Statistical Tests: T-Tests Page 1/3
A study was set up to look at counts of CD4+ T helper cells in a group of 17 healthy volunteers and a separate group of 7 immunocompromised patients. The following table is a snapshot of the data:
|
Subject |
Group |
CD4+ count (cells/mm3) |
|
1 |
Healthy volunteer |
1024 |
|
2 |
Healthy Volunteer |
789 |
|
3 |
Patient |
337 |
|
24 |
Patient |
243 |
The following Histograms display the distribution of reported alcohol consumption (units) in patients diagnosed with alcoholic liver disease before an intervention and after the intervention has been completed. A histogram of the difference (before minus after) is also presented.
Welcome to the "T-Tests" quiz. There are 4 questions to answer.
Please remember to click the Submit button for each separate question, and read the feedback comments!
Click the Next button to begin the quiz.
Q1. A study was set up to look at whether there was a difference in the mean arterial blood pressure between two groups of volunteers, after 6 weeks of following one of two treatment programs. One group of volunteers were given an exercise regimen to follow for the 6 weeks and the other group were given the same exercise regimen with the addition of an experimental tablet.
Which type of t-test should be used in this situation?
The answer is b). As we are wanting to compare the mean arterial blood pressure between the two groups then a test that is used for continuous outcomes is required. As the two groups are independent of each other and we are wanting to compare them then an Independent samples t-test would be the test to use.
Q2. If we wanted to produce a graphical display to summarise this data separately by group then which of the following chart types could be used (select all that apply)?
The answers are c) and g). As the outcome variable is continuous and we additionally want to produce separate summaries for a couple of groups then we have a few options of plots we could use with Box & Whisker and Dot Plots the best options. You will also see Bar charts presented for this type of data with error bars included. Although not the clearest plot they are commonly seen in laboratory scenarios. If these plots are used then it is crucial to label what the error bars represent as they could be 95% confidence intervals, SE’S, SD’s, 2xSE’s etc.
Q3. A histogram of these CD4+ cell counts has shown that the distribution is negatively skewed. If we wanted to test for differences between the average values in Healthy volunteers compared to immunocompromised patients which type of t-test should be used?
The answer is d). As the outcome variable is skewed and the sample size is small then a t-test would not be appropriate here and we should use a non-parametric test. If we were to take a transformation of the data (such as a log) that happened to normalise the data then we could use a t-test on the transformed data.
Q4. If we were interested in testing to see if there had been a significant change in reported alcohol consumption then we could use which of the following t-tests and for what reason?
The answer is d). We are interested in the change from “Before” to “After” and as this “Difference“ is normally distributed then a paired samples t-test would be the test to use.
You have completed the quiz and here is your result:
If you would like to try this quiz again, click here.
You have not answered questions 1, 2, 3, 4.
Please go back and complete the questions.
Please remember to click submit for each question, and read the feedback comments!
Score 0/0