Model fit during a Confirmatory Factor Analysis (CFA) in AMOS

This is a model fit exercise during a CFA in AMOS. I demonstrate how to build a good looking model, and then I address model fit issues, including modification indices and standardized residual covariances. I also discuss briefly the thresholds for goodness of fit measures. For a reference, you can use:
Hu & Bentler (1999) Cutoff criteria for fit indexes in covariance structure analysis: Conventional criteria versus new alternatives, Structural Equation Modeling: A Multidisciplinary Journal, 6:1, 1-55
Generally speaking, it is not good practice to covary error terms. See here for an explanation: statwiki.gaskination.com/index...

[@Gaskination]

Here's a fun pet project I've been working on: udreamed.com/. It is a dream analytics app. Here is the KZbin channel where we post a new video almost three times per week: kzbin.info/door/iujxblFduQz8V4xHjMzyzQ Also available on iOS: apps.apple.com/us/app/udreamed/id1054428074 And Android: play.google.com/store/apps/details?id=com.unconsciouscognitioninc.unconsciouscognition&hl=en Check it out! Thanks!

[@mikefung5463]

Hi Dr. Gaskin! You are helping many people. Do you know that?. After watching your tutorial, I can solve my problem. Thank you so much!!. Now I am preparing for final defense in this month. Thanks again!!. Wish you all the best!!. Mike (from Taiwan)!

[@heckler2.022]

I am feeling and doing exactly what you did 8 years ago, wow. preparing for my final defense this month and here to thank Dr. Gaskin

[@Gaskination]

Also take a look at my wiki: statwiki. kolobkreations. com for more info on thresholds for model fit.

[@sukhdeepkaursekhon2571]

Hiio Can i have guidance on CFA OF SERVQUAL SCALE please???

Hi James, I am still a bit confused about Modification index. If the Model fit is good and there are some MIs having large values, should I just leave the MI or should I covary the errors? Thank you

[@Gaskination]

I would recommend avoiding covarying errors if at all possible. So, if model fit is already good, then don't covary the errors.

@@Gaskination Thank you :)

[@MsSerenaSasi]

Thank you for the video!

[@Gaskination]

I usually do at least the following three: 1. CMIN/DF: should be between 1-3 (this is a measure of absolute fit) 2. CFI: should be greater than 0.95 (this is a measure of relative fit) 3. RMSEA: should be less than 0.6 or so (this is a parsimony adjusted measure of fit)

[@ThanhBinhVu-mj8eg]

Dear James, can you give some references for these fit indices. Thank you very much

[@Gaskination]

@@ThanhBinhVu-mj8eg Here you go: statwiki.gaskination.com/index.php?title=References#Model_Fit

[@lalaliza315]

Sir how can i improve my RMSEA value if it's showing .000 after one modifications. Plz help

[@Gaskination]

@@lalaliza315 RMSEA should be low. So, 0.000 is as "good" as you can get. No need to improve it.

[@lalaliza315]

@@Gaskination thank you so much sir for the reply...

[@hikakagirl]

Dr. Gaskin, just wanted to thank you for putting together such a great walk-through. I've had CFA / SEM covered in a few classes, but only conceptually. I've used your walk-through with some of the data from my dissertation, and it all makes so much more sense (and, I can actually do the analysis now). Thanks for sharing your knowledge!

[@pooranimani3925]

Sir, from the day i began my tool standardization i had sincerely learned using AMOS through your videos. I post this here as a gratitude, since this was the first video of your i watched. And today, when i have doubts on CFA or SEM, I jus type your name on youtube. Thankyou so much.

[@Gaskination]

You can look at standardized residual covariances instead. I show how to do that in this video.

[@GunniTheGunman]

This video helped me a great deal with writing my master's thesis! Thank you!

[@SuzetteScheuermann]

Dr. Gaskin, Thanks so much for the excellent step by step! It was priceless in my assistance with a graduate student soon to be PHD.

[@Gaskination]

smellofstrings: The reply function on KZbin video pages is not working currently, and KZbin is trying to fix it. So, until then, I will reply to your questions directly on your Channel instead of here.

[@Gaskination]

I'm not sure I understand the question. If you want to see how few items you can use to still result in a reliable latent construct, then you could use the new video I created to show how to improve reliability. But I'm not sure that was your question.

[@surfergirl0519]

Thank you so much for taking the time to post this! You may have literally saved my manuscript! I don't know why they don't teach us this in grad school or at least sell a good book on it.

[@NikiteshVadhani]

+surfergirl0519 without any offense to the great work James has done by uploading this video, there is a book by Hair et al. named Multivariate Data Analysis. It is fantastic!

