)
• The result could have occurred by chance if
in reality the null hypothesis was true
• The null hypothesis- the factor of interest (e.g.
treatment) has no impact on outcome (e.g.
risk of death)
• P value of less than 0.05 means likelihood of
results being due to chance is less than 1 in
20 = “Statistically significant”
References
McGovern, D.P.B. etal, Evidence-based medicine, BIOS Scientific
Publishers Ltd., 2001
Greenhalgh, T., How to read a paper, 3rd ed., BMJ Publishing Group,
2006
Kelsey, K.D., (Lecture 2) Quantitative and qualitative approaches to
research- PowerPoint Presentation
Ward, L., Critical reading made easy:effectiveness and experience,
University Hospitals of Leicester NHS Trust- PowerPoint Presentation
Jackson, N., Conducting systematic reviews of public health and
health promotion interventions, Cochrane Health Promotion and Public
Health Field- PowerPoint Presentation
The Cochrane Library’s Glossary of Terms, Wiley InterScience
Andrew Hayward, Critical Appraisal of Analytical Studies- PowerPoint
Presentation
Download