Glossary of Terms

Accuracy An accurate measurement is one which is close to the true value.

True Value The perfect measurement, only found if the quantity being measured had no errors in it.

Calibration This involves fixing known points and then marking a scale on a measuring instrument, between these fixed points.

Data This refers to a set of measurements.

Random Errors These cause readings to be different from the true value. Random errors can be detected and reduced by taking a large number of readings. eg: Random errors may be caused by human error, a faulty technique in taking the measurements, or by faulty equipment.

Systematic Errors These cause readings to be spread about a value other than the true value; in other words, all the readings are shifted one way or the other way from the true value. eg: A systematic error occurs when using a wrongly calibrated instrument.

Zero error A type of systematic error caused when a measuring instrument has a false zero.

eg: A zero error occurs when the needle on an ammeter fails to return to zero when no current flows, or when a top-pan balance shows a reading when there is nothing placed on the pan.

Precision This is set by the limits of the scale on the instrument being used. Precision is about the smallest scale division on the measuring instrument that you are using. A set of precise measurements has very little spread about the mean value.

eg, using a ruler with a millimetre scale on it to measure the thickness of a book will give greater precision than using a ruler that is only marked in centimetres.

Reliability Can be improved with repetition, and then calculating an average value. If someone else can carry out your investigation and get similar results, then your results are more likely to be reliable. You can check reliability by comparing your results with others.

Fair test Only the independent variable has been allowed to affect the dependent variable.

eg: Keep all other variables constant.

Validity Data is only valid if the measurements taken are affected by a single independent variable. Data is not valid if for example a fair test is not carried out or there is observer bias. eg: In a rate of  reaction experiment when the concentration of the acid is changed, it is important that concentration is the only independent variable. If say, the temperature also changed as you increased the concentration, this would affect your results and the data would no longer be valid.

Evidence This is data that has been validated. It is possible to give a measure of importance to data that has been validated when coming to an overall judgement.

Categoric Variable has values which are really labels. When you present categoric data you should you must use a bar chart or pie chart, not a line graph. eg. colour is categoric.

Continuous Variable is one which can have any numerical value. When you present continuous data you should use a line graph.

Control Variable As well as the independent variable, this could affect the outcome of the investigation. So these variables should be kept constant; otherwise it won’t be a fair test. If it is impossible to keep it constant, try to monitor it; then you can see how much it changes and you can judge how much effect it has had on the outcome of the experiment.

Dependent Variable is the variable you measure for each change in the independent variable.

Independent Variable is the variable that you deliberately change.

Discrete Variable is a type of categoric variable whose values are restricted to whole numbers.

eg. number of blades on a wind turbine 2, 3, 4, 5, etc

Ordered Variable is a type of categoric variable that can be put in,the size of marble chips could be described as large, medium or Small, or days of the week.