Questions related to Structural Equation Modeling
I am attempting to conduct a genomic SEM with a GxE term and a term for the effect of G on E. The model would also include 11 other covariates. The study was a case-control design.
I used the R package gwsem to conduct a GxE analysis without the effect of G on E. However, I can not use it for the current analysis since the package does not permit a term to be a covariate and a dependent variable.
I have tried to create a custom model by writing mxPath statements from OpenMx, but I ran into two problems. One, I am not sure how to specify the interaction term. Two, I get an error message when I run mxRun that the E term is not specified although it is included in two path statements: once as from=E and once to=E.
How would I specify such a model in gwsem or OpenMx? Or is there another R package or program to create this type of model?
I would greatly appreciate any help in specifying my model.
I have extended the UTAUT2 model and I have already developed my model hypotheses. I read about various methods/techniques used such as (Factor Analysis, Partial Least Square (PLS), Structure Equation Model (SEM), Regression Analysis) and tools such as (SPSS, Smart-PLS, Mplus, R, PLS-graph, AMOS). But I am not sure which one to use.
Please I would like some advice about recommended techniques and tools. I am really looking to find out what you consider to be the most efficient method and your rationale as cost and time are limited factors.
1) In the first situation which I am facing, both indirect (a*b) and direct (c') effects are insignificant, while their sum, i.e. total effect [(a*b)+c'] is significant.
2) In the second scenario, the indirect effect is insignificant, while direct effect is significant, so there is no mediation, but yet, the total effect is significant.
I would appreciate if someone can share interpretation of these scenarios. What role does total effect play in such a scenarios? What is the best way to report such situations in a research paper?
P.S. I am using confidence interval method to assess significance (whether 0 falls in between LL and UL or not). Attached are the screenshots of both the scenarios.
Hi dear scholars! I have a 64 sample size for applying SEM. I know this sample size is samll. I have 7 latent variables. I am developing covariance-based SEM analysis using AMOS. my data is not normal that's why I want to apply Unweighted Least Square (ULS). when I select the ULS option in AMOS then I got no result. For ULS analysis does not run. I don't obtain Red arrow for obtaining results. I don't understand where the problem is. when I select the Maximum likelihood option, I obtain results, but my data is not normal and I want to apply ULS. I am using 64 countries' data yearly. I want to get international trade data from UNCTAD Statistics Database. but I did not understand the data from there. so I took data from the world bank. dear scholar, please guide me I am really worried. I will myself do work just guide me and tell my mistake. why ULS is not running and Maximumlikehod provides covariance greater than 1. I also don't want to run Maximumlikehod because my data is not normal.
I am planning to investigate the socio economic factors: age, income, gender, labor affecting for the adoption of farming practice in rural farmer community. Structural equation model is using to build a relationship among the factors. In what way do I need to prepare the questionnaire for that.
Are multigroup analyzes via structural equation model an alternative to investigate the influence of background variables, considering the model of the Theory of Planned Behavior?
If so, would this also be a way to deal with confounding factors?
I am looking for a brief and comprehensive resource that illustrates running various types of Structural Equation Modeling (SEM) in Mplus software. I am so grateful if you share any information about this topic.
I performed a CFA and got model fit. however, while performing path analysis by taking composite variable to test the hypothesis, CFI, GFI, Chi-square of SEM path model are above threshold limit but RMSEA is above 0.9. Is it ok to report only CFI, GFI and Chi-square? If report RMSEA too, Is model still called fit?
Hello! I'm currently testing out a SEM model using R for the first time and I was wondering whether I might have some help interpreting my RMSEA output. I received an RMSEA value .044 (CI .041, .046) and a p-value of 1. Why would the p-value be 1?
We have a Ga2O3 sample to perform cathodoluminescence with. The CL system uses an SEM machine for the incident beam. In SEM its traditional to plate the sample in Au/Pd, or something similar, prior to observation. Should the sample be plated in Au/Pd for cathodoluminescence as well? Will this greatly affect the results if it is plated versus not?
I performed a dry ball-on-disk wear test on In-718 plate, but in my wear profile, I am getting a "hump" in the middle of the wear track. By looking at the SEM images, it appears that this extra material that forms the "hump" is not uneroded material, but is just In-718 that has adhered to the wear track.