[@Gaskination]

+Sabin Khadka, sorry for the delay in responding. KZbin has decided to stop notifying content creators when users post comments... In AMOS you can do it: kzbin.info/www/bejne/mqSyhGyqhs-rjZo

[@victoriaw7558]

May God (or whoever or whatever) bless you, Dr. Gaskin! You cou can spend weeks and months paying for courses that don't do anything except raise more questions & insecurities, and then comes along such a selfless individual who easily explains everything in a 10minute KZbin video. I got teary-eyed when I realized I was finally understanding something. Instant subscribe.

[@Gaskination]

Thanks for the kind feedback! Makes it all worth it :)

Hi James, one of the examiners asked me what kind of SEM I am using for analysis, is it PLS SEM or Covariance based SEM? I have been learning a lot from your videos, but I still cannot find the answer for that question. Thank you.

[@Gaskination]

Software like AMOS is covariance based. Software like SmartPLS is PLS SEM.

[@rurazar1686]

@@Gaskination This is another question entirely. But I was wondering if newer iterations of AMOS still require you to redefine the constrained regression weight of an item, upon removing it from the model? As was shown in 6:35

[@Gaskination]

@@rurazar1686 Yes, this is still not done automatically. IBM has not really updated the software, despite coming out with "new" versions each year.

[@rurazar1686]

@@Gaskination Thanks for your reply James! Quite interesting to see how a function like this has still not been implemented yet. I would imagine that this is not entirely a very complex feature to add. Moreso, just for ease of access and for convenience's sake. As I can potentially see this as being quite a repetitive task if let's say you might have a lot of constructs and items attributed to each construct in any given model.

[@Gaskination]

@@rurazar1686 agreed. I wish they would update their software. That would save me a lot of time building plugins and estimands :)

[@toanpham2040]

omg. This is exactly what i'm looking for. Thanks for your videos, it's so helpful to solve my problem with model fit. Love you from Vietnam

[@hthunebe1]

This is so great! Clear and simple and helpful. Thank you so much for all your videos!

[@LasanthaWickremesooriya]

Excellent presentation. Clarity at its best. Thank you very much.

[@tienganhcham]

Hi James, is it acceptable when the TLI and NFI are close to 0.9, for example, 0.87? All values in my analysis meet the goodness of fit but the TLI and NFI are not greater than 0.9. Should I remove some more items so that it will be greater than 0.9? Or it is still acceptable if the values are close to 0.9? Thanks again James

[@Gaskination]

I never report TLI and NFI (I usually just use CFI, RMSEA/PClose, and SRMR). Model fit has many measures. If there is enough evidence that model fit is good, then a couple metrics suggesting it is borderline is probably not a problem.

[@tienganhcham]

James Gaskin thanks, you saved my life

[@chaitanya183]

If I could tell you how much I appreciate your work. Thank you so so much

[@Argenfels]

That was exactly the problem. Thanks for this and all the other awesome videos and the tools on your website. You are simply the best.

[@011-salsabilaoktavianiputr7]

Hello Mr. James! Thank you for this video. After learning amos dor 2 months, I can solve my problem related to Badness of fit of my mediation model. God bless!!!

[@Sonnycpa]

Thank you James! You saved my life for my Ph.D. homework.

[@Gaskination]

These three can all do it. There are others, but these are the most popular. Stay tuned for a cool new video about how to automatically produce a CFA model in AMOS using the pattern matrix from the EFA. Hopefully I'll create this video this week.

[@elkiza10]

Finally I've got to use amos for my master degree. Definitely subscribe.

[@chaitanya183]

@Gaskination Thank you so much. I am going to share your tutorials with students at Information Systems department at Georgia State University. Really appreciate the work Sir.

[@dipankarbiswas3834]

I have published a paper in springer a renowned journal using your SEM techniques and cite your statwiki. Thank you for your education vedieos..

[@hannansyed1082]

Absolute champion, James Gaskin ❤

[@anasousa658]

Thank you, James! Great video :)

[@AbdulrahmanHariri]

When I was referring to consulting I meant like over the e-mail rather than training stuff :). I just found about your wiki/video series and I am going through them and making some notes! I am new to SEM and I heard it's pretty useful! Thanks!

[@Billy-dj8zw]

Thanks so much for posting this. It is perfect and helped me a lot.

[@nasimsalehi859]

Thanks very much for these very helpful programs! Much appreciated! Nasim

[@koztemel]

Hello James Useful video, I have learned to conduct CFA with amos within 5-10 minutes. Thank you very much. Kemal

[@Gaskination]

@chaitanya183 I've just received permission from the owner of the datasets. I'll post them on the wiki right now. They should be available within the next 20 minutes. Enjoy!

