AP Statistics Curriculum 2007 ANOVA 2Way

From Socr

(Difference between revisions)
Jump to: navigation, search
Line 107: Line 107:
====Treatment Groups====
====Treatment Groups====
Treatement Groups are formed by making all possible combinations of the two factors. For example, if the first factor has 5 levels and the second factor has 6 levels, then there will be <math>5\times6=30</math> different treatment groups.
Treatment Groups are formed by making all possible combinations of the two factors. For example, if the first factor has 5 levels and the second factor has 6 levels, then there will be <math>5\times6=30</math> different treatment groups.
====Main Effect====
====Main Effect====

Revision as of 20:53, 28 June 2010


General Advance-Placement (AP) Statistics Curriculum - Two-Way Analysis of Variance (ANOVA)

In the previous section, we discussed statistical inference in comparing k independent samples separated by a single (grouping) factor. Now we will discuss variance decomposition of data into (independent/orthogonal) components when we have two (grouping) factors. Hence, this procedure called Two-Way Analysis of Variance.

Motivational Example

Suppose we want to study the dynamics of the US Consumer Price Index (CPI), which is a major economic indicator that measures the average price changes of consumer goods and services.

To motivate 2-way ANOVA we can focus on a 5-year annual summary of the CPI for different types of consumer good (items). The complete dataset can be found here and a small 5-year excerpt is included below. Clearly, we have two-factors that may explain the dynamics of the CPI - year and item-type.

Year CPI-Value Item-Code Year-Code Item
2003 180.5 1 1 Food
2003 184.8 2 1 Housing
2003 157.6 3 1 Transportation
2003 297.1 4 1 MedicalCare
2004 186.6 1 2 Food
2004 189.5 2 2 Housing
2004 163.1 3 2 Transportation
2004 310.1 4 2 MedicalCare
2005 191.2 1 3 Food
2005 195.7 2 3 Housing
2005 173.9 3 3 Transportation
2005 323.2 4 3 MedicalCare
2006 195.7 1 4 Food
2006 203.2 2 4 Housing
2006 180.9 3 4 Transportation
2006 336.2 4 4 MedicalCare
2007 203.3 1 5 Food
2007 209.586 2 5 Housing
2007 184.682 3 5 Transportation
2007 351.054 4 5 MedicalCare

Year Food Housing Transportation MedicalCare
2003 180.5 184.8 157.6 297.1
2004 186.6 189.5 163.1 310.1
2005 191.2 195.7 173.9 323.2
2006 195.7 203.2 180.9 336.2
2007 203.3 209.586 184.682 351.054

Using the SOCR Charts (see SOCR Box-and-Whisker Plot Activity and Dot Plot Activity), we can generate plots that enable us to compare visually the 4 different CPI items (food, housing, transportation and medical-care) across the 5 years.

We can also plot the time courses of these 4 CPI items (using the SOCR Line Chart.

Two-Way ANOVA Calculations

Let's make the following notation:

Two-way Model: yi,j,k = μ + τi + βj + γi,j + εi,j,k, for all 1\leq i\leq a, 1\leq j\leq b and 1\leq k\leq r. Here μ is the overall mean response, τi is the effect due to the ith level of factor A, βj is the effect due to the jth level of factor B and γi,j is the effect due to any interaction between the ith level of factor A and the jth level of factor B.
yi,j,k = the A-factor level i and B-factor level j, observation-index k measurement.
k = number of replicates.
ai = number of A-factor observations at level i, a= a_1 + a_2 + \cdots + a_I.
bj = number of B-factor observations at level j, b= b_1 + b_2 + \cdots + b_J.
N = total number of observations, N=a\times a \times b.
The mean of the A-factor group mean at level i and B-factor at level j is: \bar{y}_{i,j,.} = {\sum_{k=1}^{r}{y_{i,j,k}} \over r}
The grand mean is: \bar{y}=\bar{y}_{.,.,.} = {\sum_{k=1}^r{\sum_{i=1}^a {\sum_{j=1}^{b}{y_{i,j,k}}}} \over N}.

When an a \times b factorial experiment is conducted with an equal number of observation per treatment combination, and where AB represents the interaction between A and B, the total (corrected) sum of squares is partitioned as:

SS(Total) = SS(A) + SS(B) + SS(AB) + SSE


There are three sets of hypotheses with the two-way ANOVA.

The null hypotheses for each of the sets

  • The population means of the first factor are equal. This is like the one-way ANOVA for the row factor.
  • The population means of the second factor are equal. This is like the one-way ANOVA for the column factor.
  • There is no interaction between the two factors. This is similar to performing a test for independence with contingency tables.