Does anyone know of any methods to remove this adhered material on the track? It could be mechanical or chemical, but my objective is to remove this material to get the proper profile of the wear track.
I am currently working on earthquake risk perception. I have information of perceived probability of occurrence of an earthquake, perceived damage to property, perceived damage to life, perceived level of fear of earthquake (on an ordinal scale). All these four risk perception variables, loads into single latent variable.Let's name the factor score value from factor analysis as a variable Overall Risk Perception. I have information on sociodemographic factors, no of earthquake experienced, time gap from last earthquake experienced etc which I can hypothesize that influence these four risk perception variables. I found from Multiple logistic regression that risk perception parameters have significant relation with four risk perception parameters and overall risk perception.
I would like to hypothesis perceived damage to life and perceived damage to property are related with perceived fear (it would be a two way arrow) and develop a SEM. I do not have any other latent variable. As I have only one latent variable will it be possible to develop Structural Equation Modelling.
Calling SEM experts and those with SEM in bacteriology. We ran an air dried layer of LB cultured bacteria over the SEM stub. This is like some canalicules being witnessed. can this be bacteria. ON LB agar, we see swarming effect of this bacteria. Please help?
I am trying to create an SEM for a microcosm experiment. However, some of the stressor effects or trophic interaction effects by the end of the experiment have disappeared but are evident when we look at the temporal data. My question is whether I can create an SEM that includes selective temporal data with the final data, or would this not make sense?
I want to know how to report such result in research where second order relationship comes into existence.
Variable A, B and C ; all are individual and separate constructs (First order) as per previous studies.
But in my survey, post checking validity parameters in CFA using AVE, MSV , ASV etc values , it is found that Variable A and Variable B are making second order constructs, then how to justify this second order relationship with theory if Previously no such relationship is established.
I am using Structural Equation Modeling (SEM) to determine the relationship between job demands and job strain. Five job demands are measured using 3 items, and job strain is measured using 4 items. A competing measurement model strategy utilizing a Confirmatory Factor Analysis (CFA) approach revealed that a model where job demands is estimated by a first-order five factor model comprised out of the five measured job demands and where job strain is estimated as a one-factor model fits the data best.
The next step in my analysis was to add directionality, resulting in the structural model. Estimating the standardized regression weights of the five job demands showed that two job demands, work overload and emotional demands, have a beta higher than |1|. I already checked for multicollinearity using the VIF score and this revealed that the highest VIF score, a score of 2.1, was assigned to emotional demands. This does not clearly indicate multicollinearity.
The emotional demands variable has a significant correlation of .42** with job strain, work overload has a significant correlation of .20** with job strain and emotional demands and work overload have a correlation .56**. Interestingly is that the beta of work overload equals -1.44, which is negative, whereas the its correlation is positive. Further, the beta of emotional demands is 2.11. When all variables are included, the R^2 in job strain equals 0.73.
When removing the work overload variable, the beta of emotional demands decreases to .58 and the R^2 decreases to 0.39. Likewise, when removing the emotional demands, the beta of work overload increases to -.08 and the R^2 decreases to 0.28. Looking at this effect, it seems to me that work overload is a suppressor variable in my model. However, I am not sure if this is the case, nor if it is correct for my standardized regression weights to be larger than |1|.
Does anyone know what to do with this issue?
If you require any additional information or data, please let me know.
Thank you in advance!
I am working on a machine learning based SEM image super resolution. To train my model, I got image pairs with two different resolutions (2048*2048 and 4096*4096).
For each image pair, both images were supposed to show the exact same region on a specimen.
However the image pairs turned out to be slightly misaligned. It is easiest to see on the edges of the attached images.
Is there a tool that is able to cut out the region that both images of one image pair have in common?
I am conducting Ph.D. in Finance in which I will use panel data methodology and data collection method will be secondary (Quantitative data). In one of the objective of thesis, I will use simultaneous equation model and in another, I will use structural equation model (SEM). But I do not know any expert who used to conduct workshops on these topics in case of secondary data. Can anyone tell me about the name of some famous experts, I should follow. Please share your knowledge and experience. Thanks a lot.
