MANOVA in SPSS (Multivariate Analysis of Variance) - Part 4

A step-by-step introduction to MANOVA is covered in this video (part 4).

Video Transcript: with each ANOVA evaluated at an alpha level of .025. Recall that was the Bonferroni adjustment or correction. Now I'm going to go down to the ANOVA results here which was right here in this gender row. So we'll be consulting these values to write the results. So our first ANOVA, I talk about the significant result first. I say there was a significant difference between males and females on empathic concern and I have F of 1 and 28, that's right here 1 and then 28 for error. One and 28 is equal to 6.72, p is .015 and partial eta-squared of .19. So you can see all of that right here. And then I said with females and I gave a mean there, 35.27, scoring higher than males, with a mean of 27. So once again we got that down here. Here's the 35.267 for females, and then 27 for males. And then going to our last ANOVA result, let's go back up here for a minute, here we have this result, perspective-taking. I say there was not a significant difference between males and females on perspective-taking, F of 1 and 28 that's the 1 and then 28 for error, which is right there, equals 2.33, which you see right here under F. And then p is .138, partial eta-squared of .08, and that's right there, the partial eta-squared. So the written results in summary once again we have our first sentence, this is just one of many ways you could do it, but the first sentence shows the results of the MANOVA and then after that I talked about the ANOVA, first of all saying what each ANOVA was conducted at, what alpha level, and then I gave the significant result and I discussed the group means, so the reader would know which group was higher, and then I gave the non significant results after that. That's really about it for our two group MANOVA. Once again this was the most basic kind of problem you can get with MANOVA, where we have two groups and two dependent variables. And one last thing before we close here, partial eta-squared, we can think about this as being similar to eta-squared in the univariate case, in the ANOVA case. It's a little bit different in terms of how it's calculated behind the scenes, but basically there's really no effect size standard for small, medium, and large for partial eta-squared for MANOVA but, as always, bigger is better. So the bigger the partial eta-squared, the stronger the effect, or the more variance that the different groups accounted for on the dependent variables. This concludes our example on MANOVA with two groups and two dependent variables. Thanks for watching.

For step by step help with statistics, with a focus on SPSS. Both descriptive and inferential statistics covered. For descriptive statistics, topics covered include: mean, median, and mode in spss, standard deviation and variance in spss, bar charts in spss, histograms in spss, bivariate scatterplots in spss, stem and leaf plots in spss, frequency distribution tables in spss, creating labels in spss, sorting variables in spss, inserting variables in spss, inserting rows in spss, and modifying default options in spss. For inferential statistics, topics covered include: t tests in spss, anova in spss, correlation in spss, regression in spss, chi square in spss, and MANOVA in spss. New videos regularly posted. Videos series coming soon include: multiple regression in spss, factor analysis in spss, nonparametric tests in spss, multiple comparisons in spss, linear contrasts in spss, and many more. Subscribe today!

[lionsandhyenas]

I've spent many long hours stumbling through unwieldy tutorials. This was exactly what I was looking for. I hope you've done several others

[atikhomthienthong]

The most comprehensive and easy to understand video on manova. Thank you.

[samula]

I watched many tutorials but only this was amazing. You have described everything with clear information. Big thanks to you for making such a nice helpful video.

[suhailazainol]

I was struggling for weeks looking for answer. This series of video really help. Great delivery, informative and well structured. Other series are great too. Thanks a lot!

[izhakama]

I am so lucky to watch your video, all complicated assumption about Manova was completely deleted from my mind. You make it so simple. Unbelievable... I don't know, but I wonder why such a smart and great people like you, so kind sharing your skills and knowledge for free just like that, I really appreciate. You are Awesome! 

[tresha-gayroper]

Excellent delivery, information was shared in a timely and coherent manner. This REALLY helped!

[epawelczuk]

One of the best explanation I have found, THANK YOU

[WaKeNinjaz]

lets say the multivariate table was not sign., are you still allowed to look at the between subj. table?

[jaysonclemente]

Neat and straightforward. Thank you so much, Sir!

[ICQwhereRU]

thank you, great video, simple and clear.

[sathishkumar]

Excellent video. Why didn't you make a video on K-means clustering. Waiting..

[kungfuskunk]

Um, Just a quick question, how did you determine the Bonferroni Corrected alpha value? Does it show on SPSS?

[islamalfahal]

How to do follow up analysis when I have 3 groups of independent variable??