[@mille7610]

Thank you Dr. Gaskin.

[@ranywayz]

this is such an excellent video! thank you!

[@abbassyedgohar3824]

Hello .. Thanks a lot for your prompt replies. I agree with you regarding three factors of Burnout (Third one is LACK OF PERSONAL ACCOMPLISHMENT) but my pilot surveys revealed that Lack of Personal Accomplishment does not effect employee burnout, so I have ignored it for the time being. I shall browse your formative construct and shall reconsider it .. Really greatful.

[@henrylangam]

Your videos are really helpful. How I wish you're my professor...

[@Gaskination]

@chaitanya183 Thanks! I'm glad it is helping someone. I plan on continuing to make more videos. I hope you have found my wiki as well: statwiki. kolobkreations. com James

[@TheKindDoc]

Great video! Very clear and useful!

[@chaitanya183]

found them all. That is fantastic!! Thank You :)

[@Gaskination]

Yes, you need to select the exogenous variables (IVs) before you can covary them. AMOS doesn't know which variables you want to covary, so you need to select them. Watch the video more closely to see me do this around 2:40.

[@yv28w]

Woohoo, this has helped us a lot. Thank you!

[@Dr.Blockchain]

Thank you dear James.

[@Gaskination]

This is an acceptable approach. My recommendation is to use either a random sample of your data for each, or to use the same data that you will be using for the structural model. Most people do not have the luxury of an abundance of data, so they simply use everything they have for both EFA and CFA (which is what I have done here).

[@kaleem994]

great way of doing analysis.....

[@user-os4zq5hm4j]

I'm confused. So what you mean by this? Is it a good way or not. I'm new to statistics to be honest.

[@orpado1968]

A great help for my Ph.D study. I didn't tie the covariances in the errors and have low values when discriminant validity is done.

[@samrande]

thanks so much..I wish I could ask you a week ago for my problem....Wish u all the best.

[@suryamintu193]

Thank you a lot, this is so clear to understand

[@Gaskination]

Sounds like you already have sources to support your model fit. You don't need my additional confirmation. For thresholds I've put together, refer to my wiki: statwiki. kolobkreations. com

[@estelleghost]

Thank you so much, very helpful!

[@abbassyedgohar3824]

Thanks a lot dear ... I really appreciate your noble efforts ...

[@cxwww18]

Thanks James - it works now!

[@sabinkhdk]

Hi James- Thanks for all your helpful comments. If I want to compute factor scores for each individuals participants/factors from the CFA model, how would I do it? While doing EFA, SPSS would allow you to save the factors scores (using regression, Bartlett and Anderson-Rubin) but AMOS won't. I found a blog where it suggest to standardize the original scores and muliply with factor loading scores and sum them up. Is this a correct approach? If yes, do you know of any literature that I can cite for this approach. TIA

[@dn2042]

Hi Mr.Gaskin! Is there a maximum number of covarying the error terms by examining the modification indices? I mean can one say that X number of correlations is too much to be acceptable? I had to link 11 errors to each other in total (within the same factors), I know it is not a good way of doing it but I had to do it to reach the desirable cut-off values. Is there a refrence that I can support my self? Thank you.

[@abbassyedgohar3824]

Hello .. Thanks James .. You are right, as I have these names repeated in dataset. I shall try again with names changed .. Hats-off ....

[@Gaskination]

1. see dave kenny's website about this: davidakenny. net/ cm/ respec. htm 2. I have several videos about this. Go to my channel by clicking on my name. There you will see all my videos (about 80).

[@alexbarus1452]

Thanks so much, Pak Gaskin it helps me alot

[@Gaskination]

what version of AMOS are you using? RMR and GFI should come out in the model fit section. The estimate means and intercepts cannot run at the same time as certain other options (like modification indices). So you need to uncheck it, but you can only do that if you aren't missing any data :)

[@Gaskination]

Rely on the pattern matrix. You might also try the Maximum Likelihood approach (instead of Principle Components Analysis or Principle Axis Factoring) because this is the algorithm that AMOS uses during the CFA.

[@uyo77]

oh thanks for your time to reply my question, i figure it by myself, that there are some empty section there, the respondents doesnt fill it properly. ^^ thanks now i can finish my thesis, this video help me a lot

[@khajimarka]

My model is working now ...thaks to your video

[@TheNegk]

Thanks James, You rock!

