Building SEMs in Lavaan (R) - How can I obtain better values of model fitness?

Pedro Luiz Silva de Miranda @Pedro_Luiz_Silva_De_Miranda

04 April 2018 0 672 Report

Hello ResearchGate community,

I have been working on a series of SEMs as a part of my PhD. All of them seem to be running smoothly, but I am not being able to obtain decent measures of model fitness (I'm focusing on chisquare, CFI, BIC e RMSEA) for some of them. I copied one of these models bellow. So far, I have tried all of the resources I could think of: I increased and decreased the number of indicators on my latent variables, I removed latent variables and used the indicators directly in the regressions, I removed outliers and I also changed the order of indicators in each one of my latent variables. Would anyone around here be able to spot something that might be triggering these low values of model fitness?

Some extra information on the model: response variable is categorical and has two levels only. All other variables are continuous and have been put in the same scale.

A big thank you to you all,

Pedro Miranda

Model:

model1 |z|) Std.lv Std.all

soil ~

climate 0.529 0.187 2.828 0.005 0.522 0.522

FireLOG ~

climate 0.446 0.156 2.862 0.004 0.405 0.355

Biome ~

climate 0.198 0.075 2.623 0.009 0.179 0.470

soil 0.034 0.053 0.643 0.520 0.031 0.082

FireLOG -0.085 0.037 -2.295 0.022 -0.085 -0.253

SB ~

cwdLOG -0.085 0.241 -0.353 0.724 -0.085 -0.031

Al.cmol. 0.200 0.579 0.345 0.730 0.200 0.076

DroughtLOG -0.160 0.092 -1.740 0.082 -0.160 -0.146

Covariances:

Estimate Std.Err z-value P(>|z|) Std.lv Std.all

.SB ~~

.FireLOG 0.310 0.200 1.553 0.120 0.310 0.195

.SandLOG ~~

.SB -0.939 0.236 -3.986 0.000 -0.939 -0.624

.Al.cmol. ~~

.DroughtLOG -0.204 0.215 -0.949 0.343 -0.204 -0.111

.SandLOG ~~

.DroughtLOG 1.059 0.320 3.307 0.001 1.059 0.415

.DroughtLOG ~~

.FireLOG 0.657 0.297 2.216 0.027 0.657 0.244

.cwdLOG 0.310 0.166 1.864 0.062 0.310 0.178

Variances:

Estimate Std.Err z-value P(>|z|) Std.lv Std.all

.pH 0.198 0.101 1.966 0.049 0.198 0.190

.SandLOG 1.016 0.175 5.819 0.000 1.016 0.985

.P.totalLOG 0.338 0.058 5.825 0.000 0.338 0.987

.Al.cmol. 0.526 0.134 3.937 0.000 0.526 0.424

.SB 2.231 1.018 2.191 0.028 2.231 0.258

.DroughtLOG 6.407 1.060 6.046 0.000 6.407 0.886

.mapLOG -0.021 0.009 -2.386 0.017 -0.021 -0.161

.cwdLOG 0.471 0.085 5.531 0.000 0.471 0.398

.MnTmpCldMntLOG 0.014 0.002 6.055 0.000 0.014 0.634

.FireLOG 1.135 0.190 5.979 0.000 1.135 0.874

.Biome 0.110 0.018 6.069 0.000 0.110 0.760

.soil 0.616 0.146 4.226 0.000 0.728 0.728

climate 0.824 0.503 1.640 0.101 1.000 1.000

Badges
Science topic

More Pedro Luiz Silva de Miranda's questions See All

Is it possible to convert soil variables (nutrients) that are in cmol/dm3 to cmol/kg?

10 November 2016 2,093 6 View

How climate change will influences human and animal behavioral change?

The role of climate change influencing the human behavior as well as economics interest

01 June 2021 0 0 View

Dear all, I was wondering if anyone knows whether MGLtools and Autodock can run on Mac OS?

I have tried to download the 64-bit version of MGLtools however, as many times as I have downloaded and uninstall the programs, an error arises that the app needs to be updated. Thank you.

03 March 2021 5,997 2 View

I got 02 moderator values defining Johnson-Neyman significance regions. Is it an error?

Hi everyone, I am conducting research for my Master's thesis. I am using PROCESS by Johnson-Neyman to analyze my Moderator model. I test the relationship between Public Service Motivation and...

03 March 2021 2,350 2 View

Logistical regression using SPSS for a dichotomous dependent variable, with an independent variable of 1, 2, 5 and 10 seconds?

I have an experiment with 28 participants The independent variable is the times 1, 2, 5, and 10 used as the cross hairs during a task These 4 times were tested using 4 different blocks, each...

03 March 2021 9,692 2 View

Do I need to do linear regression before running mediation analysis using PROCESS MACRO by Hayes ?

I just wanted to check if I need to run a linear regression separately if I am using PROCESS MACRO to run mediation analysis. Thank you.

02 March 2021 4,359 3 View

Do I need to strip the PVDF membrane before staining it with colloidal gold?

Dear Colleagues, After running Western blot on PVDF membrane and detection using ECL, I would like to stain my PVDF with colloidal gold to be able to allign the ECL image with total proteins on...

02 March 2021 7,829 3 View

PACYC PCR not working after several attempts. Would anyone have any suggestions?

So, I have been trying to run a pACYC PCR which will be used later on for a Gibson Assembly. However the PCR is not working. I have already tried gradient PCR and changing extension time; however...

02 March 2021 1,146 2 View

What SPSS analysis should I run with one IV (with two levels) and two DVs?

Hi, I am trying to figure out which test would be most appropriate to run for the following question: Is there a difference in task blood pressure between smokers and non-smokers? There are two...

01 March 2021 8,235 2 View

OpenBCI eeg--has anyone used them?

I'm looking to try out an off-the-shelf EEG set for some exploratory work. Curious if anyone has used the OpenBCI, and how much set-up work is required. I've heard they are more difficult to get...

01 March 2021 4,128 3 View

What are the countries most affected by extreme rainfall as a result of climate change?

Increased heat, drought and insect outbreaks, all associated to climate change, have increased wildfires. Decreasing water supplies, declined agricultural yields, health impacts in cities owing to...

01 March 2021 7,168 9 View