Week 4 - Non-experimental designs and systematic reviews

Question 1

What are non-experimental designs?

Answer 1

• Focus on kind of relationships that naturally occurring variables have with one another and in what way (consider type of hypothesis!)
• Observational studies
• Can be descriptive (focus on frequency) or analytical (quantifying relationship
  between two factors, ie exposure on an outcome)
• Basis of most epidemiological research

Question 2

Survey (cross-sectional descriptive)

Answer 2

• Samples need to be representative in order to make generalizable statements
• Focus on correlation not causation

Pros:
- Easy and relatively quick way to collect large amounts of data
- Easy/ cheap (?) to distribute

Cons:
- Focus is on breadth rather than depth
- You can only make a statement on questions asked
- Robust (valid and reliable) surveys take time in development

Question 3

Descriptive/ exploratory Surveys

Answer 3

Describe a specific population and characteristics in relation to Research Question

Question 4

Comparative Surveys

Answer 4

• What are the different experiences of nursing education by 1st year nursing students in Canada compared to UK?
• Question types can be Likert scale, rating scale, ranking questions, multiple choice questions, single choice question, binary questions, open-ended questions.

Question 5

Cohort studies

Answer 5

• Can be retrospective or prospective
• In retrospective studies the exposure and outcomes have already happened –
  already existing data sets are used (eg medical records)
• In prospective studies (more common) people are recruited into the study regardless of their exposure or outcome (but because of other shared characteristics)

Pros:
- Good for assessing risk factors, harm and prognosis (outcome focuses on risk ration/ relative risk)

Cons:
- Expensive, time consuming esp if long follow up period and disease is rare/ has a long latency

Question 6

Case-control studies

Answer 6

• Retrospective research design
• Clearly define two groups at the start: one with the outcome/disease and one without the outcome/disease. Identical expect for their outcome/ disease status
• They look back to assess whether there is a statistically significant difference in the rates of exposure to a defined risk factor between the groups.
• The main outcome measure in case-control studies is odds ratio (OR).
• Data are collected medical records or patient self-report

Pros:
- Cheaper and faster than most other studies
- Understand single and multiple exposures/ risk factors for diseases
- Good for rare disease and long latency periods
- Confounders!

Cons:
- Bias: recall bias
- Incomplete records
- Cannot establish risk (focus on odds)

Question 7

Cross-sectional studies (observational analytic)

Answer 7

• Similar to cohort study but data collected at one point in time in relation to exposure and outcome
• Outcome and exposure are measured at the same time
• Participants selected based in inclusion criteria (rather than outcome status or exposure status)
• Population based and used often to assess prevalence of disease or risk factor in clinic based samples

Pros:
- Cheap and simple
- Ethically safe

Cons:
- Association not causality
- Group sizes may not be equal

Question 8

Systematic Reviews

Answer 8

A systematic review attempts to identify, appraise and synthesize all the empirical evidence that meets pre-specified eligibility criteria to answer a specific research question.
- Researchers conducting systematic reviews use explicit, systematic methods that are selected with a view aimed at minimizing bias, to produce more reliable findings to inform decision making.
- Totality of evidence rather than relying on evidence from one study
- Systematic reviews can include qualitative, quantitative or both types of empirical evidence (secondary data collection)
- Systematic and detailed methods to search literature, screen papers according to inclusion criteria, extract data of included papers and synthesise (analyse) evidence to answer RQ
- RQ can sound similar to primary research questions
- Descriptive analysis of evidence (what is the evidence)
- Critical appraisal of studies included (how “good” is the evidence)
- Synthesis (narrative) or meta-analysis of included evidence (what does the evidence tell us in relation to the RQ)

Question 9

Cochrane collaboration

Answer 9

• Types of Cochrane Review
  -> Intervention reviews assess the benefits and harms of interventions used in healthcare and health policy.
• Diagnostic test accuracy reviews assess how well a diagnostic test performs in diagnosing and detecting a particular disease.
• Methodology reviews address issues relevant to how systematic reviews and clinical trials are conducted and reported.
• Qualitative reviews synthesize qualitative evidence to address questions on aspects of interventions other than effectiveness.
• Prognosis reviews address the probable course or future outcome(s) of people with a health problem.