[@sumedhachauhan]

Dear James Gaskin, Thanks for the wonderful online tutorial. I have a proposed model that includes 10 independent, 1 moderator and 2 dependent variables. While testing its “model fit” for the first time, I got GFI = 0.888 and the rest of the measures were just perfect. Then I performed following steps to improve GFI: 1) Co-varied the error terms of the same variables as per the modification indices. Then I got: GFI=0.890, P-value = 0.123, CMIN/DF = 1.051, AGFI=0.871, CFI=0.991, RMSEA=0.012, PClose=1.0 2) Used your stats tool package “Fit check”. It suggested dropping an item. I dropped that item and got: GFI=0.892, P-value = 0.158, CMIN/DF = 1.045, AGFI=0.873, CFI=0.992, RMSEA=0.011, PClose=1.0 3) Again used your stats tool package “Fit check”. It suggested dropping one more item. I dropped that item and got: GFI=0.896, P-value = 0.236, CMIN/DF = 1.033, AGFI=0.877, CFI=0.994, RMSEA=0.010, PClose=1.0 As you can see, all the values were perfect except GFI. There was no significant improvement in the value of GFI even on performing these three steps. Kindly suggest how the value of GFI can be improved in such cases.

[@Gaskination]

I usually have trouble with GFI when I have a lot of variables and/or when I have a lot fo sample size. These two things inflate the chi-square, and GFI is not robust to them. I would attribute it to model complexity in your case (not knowing the sample size).

[@sumedhachauhan]

James Gaskin Thanks a lot for the reply Dr. Gaskin. Sharma et al. (2005), among many others, articulate that in, context of SEM using AMOS, given the issues with GFI, it has lost its popularity in recent years and therefore its use should be discouraged. Despite this, recent research papers which use AMOS do consider GFI as a measure of model fit. What's your views regarding use of GFI? Sharma, S., Mukherjee, S., Kumar, A., and Dillon, W.R. (2005), "A simulation study to investigate the use of cutoff values for assessing model fit in covariance structure models," Journal of Business Research, 58 (1), 935-43.

[@Gaskination]

Sumedha Chauhan I never use it unless the reviewers specifically request it. I usually report CFI instead (as well as cmin/df, RMSEA).

[@neur0ptic]

Helpful video, thanks.

[@Gaskination]

I think they only show up if you check the box for standardized estimates in the output tab of the analysis properties window.

[@Gaskination]

Yes, they will be different. We would test measurement hypotheses (which are uncommon) by examining convergent and discriminant validity and reliability, as well as model fit. We test structural hypotheses (much more common) by developing a causal model and examining the regression weights. Hope this helps. I have videos about this stuff too.

[@Gaskination]

@AtyDeh It definitely works. I'm sorry you are not able to watch it. There may be filter issues at your location. If you are trying to access it from work, then they probably block youtube. If you cannot access it from home, then you probably just need to try again another time. In the meantime, feel free to refer to my wiki for info on model fit: statwiki. kolobkreations. com

[@wefald]

Thank you for this!

[@user-sd9rk6go4y]

Hi James, when I'm running this model AMOS is writing me an error: "The observed variable, Child.Prac, is represented by an ellipse in the path diagram" what can I do? Thanks in advance

[@Gaskination]

אור ענבי This means that you have an ellipse in your amos model that is named the exact same thing as a variable in your dataset. You'll need to name it something else.

[@kinner78utube]

Thank you so much for the video :) Am a huge fan :)

[@Gaskination]

Emanuele Fino If they still demonstrate sufficient discriminant validity, then just move forward. Otherwise, you might want to consider making them a 2nd order factor (reflective). This will probably turn out better results than a single factor with all items.

[@detful83]

Thanks you!

[@namiraratu7270]

James Gaskin if the data not good in all criteria lika cmin=10, Rmsea>0.08, the IFI, TLI,CFI >0.9 and AGFI, GFI >0.9, my result not good in all criteria. How could i do?

[@AbdulrahmanHariri]

Great! That's good news for me, kinda :). Thanks James!

[@Gaskination]

@ecmlau I don't understand what you mean by reducing the model, unless you mean to trim off the items that are not correlating very well with others. I don't have links for that, other than this video. But the general rule is that you want the average standardized loadings from items within a latent factor to be higher than the correlations between factors.

[@Gaskination]

@vyeniaras This tutorial is meant to be a mechanical demonstration. So, trimming is really more subjective than I make it out to be. To meet the criterion for convergent validity (AVE>0.50, CR>0.70) then loadings on a single factor should at least average out to > 0.70. However, if you are working with established measures, and you're not worried about the validities, you can probably accept loadings as low as 0.30 (several references for this). Accepting low loadings may cause other problems.

