Probits analysis for a newbie

Firstly, thank you for your time and attention.

I have been assigned by a professor to explain a research paper describing the lethal effects of herbicides on various animals. Unfortunately, the paper makes heavy use of probits analysis. I have no background in statistics or any maths higher than college Calculus I. In my search for an understandable explanation of probit analysis, I have exhausted all of my resources here at college.

If someone would be so kind, could you point me to an easily understood explanation on probits analysis? An explanation of probit analysis would also do very well.

Thank you for your help!

This isn’t what you want to hear, but if you don’t have a basic background in statistics, it’s just not going to make sense to you. If you’re working in a field where you need to understand these things, you’re going to need to learn some statistics.

You’re right. That’s not what I want to hear. :wink:

I know that I’m pretty out of my league here, but I am willing to learn. At this point, any resource on the topic would be very helpful.

Wiki has a decent explanation of the concept, but if the prof is expecting you to parse out the explanation mathematically what ultrafilter said holds. If you just need to understand what the probit analysis is *saying *the wiki explanation will do.

You might have to read up on the basics of statistical analysis to make much sense of any answer, but I’ll try here:

In a normally distributed population, one standard deviation represents 68.3% of the population. Converting this into a normal equivalent deviation would yield 84.1% response (0.5*68.3 + 50%). In order to avoid negative numbers, a probit unit = NED + 5. This means that if you have a probit unit of 6, that equals a NED of 1, which means that 84.1% of the population shows whatever criterion you happen to be measuring; in this case about 84% of the animals tested died from the herbicide. Similar analysis means that a probit of 5 = 50% affected, probit 4 = 16%, etc.

Probit analysis is essentially a way of making your data appear linear, which is easy to analyze.

My thanks to everyone who posted in this thread. But especially…

Taenia spp.:

THANK YOU! That made perfect sense! I think I can actually explain this paper now! You have my most sincere appreciation.