Descriptive stats

• What is a population 


  An entire group of people we are interested in
• What is a sample 


  A subset of our population
• How is sample size normally represented 


  Represented with n
• Describes categorical data 


  Categories of data that have no correlation or hierarchal means e.g. height and eye colour
• Describe what it is meant by discrete data


  Ordinal, ratio or interval data that has fixed value with a logical order e.g. rating happiness levels on a scale from 1-10
• describe what it is meant by continuous data


  Usually a ratio or interval that can take any fractional value e.g. reaction times
• How is the median calculated with odd value datasets 


  (n+1)/2
• Pros of using median data 


  Insensitive to outliers

  often gives real, meaningful data value

  useful for ordinal data, and skewed interval/ratio data
• Cons of using the median 


  ignores alot of the data

  difficult to calculate without a computer

  cant use this with nominal data
• Pros of using the mean


  uses all the data

  is most effective for normally distributed datasets
• Cons of using the mean


  sensitive to outliers

  values are not always meaningful

  only meaningful for ratio or interval data
• Describe the interquartile range 


  is the range of scores within the middle 50% of scores
• How to calculate the interquartile range 


  The upper quartile range - the lower quartile range
• Describe what deviance is 


  each score is subtracted from the mean

  could see a deviance of 0
• what is it meant by the sum of squared errors 


  deviance is squared and all deviances are summed

  more data points = bigger SS
• what is it meant by variance 


  an average of our sum of squares
• Pros of variance 


  uses all the data

  forms the basis of serval other tests/statistics
• cons of variance 


  requires a normal distribution

  sensitive to outliers

  units are not sensible
• what is it meant by standard deviation 


  A measure of spread that is equal to the unit of measurement of the dependent variable
• how is SD calculated 


  Using the square root of variance
• when can we use SD's 


  to measure a population or estimate SD of a population based on a sample
• why do we use SD's 


  allows us to get an unbiased estimate of the population SD if we only have access to a sample of the data
• How to calculate the variance 


  Find out the mean of the sample set, then subtract each data set from the mean and square the values and finally then find the average of the squared values.
• How to calculate the variance 


  square root the variance