Study design, data types and distributions Flashcards
What are the different study desgins
- Experimental study
- Observational study
- Prospective vs retrospective
- Cross sectional vs longitudinal
- Representative
What is an Experimental study
- Randomised controlled trial (RCT)
- Intervention group (e.g. new drug) vs placebo group
What is an observational study
- No interventions, just observations
- Cohort study: A group of subjects linked in some way, e.g. geographical region
- Case-control study: e.g. people with a disease vs those without
What is the difference between Prospective vs Retrospective
- Prospective (real-time) vs Retrospective study (data collected about past)
What is the difference between Cross-sectional and longitudinal study
- Cross-sectional (a point in time) vs longitudinal study (collection of data on same participants over an extended period of time)
What counts as a Representative sample
- Random Sample
What are the two different types of data
- Quantitative and Qualitative
What is Qualitative data
- Subjective characteristics and opinions
- Things that cannot be expressed as a number
What type of quantitative data is there
- Continuous and discrete data
What is continuous data and give examples
- Data that can be measured
- e.g. height, weight, age, tempreature
What is discrete data and what are the 3 different types of discrete data is there
- Can be counted
- 3 different types are nominal, ordinal and interval
What is Nominal data and give examples
- Categories with no ordering
- e.g. number of students
- e.g. male, female
What is ordinal data and give examples
- Ordered categories
- e.g. first, second, third
- o hours, 1-4 hours, 5+ hours
What is interval data and give examples
- Known, equal intervals
- e.g. £0-10k, £10-20k, £20-30k
what words can describe the distribution of data
- Normal (also called the Gaussian distribution)
- Uniform
- Exponential
- Binomial
- Geometric
- Poisson
What is the purpose of descriptive statistics?
- To describe the distribution of a phenomenon
- e.g. height in a population
- e.g. proportion of highly educated in a population
Descriptive statistics cannot be used to make an inference without what?
- Statistical test
What does descriptive statistics measure?
- Location, dispersion (spread) of data, association (for two variables)
What statistical measurements are used to describe a middle point or central tendency
- Arithmetic mean, median
What is the purpose of the mode
- To describe the most common value in data
What statistical measurements is used to describe the cut-off point where the distribution reaches a certain probability, e.g. 25% of the sample?
- Fractile, e.g. quartiles, frequencies, percentage
What statistical measurements are used to describe how spread out the data is?
- Standard deviation, range (min, max), interquartile range
What statistical measurements is used to describe the association between two variables
- Contingency tables (cross-tabulations), Correlation
What is the standard deviation?
- The most commonly used measure of spread or variability in the sample
- Measure how spread the data are around the mean
What is the relationship between variance and standard deviation
- SD = squared variance
What does a high and low SD indicate
- High SD = very spread out data, lots of variability
- Low SD = data are tightly grouped, very similar values, there is little variability
What does SEM mean
- Standard Error of the Mean
What does SEM measure?
- Measure the variability across many samples in a population
What is skewness used to measure?
- Measure the degree of asymmetry of a distribution.
- Quantifies the degree of distortion from the normal distribution.
For skewed distribution is it better to report median or mean
- Median
What is Kurtosis used to measure?
- measure that describes how heavily the tails of a distribution differ from the tails of a normal distribution
What are the two commonly used measurements for correlation
- Pearson correlation and Spearman correlation
Both Pearson and Spearman correlation both give us what?
a correlation coefficient
Name the qualities of the Pearson correlation
- Quantitative traits
- Linear relationships
What are the qualities of Spearman correlation
- Quantitative or ordinal data, e.g. Likert scale (1,2,3,4,5)
- Does not require a linear relationship; however, needs the data to follow a monotonic relationship
- Good for non-normal data
- Based on ranks of the data
Explain correlation of two variables
- If the two variables are not associated, their correlation is 0 but it is not true and vice versa - correlation 0 does not necessarily imply no associations
What are the different graphical ways of describing data
- Bar chart
- Histogram
- Boxplot
- Density plot
- Scatter plot
