{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

Identify the subjects factors levels treatments and

Info icon This preview shows pages 5–7. Sign up to view the full content.

View Full Document Right Arrow Icon
a. Identify the subjects, factor(s), levels, treatments, and the response (outcome) variable. Subjects: 300 patients Factor: type of medicine Treatments: levels = new medicine, aspirin, control group Response variable: percentage of pain relief experienced after 2 hours b. How can the researchers ensure this is a double-blind experiment? Make sure all the pills look the same to the subject and reseasrcher who is giving the pills, and they are not told what they are getting. Make sure the researcher does not know who is assigned to what treatment (have someone else do the randomization.)
Image of page 5

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Stat 133 Recitation 3.1-3.2 c. Evaluate this experiment in terms of the 3 criteria used in class. If you can improve it, say how. Make comparisons: it uses a control group, which is a good thing, and they are trying to compare aspirin to the new medicine also. Avoid bias: Some bias can happen here. For example, people have different pain tolerances and different ideas of how much better they feel, so this can cause problems. Ask more specific questions before and after to help minimize this problem. Another issue is how much pain they had to begin with. Have enough data: yes; 100 in each group is a good number. d. What would it mean if the researchers found a ‘significant difference’ in pain relief for the new medicine? Use statistical terms to explain. It would mean there was a difference in the average response compared to the other treatments and this difference is likely not due to random chance. e. If there was a ‘significant difference’ found, could you say that the new treatment causes more pain relief? Why or why not? Only if 1) the experiment made sure to eliminate major bias issues, and 2) if the significant difference found showed that the new medicine was significantly better than both the control group and the aspirin. f. Assuming the new medicine is on the market, design an observational study that tries to answer the same question as the experiment did. Explain why its results would NOT be near as powerful as those of the experiment. Lots of possible answers here. Assuming the new medicine is on the market, find people who buy it, and ask them the same question; then find people who take aspirin, as them the question, and find people who take neither and see whether their pain relief subsides in 2 hours. Or you could give out free samples and have them try them and give you feedback. Any observational study here will be bogus because it’s not under any kind of control. 15. Twenty overweight dogs are participating in a weight loss study involving four weight-loss treatments: A, B, C, D. The researcher calculates how overweight each dog is by comparing their actual weight to their ideal weight for age and type of dog. Before the experiment, the dogs are grouped together by how overweight they are. The result is five groups of four dogs each. The four dogs in each group are randomly assigned to the four weight loss programs. The response variables is the amount of weight lost after 8 weeks of a treatment.
Image of page 6
Image of page 7
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}