Closed Yuxi913 closed 1 year ago
Dear Yuxi,
You can get more details about the estimation status by using the verify() function on your cSEM results object, e.g., verify(BD_all_res).
Usually, at least one of the absolute standardized factor loadings is larger than 1 or at least one reliability estimate is larger than 1.
Best regards, Florian
From: Yuxi Guo @.> Sent: zondag 17 september 2023 16:28 To: FloSchuberth/cSEM @.> Cc: Subscribed @.***> Subject: [FloSchuberth/cSEM] Why Estimate status doesn't match after adding a latent variable (Issue #509)
I firstly run a model below with three constructed latent variables, the summary suggested that estimation status is not ok. However, when I run a model later with the fourth latent variable that is constructed with these three latent variables, the summary suggested that estimation status is ok. I attached my models and their corresponding summaries below. Why the estimation status would change? What is the criteria of the estimation status? Thank you!
BD_all <- " PlantDiv =~ Plant_1 + Plant_2 InvertDiv =~ Invert_1 + Invert_2 FunDiv =~ Fun_1 + Fun_2
Pasture_type <~ Pasturetype Grazing_T <~ GrazingT Burning_T <~ BurningT
PlantDiv + InvertDiv + FunDiv ~ Pasture_type + Grazing_T + Burning_T"
BD_all_res <- csem(.model = BD_all, .data = BiodivAll) (summary_BD_all_res <- summarize(BD_all_res))
----------------------------------- Overview -----------------------------------
General information:
Estimation status = Not ok!
Number of observations = 78
Weight estimator = PLS-PM
Inner weighting scheme = "path"
Type of indicator correlation = Pearson
Path model estimator = OLS
Second-order approach = NA
Type of path model = Linear
Disattenuated = Yes (PLSc)
Construct details:
Name Modeled as Order Mode
Pasture_type Composite First order "modeB"
Grazing_T Composite First order "modeB"
Burning_T Composite First order "modeB"
PlantDiv Common factor First order "modeA"
InvertDiv Common factor First order "modeA"
FunDiv Common factor First order "modeA"
----------------------------------- Estimates ----------------------------------
Estimated path coefficients:
Path Estimate Std. error t-stat. p-value PlantDiv ~ Pasture_type -0.4481 NA NA NA PlantDiv ~ Grazing_T 0.2094 NA NA NA PlantDiv ~ Burning_T 0.1172 NA NA NA InvertDiv ~ Pasture_type 0.0199 NA NA NA InvertDiv ~ Grazing_T -0.0598 NA NA NA InvertDiv ~ Burning_T -0.1206 NA NA NA FunDiv ~ Pasture_type 0.1747 NA NA NA FunDiv ~ Grazing_T -0.1478 NA NA NA FunDiv ~ Burning_T -0.0934 NA NA NA
Estimated loadings:
Loading Estimate Std. error t-stat. p-value Pasture_type =~ Pasturetype 1.0000 NA NA NA Grazing_T =~ GrazingT 1.0000 NA NA NA Burning_T =~ BurningT 1.0000 NA NA NA PlantDiv =~ Plant_1 0.9300 NA NA NA PlantDiv =~ Plant_2 1.0310 NA NA NA InvertDiv =~ Invert_1 0.9281 NA NA NA InvertDiv =~ Invert_2 0.6397 NA NA NA FunDiv =~ Fun_1 0.9405 NA NA NA FunDiv =~ Fun_2 0.5979 NA NA NA
Estimated weights:
Weight Estimate Std. error t-stat. p-value Pasture_type <~ Pasturetype 1.0000 NA NA NA Grazing_T <~ GrazingT 1.0000 NA NA NA Burning_T <~ BurningT 1.0000 NA NA NA PlantDiv <~ Plant_1 0.4792 NA NA NA PlantDiv <~ Plant_2 0.5312 NA NA NA InvertDiv <~ Invert_1 0.6603 NA NA NA InvertDiv <~ Invert_2 0.4551 NA NA NA FunDiv <~ Fun_1 0.6870 NA NA NA FunDiv <~ Fun_2 0.4367 NA NA NA
Estimated construct correlations:
Correlation Estimate Std. error t-stat. p-value Pasture_type ~~ Grazing_T 0.0263 NA NA NA Pasture_type ~~ Burning_T 0.0263 NA NA NA Grazing_T ~~ Burning_T -0.0263 NA NA NA
------------------------------------ Effects -----------------------------------
Estimated total effects:
