L2&3 - Observational Health Research 1 & 2

Question 1

What are the aims of health research?

Answer 1

Aim to answer/contribute:

• better screening and diagnosis
• better therapies and treatments
• better prevention through the identification of risk factors and subsequent work in education

Question 2

What is experimental research?

Answer 2

The researcher manipulates 1+ variables and observes the outcomes

Question 3

What is observational research?

Answer 3

No manipulation of the situation, just observation of the outcome measures within pre-existing groups

Question 4

How is the efficacy of intervention typically tested?

Answer 4

Experimental research design - RCT

Question 5

How are risk factors for a disease typically investigated?

Answer 5

Observational research design.

Not the best but experimental design here would be unethical.

Question 6

What is an association with variables?

Answer 6

A change in one variable causing a change in another

Question 7

What are categorical variables?

Answer 7

Variables that take 1 value from a fixed selection. e.g. hair colour, favourite film, smoker/non smoker

Question 8

What are non categorical variables?

Answer 8

Represented numerically e.g. height, weight, age, test score

Question 9

How are associations between categorical variables shown?

Answer 9

Bar chart

Question 10

How are associations between non-categorical variables shown?

Answer 10

Scattergrams

Question 11

What does a positive correlation show?

Answer 11

When the value of one variable increases, the value of the other variable increases

Question 12

What does a negative correlation show?

Answer 12

When the value of one variable increases, the value of the other variable decreases

Question 13

What does no correlation look like?

Answer 13

The scatter is random and no line of best fit can be drawn

Question 14

What is a non-linear association?

Answer 14

A random scatterplot with no line of best fit, showing no correlation between the variables

Question 15

How is the strength of a correlation determined?

Answer 15

• ‘Correlation coefficient r’ ranges from -1 to 1.
• 0 means no correlation
• -1 means perfect negative
• 1 means perfect positive

Question 16

How do we test for a correlation?

Answer 16

Pearson’s Correlation Coefficient tests the null hypothesis that there is no linear relationship

H0 >> r=0

Question 17

What are the alternative terms for an exposure variable?

Answer 17

• Risk factor
• Predictor variable
• Independent variable
• Explanatory variable

Question 18

What are the alternative terms for an outcome variable?

Answer 18

• Predicted variable
• Dependent variable
• Response variable

Question 19

What is a confounder?

Answer 19

• A confounding variable is associated with both the exposure and outcome variables.
• If not controlled for, the confounder can show an association between the outcome and exposure variables that is not causal.

Question 20

What are some key confounders in health studies?

Answer 20

• Age
• Gender
• Socio-economic Status
• Anything evidenced in your lit. review
• Anything that could plausibly be a confounder, even if the lit doesn’t mention it

Question 21

How can confounders be controlled?

Answer 21

• Use inclusion/exclusion criteria
• Through statistical analysis

Question 22

What is the principle of fair subject selection?

Answer 22

Emanuel et al, 2000 – “groups of individuals should not be excluded from the opportunity to participate in research without a good scientific reason or susceptibility to risk that justifies their exclusion”

Question 23

What are some traditionally underrepresented groups in health studies?

Answer 23

• Women
• The elderly
• People from ethnic minority groups
• Children
• ‘Real-world patients’ - those with co-morbidities

Question 24

What is a cross-sectional study?

Answer 24

• Takes all data from one point in time
• Samples participants blindly -
• Simultaneously collects data about outcome and exposure variables
• No follow up
• Allows prevalence to be calculated
• Observational Design

Question 25

What is a chi-squared test?

Answer 25

Chi-squared tests the null hypothesis that there is no association between 2 variables

Question 26

What are the requirements/assumptions for chi-squared?

Answer 26

* Both variables must be categorical (nominal or ordinal) * Data points for each variable must be independent (i.e. only one measurement per variable per person) * Each cell must have at least 5 expected cases

Question 27

What is a cohort-study design?

Answer 27

* Follow groups of people overtime, and compare how many develop the outcome of interest

Question 28

What does a cohort-study design look like?

Answer 28

Question 29

How do you calculate the risk of disease?

Answer 29

Risk of disease in the specified group = number of cases/total at risk x 100

Question 30

How do you calculate comparative risk?

Answer 30

Risk of disease in exposed group/risk of disease in the non-exposed group = x amount higher risk

Question 31

What is a case-control study design?

Answer 31

Identify the cases and the controls (with no disease), work out the exposure in both groups, then compare the exposed to non-exposed. It is often used to investigate rare outcomes.

Question 32

What does a case-control study look like?

Answer 32

Question 33

What is a prospective cohort?

Answer 33

Both exposure and outcome variables are determined in the future, after the study has begun

Question 34

What is a retrospective cohort?

Answer 34

Both the exposure and outcome data were collected before the study began

Question 35

What is a combined retrospective and prospective cohort?

Answer 35

Exposure data is collected in the past, but outcome data is collected after the study has begun

Question 36

What are the advantages of prospective cohorts?

Answer 36

* Establish temporal relationships * The research has better control over the data collection methods (as they do it theirself), meaning they have better control over confounders (when compared to a retrospective cohort).

Question 37

What are the disadvantages of a prospective cohort?

Answer 37

* Outcome may take a long time to develop making the project very lengthy * If the outcome is rare, you may need to recruit a high number of participants * Very expensive * Hard to gain funding for

Question 38

What are the advantages of retrospective cohorts?

Answer 38

* Can establish temporal relationships * Studies are shorter because they use existing data * Cheaper * Easier to win funding for

Question 39

What are the disadvantages of retrospective cohorts?

Answer 39

* No control over the data collection methods * This means data for exposure and outcome variables can be incomplete * Data about confounders may be lacking

Question 40

What are 3 reasons for false results?

Answer 40

* Chance through sampling * Confounding * Bias

Question 41

How can you control for confounding?

Answer 41

* Widen exclusion criteria * Use statistical analysis (only if the confounder is known in advance) * Stratified analysis compares like with like

Question 42

What is bias?

Answer 42

Systematic error in the design, conduct or analysis of a study

Question 43

What are the two types of bias?

Answer 43

* Selection Bias * Information Bias

Question 44

What is selection bias?

Answer 44

When cases and control patients are selected in a way that the association is observable in the study, but doesn't exist in the real population

Question 45

What is information bias?

Answer 45

When the methods used for data collection are inadequate, leading to incorrect results about exposure and/or disease outcomes

Question 46

What is recall bias?

Answer 46

When the participant misremembers an event

Question 47

What does association but not causation show?

Answer 47

A pattern in the observed data

Question 48

What does chi-squared compare?

Answer 48

Patterns in the observed data with patterns in the expected data (the population)

Question 49

What does a P value/alpha value of \<0.05 mean?

Answer 49

Significant because it shows the probability of finding those results due to chance is less than 5%. The p value shows if the relationship is statistically relevant - if it exists within the population, not just the sample.