Lecture 3 REVISED Flashcards
what does measures of central tendency and measures of variability focus on?
measures of central tendency focuses on the average or middle values
measures of variability focuses on the dispersion of data
measures of central tendency
describes the centre position of a distribution for a dataset
e.g., mean, median, mode
measures of variability
aid in analysing how dispersed a data distribution is
e.g., mean is 65/100, but data points can be at both 1 and 100
how do measures of variability help communicating the dispersion of data?
through the shape and spread of the data distribution
examples of measures of variability?
variance, range, quartiles
variables?
factors that can take on more than one value
what does a distribution represent?
all possible values for a set of data and how frequently those values occur
how do discrete data distributions look?
no curve, blocks of rectangles where the height indicates the frequency
how do continuous data distributions look?
smooth curve, the area underneath the curve indicates the frequency
normal distribution
bell shaped curve
symmetric
uni modal (only 1 peak)
set by mean and standard deviation
where is the mean located in a normal distribution?
at the peak
what does the standard deviation tell us in a normal distribution?
how thin or flat the curve is
standard deviation
the average distance between any point and the mean
positive/negative skew?
positive: curve is on the left
negative: curve is on the right
distributions where there are two peaks are called…
bimodal data distributions
uniform distribution
distribution where there is equal chance of something occurring
describing one variable at a time is called…
univariate descriptive statistics
good practice with tables
- graphs/tables should be able to stand on their own
- titles should clearly explain what the graph is about
- notes aim to inform the reader about data source
- notes can be used to explain abbreviations/symbols
when are pie charts useful?
good at presenting data when:
- discrete
- small number of categories (6 or less)
- exhaustive (total adds up to 100%)
characteristics of bar charts
- enables direct comparison
- categories are discrete
- summing across all bars should equal 100% (exhaustive)