Learn moreLearn moreApplied Statistics Handbook

Table of Contents

 


 

Comparing the mean incomes of high school graduates and high school dropouts from 1993 survey data.

 

 

Two-Sample Difference of Means

 

 

Independent Variable: EduCat        Education Level

Dependent Variable: Income  Respondent individual income

 

Sample One: 1 <12 yrs

Sample Two: 2 HS Grade

 

                         Sample 1         Sample 2

                         <12 yrs          HS Grade

------------------------------------------------------------

Sample Mean              23042.5000       31000.8235

Std Deviation             4450.5413        9442.4477

Sample Size (n)              6                17

 

 

                        Homogeneity of Variance

------------------------------------------------------------

              F-ratio   5.08     DF (16, 5)   p < 0.0408 A

 

 

                  T-statistic          DF     p < (2-tailed)

------------------------------------------------------------

Equal Variance         -1.9660        21            0.0627 B

Unequal Variance       -2.7220        21.67         0.0124 C

 

 

 

 

Interpretation

A   The F-ratio is statistically significant. Use the unequal variance test statistic.

B   For a 2-tailed test, the p-value represents the probability of making a type 1 error (concluding there is statistical significance when there is none).  Since there is about 1.2% (p < .0124) chance of making a type 1 error, which does not exceed the 5% error limit (p=.05, alpha), you conclude there is statistical significance.

C   If you had not checked for homogeneity of variance, you would have erroneously failed to find statistical significance. 

 


Google

 


Copyright 2015, AcaStat Software. All Rights Reserved.