Question

Discuss the Utility of concomitant variable in design of experiment. Thank you

Answer 1

A variable that is observed in statistical experiment but is not specifically measured or utilised in the analysis of data. It is sometimes necessary to correct for concomitant variable in order to prevent distortion of result of experiment or research. Thus variable is also called covariate, independent, ancillary variable.

In experimental design we use concomitant variable in order to knew the relationship between the exposure of interest variable and outcome variable.

Consider an example where we had a study which compares male vs female salaries of a college graduates. The variable being studied are gender and salary and the primary survey questions are related to these two main topics.but since salaries increase the longer someone has been in the workplace ,but the concommitant variable'time out of college' has the potential to skew our data if it is not accounted for .

If this variable is observed, recorded for and accounted for in the final results, our conclusion will be more valid. Typically this is done by noting the concommitant variable ( here, age) in the initial data gathering, and then running a regression to ' equalize' all the data points to the same number of years out of college.

So , from the above example we see the utility of concomitant variable in experiment and research design i.e. by using concomitant variable it easy and accurate to measure the effect of other factors on dependent variable.

Another example where we can see the utility of concomitant variable.

Suppose we want to compare the of some diets on the weight of animals.we can analyse these data by performing ANOCOVA techniques by regarding

Y: the final weight of the animals taking the diets after a specified period ( either day, monym, years) as a response variable.

X: the initial weight of the animals at the time of starting the experiment as the concommitant variable.

To ensure the real difference between in weights ( Y) are due to rations or diets , we must adjust for linear effect of X on Y. Or in other words after considering concomitant variable (X) we can more easily know the effect of diets on a animals with more precision.