The two independent variables in a two-way ANOVA are called factors (denoted by A and B). The idea is that there are two variables, factors, which affect the dependent variable (Y). Each factor will have two or more levels within it, and the degrees of freedom for each factor is one less than the number of levels.

Treatment Groups

Treatment Groups are formed by making all possible combinations of the two factors. For example, if the first factor has 5 levels and the second factor has 6 levels, then there will be 5\times6=30 different treatment groups.

Main Effect

The main effect involves the independent variables one at a time. The interaction is ignored for this part. Just the rows or just the columns are used, not mixed. This is the part which is similar to the one-way analysis of variance. Each of the variances calculated to analyze the main effects is like the between variances

Interaction Effect

The interaction effect is the effect that one factor has on the other factor. The degree of freedom here is the product of the two degrees of freedom for each factor.

Within Variation

The Within variation is the sum of squares within each treatment group. You have one less than the sample size (remember all treatment groups must have the same sample size for a two-way ANOVA) for each treatment group. The total number of treatment groups is the product of the number of levels for each factor. The within variance is the within variation divided by its degrees of freedom. The within group is also called the error.


There is an F-test for each of the hypotheses, and the F-test is the mean square for each main effect and the interaction effect divided by the within variance. The numerator degrees of freedom come from each effect, and the denominator degrees of freedom is the degrees of freedom for the within variance in each case.

Two-Way ANOVA Table

It is assumed that main effect A has a levels (and df(A) = a-1), main effect B has b levels (and (df(B) = b-1), r is the sample size of each treatment, and N = a\times b\times n is the total sample size. Notice the overall degree of freedom is once again one less than the total sample size.

Variance Source Degrees of Freedom (df) Sum of Squares (SS) Mean Sum of Squares (MS) F-Statistics P-value
Main Effect A df(A)=a-1 SS(A)=r\times b\times\sum_{i=1}^{a}{(\bar{y}_{i,.,.}-\bar{y})^2} {SS(A)\over df(A)} F_o = {MS(A)\over MSE} P(F(df(A),df(E)) > Fo)
Main Effect B df(B)=b-1 SS(B)=r\times a\times\sum_{j=1}^{b}{(\bar{y}_{., j,.}-\bar{y})^2} {SS(B)\over df(B)} F_o = {MS(B)\over MSE} P(F(df(B),df(E)) > Fo)
A vs.B Interaction df(AB)=(a-1)(b-1) SS(AB)=r\times \sum_{i=1}^{a}{\sum_{j=1}^{b}{((\bar{y}_{i, j,.}-\bar{y}_{i, .,.})+(\bar{y}_{., j,.}-\bar{y}))^2}} {SS(AB)\over df(AB)} F_o = {MS(AB)\over MSE} P(F(df(AB),df(E)) > Fo)
Error N-a\times b SSE=\sum_{k=1}^r{\sum_{i=1}^{a}{\sum_{j=1}^{b}{(\bar{y}_{i, j,k}-\bar{y}_{i, j,.})^2}}} {SSE\over df(Error)}
Total N-1 SST=\sum_{k=1}^r{\sum_{i=1}^{a}{\sum_{j=1}^{b}{(\bar{y}_{i, j,k}-\bar{y}_{., .,.})^2}}} ANOVA Activity

To compute the difference between the means, we will compare each group mean to the grand mean.

SOCR ANOVA Calculations

SOCR Analyses provide the tools to compute the 2-way ANOVA. For example, the ANOVA for the Consumer Price Index data above may be easily computed - see the image below. Note that SOCR ANOVA requires the data to be entered in the column format of the first table in this section.

Under the Graphs tab-pane, we can see a variety of plots demonstrating the ANOVA results.

The ANOVA table for these data is reported under the Results tab-pane.

Sample Size = 20
Dependent Variable = CPI-Value
Independent Variable(s) = Year Item
--- Two-Way Analysis of Variance Results ---
Variable: Year
Degrees of Freedom = 4
Residual Sum of Squares = 2624.8073168000
Mean Square Error = 656.2018292000
F-Value = 19.3405175758
P-Value = .0000363212
Variable: Item
Degrees of Freedom = 3
Residual Sum of Squares = 71900.0898230001
Mean Square Error = 23966.6966076667
F-Value = 706.3807145121
P-Value = .0000000000
Residual: Degrees of Freedom = 12
Residual Sum of Squares = 407.1463920000
Mean Square Error = 33.9288660000
F-Value = 322.4822657900
P-Value = 0.0
R-Square = .9945664582

Two-Way ANOVA Conditions

The Two-way ANOVA is valid if:

  • The populations from which the samples were obtained must be normally or approximately normally distributed.
  • The samples must be independent.
  • The variances of the populations must be equal.
  • The groups must have the same sample size.


Translate this page:









الامارات العربية المتحدة


इस भाषा में









Česká republika





Personal tools