lol

• Types of Data


  • Quantitative
  • Qualitative
  • Continuous
  • Discrete
  • Categorical
  • Ordinal
  • Bivariate
  • Multivariate
• Quantitative


  Numerical observations or measurements
• Qualitative


  Non-numerical observations
• Continuous


  Can take any value on a continuous numerical scale
• Discrete


  Can only take particular values
• Categorical


  Can be sorted into non-overlapping categories e.g. gender
• Ordinal


  Can be written in order or be given a rating scale
• Bivariate


  Involves a pair of related data
• Multivariate


  Involves sets of 3 or more related data values
• Primary data


  Collected by, or for, the person using it
• Secondary data


  Has already been collected by someone else
• Measures of Central Tendency/Averages

  • Mode
  • Modal Class
  • Median
  • Mean
• Mode


  Most common value
• Modal Class


  Class with the highest frequency
• Estimating median from grouped data

  1. Find cumulative frequency of freq column until you get to inth value

  2. Find the class interval with the median

  3. See how many more values you need in that class to get the median

  4. Divide this number by the freq for that class

  5. Multiply your answer by the class width

  6. Add your answer to the lower bound for the class interval
• Estimated median


  L + (n/2 - F)/f * w, where L is the lower boundary of the class containing the median, n is the total number of values, F is the cumulative frequency of the intervals before the one containing the median, f is the frequency of the median class interval, and w is the width of the median class interval
• Calculating mean (x) for discrete data

  x = Σx/n, where Σx is the sum of all values and n is the number of values
• Calculating mean (x) for continuous data

  x = Σfx/Σf, where f is the frequency and x is the first column (use midpoints for grouped data)
• Weighted Mean


  Σ(value x weight)/Σweights
• Scatter Diagrams


  • Used for bivariate data
  • X-axis is explanatory (independent) variable
  • Y-axis is response (dependent) variable
• Correlation


  An association between 2 variables where as one variable increases, the other variable increases or decreases
• Causal Relationship


  When a change in one variable directly causes a change in another variable
• Correlation does not necessarily imply causation. In real life situations, multiple factors interact to cause variables to change.
• Drawing Line of Best Fit (LOBF)

  Draw the line through the mean point (x,y) to get a good fit
• Interpolation


  Using LOBF to estimate within the range of values already plotted, usually reliable
• Extrapolation


  Extending LOBF and reading values outside of the range of values plotted, less reliable
• Equation of LOBF


  y = ax + b, where a is the gradient and b is the y-intercept
• Calculating SRCC/PMCC


  1. SRCC measures the strength of the correlation between two variables, ranges from -1 to 1

  2. PMCC tests for linear correlation
• Histogram


  Frequency chart where the area of each bar is proportional to the frequency
• Frequency Density


  Frequency/Class Width
• Cumulative Frequency


  Running total of the frequencies of each class interval
• CF Curves


  Used for continuous data
• CF Step Polygons


  Used for discrete data, plot points at upper bound of class interval
• Comparative Pie Charts


  • Used to compare sets of data where the frequencies or some ratio is the same for the two total frequencies
  • The areas of the pie slices are proportional to the frequencies
• Types of Experiments


  • Laboratory
  • Field
  • Natural
• Laboratory Experiments


  • Conducted in a controlled environment
  • Researcher can change explanatory variables and observe response variables
• Field Experiments


  • Carried out in test subjects' everyday environment
  • Researcher sets up the situation and varies one or more variables
• Natural Experiments


  • Carried out in test subjects' everyday environment but researcher has no control over any variables
• Data Collection Methods


  • Interview
  • Anonymous Questionnaire
• Interview


  Advantages: Interviewer can explain questions, put people at ease, respondents can explain answers

  Disadvantages: Less likely to answer personal questions, time consuming, expensive, smaller sample size, interviewer bias