KEVOS® MAKEOS · Quality
Linear Calibration Check (Straight-Line Fit, Calibrated Value, Calibration Interval)
I have measured a set of reference standards with my instrument: what straight-line calibration do they give, what is the true value for a new reading, and is the uncertainty of that calibrated value within my tolerance?
Straight-line calibration from up to eight reference standards: the least-squares intercept and slope with their standard errors, the residual standard deviation, t tests of zero intercept and unit slope, the calibrated value for a new instrument reading by inverting the line, and the approximate calibration interval for that value at your confidence level, against the half-width you can accept.
Open the calculatorRuns in your browser. No account needed.
How this tool works
Inputs, units and where to find them
| Input | Unit | Typical source |
|---|---|---|
| Number of standards used | standards | How many standards below to use (at least 3). |
| Reference values and instrument readings | ||
| Standard 1 reference value | Certified value of reference standard 1. | |
| Standard 2 reference value | Certified value of reference standard 2. | |
| Standard 3 reference value | Certified value of reference standard 3. | |
| Standard 4 reference value | Certified value of reference standard 4. | |
| Standard 5 reference value | Certified value of reference standard 5. | |
| Standard 6 reference value | Certified value of reference standard 6. | |
| Standard 7 reference value | Certified value of reference standard 7. | |
| Standard 8 reference value | Certified value of reference standard 8. | |
| Standard 1 reading | Instrument reading when measuring standard 1. | |
| Standard 2 reading | Instrument reading when measuring standard 2. | |
| Standard 3 reading | Instrument reading when measuring standard 3. | |
| Standard 4 reading | Instrument reading when measuring standard 4. | |
| Standard 5 reading | Instrument reading when measuring standard 5. | |
| Standard 6 reading | Instrument reading when measuring standard 6. | |
| Standard 7 reading | Instrument reading when measuring standard 7. | |
| Standard 8 reading | Instrument reading when measuring standard 8. | |
| New measurement | ||
| New instrument reading | Instrument reading to convert to a calibrated value. | |
| Confidence level | choice | Confidence level of the calibration interval. |
| Half-width accepted | Largest half-width of the calibration interval you accept, in reference units. | |
What each input means
Open an input to see what it is, its units, the worked example and the common mistakes, with a small diagram.
What this means: Number of standards used
- What it is
- How many of the calibration standards listed below are used in the fit, counting from the first.
- Units and format
- Enter a number in standards: standards. The form accepts 3 standards to 8 standards. Use a whole number. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 6 standards as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Standards beyond this count are ignored; more standards narrow the interval.
- Get it right
- Use at least four standards spread over the working range; three leave only one degree of freedom.
Reference values and instrument readings
What this means: Standard 1 reference value
- What it is
- The certified (reference) value of calibration standard 1, the true value the instrument should read.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 0 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Sets where this standard sits on the calibration line; spreading the standards across the range narrows the interval.
- Get it right
- Take standard 1’s value from its calibration certificate, in the units you want the corrected readings in.
What this means: Standard 2 reference value
- What it is
- The certified (reference) value of calibration standard 2, the true value the instrument should read.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 20 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Sets where this standard sits on the calibration line; spreading the standards across the range narrows the interval.
- Get it right
- Take standard 2’s value from its calibration certificate, in the units you want the corrected readings in.
What this means: Standard 3 reference value
- What it is
- The certified (reference) value of calibration standard 3, the true value the instrument should read.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 40 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Sets where this standard sits on the calibration line; spreading the standards across the range narrows the interval.
- Get it right
- Take standard 3’s value from its calibration certificate, in the units you want the corrected readings in.
What this means: Standard 4 reference value
- What it is
- The certified (reference) value of calibration standard 4, the true value the instrument should read.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 60 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Sets where this standard sits on the calibration line; spreading the standards across the range narrows the interval.
- Get it right
- Take standard 4’s value from its calibration certificate, in the units you want the corrected readings in.
What this means: Standard 5 reference value
- What it is
- The certified (reference) value of calibration standard 5, the true value the instrument should read.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 80 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Sets where this standard sits on the calibration line; spreading the standards across the range narrows the interval.
- Get it right
- Take standard 5’s value from its calibration certificate, in the units you want the corrected readings in.
What this means: Standard 6 reference value
- What it is
- The certified (reference) value of calibration standard 6, the true value the instrument should read.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 100 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Sets where this standard sits on the calibration line; spreading the standards across the range narrows the interval.
- Get it right
- Take standard 6’s value from its calibration certificate, in the units you want the corrected readings in.
What this means: Standard 7 reference value
- What it is
- The certified (reference) value of calibration standard 7, the true value the instrument should read.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 50 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Sets where this standard sits on the calibration line; spreading the standards across the range narrows the interval.
