Drawing graphs and interpreting results

• What are results that are totally different called?

  Anomalous results
• What causes anomalous results?

  Human errors during measurement or setup
• How can you identify an anomalous result in an experiment?

  Look for results that don't fit the pattern
• What should you do if calculating an average with anomalous results?

  Ignore the anomalous results
• What should you calculate after repeating an experiment?

  The mean (average)
• How do you calculate the mean of a data set?

  Add all values and divide by total count
• What is the formula to calculate the range of data?

  Largest number minus smallest number
• What are the steps to calculate the mean and range for mass of gas lost?

  • Mean: Add all repeats, divide by 3
  • Range: Subtract smallest from largest
• What type of data can bar charts display?

  Categoric, discrete, and continuous data
• What is categoric data?

  Data in distinct categories
• What is discrete data?

  Data that can be counted in chunks
• What is continuous data?

  Numerical data that can have any value
• What are the golden rules for drawing bar charts?

  • Use a sensible scale
  • Label both axes
  • Draw bars of equal width
  • Leave gaps between bars
• What should you do when plotting points on a graph?

  Use a sharp pencil for clear marks
• What goes on the y-axis of a graph?

  The dependent variable
• What goes on the x-axis of a graph?

  The independent variable
• How do you draw a line of best fit on a graph?

  Draw through as many points as possible
• What does a straight line through the origin indicate on a graph?

  Direct proportionality between variables
• What is a positive correlation?

  As one variable increases, the other increases
• What is an inverse (negative) correlation?

  As one variable increases, the other decreases
• What is no correlation?

  No relationship between the two variables
• What are the possible reasons for a correlation between variables?

  • Chance
  • Linked by a third variable
  • Cause
• When can you conclude that a correlation is due to cause?

  When all other variables are controlled