Total effect Estimate Std. error t-stat. p-value PlantDiv ~ Pasture_type -0.4481 NA NA NA PlantDiv ~ Grazing_T 0.2094 NA NA NA PlantDiv ~ Burning_T 0.1172 NA NA NA InvertDiv ~ Pasture_type 0.0199 NA NA NA InvertDiv ~ Grazing_T -0.0598 NA NA NA InvertDiv ~ Burning_T -0.1206 NA NA NA FunDiv ~ Pasture_type 0.1747 NA NA NA FunDiv ~ Grazing_T -0.1478 NA NA NA FunDiv ~ Burning_T -0.0934 NA NA NA
BD_all <- " PlantDiv =~ Plant_1 + Plant_2 InvertDiv =~ Invert_1 + Invert_2 FunDiv =~ Fun_1 + Fun_2 Biodiversity =~ PlantDiv + InvertDiv + FunDiv
Pasture_type <~ Pasturetype Grazing_T <~ GrazingT Burning_T <~ BurningT
Biodiversity ~ Pasture_type + Grazing_T + Burning_T"
BD_all_res <- csem(.model = BD_all, .data = BiodivAll) (summary_BD_all_res <- summarize(BD_all_res))
----------------------------------- Overview -----------------------------------
General information:
Estimation status = Ok
Number of observations = 78
Weight estimator = PLS-PM
Inner weighting scheme = "path"
Type of indicator correlation = Pearson
Path model estimator = OLS
Second-order approach = 2stage
Type of path model = Linear
Disattenuated = First stage: Yes
= Second stage: Yes
Construct details:
Name Modeled as Order Mode
Pasture_type Composite First order "modeB"
Grazing_T Composite First order "modeB"
Burning_T Composite First order "modeB"
PlantDiv Common factor First order "modeA"
InvertDiv Common factor First order "modeA"
FunDiv Common factor First order "modeA"
Biodiversity Common factor Second order "modeA"
----------------------------------- Estimates ----------------------------------
Estimated path coefficients:
Path Estimate Std. error t-stat. p-value Biodiversity ~ Pasture_type -0.7293 NA NA NA Biodiversity ~ Grazing_T 0.3921 NA NA NA Biodiversity ~ Burning_T 0.2413 NA NA NA
Estimated loadings:
Loading Estimate Std. error t-stat. p-value Pasture_type =~ Pasturetype 1.0000 NA NA NA Grazing_T =~ GrazingT 1.0000 NA NA NA Burning_T =~ BurningT 1.0000 NA NA NA PlantDiv =~ Plant_1 0.9390 NA NA NA PlantDiv =~ Plant_2 1.0211 NA NA NA InvertDiv =~ Invert_1 0.7219 NA NA NA InvertDiv =~ Invert_2 0.8224 NA NA NA FunDiv =~ Fun_1 1.2236 NA NA NA FunDiv =~ Fun_2 0.4595 NA NA NA Biodiversity =~ PlantDiv 0.5896 NA NA NA Biodiversity =~ InvertDiv -0.0881 NA NA NA Biodiversity =~ FunDiv -0.2279 NA NA NA
Estimated weights:
Weight Estimate Std. error t-stat. p-value Pasture_type <~ Pasturetype 1.0000 NA NA NA Grazing_T <~ GrazingT 1.0000 NA NA NA Burning_T <~ BurningT 1.0000 NA NA NA PlantDiv <~ Plant_1 0.4840 NA NA NA PlantDiv <~ Plant_2 0.5264 NA NA NA InvertDiv <~ Invert_1 0.5234 NA NA NA InvertDiv <~ Invert_2 0.5962 NA NA NA FunDiv <~ Fun_1 0.7998 NA NA NA FunDiv <~ Fun_2 0.3004 NA NA NA Biodiversity <~ PlantDiv 0.8607 NA NA NA Biodiversity <~ InvertDiv -0.1125 NA NA NA Biodiversity <~ FunDiv -0.3746 NA NA NA
Estimated construct correlations:
Correlation Estimate Std. error t-stat. p-value Pasture_type ~~ Grazing_T 0.0263 NA NA NA Pasture_type ~~ Burning_T 0.0263 NA NA NA Grazing_T ~~ Burning_T -0.0263 NA NA NA
------------------------------------ Effects -----------------------------------
Estimated total effects:
Total effect Estimate Std. error t-stat. p-value Biodiversity ~ Pasture_type -0.7293 NA NA NA Biodiversity ~ Grazing_T 0.3921 NA NA NA Biodiversity ~ Burning_T 0.2413 NA NA NA
- Reply to this email directly, view it on GitHubhttps://github.com/FloSchuberth/cSEM/issues/509, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AD5KRRHC5KODQVEEB76MF7LX24CFLANCNFSM6AAAAAA43U45BM. You are receiving this because you are subscribed to this thread.Message ID: @.**@.>>
Hi Florian,
Thank you so much for the quick response, which perfectly answered my question.