I want characterization of green synthesis of silver nanoparticles by SEM,TEM and XRD .
the problem is that my sample is liquid form and all above analysis required sample in power form or thin film
so kindly let me know how to make thin film for SEM ,TEM and XRD
I have four variables i.e. selfie posting, selfie viewing, group posting and group viewing, respondents were asked to rate frequently and infrequently similarly another variable self-esteem ( 10 statements), need for popularity (12 Statements) and life satisfaction(5 statements) which were asked on 7 points Likert scale (strongly disagree to strongly agree). My question is that how to deployed SEM using AMOS 20.0
The same has been employed in the mentioned paper. bt how?? Let anyone know me.. Thanks well in advance..... Wang, R., Yang, F., & Haigh, M. M. (2017). Let me take a selfie: Exploring the psychological effects of posting and viewing selfies and groupies on social media. Telematics and Informatics, 34(4), 274-283
I trust this email finds you well.
I am currently testing a theorical model using the PLS-SEM and Smartpls. The aim is to assess the influence of certain soft skills (empathy) on client relationship outcomes (e.g customer loyalty).
I would like to control to assess the effect of certain (control) variable on some of my dependent variables.
The issue that I am encountering is the following.
I have 5 control variables:
· Gender (w/ 2 groups: male female)
· Salary (w/ 5 groups: below 20k, 21-30k, 31-50k, 51-70k, +70k)
· Education (w/ 5 groups: no diploma, high school diploma, bachelor, master, PhD)
· Visit frequency (w/ 5 groups: once a year, once every 6 months, ect...)
If I understood things correctly to yield significant result and interpret findings correctly, I will need to use dummy variables. Which means that, based on the above, there will be a total of 17 control variables.
Based on your experience, is there a way to simplify the above? I was thinking to reduce the number of groups for each variable. For instance, instead of having 5 salary categories, reduce the number of categories down to 2 such as:
- Salary: above and below the national average salary.
- Education: those who have at least a master, those who do not.
What do you think of the above?
Of course, if you have any information / resources / material / that may allow me to address the above issue, that will be appreciated.
I thank you once more for your assistance and wish you a nice day.
Do we need to rescale items that have different categories for a latent variable in SEM? For instance, I have three items measured on a 1-5 scale, one measured on 1-4 scale, and one measured on a 1-6 scale. I have put them all together to create a latent variable and running an SEM analysis. I had the impression that categories of items do not matter to form a latent variable in SEM. But, a reviewer has asked to justify the method with citation of relevant reference, and I am needing a reference for this approach.
Is there any one can help me to answer these comments:
1/More information need to be added in SEM image based on shape and figure prints
2/Please comment on the SEM result. What insight can be obtained from the micrographs? is the applied magnification suitable???
FIGURE: Scanning electron micrographs showing structural changes of pretreated OPWP. (a) untreated OPWP (A and S). (b) Acid and steam explosion pretreatment of OPWP (A1 and S1).
The micrographs showing the surface morphology of untreated and pretreated Orange peel waste (OPWP) are depicted in Figure 3. From Figure 3 (a), the surface of untreated OPWP A and S is irregular, rough and uneven. Also, the particle size and shape are different. Whereas Figure 3 (b), it has more irregular, rougher and more porous surface than the untreated OPWP. In addition, it has a swollen structure. (Borah et al. 2016) described that high pressure and temperature pretreatment causes lignin to fluidize and coalesce, resulting in a globular shape. Thus, the dilute acid sulfuric removes the hemicellulose and causes holes on the biomass surface as seen in Fig. 3 (b). (Saha et al. 2016; Yi et al. 2013) demonstrate that the dilute acid has major effect on cellulosic fibers by compromising the integrity of the cell wall of orange peel with release of sugar molecules.
I have fit a random intercept factor model (Maydeu-Olivares & Coffman, 2006) in Mplus by the following syntax. One substantial factor where all item loadings are freely estimated and one random intercept factor where all item loadings are constrained to be 1. The random intercept factor variance is estimated.
