0
$\begingroup$

So I have this raw data for a case study: enter image description here

Note: 1 stands for average weight and 2 for overweight.

I need to calculate the following:

  1. What is the mean expected time spent for the average-weight patients? What is the mean expected time spent for the overweight patients?
  2. What is the difference in means between the groups? By approximately how many standard deviations do the means differ?

I have already solved the first one and the first part of the 2nd question. However how do I answer the 2nd part of the 2nd question?(the standard deviations part)

Answers:

1) Average weight mean = 31.36; overweight mean = 24.74

2) Difference = 6.62; they differ by 0.68 standard deviations

$\endgroup$
  • 2
    $\begingroup$ There is a formula for standard deviation in your textbook. Apply it to the whole sample - not just group 1 or 2. How many times the standard deviation is the difference? $\endgroup$ – Paul Sinclair Mar 22 at 3:11
  • $\begingroup$ I got the standard deviation of the whole sample as 10.238. Dividing the difference between the means by this gives me 0.65. Is this how you wanted me to solve? If it is can you explain how this corresponds to the answer? . $\endgroup$ – RaphX Mar 22 at 6:55
  • $\begingroup$ Obviously they used a different standard deviation. I don't know if your formula was std dev for the full population (where you divide by $n$) or for a sample (where you divide by $n-1$), nor which would be appropriate here since I don't know the source nor use of this data, but that is too small to explain the difference. My guess is that they used the std dev of either just the "1" entries or of just the "2" entries. But I don't see a justification for using either instead of the full population. $\endgroup$ – Paul Sinclair Mar 22 at 12:59
  • $\begingroup$ That is possible. $\endgroup$ – RaphX Mar 22 at 13:29

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.