Best regards, Yuxi
From: FloSchuberth @.> Date: Sunday, September 17, 2023 at 11:10 AM To: FloSchuberth/cSEM @.> Cc: Guo,Yuxi @.>, Author @.> Subject: Re: [FloSchuberth/cSEM] Why Estimate status doesn't match after adding a latent variable (Issue #509) [External Email] Dear Yuxi,
You can get more details about the estimation status by using the verify() function on your cSEM results object, e.g., verify(BD_all_res).
Usually, at least one of the absolute standardized factor loadings is larger than 1 or at least one reliability estimate is larger than 1.
Best regards, Florian
From: Yuxi Guo @.> Sent: zondag 17 september 2023 16:28 To: FloSchuberth/cSEM @.> Cc: Subscribed @.***> Subject: [FloSchuberth/cSEM] Why Estimate status doesn't match after adding a latent variable (Issue #509)
I firstly run a model below with three constructed latent variables, the summary suggested that estimation status is not ok. However, when I run a model later with the fourth latent variable that is constructed with these three latent variables, the summary suggested that estimation status is ok. I attached my models and their corresponding summaries below. Why the estimation status would change? What is the criteria of the estimation status? Thank you!
BD_all <- " PlantDiv =~ Plant_1 + Plant_2 InvertDiv =~ Invert_1 + Invert_2 FunDiv =~ Fun_1 + Fun_2
Pasture_type <~ Pasturetype Grazing_T <~ GrazingT Burning_T <~ BurningT
PlantDiv + InvertDiv + FunDiv ~ Pasture_type + Grazing_T + Burning_T"
BD_all_res <- csem(.model = BD_all, .data = BiodivAll) (summary_BD_all_res <- summarize(BD_all_res))
----------------------------------- Overview -----------------------------------
General information:
Estimation status = Not ok!
Number of observations = 78
Weight estimator = PLS-PM
Inner weighting scheme = "path"
Type of indicator correlation = Pearson
Path model estimator = OLS
Second-order approach = NA
Type of path model = Linear
Disattenuated = Yes (PLSc)
Construct details:
Name Modeled as Order Mode
Pasture_type Composite First order "modeB"
Grazing_T Composite First order "modeB"
Burning_T Composite First order "modeB"
PlantDiv Common factor First order "modeA"
InvertDiv Common factor First order "modeA"
FunDiv Common factor First order "modeA"
----------------------------------- Estimates ----------------------------------
Estimated path coefficients:
Path Estimate Std. error t-stat. p-value PlantDiv ~ Pasture_type -0.4481 NA NA NA PlantDiv ~ Grazing_T 0.2094 NA NA NA PlantDiv ~ Burning_T 0.1172 NA NA NA InvertDiv ~ Pasture_type 0.0199 NA NA NA InvertDiv ~ Grazing_T -0.0598 NA NA NA InvertDiv ~ Burning_T -0.1206 NA NA NA FunDiv ~ Pasture_type 0.1747 NA NA NA FunDiv ~ Grazing_T -0.1478 NA NA NA FunDiv ~ Burning_T -0.0934 NA NA NA
Estimated loadings:
Loading Estimate Std. error t-stat. p-value Pasture_type =~ Pasturetype 1.0000 NA NA NA Grazing_T =~ GrazingT 1.0000 NA NA NA Burning_T =~ BurningT 1.0000 NA NA NA PlantDiv =~ Plant_1 0.9300 NA NA NA PlantDiv =~ Plant_2 1.0310 NA NA NA InvertDiv =~ Invert_1 0.9281 NA NA NA InvertDiv =~ Invert_2 0.6397 NA NA NA FunDiv =~ Fun_1 0.9405 NA NA NA FunDiv =~ Fun_2 0.5979 NA NA NA
Estimated weights:
