Module 1 (Practicals/maths/skills)

• Accuracy - how close the replicated values are to the correct value
• Precision - how close replicated values are to each other
• A large range or standard deviation means that the replicated data had a broad range of results.
• A small range or standard deviation means that the replicated data were much more similar in value.
• Range and standard deviation are a measure of precision
• Replication - the same data point is recorded multiple times in the same experiment
• Independent Variable: The variable that you purposefully set to different values during the experiment
• Dependent Variable: The variable that you measure during the experiment, which is unknown until it is measured
• Data that overlaps means the two samples cannot be considered independent or significantly different
• When standard deviation errors bars overlap it suggests that the difference is not statistically significant

  BUT

  You must perform a statistical test to draw a conclusion
• When standard deviation errors bars overlap, it suggests:

  the difference is not statistically significant

  BUT

  You must perform a statistical test to draw a valid conclusion

  
• Standard deviation measures amount of variability among the numbers in a data set
• A large standard deviation means the data is spread out away from the mean
• An unpaired t-test compares the means of two independent samples
• A paired t-test compares the means of two measurements taken from the same sample

  (usually a measurement taken at two different times)
• Spearman's rank compares whether 2 variables are correlated
• Chi squared determines if there is a significant association between two variables. 
• Chi squared determines if a difference between observed data and expected data is due to chance, or if it is due to a relationship between the variables you are studying.
• Reliability - the consistency of a measure over time
• Validity - the accuracy of a measure
• Repeatability - obtain one result from an experiment and produce same result when experiment is conducted again
• Reproducibility - same result can be attained by a different group using the same resources
• SA:V ratio - SA/V
• SA of a sphere - 4(pi) x r^2
• Volume of a sphere - 4/3 (pi) x r^3
• dm x 1000 = cm
• P > 0.01

  Probability is less than 0.1%

  differences between means were due to chance
• Why is SD better for some data than range?

  less affected by an anomaly

  takes into account every value in the data
• unpaired t-test

  compares two means
• Evaluation points

  Yes - overall trend of graph

  No -

  • no error bars / SD / statistical test
  • correlation not evidence of causation
  • risk of bias
  • no species named
  • reference to time / duration / sample size
  • no control variables given/ specified - temp
  • no control group to compare results
  • no evidence of repeats
  • no scale/ numerical value of graph axis
• independent variable - x axis
• dependent variable - Y axis
• Confidence - qualitative judgement