statistics.com

[frodo.jedi]

Hi all,
I have problems in understanding how to perform ANOVA with R.

I have a very simple case to analize. I did an experiment with a recognition task. I presented 3 types od stimuli: audio, visual and audio-visual.
I want to know if the differences are statistically significant, i.e. if with the audio-visual stimuli the performances are better than the audio stimuli or the visual stimuli.

Here the row data (frequencies):

| Correct answers | Wrong answers
Visual  | 49 | 31
Audio | 59 | 41
Audio-Visual | 80 | 20


Can you please give me a R code example in order to perform this analisis?
I really have problems in understanding, even if I tried to study different materials.

Help!

Thanks in advance

Frodo

[alethephant]

This is not actually an ANOVA application. It is a contingency table application.

> x<- matrix(c(49,31, 59,41, 80,20), ncol=2, byrow=TRUE)
> rownames(x)<- c('Visual','Audio', 'Audio-Visual')
> colnames(x)<- c('Correct','Wrong')
> x
Correct Wrong
Visual 49 31
Audio 59 41
Audio-Visual 80 20
> chisq.test(x)
Pearson's Chi-squared test
data: x
X-squared = 11.7579, df = 2, p-value = 0.002798

> chisq.test(x[1:2,])
Pearson's Chi-squared test with Yates' continuity correction
data: x[1:2, ]
X-squared = 0.0234, df = 1, p-value = 0.8783

> chisq.test(x[c(1,3),])
Pearson's Chi-squared test with Yates' continuity correction
data: x[c(1, 3), ]
X-squared = 6.7992, df = 1, p-value = 0.00912

> chisq.test(x[2:3,])
Pearson's Chi-squared test with Yates' continuity correction
data: x[2:3, ]
X-squared = 9.4351, df = 1, p-value = 0.002129

Row 3 has a different proportion correct than rows 1 and 2, which are indistinguishable.

[frodo.jedi]

Hello,
thanks a lot for your answer. I know the chi square test (also with R), and also for me it would be better to apply it for this case. But I must apply the ANOVA, and moreover I want to learn it.

Could you help me?

Cheers


Frodo

[frodo.jedi]

Hi all,
the formulation of my problem was not correct in order to justify the ANOVA.
With that data was better to use a chi-square test.

The ANOVA can be applied in this case if I formulate the problem in this way:

H=c(7,7,7,7,7,7,7,7,7,0,7,7,7,7,7)
H_1=c(7,7,7,6,7,7,7,7,7,1,7,7,6,7,7)
H_2=c(7,7,7,7,7,7,7,7,7,0,7,7,7,6,7)
H_S1=c(6,7,7,7,7,7,7,7,6,7,3,7,6,7,6)
H_S2=c(7,7,7,7,6,7,7,7,6,4,5,7,7,7,7)
H_S3=c(1,2,1,2,6,7,1,7,6,4,5,1,11,1)

I need to know if the differences between these groups are statistically significant. I need to find also the p-values.

At the moment I have problems with the R code. Please help.

Indeed from one side I do not understand the difference between the functions aov() and anova().
From the other side I am not able to apply them ;-(

Could you please give me a quick example with these data?

Thanks in advance

Best regards

Frodo