RESS Term 1 Lectures Flashcards
What is evidence based medicine?
The conscientious use of current best evidence in making decisions about patient care
What is a research question?
A question that directs and focuses your research
What is an acronym that can help you develop a research question?
PICOT
Patients/Population - who will be participating?
Interest - what is being tested?
Comparison - what is the comparison group?
Outcome - what is the outcome or endpoint?
Time - when should outcome be measured?
What is a non-randomised control trial?
An ‘uncontrolled’ study - no control group
What are the strengths of Randomised Clinical Trials? (RCTs)
- provide evidence of causality- more chance of having ‘impact’
- rigorous evaluation of a single variable
What are the limitations of Randomised Clinical Trials? (RCTs)
- resource intensive: costs, time and money
- needs a large number of participants- many studies underpowered
- ethical challenges
What is a cohort study?
Cohort studies are a type of medical research used to investigate the causes of disease and to establish links between risk factors and health outcomes
What are the strengths of cohort studies?
- can establish population-based incidence
- can study several outcomes for each exposure
- can establish cause-effect
What are the limitations of cohort studies?
- resource intensive: costs time and money
- needs a large number of participants
- loss to follow up
- inefficient for rare conditions
What is a cross-sectional study?
A document health status in a specific population at a specific point
Provides a snapshot, patients not followed
What are the strengths of cross sectional studies?
- Provides estimates of prevalence of a disease
- Can identify population healthcare needs
- Easy, fast and inexpensive
- No follow-up required
What are the weaknesses of cross sectional studies?
- Cannot determine causal relationships
- Participants may provide socially desirable answers
- Impractical for studying rare diseases
What are the strengths of qualitative studies?
- Enables an understanding of patients’ experiences/perspectives
- Unpredictable and insightful findings
What are the limitations of qualitative studies?
- difficult to generalise
- sample selection based on certain experiences
- small sample size
Which study design would you use to answer the following:
- How common is oestrogen treatment in women after menopause?
- What are women’s experiences of taking oestrogen treatment?
- Is taking oestrogen after menopause associated with a higher risk of breast cancer?
- Does drug X, hormone treatment , reduce the symptoms of menopause?
- Cross sectional - to assess prevalence of exposure
- Qualitative - to explore patient experiences
- Cohort study - to evaluate association of exposure and disease
- RTC - to establish the effect of this intervention
What are descriptive statistics?
Techniques we use to describe the main features of a data
What is statistical inference?
The process of using the value of a sample statistic to make an informed guess about the value of a population parameter
What is a variable?
A particular characteristic being studied
Explain the 2 main data types?
- Categorical - can only be assigned to a number of distinct categories e.g sex (male or female)
- Numerical - takes a numerical value e.g age, weight
What can categorical data be divided into?
- Nominal - no natural ordering e.g sex, blood type
2. Ordinal- ordered categories e.g severity or disease stage
What can numerical data be divided into?
- Continuous - no value limitation e.g weight 87.2345kg
2. Discrete - whole values only e.g number of hospital visits
What type of data do bar charts and pie charts show?
Categorical
What type of data do scattergraphs show?
Relationships within numeric data (using two continuous variables)
What type of data do box plots show?
Summary statistics for numeric data
What type of data do histograms show?
Numerical data
How do you calculate the median?
- Sort observations in numerical order
- Find the mid point
- If two values lie at the mid point, average them
What does the standard deviation tell us about the data?
Summarises the average spread of values around the mean
The larger the SD, the more spread out the values
Which data values should you report for normally distributed data?
Report mean and SD
Which data values should you report for skewed data?
Report median and inter-quartile range
What is a parameter?
A particular characteristic of the population that we are interested in e.g the population mean
What are the two common forms of statistical inference?
- Estimation - the process of using summary statistics from collected sample data to represent the population
- Hypothesis testing - making a hypothesis about a population and then collect sample data toes whether it gives evidence against the hypothesis
What are the 5 steps for calculating standard deviation?
- Calculate the mean
- Subtract the mean from every value
- Square these new values, and add up
- Divide this total by (n-1) = variance
- Take the square root = sd
What is the standard error?
The standard deviations of different estimates from repeated samples of a population
Standard error of the estimate represents the average distance between an estimate and its population parameter
What is the frame work for hypothesis testing?
- State the null and alternative hypothesis
- Decide a level of significance (p-value cut-off)
- Define and evaluate a test statistic
- Calculate the p-value
- Interpret the results
What is the difference between estimation and hypothesis testing?
- estimation is used to generate better understanding of the likely true value of a measurement and the degree of uncertainty surrounding this estimate
- hypothesis testing evaluates whether our data provide confidence that our sample estimate is different from another “population” value
What are the two types of research?
- Observational:
- cohorts
- cross sectional surveys - Experimental:
- lab experiments
- randomised clinical trials
What is correlation?
Correlation measures the strength of the linear relationship between two numerical variables
When do we use spearman correlation coefficient?
When data is not normally distributed
When do we use Pearson correlation coefficient?
to measure the association between two normally-distributed variables
What is proportion difference?
Measures the strength of the relationship between two categorical variables
When is chi squared used?
- To work out association between two categorical variables (in two independent groups)
- difference between two proportions
Why is the chi squared test sometimes not accurate?
- Continuity correction (Yates’s correction)
For small sample sizes the chi-squared test is too likely to reject the null hypothesis. A continuity correction can be made to allow for this. - Fisher’s exact test
If a contingency table fails to meet the conditions required for the chi-squared test then Fisher’s exact test can be used.
What test do we use if theres one continuous variable and one binary variable?
T test
Explain the structure of a research paper?
- Title - clearly describes content
- Abstract - brief summary of the paper
- Introduction - explains the problem
- Methods- describes what was done
- Results - describes the results obtained
- Discussion - interpretation and implications
- References
