We can draw a cause-effect conclusion since there would essentially be no difference between the two groups on other variables and this eliminates selection bias.
NOTE: Suppose a sample of students is randomly selected from university and then assigned to one of two stress treatment groups. A researcher measures their stress levels before and after the 10-week program. Which of the following is the main advantage for randomly selecting the sample?
A randomly selected sample represents the population at the university best so one can generalize the findings to the entire university
[Outcome D1] Macular degeneration is a serious disease of the eyes that can lead to blindness. Researchers wanted to learn whether eating green leafy vegetables can slow the onset and progress of macular degeneration. A large group of individuals, who were 55 years old or older, volunteered to participate in the study. The subjects were divided into two groups based on the dietary information they provided: Those who ate green leafy vegetables five or more times a week and those who ate them fewer than two times a week. Researchers then collected data about the occurrence of macular degeneration in both groups. The group who ate these vegetables fewer than two times a week had a significantly higher rate of macular degeneration than the other group. It was concluded that there is a possible benefit to eating green leafy vegetables to slow down the disease. (Use this study to answer parts “a – d” on the next page too)
Complete the four steps of statistical analysis for this study in the table.
[D2] Research Design
1. What question can be answered by collecting data.
2. Decide what to measure and then collect data.
3. Summarize and analyze the data.
4. Draw a conclusion and communicate the results.
A researcher at King’s College in London found that infomania (information overload) has a temporary, negative effect on intelligence quotient (IQ). Imagine that a group of researchers wished to further test this conclusion. These researchers randomly divided volunteers into two groups. Each subject took an IQ test. One group had to check email and respond to instant messages while they were taking the test. The other group took the IQ test without any distractions. Researchers found that the distracted group’s average IQ test score was 10 points lower than the average IQ test score for the group that was not distracted.
What is the explanatory variable, and what are its values (the individual treatments)?
What is the response variable in this experiment?
Did the researchers use random assignment? Can researchers conclude that infomania reduces IQ scores?
Did the researchers use random selection? Can the researchers generalize their conclusion to the entire population of King’s College?
Is it possible for the subjects of this study to be blinded? Explain your answer.
Is it possible for the subjects of this study to experience a placebo effect? Explain.
[D3] Random Sampling Methods
According to a 2022 study from the U.S. Census Bureau, California consists of 57 counties and 482 cities, towns, and villages, plus 2,949 special districts. A local research group is interested in determining the proportion of cities that support Governor Gavin Newsom. The researchers plan to conduct a simple random sample of 50 cities to estimate the level of support for our current government.
Explain how you would design a simple random sample to collect this data.
The lead researcher decides to divide the cities into the northern and southern regions and then randomly selects 25 from each region. Explain why this would not be considered a simple random sample.
You want to estimate the average amount of time, per week, that students at a particular college spend studying. You and your research team are deciding how to collect your data and came up with the following options:
Method A: Select 100 students at random from the students at the college.
Method B: Select 100 students as they enter the library.
Method C: Select 200 volunteers.
Method D: Select 300 students who enrolled in Statistics this semester.
Which ONE of the methods above would collect the most representative sample for the college? WHY?
D4] Ethics & Bias
Researchers are collecting data on which handwashing method is more effective to prevent the spread of COVID-19. Hand washing methods include washing with soap for 30 seconds or with anti bacterial (no water) for 30 seconds. Describe how the researchers would create a control group in this experiment, and explain what the purpose of the control group would be.
Researchers are collecting data on which handwashing method is more effective to prevent the spread of COVID-19. Hand washing methods include washing with soap for 30 seconds or with anti bacterial (no water) for 30 seconds. Describe how the researchers would create a placebo group in an experiment, and explain what the purpose of the placebo group would be.
Researchers are collecting data on which handwashing method is more effective to prevent the spread of COVID-19. Hand washing methods include washing with soap for 30 seconds or with anti bacterial (no water) for 30 seconds. Describe the purpose of blinding in an experiment and give an example of how researchers could use blinding in this experiment.
You want to estimate the average amount of time, per week, that students at a particular college spend studying. You and your research team are deciding how to collect your data and came up with the following options:
Method A: Select 100 students at random from the students at the college.
Method B: Select 100 students as they enter the library.
Method C: Select 200 volunteers.
Method D: Select 300 students who enrolled in Statistics this semester.
Identify all the methods above that would introduce bias? WHY? (there is more than one answer) – from Unit 1.4
Read the following description of an experiment. Describe any features that might be unethical in this experiment?  How might you improve this experiment?
A group of people in a small town volunteered to participate in the testing of a new drug for treating blood pressure in adults. Researchers used a computer program that assigns an identification number to each person and randomly assigns them into two groups. The first group took a pill that contains the drug, the second group took a pill that looks like the “real” pill, but doesn’t contain the drug.Â
Â