- Get it right
- Take standard 7’s value from its calibration certificate, in the units you want the corrected readings in.
What this means: Standard 8 reference value
- What it is
- The certified (reference) value of calibration standard 8, the true value the instrument should read.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 50 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Sets where this standard sits on the calibration line; spreading the standards across the range narrows the interval.
- Get it right
- Take standard 8’s value from its calibration certificate, in the units you want the corrected readings in.
What this means: Standard 1 reading
- What it is
- The instrument’s reading when measuring calibration standard 1.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 0.3 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Changes the fitted slope and intercept and the residual scatter, which sets the interval width.
- Get it right
- Let the instrument settle before reading standard 1; average repeat readings if the display fluctuates.
What this means: Standard 2 reading
- What it is
- The instrument’s reading when measuring calibration standard 2.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 20.6 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Changes the fitted slope and intercept and the residual scatter, which sets the interval width.
- Get it right
- Let the instrument settle before reading standard 2; average repeat readings if the display fluctuates.
What this means: Standard 3 reading
- What it is
- The instrument’s reading when measuring calibration standard 3.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 40.4 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Changes the fitted slope and intercept and the residual scatter, which sets the interval width.
- Get it right
- Let the instrument settle before reading standard 3; average repeat readings if the display fluctuates.
What this means: Standard 4 reading
- What it is
- The instrument’s reading when measuring calibration standard 4.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 61.1 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Changes the fitted slope and intercept and the residual scatter, which sets the interval width.
- Get it right
- Let the instrument settle before reading standard 4; average repeat readings if the display fluctuates.
What this means: Standard 5 reading
- What it is
- The instrument’s reading when measuring calibration standard 5.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 80.7 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Changes the fitted slope and intercept and the residual scatter, which sets the interval width.
- Get it right
- Let the instrument settle before reading standard 5; average repeat readings if the display fluctuates.
What this means: Standard 6 reading
- What it is
- The instrument’s reading when measuring calibration standard 6.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 101.2 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Changes the fitted slope and intercept and the residual scatter, which sets the interval width.
- Get it right
- Let the instrument settle before reading standard 6; average repeat readings if the display fluctuates.
What this means: Standard 7 reading
- What it is
- The instrument’s reading when measuring calibration standard 7.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 50.5 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Changes the fitted slope and intercept and the residual scatter, which sets the interval width.
- Get it right
- Let the instrument settle before reading standard 7; average repeat readings if the display fluctuates.
What this means: Standard 8 reading
- What it is
- The instrument’s reading when measuring calibration standard 8.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 50.5 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Changes the fitted slope and intercept and the residual scatter, which sets the interval width.
- Get it right
- Let the instrument settle before reading standard 8; average repeat readings if the display fluctuates.
New measurement
What this means: New instrument reading
- What it is
- The new instrument reading you want to convert to a calibrated (true) value using the fitted line.
- Units and format
- Enter a plain number with no unit. Negative values are accepted. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 50 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Moves the calibrated value; the interval is narrowest near the middle of the standards.
- Get it right
- Read it under the same conditions as the standards were measured.
What this means: Confidence level
- What it is
- The confidence level of the calibration interval around the calibrated value.
- Units and format
- Choose one of 3 options from the list: 90%; 95%; 99%.
- Example
- The form opens with “95%” selected as a worked example. Choose the option that matches your case.
- Effect on the result
- A higher confidence widens the interval.
- Get it right
- Ninety-five per cent is usual for calibration certificates and uncertainty statements.
What this means: Half-width accepted
- What it is
- The largest half-width of the calibration interval you can accept, in the units of the reference values.
- Units and format
- Enter a plain number with no unit. The form accepts 0.000001 or more. Required: the tool does not calculate until every input is valid.
- Example
- The form opens with 1 as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Only moves the pass or fail line; the interval does not change.
- Get it right
- Set it from the tolerance of the measurement the instrument is used for, typically a quarter to a tenth of it.
Method and formulas
- Least-squares line Y = a + bX through the readings Y against the reference values X; residual standard deviation s with ν = n − 2 degrees of freedom; s_b = s ÷ √Sxx, s_a = s √(1 ÷ n + X̄² ÷ Sxx).
- Calibrated value X′ = (Y′ − a) ÷ b; tests of a = 0 and b = 1 compare |a| ÷ s_a and |b − 1| ÷ s_b with t₁₋α/₂,ν (NIST e-Handbook 2.3.6.6).
- Calibration interval: the values of X where Y′ − (a + bX) = ± t₁₋α/₂,ν σ_p(X), with σ_p(X) = s √(1 + 1 ÷ n + (X − X̄)² ÷ Sxx), the standard deviation of a new reading (NIST e-Handbook 4.5.1.2 and 4.5.2.1), solved exactly as a quadratic.
