One Way F test or One Factor Analysis of Variance (ANOVA) Objectives: 1.

To be able to know One Way F-test/ One Factor ANOVA in a nutshell and its importance 2. To be able to understand the Analysis of Variance and its components 3. To be able to apply the One-way F-test as statistical treatment in research Background about F test ANOVA:  It is an extension of t-test (Stark, 2010)  Both are used to find out the non-significance difference of means

 Both are used to find out the non-significance of difference between two groups, while the former is used to test the non-significance of difference among several groups.  The Analysis of Variance (ANOVA) F-test is a method for dividing the variation observed into different parts, each part assignable to a known source, cause, or factor. It was developed by Ronald Aylmer Fisher and reported by him in 1923.

Assumptions of f-test (the same as the assumptions ascribed for parametric tests) o Random selection of subjects from a normal population with equal variances; o Samples or groups are independent; and o Data being analyzed must be interval.

ALWAYS REMEMBER:  The One-Way-F-test or One-Factor Analysis of Variance (ANOVA) has only one factor being studied as the independent variable.

educational approaches. Raw Score method.x ) Between-groups Sum of Squares (SSb)  This is the sum of the squared deviations of individual group mean from the mean of the total distribution. You can solve between-groups sum of squares by determining the difference between each group mean and the mean of the total distribution (X-Xtotal). educational attainment. This is done by squaring or multiplying by itself the deviations from the mean of the group of scores and adding these deviation scores together (∑X2) b. X= a deviation score ( X . This is equal to the sum of the within-group sum of squares and betweengroups sum of squares. Understanding the Components of ANOVA (Analysis of Variance) Sum of Squares a. teaching methods. Within-groups Sum of Squares (SSw) This is the sum of the squared deviations of individual scores from their group mean.Xtotal)2 N Whereas. This is the sum of the squared scores (∑X2). Xtotal = mean of the total distribution. Lastly . socio-economic status or other factors that may have two or more levels. the within-groups sum of squares can be computed by just combining the sum of squares with each group. The. Thus. you square this difference and multiply it by the number of scores in the group. by formula: SSw = ∑X21 + ∑X22 + ∑X23 + ∑X24 Whereas. This is the sum of the squared deviations from a mean. Deviation Method. This independent variable may be different experimental conditions. guidance techniques. add terms or quantities by the formula: SSb = (X . values education approaches. by the formula: SS t = SSb + SSw or SS t = (X-X t )2 . N= the number of scores in any group Total Sum of Squares (SSb)  This is defined as the sum of the squared deviations of every raw score from the mean of the total distribution. X = mean of any group.

1 dfw = Nt – k whereas. MSb is mean square of the between groups SSb is the sum of squares of the between groups df b is degrees of freedom between groups Whereas. it is significant or the null hypothesis is rejected. Always remember If the F-value (computed) is equal to or greater than its tabular value. the formulas are:   dfb = k. by the formula: MSb = SSb / dfb       MSw = SSw / dfw Whereas. while if the F-value (computed) is less than the region of acceptance or tabular value. The above average. 1. Null hypothesis. Nt = total number of scores in all groups combined. average and below average teaching aptitude groups do not differ with respect to academic performance. X= a raw score in any group. Xt = the mean from all the groups combined.   Ho: X1 ≠ X2 ≠ X3 Ha: X1 = X2 = X3 . it is insignificant or the null hypothesis is accepted Suppose you will test that teaching aptitude varies by academic performance. k= the number of groups.Whereas. SSt = the total of the squares • Mean Square (MS)  This is defined as a measure of variation and is obtained by dividing between-groups sum of square or within-group of squares by the appropriate degrees of freedom. MSw is mean square of the within groups SSw is the sum of squares of the within-groups df w is degrees of freedom within-groups In determining the MSb and MSw you have to solve the appropriate degrees of freedom between and within.

8 + 77 = 252.2 10.2 0.44 87 83 84 80 419 3.80 X1 = 459/5 = 91.24 -0.8 7.2 1.2 10.44 26.8 14.04 -3.64 0.6 / 3 = 84.8 Compute the Mean for Each Group Below Average X3 78 75 77 79 76 385 x 1 -2 0 2 -1 x2 1 4 0 4 1 10 X3 = 395/5 = 77 Xtotal = 91.8 X2 = 419/5 = 83.2 459 1.8 0.24 92 0. Compute the Mean for Each Group Above Average X1 x x2 (N=5) Average X2 x x2 (N=5) 90 -1.04 85 -1.80 89 -2.84 95 3.2 .8 3.8 + 83.44 22.24 93 1.2 0.

average.2)2 5 = (7.8 59. and below average teaching aptitude groups differ significantly with respect to academic performance.2)2 5 = (57.97 6.6 274.8-84.97 = 55.84)5 = 288.93 55.6  Compute the Between-group sum of squares (SSb ) = (X1 .2)2 5 + (91.16)5 + (51.8  Compute the Between-groups and Within-groups Degrees Mean Square.4 MSw = 59.88 .21 Reject We can conclude that the above average.8 + 0. Compute the within-groups sum of squares (SSw) = X12 + X22 + X32 = 22.6 / 12 = 4.8 / 2 = 274.6)2 5 + (-4) 2 5 + (-7.76) 5 + (.21 df Sum of Squares Mean of Squares Tabular F0.2 = 548. Sources of Variation Between groups Within groups Total 2 12 14 548.Xtotal )2 N+(X3 . .80 + 10 = 59.80 + 26.05 3.4 4.8 + 259.Xtotal )2 N +(X2 .Xtotal )2 N = (91.2)2 5+ (91.97 Compute the F-ratio F= MSb / MSw = 274.8-84. MSb = 548.8-84.4 / 4.01 Computed F-test Ho.