[@2aeng]

Thanks a ton James

[@Gaskination]

You are welcome to cite my materials (see the wiki's main page for how to do this) and/or put me in the acknowledgements section :) Thanks!

[@Gaskination]

@farispt The theoretical basis is that they are reflective and interchangeable items, which means that they were probably worded very similarly, which means that they probably have a systematically related error (rather than a causal one). So, yes, you can covary the error terms as long as they are within the same factor.

[@Gaskination]

Yes, this always happens. I nearly always have a few items make it through pretesting and pilot testing, but then fall out in the full study.

[@Gaskination]

1. Either use the default AMOS sets (first item for each factor) or place the constraint of 1 on the item that loaded the strongest in the EFA. 2. Covarying the error terms accounts for additional covariance represented in the covariance matrix. Model fit is the extent to which the proposed model (your CFA) accounts for the covariances in the data. So, naturally this will improve fit.

[@ThanomsilpJankanakittikul]

Thank you for the video

[@Gaskination]

Watch my playlist called "SEM Series". This will show you everything to do from start to finish. And yes, you need data to do a CFA.

[@Gaskination]

I didn't realize it was different in the new version. I'll have to check it out once my current license expires.

[@Gaskination]

As long as you have a minimum of three items on each factor, this is fine. Also, it depends a bit on if the scales come from published literature. If so, you may want to just check to see if others have also had problems with those items.

[@Gaskination]

This is an estimation problem due to items having really high correlation/communalities. To fix this, you might want to try using maximum likelihood (as opposed to principal axis factoring, or principal components analysis). You might also attempt to constrain the number of factors to a few alternative models (like try six instead of five). You might also see if there are items that are nearly identical in their wording, and eliminate one of them. Hope these suggestions help.

[@robertalia9060]

Very relevant video.

[@learner442]

thanks a lot Prof.

[@Gaskination]

These depend on many things. You want to decrease Chi-square while increasing degrees of freedom. The fastest way to do this is to address the modification indices. Also, you may have to identify items that are part of separate constructs but that are highly correlated. If possible, remove one of the two items in order to reduce cross loading.

[@user-gt6wz9ne2i]

Thanks! You help me a lot!

[@Gaskination]

1. You can make a second order factor (I have a video about this), or you can just put all the items into a single factor. 2. This depends on what scales you are using. If you are using your own scales, then fine. But if you are using existing scales from another published paper, then you need good justification for removing those items. Also, you should make sure you do not compromise content validity (meaning of construct). Also, it is best to have 3 or more items per factor.

[@AbdulrahmanHariri]

Great! I have also just came across Hair saying that a larger sample is always good. I guess I would have to follow your videos and also what the books recommend if the goodness of fit was hard to achieve. If it wasn't possible, I'll just randomly pick sub-sets based on countries or so on. Thank you!

[@Gaskination]

1. Perhaps you are accidentally looking at unstandardized loadings. Make sure you look at standardized. 2. Dave Kenny has something to say about covarying error terms: davidakenny. net/ cm/ respec. htm

[@Gaskination]

This may also be due to sample size. Large sample sizes artificially inflate the Chi-square. So, lower thresholds are acceptable for higher sample sizes. A "large" sample size is greater than 250. This is according to Hair et al 2010 "multivariate data analysis" book.

[@Gaskination]

David Kenny is a guru on many statistical matters (primarily mediation), and his thoughts on the matter can be found here: davidakenny. net/ cm/ respec

[@Gaskination]

1. Look at the loadings from the EFA to determine which items are cross-loading the strongest. These are candidates for removal, as are low loading items. 2. I almost never rely on standardized residual covariances. Rely first on the EFA, then on modification indices during the CFA. If you still have problems, then it may be due to outliers or odd distribution issues (such as kurtosis or skewness).

[@muhammadasif7691]

Hi James, in model fit during CFA one of the discriminant validity requirement is that Squared Inter-Construct Correlations < AVE. How can we measure Squared Inter-Construct Correlations during CFA model development in AMOS? (or may be on SPSS)

[@hdawod]

Thanks a lot Dr.James for sharing your valuable experience. May I ask about the max. number of items that could be deleted in one construct to achieve better fit? I attended a workshop before and they mentioned about 25% of the total number of items. but I couldn't fined a reference also :(

[@Gaskination]

Those decisions are driven by logic and theory. You should end up with as many factors as you intended during your theory development. Formative vs. reflective is determined by the relationship of the items within a factor (see Jarvis et al 2003 on specification). Second order is something we sometimes do when we have broader scope constructs (often formative - see Straub et al in MISQ I believe, not sure what year). Hope this helps.