ANALYSIS: ESTIMATOR = MLR;
ROTATION = GEOMIN(ORTHOGONAL);
MODEL: G BY a-a20 (*1); # G represents substantial factor
RI BY [email protected]; # RI represents random intercept/method factor
RI with [email protected];
But I got output as following. It looks like that the algorithm automatically takes G as the method factor because the factor loadings from this factor are much smaller than RI and so does its variance (if I delete [email protected] to let the variance be estimated too). What I want the algorithm does is to take G as the substantial factor and estimate its factor loadings and take RI as the method factor and only estimate its variance. Does anybody know how to specify this in Mplus? Thanks a lot!
Estimate S.E. Est./S.E. P-Value
A1 0.445 0.118 3.771 0.000
A2 -0.085 0.137 -0.624 0.533
A3 0.148 0.111 1.334 0.182
A4 0.106 0.118 0.898 0.369
A5 0.184 0.162 1.137 0.255
A6 0.239 0.095 2.523 0.012
A7 0.444 0.125 3.556 0.000
A8 0.193 0.093 2.077 0.038
A9 -0.008 0.084 -0.092 0.926
A10 0.395 0.133 2.972 0.003
A11 0.094 0.166 0.563 0.574
A12 0.258 0.137 1.879 0.060
A13 0.318 0.117 2.717 0.007
A14 0.712 0.091 7.819 0.000
A15 0.316 0.104 3.027 0.002
A16 0.504 0.129 3.911 0.000
A17 0.290 0.104 2.786 0.005
A18 0.957 0.086 11.064 0.000
A19 0.485 0.164 2.951 0.003
A20 0.484 0.122 3.974 0.000
A1 1.000 0.000 999.000 999.000
A2 1.000 0.000 999.000 999.000
A3 1.000 0.000 999.000 999.000
A4 1.000 0.000 999.000 999.000
A5 1.000 0.000 999.000 999.000
A6 1.000 0.000 999.000 999.000
A7 1.000 0.000 999.000 999.000
A8 1.000 0.000 999.000 999.000
A9 1.000 0.000 999.000 999.000
A10 1.000 0.000 999.000 999.000
A11 1.000 0.000 999.000 999.000
A12 1.000 0.000 999.000 999.000
A13 1.000 0.000 999.000 999.000
A14 1.000 0.000 999.000 999.000
A15 1.000 0.000 999.000 999.000
A16 1.000 0.000 999.000 999.000
A17 1.000 0.000 999.000 999.000
A18 1.000 0.000 999.000 999.000
A19 1.000 0.000 999.000 999.000
A20 1.000 0.000 999.000 999.000
G 0.000 0.000 999.000 999.000
A1 3.251 0.096 33.728 0.000
A2 3.246 0.098 32.988 0.000
A3 2.071 0.079 26.213 0.000
A4 1.976 0.083 23.804 0.000
A5 2.915 0.107 27.167 0.000
A6 1.773 0.069 25.742 0.000
A7 2.668 0.091 29.478 0.000
A8 2.431 0.077 31.708 0.000
A9 1.498 0.066 22.761 0.000
A10 2.545 0.092 27.682 0.000
A11 2.910 0.101 28.903 0.000
A12 2.720 0.098 27.665 0.000
A13 1.891 0.079 23.824 0.000
A14 2.346 0.083 28.217 0.000
A15 1.739 0.070 24.819 0.000
A16 3.057 0.091 33.654 0.000
A17 2.066 0.072 28.682 0.000
A18 2.445 0.089 27.498 0.000
A19 3.289 0.113 29.187 0.000
A20 2.654 0.098 27.014 0.000
G 1.000 0.000 999.000 999.000
RI 0.492 0.073 6.751 0.000
Reference: Maydeu-Olivares, A., & Coffman, D. L. (2006). Random intercept item factor analysis. Psychological methods, 11(4), 344.
The Probability Level (P-value?) of Structural Equation Model (SEM) is ,560. Some sources claim that a high Probability Level makes The Default Model insignificant. In contrast, some other sources claim that a low Probability Level indicates a poor fit. Which one is correct? How should the model be interpreted?
The sample size is 444. The Model Fit Indices' screen shoot in the attachment.
When we are evaluating the remineralization in the interface layer between the sealant and enamel using scanning electron microscopy (SEM)could we assess in the same time the mineral content in a quantitative way of the interface enamel?
Hello, I have a few samples of SS316, polished and etched. They are mounted in bakelite (which in non-conductive). I would like to take a few SEM images to see the microstructure. I was wondering if I deposit a carbon layer, is it going to cover the surface of the samples, so the microstructure will not be shown? Any thought on how to make it conductive.
