Question

#1. Which of the following scenarios would be best described as having a true experimental research design?

A		Research Question: Do a smaller proportion of graduates attend graduation when it is held on a Sunday compared to Saturday? Design: Randomly select 40 graduates the year it is held on a Saturday and record how many attend graduation. Do the same thing on a year the ceremony is held on a Sunday.
B		Research Question: Is a new vaccination effective at limiting the risk of catching a cold? Design: Randomly select 50 students from the University of Michigan and give them the vaccine. Compare the average number of colds in this group to 50 randomly selected students from the University of Florida who did not receive the vaccine.
C		Research Question: Do students who live on campus walk more steps per day than those who live off campus? Design: Randomly select 50 students who live on campus and another 50 who live off campus. Provide each student with a fitbit and ask them to record their steps for 30 days.
D		Research Question: Does working at a standing desk improve productivity? Design: Randomly assign 10 employees to work at a standing desk and 10 to work at a sitting desk for 2 weeks. Measure productivity at the end of the 2 weeks.

Use the following to answer questions 2 and 3

#2 J. Holt owns Holt’s Haven, a seedy bar somewhere south of Dickson St. He has a regular set of customers but they tend not to be big spenders. It’s unlikely that there are many more people in town who would be attracted to his kind of establishment, so he thinks the best way to increase revenues is to get his regular customers to spend more. He reasoned that if he put in some entertainment he could get them to stay longer and spend more. So he tried the following experiment. He installed a used pool table and allowed his customers to play for free (as long as they drank beer).   He kept track of the number of beers that he sold per patron before he put in the table and compared it to the number after he put in the table. He put these numbers into an Excel file in the following way: The first column contains the number of beers purchased for each customer for a random sample of 200 customers observed on 3 different nights the week before he installed the table. The second column has the number of beers purchased per customer for another random sample of 200 customers observed during 3 nights the week after he installed the table.  

                       

	Before Table	After Table
5.8		7.6
2.0		2.7
6.5		10.1
5.3		4.1
.		.
.		.
.		.

            His research design would be described as:

	A.	pretest-posttest quasi-experiment
	B.	post-test only quasi-experiment
	C.	non-experimental study
	D.	pretest-posttest true experiment

#3How many of the criteria for inferring cause and effect can his design satisfy?

A.		one
B.		two
C.		three
D.		none

Use the following to answer questions 9 and 10

Researchers conducted an RCT to study the effect of progressive resistance exercises in depressed elders. They studied 35 volunteers who had depression. Participants were randomly assigned to an exercise group, which met three times per week for 10 weeks, or a control group which met 2 times per week for an interactive health education program. The outcome variables were: level of depression, functional status, and quality of life, using standardized instruments. Pretest and posttest measures were taken for both groups and differences were compared.  Results indicate the differences between these two groups are significantly different from zero at 0.01 level of significance.

#9 What type of study design it is?

A.		Experimental design
B.		Quisi-experimental design
C.		Non-experimental design
D.		None of above

#10 How many of the criteria for inferring cause and effect can his design satisfy?

A.		one
B		two
C		three
D		none

Answer 1

1)
For an experiment to be classed as a true experimental design, it must fit all of the following criteria.

The sample groups must be assigned randomly.
There must be a viable control group.
Only one variable can be manipulated and tested. It is possible to test more than one, but such experiments and their statistical analysis tend to be cumbersome and difficult.
The tested subjects must be randomly assigned to either control or experimental groups.

option B) is correct