Weight Estimate Std. error t-stat. p-value Pasture_type <~ Pasturetype 1.0000 NA NA NA Grazing_T <~ GrazingT 1.0000 NA NA NA Burning_T <~ BurningT 1.0000 NA NA NA PlantDiv <~ Plant_1 0.4792 NA NA NA PlantDiv <~ Plant_2 0.5312 NA NA NA InvertDiv <~ Invert_1 0.6603 NA NA NA InvertDiv <~ Invert_2 0.4551 NA NA NA FunDiv <~ Fun_1 0.6870 NA NA NA FunDiv <~ Fun_2 0.4367 NA NA NA
Estimated construct correlations:
Correlation Estimate Std. error t-stat. p-value Pasture_type ~~ Grazing_T 0.0263 NA NA NA Pasture_type ~~ Burning_T 0.0263 NA NA NA Grazing_T ~~ Burning_T -0.0263 NA NA NA
------------------------------------ Effects -----------------------------------
Estimated total effects:
Total effect Estimate Std. error t-stat. p-value PlantDiv ~ Pasture_type -0.4481 NA NA NA PlantDiv ~ Grazing_T 0.2094 NA NA NA PlantDiv ~ Burning_T 0.1172 NA NA NA InvertDiv ~ Pasture_type 0.0199 NA NA NA InvertDiv ~ Grazing_T -0.0598 NA NA NA InvertDiv ~ Burning_T -0.1206 NA NA NA FunDiv ~ Pasture_type 0.1747 NA NA NA FunDiv ~ Grazing_T -0.1478 NA NA NA FunDiv ~ Burning_T -0.0934 NA NA NA
BD_all <- " PlantDiv =~ Plant_1 + Plant_2 InvertDiv =~ Invert_1 + Invert_2 FunDiv =~ Fun_1 + Fun_2 Biodiversity =~ PlantDiv + InvertDiv + FunDiv
Pasture_type <~ Pasturetype Grazing_T <~ GrazingT Burning_T <~ BurningT
Biodiversity ~ Pasture_type + Grazing_T + Burning_T"
BD_all_res <- csem(.model = BD_all, .data = BiodivAll) (summary_BD_all_res <- summarize(BD_all_res))
----------------------------------- Overview -----------------------------------
General information:
Estimation status = Ok
Number of observations = 78
Weight estimator = PLS-PM
Inner weighting scheme = "path"
Type of indicator correlation = Pearson
Path model estimator = OLS
Second-order approach = 2stage
Type of path model = Linear
Disattenuated = First stage: Yes
= Second stage: Yes
Construct details:
Name Modeled as Order Mode
Pasture_type Composite First order "modeB"
Grazing_T Composite First order "modeB"
Burning_T Composite First order "modeB"
PlantDiv Common factor First order "modeA"
InvertDiv Common factor First order "modeA"
FunDiv Common factor First order "modeA"
Biodiversity Common factor Second order "modeA"
----------------------------------- Estimates ----------------------------------
Estimated path coefficients:
Path Estimate Std. error t-stat. p-value Biodiversity ~ Pasture_type -0.7293 NA NA NA Biodiversity ~ Grazing_T 0.3921 NA NA NA Biodiversity ~ Burning_T 0.2413 NA NA NA
Estimated loadings:
Loading Estimate Std. error t-stat. p-value Pasture_type =~ Pasturetype 1.0000 NA NA NA Grazing_T =~ GrazingT 1.0000 NA NA NA Burning_T =~ BurningT 1.0000 NA NA NA PlantDiv =~ Plant_1 0.9390 NA NA NA PlantDiv =~ Plant_2 1.0211 NA NA NA InvertDiv =~ Invert_1 0.7219 NA NA NA InvertDiv =~ Invert_2 0.8224 NA NA NA FunDiv =~ Fun_1 1.2236 NA NA NA FunDiv =~ Fun_2 0.4595 NA NA NA Biodiversity =~ PlantDiv 0.5896 NA NA NA Biodiversity =~ InvertDiv -0.0881 NA NA NA Biodiversity =~ FunDiv -0.2279 NA NA NA
Estimated weights:
Weight Estimate Std. error t-stat. p-value Pasture_type <~ Pasturetype 1.0000 NA NA NA Grazing_T <~ GrazingT 1.0000 NA NA NA Burning_T <~ BurningT 1.0000 NA NA NA PlantDiv <~ Plant_1 0.4840 NA NA NA PlantDiv <~ Plant_2 0.5264 NA NA NA InvertDiv <~ Invert_1 0.5234 NA NA NA InvertDiv <~ Invert_2 0.5962 NA NA NA FunDiv <~ Fun_1 0.7998 NA NA NA FunDiv <~ Fun_2 0.3004 NA NA NA Biodiversity <~ PlantDiv 0.8607 NA NA NA Biodiversity <~ InvertDiv -0.1125 NA NA NA Biodiversity <~ FunDiv -0.3746 NA NA NA
