Question:

A company is studying the effects of a new drug on an illness called ataraxia. 100 patients suffering from ataraxia are found. The

company plans to give the new drug to 50 of them and a placebo to 50 of them. The recovery rates for the two groups will then be

compared

1. The division into two groups of 50 should be made randomly. Give an example of how to do this.

2. Why is it important to divide the groups randomly? Explain, and be sure to refer to the terms control, variable, and lurking.

es)

Question

Mathematics

Armani Rush

19 December, 00:29

Question:

A company is studying the effects of a new drug on an illness called ataraxia. 100 patients suffering from ataraxia are found. The

company plans to give the new drug to 50 of them and a placebo to 50 of them. The recovery rates for the two groups will then be

compared

1. The division into two groups of 50 should be made randomly. Give an example of how to do this.

2. Why is it important to divide the groups randomly? Explain, and be sure to refer to the terms control, variable, and lurking.

es)

+1

Answers (2)

Know the Answer?

Denisse Whitaker · Answer 1

1 do the division by a draw of their names into 2 teams

2 there might be one group with a higher age and thus a lower chance of being cured and you should know all variables and have control over the project

Rhys Lara · Answer 2

1. There are multiple methods to choosing randomly from a selection. One instance could be choosing names from a hat.

2. Dividing the groups randomly allows for an equal and fair distribution of people for the control and variable groups. The 50 people receiving the drug are the variable group, while the other 50 receiving the placebo are the control group.

Step-by-step explanation:

Random selection is used in testing in order to assure the lack of bias from researchers. In real trials, random selection would likely be done through the company's own software, or an Excel spreadsheet.

Random selection is also used in order to remove lurking variables. An example of a lurking variable could be shown as follows:

A researcher is studying a connection between heart disease and cholesterol intake. Aspects unrelated to the study could still have an effect on the quality of the results, like whether people in the groups smoked or was very stressed. Random distribution assists in removing any lurking variables - and if it can't fully remove them, it will at least distribute them fairly across the control and variable groups.