17.1.15 Dixon's Q-Test
Contents
Supporting Information
To open the Dixon's Q-test dialog box from the menu:
- Click Statistics: Descriptive Statistics: Dixon's Q-test (Open Dialog...)
See Also:
Dialog Box Controls
| Results Log Output |
Select to output results to the Results Log. |
|---|---|
| Recalculate |
Controls recalculation of analysis results:
For more information, see: Recalculating Analysis Results |
| Input |
Number of (replicate) observations must be between 3 and 10 (inclusive) and contained in one column. For help with range controls, see: Specifying Your Input Data |
| Significance Level |
Option list:
|
| Outlier Plot |
Select to generate an outlier plot. Scatter plot with upper and lower confidence limits and dataset mean as line plots. |
| Q-Test Plot Data |
Worksheet range to output the outlier plot data (available if Outlier Plot is selected). For help with the range controls, see: Output Results |
| Grubbs Report |
The worksheet range to output the report table. |
Algorithm
For a series of results from repeated measurements:
- Rank \(n\) results in ascending order, assigning them values of \(x_{1}\) to \(x_{n}\).
- Calculate the test statistic \(Q\), as:
\(Q=\frac{ x_{2}-x_{1} }{x_{n}-x_{1} }\) (for testing if smallest observation is an outlier),
or
\(Q=\frac{ x_{n}-x_{n-1} }{x_{n}-x_{1} }\) (for testing if highest observation is an outlier). - Compare the calculated \(Q\) value with \(Q\)critical (critical value is obtained from a table of \(Q\) values, using sample size \( n\) and significance level).
Handling Missing Values
The missing values in the data range will be excluded in the analysis
References
Stephen L R. Ellison, Vicki J. Barwick and Trevor J Duguid. Farrant. 2009. Practical Statistics for the Analytical Scientist. The Royal Society of Chemistry, Cambridge, UK.
