Introduction to path analysis with manifest variables using AMOS Oct 2020

[@mastewalbitew3778]

Thanks Mike. It indeed hugely helped me start working on my dissertation!!!

[@mitrajazayeri1863]

Great way to start working on path analysis :) Thanks Mike, much appreciated!!!

[@firebirdpsych348]

Thank you so much for this - excellent video and very clear powerpoint.

[@mikecrowson2462]

Glad it was helpful!

[@origingaming4248]

I have a model with 6 latent variables contributing to one latent variable and that particular variable has its own observed variables as well cant figure out how to explain it or search for it in internet help!

[@i0love0skateboarding]

Hi Dr. Corwson, thank you very much for the video. How / with which tool can I calculate the a priori power analysis to determine the sample size? Regards

[@ThisIsTheX]

Great video, your explanations were very helpful! Thank you!

[@vitalisugwu1429]

Hi, thanks for the video. Please, are the variables in the path diagram in the video actually manifest or latent variables?

[@mikecrowson2462]

The boxes are all manifest variables. The circles represent residuals in the diagram.

[@yiings24]

Hi Mike, would you be able to advise how to obtain the R squared value for the entire model please, rather than for each endogeneous variable? Thank you!

[@mikecrowson2462]

Hi Ying, R square refers to the proportion of variation accounted for in a single endogenous variable (same as in the context of linear regression). There is no model level r- square when you have multiple endogenous variables. Cheers!

[@arslanhyderkhan]

Very informative video. I have a question if you can help. Do we need to draw the covariances among all the independent variables? Is there any resource on this issue? I will be highly obliged. Thanks in advance.

[@HealthbeautyluckyshahBlogspot]

Yes you do have to draw covariance

[@arslanhyderkhan]

@@HealthbeautyluckyshahBlogspot thanks

[@agilitydna]

Hi Dr Mike , Thanks for this comprehensive video. One question. in this path analysis , error terms d1 and d3 are co-related. Is that permissible? I understand this is normally done to get the model fit. however i have seen few papers advising against errior term corealtion. Hermida, R. 2015. "The Problem of Allowing Correlated Errors in Structural Equation Modeling: Concerns and Considerations," Computational Methods in Social Sciences (3:1), p. 5.. So I am bit lost here as my path analysis too, required error term corealtion to achive model fit. but would it be rejected ? What is your input in that regards or are there any reference which explain permissablity of error tearm corelation ?

[@grantaltay5633]

Any answers?

[@pmbees7454]

Thanks for this great example, but I did not see how you brought the data from spss!

[@mikecrowson2462]

Hi there. Go to the 6:20 mark in the video and I start talking about importation of the data there. You can also see it in the Powerpoint (drive.google.com/file/d/1U1ExQrBr_EOXioaYij85SKT-lLTXMiYr/view) on slide 5. Cheers!

[@pmbees7454]

Thanks professor🌷🙏

[@gollagariramakrishna9854]

Good presentation

[@I-AM-Yousuf]

Thanks sir so much

[@akonleestein585]

Hi. Do you have an email I can reach you at