Into to Comparing 2 Groups Analysis of Biological DataBiometrics Dr Ryan McEwan Department of Biology University of Dayton ryanmcewanudaytonedu First Principle As a scientist investigator or data handler it is your personal responsibility to make sure that the analysis you are do ID: 599938
Download Presentation The PPT/PDF document "Normality, P-values," is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Normality, P-values, Into to Comparing 2 Groups
Analysis of Biological Data/Biometrics
Dr. Ryan McEwan
Department of Biology
University of Dayton
ryan.mcewan@udayton.eduSlide2
First Principle:As a scientist, investigator or data handler, it is your personal responsibility to make sure that the analysis you are doing is appropriate.If you have a collaborator on the project who is a statistician, that is dandy, however, you should be able to explain the analysis, or else couch it in your own ignorance.
If you do not have a statistician working directly with you, then you need to commit yourself to grinding out the proper analysis.Read some stats books! Look for analogous analyses in the literature, check out some on-line resources.
This course, and any other course you can take, will only give you “doorways” or concepts for analysis that you can apply…it is up to you to verify, explore and excecuteSlide3
Basic Challenge….how do you estimate the value from a population?
Measures of Central TendencyMean (arithmetic mean)Median (number in the middle)Mode (most often repeated)
What about variation?Slide4
Relationships among common central tendency measuresSlide5
Johann Carl Friedrich
Gauss (1777-1855)
There is a bit of quibbling about whether this fellow, The Prince of Mathematics, indeed came up with the idea of a “normal distribution”…in any case “Gaussian” is often used interchangeably with “normal” in general statistical parlance.Slide6
The Normal Distribution
Holy Grail of probability distributionsOften sought with enormous effort, rarely foundSlide7
The Normal Distribution
Various means and
deviationsSlide8
Johann Carl Friedrich
Gauss (1777-1855)
The main idea is about the probabilities of values that are arranged around the mean.
Do the values take this shape….meaning is the variation symmetrical and rapidly dropping off?Slide9Slide10Slide11
P-value:
Is the probability that a difference of magnitude revealed in the analysis would occur if the values were NOT DIFFERENT.
That is, the probability of a Type 1 Error, i.e.,
False Positive
result.Slide12Slide13
How to do a t-testSlide14