Units are the basic objects on which the experiment is done. When the units are human beings, they are called subjects.
A variable is a measured characteristic of a unit.
A dependent variable is a variable whose changes we wish to study; it is a response variable.
An independent variable is a variable whose effect on the dependent variables we wish to study. An independent variable in an experiment is called a factor.
A treatment is any specific experimental condition applied to the units. A treatment is usually a combination of specific values (called levels) of each of the experimental factors.
Validity of the conclusion of a study for the subjects of the study themselves is sometimes called internal validity.
Generalizability of the conclusion of a study to a larger population is sometimes called external validity.
The double-blind technique is when both the subjects and those who evaluate the outcome are ignorant of which treatment was given.
The basic ideas of statistical design of experiments are randomization and control:
1. Randomization is the random allocation of experimental units among treatments, most simply by assigning an SRS of units to each treatment.
2. Control is taking account of extraneous factors in the experiment design, most simply by the use of equivalent groups for comparison.
A variable is a valid measure of a property if it is relevant or appropriate as a representation of that property.
A measurement process is unbiased if it does not systematically overstate or understate the true value of the variable. A measurement process is reliable if repeated measurements on the same unit give the same or approximately the same results. For example, if a scale always weighs 10 pounds high, it is biased. However, if the same scale gives widely different weights each time exactly 10 pounds is placed on it, it is considered unreliable.