As of Ni paste, I need to add carbon coating to avoid charging of bakelite.
I am going to fit structural equation modeling despite the violation of normality assumption,Am I correct to do SEM?
I tested an SEM model with 2 IV, 4 mediators and 1 DV on a sample of 1000 participants (see attached figure). Could you please help me to find an estimation for a good sample size using power analysis for this multiple-mediator model.
Hi, I am running path analysis with latent variables. My model fit indices are good, however some of the factor loadings are negative. Also some of the standardized estimate are more than 1 like chemical on N2O is more than 1 (1.60) and topographical on N2O is -1.03.
Is it alright to have negative loadings in the attached path diagram. How can i correct this diagram?
I have a dyadic dataset with distinguishable dyads (husbands and wives). I want to test a model with a predictor (X(f) X(m)), a mediator which is a similarity/difference in a trait, and dependent variable (Y(f) Y(m)). I would normally use SEM, but I'm not sure how to treat the difference score. Thank you for your help!
Hi, I want to ask about the total effect and indirect effect. Is it possible that one of my variables is insignificant and negative indirect effect and total effect? For instance, Brand Image (independent variable) has insignificant and negative effect (indirect and total) towards customer satisfaction (mediating variable) and Brand Loyalty (dependent variable).. But the rest of my independent variables are significant and have positive effect.. Is there any problem? Thank you..
I ran a meditational model using SEM. I have an independent variable (X), a mediator (M), and two outcomes (Y1 and Y2).
Using bootstrap I found a mediation effect of M between X and both Y1-Y2 (i.e., full mediation, the direct paths between X and Y1-Y2 become n.s. when in the model is introduced the mediator).
Using SEM, I want to deepen this result highlighting for which outcomes M is the best mediator.
Is it enough to check the magnitude of the two indirect effects?
Alternatively, I thought to constrain the coefficient of the paths M->Y1 and M->Y2 to be equal and then check the models' fit.
If the model fit of the constrained model would result worsen compared to the unconstrained model could help me to sustain that the two paths are likely different in favor of the strongest ones? Thus, if the coefficient of M->Y1 is stronger than M->Y2, then I would sustain that for Y1 (vs. Y2), M is the stronger mediator.
I have a few images of fungal biofilms acquired through SEM but they all have different magnifications (i.e. 160x, 140x, 110x and 100x). Does anyone know a way to change the magnification of images so I can have them all at the same magnification?
Thanks in advance!
I'm writing this post because there is limited help on how to use Mplus as a mac user (Catalina). This was a HUGE headache to figure out so I thought I would share...
Checking system preferences
Find the Mplus folder in your Applications folder. Double click on each of the following, and try to open all of them (diagrammer, mplus, mplus editor) one-by-one. If they don’t open, click on each of them one-by-one and add them under the system preference/security & privacy/GENERAL tab. Make sure this is done for the diagrammer, mplus, and mplus editor.
Then, click on the PRIVACY tab; and allow diagrammer, mplus, mplus editor to have full disk access, and access to files and folders.
Then click on startMplus, followed by: diagrammer, mplus, mplus editor (in any order)
Syntax and Data Files:
-You can use either .txt or .dat files EVEN on a mac!
-Save syntax and data files in same place (e.g., desktop)
-save .dat data file directly from your source
-copy and paste your numerical data into textedit, and save as plain text.
-format, ‘make plain text’, convert this text into plain text? Yes. If when you clicked format, it said ‘make rich text’, the file is already in the format you want it to be, so leave it alone.
-enter FILENAME.txt, include the .txt even if you have the box checked “if no file extension is provided, use “.txt”
Open Mplus Editor, click the folder and open the syntax file (FILE.inp).
Depending on whether you are using .dat or .txt enter this!
FILE IS 'FILE.dat' ;
FILE IS 'FILE.txt' ;
Save the output.
I am working on SEM, and I am now at that stage where I got to think on what are the functions of SEM? where does it fit in?
I expect the suggestion about how to calculate the particle size of hydroxyapatite extracted from biowastes.
1. data were collected by Non probability sampling Techniques.
2. Data is non- normal.
Thanks in Advance.