Estimated construct correlations:
Correlation Estimate Std. error t-stat. p-value Pasture_type ~~ Grazing_T 0.0263 NA NA NA Pasture_type ~~ Burning_T 0.0263 NA NA NA Grazing_T ~~ Burning_T -0.0263 NA NA NA
------------------------------------ Effects -----------------------------------
Estimated total effects:
Total effect Estimate Std. error t-stat. p-value Biodiversity ~ Pasture_type -0.7293 NA NA NA Biodiversity ~ Grazing_T 0.3921 NA NA NA Biodiversity ~ Burning_T 0.2413 NA NA NA
- Reply to this email directly, view it on GitHubhttps://github.com/FloSchuberth/cSEM/issues/509, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AD5KRRHC5KODQVEEB76MF7LX24CFLANCNFSM6AAAAAA43U45BM. You are receiving this because you are subscribed to this thread.Message ID: @.**@.>>
— Reply to this email directly, view it on GitHubhttps://github.com/FloSchuberth/cSEM/issues/509#issuecomment-1722498111, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AFB7MAPNRSWLYT2WVDHAO3DX24HGXANCNFSM6AAAAAA43U45BM. You are receiving this because you authored the thread.Message ID: @.***>
Dear Yuxi,
You are welcome. Since the issue is solved, I closed it.
Best regards, Florian
From: Yuxi Guo @.> Sent: maandag 18 september 2023 03:11 To: FloSchuberth/cSEM @.> Cc: Schuberth, Florian (UT-ET) @.>; Comment @.> Subject: Re: [FloSchuberth/cSEM] Why Estimate status doesn't match after adding a latent variable (Issue #509)
Hi Florian,
Thank you so much for the quick response, which perfectly answered my question.
Best regards, Yuxi
From: FloSchuberth @.<mailto:@.>> Date: Sunday, September 17, 2023 at 11:10 AM To: FloSchuberth/cSEM @.<mailto:@.>> Cc: Guo,Yuxi @.<mailto:@.>>, Author @.<mailto:@.>> Subject: Re: [FloSchuberth/cSEM] Why Estimate status doesn't match after adding a latent variable (Issue #509) [External Email] Dear Yuxi,
You can get more details about the estimation status by using the verify() function on your cSEM results object, e.g., verify(BD_all_res).
Usually, at least one of the absolute standardized factor loadings is larger than 1 or at least one reliability estimate is larger than 1.
Best regards, Florian
From: Yuxi Guo @.<mailto:@.>> Sent: zondag 17 september 2023 16:28 To: FloSchuberth/cSEM @.<mailto:@.>> Cc: Subscribed @.<mailto:@.>> Subject: [FloSchuberth/cSEM] Why Estimate status doesn't match after adding a latent variable (Issue #509)
I firstly run a model below with three constructed latent variables, the summary suggested that estimation status is not ok. However, when I run a model later with the fourth latent variable that is constructed with these three latent variables, the summary suggested that estimation status is ok. I attached my models and their corresponding summaries below. Why the estimation status would change? What is the criteria of the estimation status? Thank you!
BD_all <- " PlantDiv =~ Plant_1 + Plant_2 InvertDiv =~ Invert_1 + Invert_2 FunDiv =~ Fun_1 + Fun_2
Pasture_type <~ Pasturetype Grazing_T <~ GrazingT Burning_T <~ BurningT
PlantDiv + InvertDiv + FunDiv ~ Pasture_type + Grazing_T + Burning_T"
BD_all_res <- csem(.model = BD_all, .data = BiodivAll) (summary_BD_all_res <- summarize(BD_all_res))
----------------------------------- Overview -----------------------------------
General information:
Estimation status = Not ok!
