Answer the following questions.

Question

A certain "Plantita" wants to test whether some plant species are more salt-tolerant than others. Some key variables she might measure are the following: the amount of salt she must add to the water, the species of plants being studied, and variables related to plant health like growth and wilting.

She needs to know which types of variables she should work with in order to choose appropriate statistical tests and interprets the results of her study.

To identify the type of variable, the following questions are raised:

1. What type of data does the variable contain?

2. What part of the experiment does the variable represent?

Answer 1

What they are asking for is rather vague. That is a problem because there are many ways I could answer this question and the only way to ensure full credit is to throw the kitchen sink at it. Here is the gist though. They want to know what variables you have, what type of variables they are, and what you could use them for. The variables are: the amount of salt, species, growth, and wilting.

..........

Okay so we know the variables. What type are they? Well there are many ways I could answer that, but based on the information I have I would say that they are likely asking if they are dependent or independent variables. We can easily say that amount of salt is independent. Plantita has full control over the amount of salt she adds so it must be independent. Wilting and growth I would assume are affected by the amount of salt, so they must be dependent.

..........

The tricky one is species type. Species type is certainly not a dependent variable so if I had to choose one or the other then I would say it is an independent variable. I think it would be even better described as a attribute variable, or moderating variable, but whether or not your teacher is expecting that sort of answer depends on how advanced your class is.

...................................................

Okay so they want to know what type of data each variable is. I am assuming they mean whether each variable is either categorical or continuous? Our information on how these variables are measured is rather vague and this is difficult to answer but we can make some guesses.

..........

First off, species is easy. It is categorical, no question. I am not a biologist but I know of no way to numerically measure species.

............

Salt amount is tricky. Normally this could be either categorical or continuous but because we said it is an independent variable then it must be categorical. It would be very difficult to make an experimentally controlled independent variable continuous so let us call it categorical.

..........

Now for Wiling and Growth, I have no idea. It all depends on how these two variables were measured and unfortunately we were not told. Perhaps the question is asking us to come up with our own way of measuring it? If that is the case then it is your call. Are you going to measure growth categorically or continuously? Let us say that growth is measured by the number of inches in height the plant achieves per day. That would be continuous. For wilting I simply have no idea.

..................................................

Okay, finally the question asks what kind of statistical test is appropriate. Again, there are many ways you could do this, but the easiest would be amount of salt as your independent variable, and growth as your dependent variable. Let us say you have 3 levels of salt: low, medium, high. And let us continue to assume growth is continuous. This would be an ANOVA. We would separate the plants into groups and give each group low, medium, or high amounts of salt in their water. Then we compare the mean growth of each plant.

...............................

If you are a graduate student your professor may be expecting an even more complex answer. That is, they may expect you to incorporate species as a control or moderating variable. I do not want to get too deep into that now, but contact me if you have any questions. I hope this was a helpful explanation. Good luck!