Statistics Overview Sheet

I. t-tests--These tests are used to compare the means of 2 populations to determine if there is a difference between them.

A.     Unpaired t-test

a.       Used for sample populations that are unrelated (independent of one another)

b.      Null hypothesis: There is no significant difference between pop. A and pop. B

c.       SPSS: Data is entered into SPSS with the first column being a grouping variable or string variable and the second column being a data or numeric variable.

B.     Paired t-test

a.       Used for sample populations that are related usually in a before and after situation

b.      Null hypothesis: There is no significant difference in the sample pop. before ______ and after ________

c.       SPSS: Data is entered in 2 numeric columns, the first column contains the before data and the second column contains the after data. The data is kept in pairs so the before data and after data are for the same individual

C.     Interpretation of results

a.       P-value:

                                                                           i.      if the p-value is < 0.05 then there is a significant difference and you will reject the null hypothesis.

                                                                         ii.      If the p-value is >0.05 then there is not a significant difference and you will accept the null hypothesis

b.      SEM

                                                                           i.      If the SEM is less than 10% of the mean then you have a large enough sample and can be confident in your results

II. Regression--A regression is used to determine if a relationship exists between 2 variables. It also implies that this is a cause and effect relationship. If no cause and effect relationship exists then you need to use a correlation

            A. Null hypothesis: There is no significant relationship between variable x                                   (independent variable) and y (dependent variable)

            B. SPSS: One column contains the data for the x variable and the next column                           contains the data for the y variable.

            C. Interpretation of results

                        a. p-value

i. if the p-value is < 0.05 then there is a significant difference and                                    you will reject the null hypothesis.

                                                                         ii.      If the p-value is >0.05 then there is not a significant difference and you will accept the null hypothesis

c.       R2  -the R2 value tells you whether or not you can make further predictions with your equation of the line.

                                                                           i.      If the R2 value is >0.8 for a biological system or >0.9 for a physical system then you can use the equation of the line to make further predictions

                                                                         ii.      If the R2 value is <0.8 or 0.9 then you cannot