ISSS608 2017-18 T3 Assign Liu Yuanjing Methodology

From Visual Analytics and Applications
Revision as of 20:13, 7 July 2018 by Yjliu.2017 (talk | contribs) (Created page with "<!----------- Main Header ------------> <div style=background:#f2ebd2;> 250px <font size = 5; color="#751102"><span style="font-family:Segoe UI...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Water pollution.jpg  Investigating chemical contamination in the Boonsong Lekagul waterways


Background

Methodology

Visualisations Analysis

Conclusion

Back to main


Tools

  • JMP Pro
  • Tableau


Methodology

Methodology

Description

Standardization method:

Because we want to go through all measures in different waterways or locations but measures have different units and if we want see the volatility changes in different paths or location and then identify potential chemical contamination. Therefore, we decided to use Z-Score to modify the data bias. Z-score represents the distance of the original data from the mean, and the standard of the distance measure is the standard deviation.

  • Z-score greater than zero indicates that the data is greater than the mean
  • Z-score less than zero indicates that the data is less than the mean
  • Z-score equal to zero indicates that the data is equal to the mean
  • Z-score equal to "1" indicates that the data is one standard deviation larger than the mean
  • Z-score equal to "-1" indicates that the data is one standard deviation smaller than the mean

If the amount of statistical data is sufficient, the Z-score data distribution is satisfied, 68% of the data is distributed between "-1" and "1", and 95% of the data is distributed between "-2" and "2", 99%. The data is distributed between "-3" and "3". You can use this to verify your data. See the Z-score data distribution below:

Z-SCORE introducation.jpg

and then we edit the formula in tableau and add one measure variable, called “Z-Score”, the formula as below: