Experimental design...plz help !!

#1
1) A corporation employs 2000 male and 500 female engineers. A stratified random sample of 200 male and 50 female engineers gives each engineer 1 chance in 10 to be chosen. This sample design gives every individual in the population the same chance to be chosen for the sample. Is it an SRS?

**I think it is an SRS b/c they make it random in the corporation among different genders, but I'm not sure....

-------------------------------------------------------------------------
2) Fizz Laboratories, a pharmaceutical company, has developed a new pain-relief medication. Sixty patients suffering from arthritis and needing pain relief are available. Each patient will be treated and asked an hour later, "About what percentage of pain relief did you experience?"

a) Why should Fizz not simply administer the new drug and record the patients responses?
b) Outline the design of an experiment to compare the drug's effectiveness with that of aspirin and of a placebo.


** (a) I said they should not b/c the way people react to the medication is different. Some will relax more and it will take less of an effect of pain relief. They would not be randomizing the sample b/c they are limiting it to 60 patients and they would be giving the same drug so the experiment would not replicated.
(b) I think you should give a random assignment between different groups of medication and divide them up among different types of medication. But I don't know how you would actually "outline" the experiment with a more detailed way...

-------------------
3)Twenty overweight females have agreed to participate in a study of the effectiveness of four weight-loss treatments: A, B, C, and D. The researcher first calculates how overweight each subject is by comparing the subject's actual weight with her "ideal" weight. The subjects and their excess weights in pounds are:

Birnbaum: 35, Brown: 34, Brunk: 30, Cruz: 34, Deng: 24, Hernandez: 25, Jackson: 33, Kendall: 28, Loren: 32, Mann: 28, Moses: 25, Nevesky: 39, Obrach: 30, Rodriguez: 30, Santiago: 27, Smith: 29, Stall: 33, Tran: 35: Wilansky: 42, Williams: 22.
*b/c a subject's excess weight will influence the response of weight loss after 8 weeks of treatment, a block design is appropriate. *


a)Arrange the subjects in order of increasing excess weight. Form 5 blocks of 4 subjects each by groupin gthe 4 least overweight, then the next 4, and so on.
(1) Williams-22, Deng-24, Hernandez-24, and Moses-25; (2) Santiago-27, Kendall-28, Mann-28, and Smith-29; (3) Brunk-30, Obrach-30, Rodriguez-30, and Loren-32; (4) Jackson-33, Stall-33, Brown-34, and Cruz-34; (5) Birnbaum-35, Tran-35, Nevesky-39, and Wilansky-42.
b) Use random digits table to randomly assign the 4 subjects in each block to the 4 weight loss treatments.
** I did part A and I arranged the subjects ... in part B, I understand I just start from a random line in the table but I don't understand HOW to assign the 4 subjects JUST by looking at the random digits. Like say the first digit starts off with 45 in line 133, I don't get how to use those random digits to assign the subjects.

-----------------------------------------------------------------
I did alot of work for these problems but I"m not sure at all about them . Please help me asap with these asap, thank you!!!!
 
Last edited:

Lark

New Member
#2
Here is a quick answer to question 2a:

Some people may get "better" just because they think the medicine is going to help them; ie the placebo effect.

2b. I think you did "outline" the procedure by what you wrote; maybe more clearly I would write: Randomize the list of people(some computer program should do this) and the first 1/3 of the list will get one medicine, the next 1/3 will get the other medicine, and the last 1/3 will get the placebo. Label the medicine a,b, c and put a,b,c next to everyones name. Give the medicne to the nurse but don't let her know what is a,b, or c (ie the nurse does not know which is asperin etc.) and the nurse will give the medicne to the patients. ie this is a double blind test.

Lark
 

Lark

New Member
#4
Start anywhere in the table of random digits. Going down the table when you get a 1,2,3, or 4 then asign the first person in group A to the first weight loss treatment; for example if your first number you come to is a 3 then assign the first person to treatment 3. Now keep going down the list until you get a 1,2, or 4 (not 3 because that was already used). For example if you get a 4 then assign the second person to treatment 4; etc.

After you have assigned the 4 people in group A then do the same to group B; keep going down the list of random digits from where you left off. If you run out of numbers then use the second number from each random number in the list of random numbers.

Lark