EC-8.6 Designing an Experiment and Reporting It
You can turn a question into a measurement plan, decide how many readings and over what range, plot the data so its shape is visible, fit a line and say what the fit does not tell you, and write a report a stranger could act on.
Before:S4-5. Probability Theory & Stochastic ProcessesPE2-4. Sensing Techniques and Sensor SystemsEC-1. Circuit AnalysisUnlocks:EC-13. Laboratory Practice, in Sequence
This is the topic that makes the rest of the module worth something, because an accurate reading of the wrong quantity is still wrong. It is also the one that transfers furthest: the same discipline of stating the question first, changing one thing at a time and reporting the uncertainty applies to a circuit, a piece of software and a manufacturing line alike.
Work through these
The question first, and the measurement second
Writing down what you expect to find, and what result would change your mind, before touching an instrument. It takes ten minutes and it is what stops a day of readings that answer nothing.
NPTEL: Measurement and Instrumentation (IIT Guwahati) · CourseControls, and changing one thing at a time
If two things change between readings, the difference cannot be attributed to either. A control measurement with nothing changed is what tells you how much your setup moves on its own.
NPTEL: Measurement and Instrumentation (IIT Guwahati) · CourseHow many readings, and over what range
Points clustered where nothing happens waste effort, and a range too narrow hides the behaviour you were looking for. Spacing points to cover the interesting region more densely is usually the better plan.
NPTEL: Electrical Measurement and Electronic Instruments (IIT Kharagpur) · CoursePlotting data so the shape is visible
Axes chosen to make the expected relation a straight line make a departure from it obvious. Logarithmic axes, error bars and plotting the residual rather than the raw value all serve the same purpose.
NPTEL: Measurement and Instrumentation (IIT Guwahati) · CourseFitting a line, and what the fit does not tell you
A least-squares fit returns a slope and an intercept whatever the data looks like. A high correlation is not evidence that the model is right, and the residuals are where a wrong model shows itself.
NPTEL: Measurement and Instrumentation (IIT Guwahati) · CourseThe laboratory report, and what a reader needs from it
Purpose, setup with part numbers and settings, method, data, uncertainty, result and what you concluded. The test of a report is whether a reader could repeat the work and get your answer.
NPTEL: Electrical Measurement and Electronic Instruments (IIT Kharagpur) · Course
Sign in to keep your progress.
Free resources
We haven't checked most of these for screen reader use yet.
Links last checked 3 Sept 2026.
Stuck here?
Ask a mentor. A real person answers, and they can see exactly which topic you're on. Usually within a couple of working days.
Checking your session…
Topics shown in module order.