- Example: reading 50 calibrates to 49.289, interval 48.566 to 50.012 (± 0.72309).
Limitations
- Straight line only, with the same scatter at every level; a curved or uneven response needs a quadratic or weighted fit.
- Few standards give wide intervals; use standards that span the working range, with repeats.
- Example values are illustrations. Replace them with values for your actual task.
Typical uses
- Calibrate a load cell, pressure transducer or thermocouple against standards
- Correct readings from an instrument with a gain or offset error
- Check whether a calibration is good enough for a tolerance
Who it is for
- Calibration and metrology technicians
- Test and laboratory engineers
- Quality engineers
What you get
- Intercept, slope and residual standard deviation
- Tests of zero intercept and unit slope
- Calibrated value for the new reading
- Calibration interval and its half-width
Interpreting the result
- If the intercept test fails the instrument has a constant offset; if the slope test fails the error grows with size (NIST 2.3.6.6). If both pass, the instrument may not need correcting.
References
- NIST/SEMATECH e-Handbook of Statistical Methods, 2.3.6.6 Calibration of future measurements — https://www.itl.nist.gov/div898/handbook/mpc/section3/mpc366.htm
- NIST/SEMATECH e-Handbook of Statistical Methods, 4.5.2.1 Single-Use Calibration Intervals — https://www.itl.nist.gov/div898/handbook/pmd/section5/pmd521.htm
- NIST/SEMATECH e-Handbook of Statistical Methods, 4.5.1.2 How can I predict the value and estimate the uncertainty of a single response? — https://www.itl.nist.gov/div898/handbook/pmd/section5/pmd512.htm
- Neter J., Wasserman W. and Kutner M. H., Applied Linear Regression Models (Irwin, 1983): variance of the fitted value on a straight line.
Learn the Concepts Behind This Tool
These KEVOS® Library readings explain the method this tool uses, with worked examples.
Method explained here · KEVOS® original book
Mixing as a random walk: how fast a blend approaches random
In Blending Bulk Solids by the Numbers
What it covers: Mixing mechanisms, why the excess variance of a blend decays exponentially, how to fit the decay rate and predict a blend time, and what a dispersion coefficient says about a blender.
Method explained here · KEVOS® original book
Electrical conductivity and what it reveals about a metal
In Eddy-Current Inspection by the Numbers
What it covers: The %IACS scale, why alloying and heat treatment change conductivity, correcting readings to 20 °C, calibrating a conductivity meter, and catching a mislabelled aluminium bar.
Method explained here · KEVOS® original book
Overlap, entanglement and the viscosity of a cement
In Polymer Chains by the Numbers
What it covers: Find the overlap concentration where coils fill a solution, see why a cement's viscosity rises with about the fourth power of concentration, and set a cement's strength by fitting its own data.
Method explained here · Library collection
Straight-line relationships and estimating models: slopes, intercepts, calibration and trend lines
In Practical Mathematics for Engineering and Manufacturing
What it covers: How the equation of a straight line underpins cost estimates, break-even, sensor calibration, interpolation and trend lines, how to fit a line to data and where straight-line thinking fails.
Method explained here · KEVOS® original book
Monitoring, soiling and degradation
In Rooftop Solar for Factories by the Numbers
What it covers: How to monitor an array's performance ratio, check the irradiance sensor's calibration, measure soiling with a cleaning trial and a t-test, and separate soiling from module degradation.
Method explained here · KEVOS® original book
Power laws from test data
In Scale Models by the Numbers
What it covers: Fit a power law to measured data on logarithmic axes, read the exponent and its uncertainty, test it against theory, and use the fit to set a model's flows without fooling yourself.
Method explained here · KEVOS® original book
Calibrating with weights and substitution
In Strain Gauges and Load Cells by the Numbers
What it covers: How to calibrate a weighing vessel with test weights, substitution and a corner test, judge the result with a straight-line fit, and why datasheet values alone are not enough.
Useful alongside · KEVOS® original book
Measuring humidity on site: wet bulb, dew point and sensors
In Humidity Control by the Numbers
What it covers: How wet-bulb psychrometers, chilled-mirror hygrometers and capacitive humidity sensors work, how to calibrate them with saturated salts, and where to put them so they read the space and not a press.
Useful alongside · Library collection
Measurement system analysis: making sure your gauges can tell good parts from bad
What it covers: Every accept, reject and adjust decision trusts a measurement. How to check bias, repeatability and reproducibility, run a gauge R&R study, judge the result and fix a weak system.
KEVOS® tools are screening and decision-support utilities. Verify important financial, engineering, safety, legal or operational decisions using appropriate professional standards and your organisation’s approved data.