Multifactor ANOVA - RESPUESTA _Unid compradas_

Analysis Summary Dependent variable: RESPUESTA _Unid compradas_ Factors: FILA Altura en estante_ COLUMNA _Presentacion_ _Tratamineto_Tipo Compota_ Number of complete cases: 25 The StatAdvisor --------------This procedure performs a multifactor analysis of variance for RESPUESTA _Unid compradas_. It constructs various tests and graphs to determine which factors have a statistically significant effect on RESPUESTA _Unid compradas_. It also tests for significant interactions amongst the factors, given sufficient data. The F-tests in the ANOVA table will allow you to identify the significant factors. For each significant factor, the Multiple Range Tests will tell you which means are significantly different from which others. The Means Plot and Interaction Plot will help you interpret the significant effects. The Residual Plots will help you judge whether the assumptions underlying the analysis of variance are violated by the data.

RESPUESTA _Unid compradas_

Scatterplot by Level Code

3 2,5 2 1,5 1 0,5 0 1 2 3 4 5

FILA Altura en estante_

Analysis of Variance for RESPUESTA _Unid compradas_ - Type III Sums of Squares -------------------------------------------------------------------------------Source Sum of Squares Df Mean Square F-Ratio P-Value -------------------------------------------------------------------------------MAIN EFFECTS A:FILA Altura en e 0,592554 4 0,148138 2,87 0,0698 B:COLUMNA _Present 0,312002 4 0,0780005 1,51 0,2598 C:_Tratamineto_Tip 3,84727 4 0,961818 18,66 0,0000 RESIDUAL 0,618504 12 0,051542 -------------------------------------------------------------------------------TOTAL (CORRECTED) 5,37033 24 -------------------------------------------------------------------------------All F-ratios are based on the residual mean square error.

The StatAdvisor --------------The ANOVA table decomposes the variability of RESPUESTA _Unid compradas_ into contributions due to various factors. Since Type III sums of squares (the default) have been chosen, the contribution of each factor is measured having removed the effects of all other factors. The P-values test the statistical significance of each of the factors. Since one P-value is less than 0,05, this factor has a statistically significant effect on RESPUESTA _Unid compradas_ at the 95,0% confidence level.

RESPUESTA _Unid compradas_

Means and 95,0 Percent LSD Intervals

2,6 2,4 2,2 2 1,8 1 2 3 4 5

FILA Altura en estante_

Multiple Range Tests for RESPUESTA _Unid compradas_ by _Tratamineto_Tipo Compota_ -------------------------------------------------------------------------------Method: 95,0 percent Duncan Level Count LS Mean LS Sigma Homogeneous Groups -------------------------------------------------------------------------------C 5 1,6302 0,10153 X A 5 2,021 0,10153 X E 5 2,3412 0,10153 X B 5 2,5468 0,10153 XX D 5 2,7364 0,10153 X -------------------------------------------------------------------------------Contrast Difference -------------------------------------------------------------------------------A - B *-0,5258 A - C *0,3908 A - D *-0,7154 A - E *-0,3202 B - C *0,9166 B - D -0,1896 B - E 0,2056 C - D *-1,1062 C - E *-0,711 D - E *0,3952 -------------------------------------------------------------------------------* denotes a statistically significant difference.

The StatAdvisor ---------------

This table applies a multiple comparison procedure to determine which means are significantly different from which others. The bottom half of the output shows the estimated difference between each pair of means. An asterisk has been placed next to 8 pairs, indicating that these pairs show statistically significant differences at the 95,0% confidence level. At the top of the page, 4 homogenous groups are identified using columns of X's. Within each column, the levels containing X's form a group of means within which there are no statistically significant differences. The method currently being used to discriminate among the means is Duncan's multiple comparison procedure. With this method, there is a 5,0% risk of calling one or more pairs significantly different when their actual difference equals 0.