Lecture 3 - Overview of quantitative research evidence Flashcards
Quantitative Research
Formal, objective and systematic process in which numerical data are utilised to obtain information about the world
-has its origin in positivism: There is an objective reality which can be observed and measured in a quantifiable manner
-usually contains numbers, proportions and statistics
Used for:
-bench top science
-medical trials
-epidemiology
Why is it important to know about research designs?
- Not all research designs are the same
- Each research design has a unique purpose
- Each research design has its own strengths and weakness
- Your question will determine the type of research design you need
Types of Quantitative Research Designs: Descriptive Studies
- Often the start of a research process
- Someone, somewhere notices something interesting, unique and unusual
- Getting a “lay of the land” – Surveys
- Describing a novel phenomena – Case reports or case series
- ***Cannot establish causal relationships
- Play an important role in describing trends and generating hypotheses about novel associations
- Often the start of the research process
Types of Quantitative Research Designs: Observational Studies
- Data is collected about the participants in this research but there is NO active intervention
- These are ideal research designs to describe the size of a disease problem and the characteristics of people with the particular problem
- Can allow for investigations of relationships between characteristics of the participants and their health status
Cross Sectional Study
Take a group of people and measure them at one point in time
Descriptive value: e.g. how many?
Analytic value: e.g.. is there an association (univariate or multivariate (controlling for confounders ie. age, gender))
Cross Sectional Study: Strengths
+ Fast/Inexpensive - no waiting!
+ No loss to follow up
+ Associations can be studied – We can identify that an activity (consuming alcohol) and an outcome (prevalence of falls) is related
+ Helpful to determine prevalence
• Proportion of people who have (had) a specific characteristic in a given time period
Cross Sectional Study: Weaknesses
- cannot determine causality e.g. high heels may be causing a fall and not alcohol
- Cannot study rare outcomes
- Susceptible to methodological issues
(Problems with the methodology such as the role of chance, bias and confounders)
Case Control Study
- We work “backwards” (from outcome to predictor)
- Sample chosen on the basis of outcome (cases), plus comparison group (controls)
- Determines the strength of the association between each predictor variable (alcohol consumption) and the presence or absence of disease (falls)
Case Control Study: Strengths
+ Rare outcome/Long latent period
+ Inexpensive and efficient: may be only feasible option
+ Establishes association
Odds ratio – measure of association between an exposure and an outcome
Case Control Study: Weaknesses
- Causality still difficult to establish
- Susceptible to methodological issues
(Problems with the methodology such as the role of chance, bias and confounders)
Cohort Studies
• A cohort (follow-up, longitudinal) study is a comparative, observational study
• A cohort is a group of people who all have something or share a characteristic within a defined period
• Useful for analysis of risk factors and/or health outcomes
• In its simplest form, a sample or cohort of people exposed to a risk factor is identified
along with a sample of unexposed controls
• The rates of outcomes among the exposed and
unexposed groups are determined and compared
Cohort Studies: Strengths
• Know that predictor variable (alcohol) was present before outcome variable (falls) occurred (some evidence of causality)
• Directly measure incidence of a disease outcome
Incidence is a measure of the risk of developing some new condition within a specified period of time
Cohort Studies: Weaknesses
- Expensive and inefficient for studying rare outcomes
- Often need long follow-up period or a very large population
- Loss to follow-up can affect validity of findings
What distinguishes observational studies from experimental?
Ability to control for confounding factors
Experimental: Pre-post Study
Subjects act as their own controls 1. Group A at time 1 2. Intervention 3. Group A at time 2 Compare pre-post data to establish response to an intervention
