Do i need to use Pearson’s X2test to evaluate the statistical significance of the differences in Antibiotic concentrations to eradicate biofilm of the same straine?
Can I use t-test? Studet test.
Thanks
It depends, if you are working with categorical or numerical variables.
T-student test(paired and unpaired) works for numerical variables. (Compare 2 means)
X2 or chi-square test works for categorical variables. (Compare proportions)
Pearson works for correlation between two numerical variables.
So if you are working with antibiotic concentrations (numerical variables) and you want to compare it in the same population/strain, you should use paired t-test
Yes you can use "paired t-test" after verification of the normality and homogeneity of your variable. So, if these conditions are note verify you can use "Wilcoxon"
Best regards
He!
Normality can be verify by Shapiro-Wilk test (swilk):
Eg: if you use STATA, it will be
*
swilk YOUR_VARIABLE
pnorm YOUR_VARIABLE
histogram YOUR_VARIABLE, normal (20)
*
YOUR_VARIABLE: replace it by your variable
The first line can tell you if distribution of your variable is normal.
you look at the value of the small p. If this value is less than 0.05 it means that the distribution is not normal. If it is above 0.05 it means that the distribution is normal.
The second and the third control line: they give you a histogram to show the bell curve.
NB: the "20" in brackets, just means the number of bar you want to have under the bell. So you can increase or decrease.
Excuse me for the delay.
Best regards
Hi Bello Hamidou
I did like you told. Where is small p?
Is my distribution normal?
Thank you
Hi
your distribution is normal.
The small p = Prob>Z
Obs = number of observation; so we can see that your have only 8 observations (8 samples).
- Badges
- Science topic
- Similar topics
- Medicine
- Physiology
- Biosignals
- Biomedical Signal Processing
- Statistical Analysis