I am working on a Fractal analysis of some shale sample SEM images using FracLac. However, it doesn't include the Succolarity calculation. I hope someone can help me with this issue. I appreciate that.
I have chitosan-TPP nanoparticles, prepared by probe sonication. Basically, I add 4 mL of TPP solution (1.76 mg/ml) to 10 mL chitosan solution (3mg/ml). Then I probe sonicate it (5 min; 30-10 on/off). Finally I separate the NPs by centrifugation (15000 rpm, 20 min, room temp).
I get quite good DLS results (app 250 nm size; 0.1 PDI). The problem is, when I try to get SEM image, I get micrographs as attached (either with the ddH20 resuspended pellet or with NP suspension obtained right after the probe sonication).
I air dry the NP (1:100 dilution) directly on SEM stub. What is that background? It is also observed on the NP as well? Did anyone observe such a micrograph? What should I do? Really appreciate your help. Thank you in advance
I am conducting confirmatory factor analysis using lavaan in R with several both first- and second-order factors in the model (20 latent constructs and 97 items in total; n = 511; no missing values). After running the CFA, the model fit is not sufficient, but some low factor loadings, a couple Heywood cases and several indications from the modification index give some pointers for model improvement. Deleting some items from the model and re-structuring two factors based on an EFA eliminates Heywood cases and results in acceptable model fit (Chi-square=4117, DF=2646, CFI=.94, RMSEA=.038, SRMR=.052), however, the CFA of the adjusted model now returns the following error message: "covariance matrix of latent variables is not positive definite". There aren't any negative values in the covariance matrix though and also not in the correlation matrix.
I'm fairly new to this kind of statistical analysis and have no clue what causes this error and how to fix the issue. I'd appreciate any help. Please find attached the original and adjusted CFA measurement model as well as the covariance and correlation matrices of the adjusted model causing the NPD error.
Thanks a lot for your input!
This picture was taken during my recent research, on lignite deposits during the Pliocene, in France. ("Silica flowers"?)
Have you seen this structure before? personal SEM photos. Thanks a lot for your help.
I have used AMOS for confirming my structural model based on parallel mediation. However, since my trial version of SPSS has expired I would like to know , if I can use SMART-PLS or some other software to calculate VIF and effect size values and include it in my final analysis.
It would be very helpful if someone of you could tell me, how to test configural measurement invariance in an intervention study with two groups and two measurment points.
I was wondering, if I have to compare the SEM of the first measurement with the second measurement (both groups together) or if I have to compare the SEM of the first measurment with two SEM of the second measurement (one SEM for each intervention group).
Thank you in advance!
I performed E-beam lithography(EBL) with multiple doses of the same pattern to determine which dose the pattern is optimally produced.
Now the dvelopment of resist is done, and I want to see how the pattern was formed.
I think verification using SEM is a good way to do it, but I'm hesitant for several reasons.
1. Is CD-SEM typically used to image EBL result?
I heared CD-SEM is good method for imaging results of EBL, because it uses lower voltage.
Is CD-SEM good method for imaging EBL result?
Or is there other method commonly used for imaging EBL result?
2. CD-SEM can be replaced by typical FESEM with lowered voltage?
CD-SEM is usually compatible with 6 or 8 inch wafer, but my sample is piece(1 inch * 1 inch).
Therefore, I can't use CD-SEM.
CD-SEM can be replaced by typical FESEM with lowered voltage?
3. SEM imaging can damage EBL results, although it uses lowered voltage?
I know that E-beam resist is weak to electron beam energy.
CD-SEM, or FESEM with lowered voltage still damage E-beam resist?
If so, how to lower damaging from imaging?
I want to use the EBL results in the next process(lift-off, etching…) after imaging. Is it possible?
4. How to avoid charge-up in non-destructive method?
Since the EBL results are dielectric, so charge-up is inevitable in the SEM.
I know sputtering metal is good method, but I want to use EBL result in the next process(lift-off, etching…) after imaging.
In that case, how to avoid charge-up in non-destructive method?
I heared conductive paste, conductive tape, or electrification dissipating material(Espacer, AquaSave) can be alternatives.
Can I use them for SEM imaging of EBL results?
Thank you in advance.
