Are you trying to predict body weight? The design doesn't make a lot of sense to me otherwise.

If so, your basic design is that your predictor variables are actually several variables. For example, food intake is two variables :

My preference is to use regression rather than anova because you can set up the predictors for the comparisons that interest you.

Thank you for suggestion Ronán Michael Conroy . I understand what you mean. But what I acutally want to check is

in two phase of study where

• if factor X is introduced in phase 1 (to Animal A lets say mother)
• if compound Y is given to the phase 2 (To Animal B lets say babies)

MAY OR NOT result in some health consequences in the animal B . For which I will be measuring for eg Body weight or other different biochemical parameters that can be clue to different metabolic disorders.

So my concern is whether on not the FACTOR in Animal A and COMPOUND in Animal B as mentioned above lead to some change in different anthropometric and biochemical parameters in animal B.

I know its super confusing!! Sorry about that.

Anishma

Your study design appears to be a 2-way ANOVA, with two independent variables (compound X and liquid intake) and one dependent variable (body weight). The two independent variables are considered factors in the ANOVA, and you are looking to see how these factors influence body weight. A 2-way ANOVA would be the best statistical test to use in this case, as it allows you to examine the main effects of each independent variable and the interaction effect between them.

It should be noted that, the data you have described is a little bit complex, if you have a large sample size and the assumptions of ANOVA are met, then a 2-way ANOVA would be appropriate. However, if your sample size is small or your data is not normally distributed, you may want to consider using non-parametric tests, such as the Kruskal-Wallis test or the Wilcoxon rank-sum test, which do not rely on the assumptions of normality and equal variances.

In addition, you can use a multiple regression analysis to control the effect of other variables and to see the effect of compound X on body weight.

Thank you so much @Dinesh Kumar.

That is so informative. I will try using the test.