Chapter 11, Problem 1E

To determine

Explain the reason for the study to be an observational study.

Check whether it is possible to conclude that steroids caused an increase in homeruns.

Answer to Problem 1E

The given study is a retrospective observational study.

No, it is not possible to conclude that the steroids caused an increase in homeruns.

Explanation of Solution

Given info:

A researcher’s wish is to examine the effect of steroids in major league baseball; in general, it is known that most of the players take steroids to increase the performance in the field. For this, the sports writer compares the homeruns and steroids intake from the 1960’s.

Justification:

Observational study:

An observational study measures the values of a variable without influencing the values of response variables and explanatory variables. Thus, in an observational study, researchers can observe the behaviors of the individuals without influencing the outcome of that study.

Here, the researcher ask the individual players whether they take steroids or not and observes their homerun totals. The researchers do not influence the individuals to take steroids but merely observe.

Hence, this is an observational study.

Here, there is a relationship between steroids and homerun totals.

Causation:

If one event is the result of the occurrence of other event, then the variables of the two events are said to be under causation. In other words, it can be said that a causal relationship exists between the two variables.

Even though there is an association between the variables “steroids” and “homerun totals”, the association between the two variables does not infer that the change in one variable is the cause of the change in other variables.

Moreover, the most important thing is that correlation between the two variables does not substantiate the causation.

Lurking variable:

The lurking variable is a type of extraneous variable which is not accounted for under the study. However, it may affect response variables or explanatory variables.

There is a chance for the variables “steroids” and “homerun totals” to not have direct association. The association exists through the lurking variable.

In general case, there is a possibility for the existence of a lurking variable which will be associated with both the variables “steroids” and “homerun totals”.

Therefore, the steroids do not cause homeruns.

Thus, there is no causation between the variables “steroids” and “homerun totals”.