Number of observations = 78
Weight estimator = PLS-PM
Inner weighting scheme = "path"
Type of indicator correlation = Pearson
Path model estimator = OLS
Second-order approach = NA
Type of path model = Linear
Disattenuated = Yes (PLSc)
Construct details:
Name Modeled as Order Mode
Pasture_type Composite First order "modeB"
Grazing_T Composite First order "modeB"
Burning_T Composite First order "modeB"
PlantDiv Common factor First order "modeA"
InvertDiv Common factor First order "modeA"
FunDiv Common factor First order "modeA"
----------------------------------- Estimates ----------------------------------
Estimated path coefficients:
Path Estimate Std. error t-stat. p-value PlantDiv ~ Pasture_type -0.4481 NA NA NA PlantDiv ~ Grazing_T 0.2094 NA NA NA PlantDiv ~ Burning_T 0.1172 NA NA NA InvertDiv ~ Pasture_type 0.0199 NA NA NA InvertDiv ~ Grazing_T -0.0598 NA NA NA InvertDiv ~ Burning_T -0.1206 NA NA NA FunDiv ~ Pasture_type 0.1747 NA NA NA FunDiv ~ Grazing_T -0.1478 NA NA NA FunDiv ~ Burning_T -0.0934 NA NA NA
Estimated loadings:
Loading Estimate Std. error t-stat. p-value Pasture_type =~ Pasturetype 1.0000 NA NA NA Grazing_T =~ GrazingT 1.0000 NA NA NA Burning_T =~ BurningT 1.0000 NA NA NA PlantDiv =~ Plant_1 0.9300 NA NA NA PlantDiv =~ Plant_2 1.0310 NA NA NA InvertDiv =~ Invert_1 0.9281 NA NA NA InvertDiv =~ Invert_2 0.6397 NA NA NA FunDiv =~ Fun_1 0.9405 NA NA NA FunDiv =~ Fun_2 0.5979 NA NA NA
Estimated weights:
Weight Estimate Std. error t-stat. p-value Pasture_type <~ Pasturetype 1.0000 NA NA NA Grazing_T <~ GrazingT 1.0000 NA NA NA Burning_T <~ BurningT 1.0000 NA NA NA PlantDiv <~ Plant_1 0.4792 NA NA NA PlantDiv <~ Plant_2 0.5312 NA NA NA InvertDiv <~ Invert_1 0.6603 NA NA NA InvertDiv <~ Invert_2 0.4551 NA NA NA FunDiv <~ Fun_1 0.6870 NA NA NA FunDiv <~ Fun_2 0.4367 NA NA NA
Estimated construct correlations:
Correlation Estimate Std. error t-stat. p-value Pasture_type ~~ Grazing_T 0.0263 NA NA NA Pasture_type ~~ Burning_T 0.0263 NA NA NA Grazing_T ~~ Burning_T -0.0263 NA NA NA
------------------------------------ Effects -----------------------------------
Estimated total effects:
Total effect Estimate Std. error t-stat. p-value PlantDiv ~ Pasture_type -0.4481 NA NA NA PlantDiv ~ Grazing_T 0.2094 NA NA NA PlantDiv ~ Burning_T 0.1172 NA NA NA InvertDiv ~ Pasture_type 0.0199 NA NA NA InvertDiv ~ Grazing_T -0.0598 NA NA NA InvertDiv ~ Burning_T -0.1206 NA NA NA FunDiv ~ Pasture_type 0.1747 NA NA NA FunDiv ~ Grazing_T -0.1478 NA NA NA FunDiv ~ Burning_T -0.0934 NA NA NA
BD_all <- " PlantDiv =~ Plant_1 + Plant_2 InvertDiv =~ Invert_1 + Invert_2 FunDiv =~ Fun_1 + Fun_2 Biodiversity =~ PlantDiv + InvertDiv + FunDiv
Pasture_type <~ Pasturetype Grazing_T <~ GrazingT Burning_T <~ BurningT
Biodiversity ~ Pasture_type + Grazing_T + Burning_T"
BD_all_res <- csem(.model = BD_all, .data = BiodivAll) (summary_BD_all_res <- summarize(BD_all_res))
----------------------------------- Overview -----------------------------------
General information:
Estimation status = Ok
Number of observations = 78
Weight estimator = PLS-PM
Inner weighting scheme = "path"
Type of indicator correlation = Pearson
Path model estimator = OLS
Second-order approach = 2stage
Type of path model = Linear
Disattenuated = First stage: Yes
= Second stage: Yes
Construct details:
Name Modeled as Order Mode
Pasture_type Composite First order "modeB"
Grazing_T Composite First order "modeB"
