Question

1) An elementary school teacher is interested in assessing the effectiveness of a new technique for the students to learn their spelling words. He learns a new technique over the summer and is eager to find out if it really works better. He wants to be able to make a comparison and knows he needs two groups. He decides that he will use the new technique for the group of students learning the harder spelling words and the old technique for those learning the easier spelling words. He compares average spelling performance for the two techniques. What is the biggest threat to the internal validity?

A) testing effect

B) history effect

C) attrition / maturation effect

D) selection effect

2) In this example, identify a confounding variable:

A nutritionist is investigating the effects of eating oatmeal for breakfast. He asks all of his participants to eat about 350 calories for breakfast every day for six months. He assigns the experimental group to eat oatmeal with honey. He asks the control group to eat anything other than oatmeal and honey. He then tests their blood levels for cholesterol and other substances.

A) eating oatmeal

B) eating honey

C) eating 350 calories for breakfast

D) eating breakfast

3) In this example, identify a confounding variable:

A school psychologist hypothesizes that fear negatively influences test performance. To test this, one group of 100 students watches a video containing fear provoking images of spiders crawling on people. The other group of 100 students listens to soothing jazz music. Both groups take a test of their general knowledge.

A) fear

B) students

C) school psychologist

D) visual stimulation

Answer 1

In situation 1, the biggest threat to internal validity is the 'selection effect'. An obvious reason for the answer is that testing effect, history effect and maturation effect are threats to single or one group design. It is important to note that inappropriate selection is not a threat in case of one group design, but a threat in case of two group design. In the first situation, the school teacher selected two groups of students. So, the most important threat to internal validity remains selection effect. The participants have to be selected randomly. Using random sampling and random assignment, all the subjects have equal chance of being in treatment or comparison groups. Even the groups then become equivalent. If random sampling and random assignment are not used for creating the two groups, then selection is the biggest threat to internal validity of the test. Selection effect occurs when the experimental group is a high-ability class, whereas the comparison group is an average ability class. In the above situation, the comparison group is given to learn easier spellings using old technique, whereas the experimental group is given hard spellings to learn via the new technique. So, the two groups are not equivalent. They should have been given same spellings to learn via different techniques, which would provide fair means of comparison.

In situation 2, a confounding variable is eating honey for breakfast. This is an extraneous or extra variable in the experiment, which can adversely affect the effects of oatmeal for breakfast. Introduction of honey as an extra variable can ruin an experiment and the expected results, as apart from oatmeal, honey will also produce it's effects, which will wrongly be attributed to oatmeal.

In situation 3, a confounding or extra variable in the experiment is the school psychologist. This is because fear is the independent variable, whose effect is being studied on the test performance. Fear is induced via visual stimulation. So, visual stimulation is not a confounding variable. Sudents are the participants on whom the experiment is being conducted. So, an extra variable in the experiment is the school psychologist.