It would be great to listen from you as this latent variable is an important one for my research !
I googled to conduct common method bias (CMB) tests in R but there is no information as such. Maximum information (including videos) is related to conducting CMB tests (like Harman's single factor) using SPSS or using AMOS (like common latent factor technique). All the constructs in my model are latent constructs and I am using covariance-based SEM techniques to analyze my model using Lavaan in R.
Now I want to conduct common method bias tests using R. Any help in this regard (e.g. sample code etc.) is welcome.
I tried synthesizing silver nanoparticles using plant extract. 1mM has not changed any colour. i then tried using 10mM and colour changed from green brown. i was monitoring the biosynthesis using UV-vis but then my peak remains at 328nm even after 72hours. i have no idea on how to explain the peak with the image i received from SEM. anyone to help on this please
I am currently working on a SEM with an N=274. The textoutput shows, that my model is unidentified, but I don't know why. Hopefully someone can point out the issue. Thank you in advance :)
I have to get an SEM image for my perovskite LED device cross section but I am not able to get a clear image. It is very blurry and I am not able to get any information from there. The machine I am using is Tescan FIB FERA. Can anyone help me with this?
I am analyzing a model using SEM, but my result seems hard to interpret the effect between non-formal learning experience(X), volition(Y), and expectancy(M) in the context of beginning farming.
1. indirect effect is positively significant (coef=0.172, p<.001)(The effect of X->M(coef=0.155, p<.001) and M->Y(coef=1.106, p<.001) is both positively significant), while direct effect(X->Y) is negatively significant(coef=-0.116, p<.001).
Q. I am confused about whether it can happen and how I could interpret the result if is possible. (See the path diagram).
2. I am concerned about the suppressor effect(X and M) because there is a low correlation between X and Y(r=.2045*) while a high correlation between X and M(r=.3497*). (correlation between M &Y is 0.6685). This positive correlation(X and Y) turns out to be negative when I analyze SEM. (When I check the partial correlation between X and Y controlling M, it turns out to appear -0.1066. )
Q. Can I say this is a suppressor effect? If it is, can someone help me with how I can deal with this suppressor effect? Should I describe all these situations in my paper? (or hopefully are there any other options to solve this problem?)
Note 1: All variables are continuous.
Note 2: observations are enough(n=407)
I would highly appreciate it if someone can help me!!! Thank you very much.
I'm writing a short paper using SEM (Structural Equation Modeling), and I just faced a problem while drawing a research model.
I wanted to use a variable which can show a 'paradox' effect; variables similar to 'distortion', but seems there isn't really such variables. I've been googling a lot of papers, but couldn't find any :(
If you know any, could you please share?
Even a short word will be a big help for me.
Thank you very much :D
Theory of Reasoned Action
Theory of Planned Behavior
I am working with Tungsten oxide nanoparticles and getting a mix of different morphologies, I wish to understand and predict the cause of the structures I am getting, the rods, the plates, and the valleys in between. I would also wish to learn about different morphologies in detail. Please suggest a book that has a good command of this.
I am characterising a volcanic deposit in which I am currently imaging at SEM the fine ash (>4 phi). For each sample I do a 500um-wide elementary cartography. I know that by superposing filter you can know which component are present but for the proportion I am worried since here I would have a ratio of surfaces and not of weight (As I have for bigger fractions between -7.0 and -0.5 phi).
Should I multiply the surface area of each component by it's density (using densities of the various components) assuming EVERY component is 1 um thick (which it is the worring assumption for me) ? This last assumption allow me to transform a surface to a volume and then to end up with a mass and not a mass.m-1.
Thank you in advance !
I'm trying to make a SEM model where my final endogenous variable is of unordered category (the variable is having three category which are not in any hierearchy/order). I want to know if it is possible to do this in AMOS, the AMOS documentation talks only aboit ordered categorical variable.
I have tried using Tool > Data Recode > Choosing the Variable and selecting Ordered Categories and clicking on Details > Then changing all three categories into the upper column of "Unordered Categories". This is not working and showing the error "Index was out of range"
We are running an SEM model for the scale development of a construct. We first ran a confirmatory factor analysis model. Since the data was non-normal, we used the ADF method of estimation. The CFI and the GFI are way below the required cutoff (around 0.72) but the RMSEA is doing very well, i.e. below 0.05. The SRMR is also 0.07. What does this imply? Which model fit statistics should be reported for ADF estimation in SEM? Is it acceptable in this case to report on RMSEA and RMR?