Burning_T Composite First order "modeB"
PlantDiv Common factor First order "modeA"
InvertDiv Common factor First order "modeA"
FunDiv Common factor First order "modeA"
Biodiversity Common factor Second order "modeA"
----------------------------------- Estimates ----------------------------------
Estimated path coefficients:
Path Estimate Std. error t-stat. p-value Biodiversity ~ Pasture_type -0.7293 NA NA NA Biodiversity ~ Grazing_T 0.3921 NA NA NA Biodiversity ~ Burning_T 0.2413 NA NA NA
Estimated loadings:
Loading Estimate Std. error t-stat. p-value Pasture_type =~ Pasturetype 1.0000 NA NA NA Grazing_T =~ GrazingT 1.0000 NA NA NA Burning_T =~ BurningT 1.0000 NA NA NA PlantDiv =~ Plant_1 0.9390 NA NA NA PlantDiv =~ Plant_2 1.0211 NA NA NA InvertDiv =~ Invert_1 0.7219 NA NA NA InvertDiv =~ Invert_2 0.8224 NA NA NA FunDiv =~ Fun_1 1.2236 NA NA NA FunDiv =~ Fun_2 0.4595 NA NA NA Biodiversity =~ PlantDiv 0.5896 NA NA NA Biodiversity =~ InvertDiv -0.0881 NA NA NA Biodiversity =~ FunDiv -0.2279 NA NA NA
Estimated weights:
Weight Estimate Std. error t-stat. p-value Pasture_type <~ Pasturetype 1.0000 NA NA NA Grazing_T <~ GrazingT 1.0000 NA NA NA Burning_T <~ BurningT 1.0000 NA NA NA PlantDiv <~ Plant_1 0.4840 NA NA NA PlantDiv <~ Plant_2 0.5264 NA NA NA InvertDiv <~ Invert_1 0.5234 NA NA NA InvertDiv <~ Invert_2 0.5962 NA NA NA FunDiv <~ Fun_1 0.7998 NA NA NA FunDiv <~ Fun_2 0.3004 NA NA NA Biodiversity <~ PlantDiv 0.8607 NA NA NA Biodiversity <~ InvertDiv -0.1125 NA NA NA Biodiversity <~ FunDiv -0.3746 NA NA NA
Estimated construct correlations:
Correlation Estimate Std. error t-stat. p-value Pasture_type ~~ Grazing_T 0.0263 NA NA NA Pasture_type ~~ Burning_T 0.0263 NA NA NA Grazing_T ~~ Burning_T -0.0263 NA NA NA
------------------------------------ Effects -----------------------------------
Estimated total effects:
Total effect Estimate Std. error t-stat. p-value Biodiversity ~ Pasture_type -0.7293 NA NA NA Biodiversity ~ Grazing_T 0.3921 NA NA NA Biodiversity ~ Burning_T 0.2413 NA NA NA
- Reply to this email directly, view it on GitHubhttps://github.com/FloSchuberth/cSEM/issues/509, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AD5KRRHC5KODQVEEB76MF7LX24CFLANCNFSM6AAAAAA43U45BM. You are receiving this because you are subscribed to this thread.Message ID: @.**@.mailto:***@***.******@***.***>>
- Reply to this email directly, view it on GitHubhttps://github.com/FloSchuberth/cSEM/issues/509#issuecomment-1722498111, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AFB7MAPNRSWLYT2WVDHAO3DX24HGXANCNFSM6AAAAAA43U45BM. You are receiving this because you authored the thread.Message ID: @.<mailto:@.>>
- Reply to this email directly, view it on GitHubhttps://github.com/FloSchuberth/cSEM/issues/509#issuecomment-1722635243, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AD5KRRADYB6SJVTO3F3RJYLX26NQRANCNFSM6AAAAAA43U45BM. You are receiving this because you commented.Message ID: @.**@.>>
I firstly run a model below with three constructed latent variables, the summary suggested that estimation status is not ok. However, when I run a model later with the fourth latent variable that is constructed with these three latent variables, the summary suggested that estimation status is ok. I attached my models and their corresponding summaries below. Why the estimation status would change? What is the criteria of the estimation status? Thank you!
