You are viewing documentation for the old version 2.30 of Analyse-it. If you are using version 3.00 or later we recommend you go to the Precision profile.

Precision profile

Precision profile examines the variation of a method over a number of analyte concentrations, days, and optionally over one or two runs per day.

The requirements of the test are:

  • A method measured on a continuous scale over a number of concentrations and days, with one or two runs per day.
  • At least two replicates must be observed for each run, and all cases must have the same number of replicates.
  • Analyte concentration,or relative analyte concentration (relative to concentration of other samples), must be known.


Arranging the dataset

 Data in existing Excel worksheets can be used and should be arranged in the List dataset layout. The dataset must contain at least two continuous scale variables containing the observations (in replicate) for a run of the method. If two runs are observed then a List dataset with repeat-measures and replicates layout should be used to arrange the two runs and replicates for each run.

When entering new data we recommend using New Dataset to create a new precision dataset.

Using the test

To start the test:

  1. Excel 2007:
    Select any cell in the range containing the dataset to analyse, then click Precision on the Analyse-it tab, then click Profile.  
  2. Excel 97, 2000, 2002 & 2003:
    Select any cell in the range containing the dataset to analyse, then click Analyse on the Analyse-it toolbar, click Precision then click Profile.

  3. Click Concentration and select the variable containing the concentration level/coding. Click are and select pre-assigned if the concentration levels are known absolute values, or coded if the levels unknown and codes indicate the analyte concentration relative to the other levels observed.
  4. Click Run 1 and Run 2 select the runs and replicates to compare. Leave Run 2 empty to perform a 1 run analysis.
  5. Enter Confidence interval to calculate for total precision and repeatability. The level should be entered as a percentage between 50 and 100, without the % sign.
  6. Click as and select SD or %CV to show the precision as an SD or CV%.
  7. Click OK to run the test.

The report shows the total number of observations analysed, runs per day, and replicates per run.

For each concentration level, or coding, the number of days analysed, mean analyte concentration, Total (within device/laboratory) and Repeatability (within run) SD/CV (depending on the Precision profile as option) are shown. Total and Repeatability precision confidence levels show the range likely to contain the true precision.

Examining the precision profile plot

The precision profile plot shows the total precision and repeatability of the method over the range of analyte concentrations.

To change the precision plot: 

  1. If the Precision Profile dialog box is not visible click Edit on the Report toolbar on the Analyse-it tab/toolbar.
  2. Click Precision profile and select Total + Repeatability to show total (within device/laboratory) and repeatability (within run) on the precision plot, or select Total or Repeatability to show one or the other. 
  3. Tick with CI bands to show the precision confidence interval at each concentration level.
  4. Click OK.

The precision profile plot (see below) shows the Total and Repeatability SD/CV (depending on the Precision profile option) over the range of analyte concentrations/codings. If with CI bands is checked error bars show the confidence interval at each concentration.

(click to enlarge)

Comparing against an imprecision goal specification

Goal precision can shown on the precision profile plot to allow visual assessment if/where precision strays outside allowable limits. Allowable imprecision can be specified in absolute units of the analyte, as a percentage of analyte concentration, or as a combination of the two in which case the larger of the absolute and percentage concentration is used.

To compare the precision profile against a goal:

  1. If the Precision Profile dialog box is not visible click Edit on the Report toolbar on the Analyse-it tab/toolbar.
  2. Click Compare against and select Imprecision specification.
  3. Enter Allowable imprecision as an absolute value, as a percentage of analyte concentration, or enter both values for a combination.
  4. Tick with Allowable Error bands to show allowable error on the precision profile plot.
  5. Click OK.

Allowable imprecision, calculated from the imprecision specification and the concentration level, is shown on the precision profile plot (see below) for visual assessment. Ideally the total (within device/laboratory) and repeatability (within run) precision confidence intervals should lie within the allowable range.

(click to enlarge)

Comparing against a TEa and Random Error%

Goal precision can shown on the precision profile plot to allow visual assessment of if/where precision strays outside allowable limits. Allowable imprecision can be specified in absolute units of the analyte, as a percentage of analyte concentration, or as a combination of the two in which case the larger of the absolute and percentage level is used.

To compare the precision profile against a random error% of total allowable error:

  1. If the Precision Profile dialog box is not visible click Edit on the Report toolbar on the Analyse-it tab/toolbar.
  2. Click Compare against and select TEa, %RE specification
  3. Enter TEa (total allowable error) as an absolute value, as a percentage of analyte concentration, or enter both values for a combination.
  4. Enter % for Random error, that is the percentage of the TEa to allow precision to vary within.
  5. Tick with Allowable Error bands to show allowable error on the precision profile plot.
  6. Click OK.

Allowable imprecision, calculated from the imprecision specification and the concentration level, is shown on the precision profile plot (see above) for visual assessment. Ideally the total (within device/laboratory) and repeatability (within run) precision confidence intervals should lie within the allowable range.

References to further reading

  1. Statistical methods in Laboratory Medicine.
    Strike P.W. ISBN 0-7506-1345-9 1991; TODO (pages).

(click to enlarge)