Statistics

An independent variable is known as a factor in an experiment.  Independent variable is an explanatory variable that is manipulated in an experiment. Each factor has different values or levels (Kenett & Zacks, 2014). In ANOVA, a treatment is a specific factor levels combination whose effects are to be compared with other treatments (Kenett & Zacks, 2014).

The first example of treatments in ANOVA is a case where a decision on the price of new products that awaits launching in the market. In such a scenario, different levels of price are seen to affect or influence the volume of sales. As a result, five different samples are selected in random situated locations. In the experiment, actual sale volumes of the product at different prices are recorded. It is seen that a variation in price results in a variation in volume of sales of the product. As a result, it can be concluded that difference in prices of a product affects the change in sale volume. In this experiment, sales are the dependent variable whereas price is the independent variable. The five levels of prices are called factors and different levels off factors are known as treatments. Therefore, ANOVA helps to determine whether the treatments are different on response variable and estimates the difference. 

Another example of treatment is evident when production plant wants to do a comparison of at least three employees basing on their hours of working. Therefore, in ANOVA, the null hypothesis is that all groups are simple random samples of a given population; in this case, the population is the employees in the production plant. In this experiment, studying the effects of different treatments on similar samples, the null hypothesis would state that there is same effect (or none) in the given treatment. In this case, the rejection of null hypothesis would mean that different treatment lead to altered effects. 

ReferenceKenett, R., & Zacks, S. (2014). Modern industrial statistics: With applications in R, MINITAB and JMP.