We are evaluating a proposal for SEM. The instrument is offered with a standard Tungsten filament or LaB6 filaments. I know LaB6 is better in terms of image quality, spot size, and filament life as compared to Tungsten filament (of course price is high). What are the other points we should consider such as high vacuum chamber, maintenance cost, operational cost, etc? Any help from an experienced user will be much appreciated.
how can I calculate the significance level (p-value) for total effects in an SEM?
I used SMSS AMOS to calculate a structural equation model (SEM). I applied the Maximum Likelihood Estimator. I get total, indirect and direct effects. However, I do not get significance levels for the total effects. Is there a way to do so? May I be able to derive the significance somehow from the direct and indirect effects?
Thank you so much for you answers!
Hi, I am working on my project for which I need assistance on this question: “Is it possible to test five continuous moderators on four independent variables and two dependent variables using SEM?” If yes, what technique or tool is appropriate? AMOS SEM, CFA, PATH ANALYSIS, MODERATED MULTIPLE REGRESSION OR HIERARCHICAL MODERATED MULTIPLE REGRESSION. I need a generous assistance to complete my project
What I want to do is to observe the cross section of a polymer/silver sample inkjet printed on thin kapton film under SEM. What I did to prepare the sample is :
Glue the sample on a thicker and more rigid substrate (this is to avoid distortion) and put the sample in a arcylic mould and wrap it with epoxy. After curing the epoxy I polish it mechanically to remove the front side of the epoxy and half of the sample , so that cross-section is revealed.
But what I observe in SEM is of un-satisfactory quality, I can find material in very un-realistic location. I feel like it is like polishing move some of the material elsewhere. I wonder does anyone has met similar problem?
with the "group" argument in the "sem" function in lavaan (R) I have created two separate models for men and women for my research. Accordingly to prior recommendations I have first tested for configural, metric, scalar and strict invariances, and the model worked well. Now I'm wondering if there is a way to compare beta coefficients between those two models, as I would like to see whether there are any significant differences between the same paths on models for different sexes. As such I would like to ask for your help!
Best regards and thanks!
I'm analyzing mediating using secondary data for 3 years. For now, I've done the regression analysis using Baron and Kenny method. My question is, can I also test the mediating effect using SEM? Since so far as I concern I can't find any related articles that use secondary data in testing mediating using SEM.
In a CFA, we have very good fit indices. For example, the CFI = 1. This, however, is not a just-identified model because degrees of freedom is not 0. When I see such super excellent fit indices in a not-just-identified model, I can't help but be suspicious.
Would such a well fitting CFA be appropriate to use in further analyses? Or should this particular CFA be thrown out?
I am university student trying to understand the interpretation of SEM. Specifically, I'd like to understand how the study of Seo & Park (2018) applied SEM in their study. The link of the study is this:
This is the part I'm having trouble understanding:
χ^2 = 576.887, df = 219, CMIN/DF = 2.634, p < 0.001, GFI = 0.855, AGFI = 0.817, RMR = 0.085, CFI = 0.918, TLI = 0.906, and RMSEA = 0.074
What is χ^2, df, CMIN/DF, p, GFI, AGFI, RMR, CFI, TLI, and RMSEA?
I'd appreciate any help.
I have used SEM before, but the results are not clear, and I have used an optical microscope ( Nikon Eclipse Lv100POL), but the light couldn't pass through. I am interested in impurities, voids, and pullouts.
I am looking for a script to run moderation analysis in R (which I am unable understand how to add to the following script for SEM wherein I want to test moderation of F upon relationship between D & E, i.e. E~D+F+D*F). The background of the model is that it is based on cross-sectional data and all are latent constructs:
A =~ A1+A2+A3
B =~ B1+B2+B3+B4
C =~ C1+C2+C3+C4
D =~ D1+D2+D3
E =~ E1+E2+E3
F =~ F1+F2+F3+F4
D ~ A+B+C
E ~ D
#Fitting SEM Model
modindices(fit1, sort. = T)
inspect(fit1, what = "std")