Intro to statistics
Lecture 3
Statistical terminology
- Parameter – a characteristic, feature or measurable factor that can help in defining a particular system. A
numerical summary about the population
- Statistics – rarely know true parameters so use statistics; a numerical summary of sample data
Statistical notation
- Σ - sigma – meaning to sum
- Π - pi – meaning to multiply
Descriptive statistics/ summary statistics
- Describe or summarise data and used to measure;
- Central tendency – mean, median and mode. } two most commonly used measures in descriptive
- Dispersion – range, standard deviation and variance } stats. Tell how clustered around centre data is and
how spread out
- Shape of distribution – skewness
Central tendency
- Tells what typical or average observation in sample looks like
- Gives idea where observations are clustered
- Allows comparison between groups
- Provides broad picture of whats normal or most likely
The Mode
- Used for categorical or count variables
- Simply most frequent or commonly occurring value
The mean
- Most common – average
- For interval or continuous level data
- Mean = ΣXi / n
- Can be influenced by extremes so important to look at frequency distribution
The median
- Middle value after we have ordered the data
- Order data from smallest to largest
- Consider whther n (no. Of observations) is odd or even
- If odd – median is centre observation
Lecture 3
Statistical terminology
- Parameter – a characteristic, feature or measurable factor that can help in defining a particular system. A
numerical summary about the population
- Statistics – rarely know true parameters so use statistics; a numerical summary of sample data
Statistical notation
- Σ - sigma – meaning to sum
- Π - pi – meaning to multiply
Descriptive statistics/ summary statistics
- Describe or summarise data and used to measure;
- Central tendency – mean, median and mode. } two most commonly used measures in descriptive
- Dispersion – range, standard deviation and variance } stats. Tell how clustered around centre data is and
how spread out
- Shape of distribution – skewness
Central tendency
- Tells what typical or average observation in sample looks like
- Gives idea where observations are clustered
- Allows comparison between groups
- Provides broad picture of whats normal or most likely
The Mode
- Used for categorical or count variables
- Simply most frequent or commonly occurring value
The mean
- Most common – average
- For interval or continuous level data
- Mean = ΣXi / n
- Can be influenced by extremes so important to look at frequency distribution
The median
- Middle value after we have ordered the data
- Order data from smallest to largest
- Consider whther n (no. Of observations) is odd or even
- If odd – median is centre observation
