In this application, you can find guided lessons and exercises to better understand some important experimental designs and their analysis. In most cases, we refer to them with the general name of Analysis of Variance (ANOVA)
Complete Randomized Design with one factor is the simplest experimental design in which the effect of several treatments are evaluated. Here, we present the basis of analyzing this design and how to interpret the results.
The most simple experimental design considers a single factor (usually called treatment) with different fixed levels decided by the experimenter. A paradigmatic example woul be measuring the effect of two treatments with respect a control or reference treatment. The response variable must be normally distributed and its variance should be the same in all the experimenatl groups.
Here we will present how to use R for exploring the result of this class of designs anf what to do when the basic assumptions do not hold.
In this link you can run a shiny app that explains technical details of a two-factor factorial design and allows running simulations to understand the analysis.
An important technique known as blocking can be used to reduce or eliminate the contribution to experimental error contributed by nuisance factors. The basic concept is to create homogeneous blocks in which the nuisance factors are held constant and the factor of interest is allowed to vary. Within blocks, it is possible to assess the effect of different levels of the factor of interest without having to worry about variations due to changes of the block factors, which are accounted for in the analysis.
In many cases, there are sources of variation that require special attention. For instance, in a clinical trial with a placebo and treatment group, we should consider differences in the response of males and females as a source of variation that should be controlled. Assuming that, sex is considered a block and the experiment is run in a sample of males and a sample of females. This is different to have a sample of patients and include sex as a factor.
Themostbasicexperimentaldesigncorrespondstoconsider a factor with severallevels,forexamplecomparingacontrolgroupwithtwotreatments.In this application,thecharacteristicsofthisdesignandthedifferentaspectsthatmustbetakenintoaccountinapracticalsituationcan be explored.
Inthe two-factordesign, the influenceoftwoconditionscontrolledbytheexperimenterandtheirpossibleinteractionisevaluated.It is importanttounderstandtheconceptofinteractionandhowitisevaluated.On the otherhand, it isimportanttounderstandhow to decidethesamplesizenecessarytoguaranteeusefulresultsofanexperiment.
