Experimental design principles

Issues that need to be considered when planning an experiment.

The following issues are the most important:

Comparison and control 

Most experiments are carried out to see whether a treatment causes an effect on a phenomenon (response). In order to see the effect of a treatment, the treatment group needs to be able to be compared fairly to a group that receives no treatment (control group). If an experiment is designed to test a new treatment, then a control group can be a group that receives an existing or established treatment.

Randomisation

A randomising method should be used to allocate individuals to groups to try to ensure that all groups are similar in all characteristics apart from the treatment received. The larger the group sizes, the better the balancing of the characteristics, through randomisation, is likely to be.

Variability

A well-designed experiment attempts to minimise unnecessary variability. The use of random allocation of individuals to groups reduces variability among the groups, as does larger group sizes. Keeping experimental conditions as constant as possible also restricts variability.

Replication

For some experiments, it may be appropriate to carry out repeated measurements. Taking repeated measurements of the response variable for each selected value of the explanatory variable is good experimental practice because it provides insight into the variability of the response variable.

Curriculum achievement objectives reference

Statistical investigation: Level 8

The quality of the images on this page may vary depending on the device you are using.