Popular in Course
Popular in Animal Science
This 2 page Class Notes was uploaded by Marlon Brown on Saturday September 19, 2015. The Class Notes belongs to ZOL 355 at Michigan State University taught by Staff in Fall. Since its upload, it has received 36 views. For similar materials see /class/207231/zol-355-michigan-state-university in Animal Science at Michigan State University.
Reviews for Ecology
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 09/19/15
ZOL 355L Ecology Lab Statistical Analysis Lecture notes Fall 1999 Goal to introduce you to three basic types of statistical tests used in ecological studies Statistical tests Determine whether an observed pattern in eld or experimental data is the result of pure chance For example is the differences between two means real or simply the result of chance variation during sampling Most tests eventually calculate a Pvalue Pvalue Is the probability that an observed pattern in data is the result of pure chance In other words the pvalue is the probability that data sets are from the same source population For example pvalue 090 means that there is a 90 chance that the pattern observed is the result of chance alone pvalue 001 means that there is only a 1 chance that the data patterns are the result ofonly pure chance At what pvalue can we conclude that the difference is due to more than just chance Is 20 probability low enough How about 10 15 30 Traditionally people have used a pvalue of 005 as this cutoff point or critical value Pvalues less than this mean the there is less the a 5 chance that the observed pattern is the result of chance alone This is a low enough probability that we say that there is a signi cant probability that the pattern is real In other words we reject the null hypothesis that there is no pattern in the data when p lt 005 ZOL 355L Ecology Lab Types of statistical tests There are literally thousands of statistical analyses The type oftest you uses is closely dependant on the type of data you have collects and the design of the experiment Categories Parametric vs Nonparametric depends on characteristics of the data normally distributed bell curve variance Continuous vs Discreet data depends on the values data can be measurements or number of offspring you can t have 12 of an offspring Numerical vs Categorical data data can be numerical measures or counts in categories We will look at three tests 1 Comparison of means Ttest Numerica continuous data Parametric data Data sets for the same measured variable Data w high variance Data w low variance lfthe mean ofanother data set treatment lies within the shaded region 25 tails we say that the means are signi cantly different Note that the lower the variance the closer the two means can be and still be signi cant Data w high variance Data w low variance
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'