BD_all <- " PlantDiv =~ Plant_1 + Plant_2 InvertDiv =~ Invert_1 + Invert_2 FunDiv =~ Fun_1 + Fun_2
Pasture_type <~ Pasturetype Grazing_T <~ GrazingT Burning_T <~ BurningT
PlantDiv + InvertDiv + FunDiv ~ Pasture_type + Grazing_T + Burning_T"
----------------------------------- Estimates ----------------------------------
Estimated path coefficients:
Path Estimate Std. error t-stat. p-value PlantDiv ~ Pasture_type -0.4481 NA NA NA PlantDiv ~ Grazing_T 0.2094 NA NA NA PlantDiv ~ Burning_T 0.1172 NA NA NA InvertDiv ~ Pasture_type 0.0199 NA NA NA InvertDiv ~ Grazing_T -0.0598 NA NA NA InvertDiv ~ Burning_T -0.1206 NA NA NA FunDiv ~ Pasture_type 0.1747 NA NA NA FunDiv ~ Grazing_T -0.1478 NA NA NA FunDiv ~ Burning_T -0.0934 NA NA NA
Estimated loadings:
Loading Estimate Std. error t-stat. p-value Pasture_type =~ Pasturetype 1.0000 NA NA NA Grazing_T =~ GrazingT 1.0000 NA NA NA Burning_T =~ BurningT 1.0000 NA NA NA PlantDiv =~ Plant_1 0.9300 NA NA NA PlantDiv =~ Plant_2 1.0310 NA NA NA InvertDiv =~ Invert_1 0.9281 NA NA NA InvertDiv =~ Invert_2 0.6397 NA NA NA FunDiv =~ Fun_1 0.9405 NA NA NA FunDiv =~ Fun_2 0.5979 NA NA NA
Estimated weights:
Weight Estimate Std. error t-stat. p-value Pasture_type <~ Pasturetype 1.0000 NA NA NA Grazing_T <~ GrazingT 1.0000 NA NA NA Burning_T <~ BurningT 1.0000 NA NA NA PlantDiv <~ Plant_1 0.4792 NA NA NA PlantDiv <~ Plant_2 0.5312 NA NA NA InvertDiv <~ Invert_1 0.6603 NA NA NA InvertDiv <~ Invert_2 0.4551 NA NA NA FunDiv <~ Fun_1 0.6870 NA NA NA FunDiv <~ Fun_2 0.4367 NA NA NA
Estimated construct correlations:
Correlation Estimate Std. error t-stat. p-value Pasture_type ~~ Grazing_T 0.0263 NA NA NA Pasture_type ~~ Burning_T 0.0263 NA NA NA Grazing_T ~~ Burning_T -0.0263 NA NA NA
------------------------------------ Effects -----------------------------------
Estimated total effects:
Total effect Estimate Std. error t-stat. p-value PlantDiv ~ Pasture_type -0.4481 NA NA NA PlantDiv ~ Grazing_T 0.2094 NA NA NA PlantDiv ~ Burning_T 0.1172 NA NA NA InvertDiv ~ Pasture_type 0.0199 NA NA NA InvertDiv ~ Grazing_T -0.0598 NA NA NA InvertDiv ~ Burning_T -0.1206 NA NA NA FunDiv ~ Pasture_type 0.1747 NA NA NA FunDiv ~ Grazing_T -0.1478 NA NA NA FunDiv ~ Burning_T -0.0934 NA NA NA
BD_all <- " PlantDiv =~ Plant_1 + Plant_2 InvertDiv =~ Invert_1 + Invert_2 FunDiv =~ Fun_1 + Fun_2 Biodiversity =~ PlantDiv + InvertDiv + FunDiv
Pasture_type <~ Pasturetype Grazing_T <~ GrazingT Burning_T <~ BurningT
Biodiversity ~ Pasture_type + Grazing_T + Burning_T"
----------------------------------- Estimates ----------------------------------
Estimated path coefficients:
Path Estimate Std. error t-stat. p-value Biodiversity ~ Pasture_type -0.7293 NA NA NA Biodiversity ~ Grazing_T 0.3921 NA NA NA Biodiversity ~ Burning_T 0.2413 NA NA NA
Estimated loadings:
Loading Estimate Std. error t-stat. p-value Pasture_type =~ Pasturetype 1.0000 NA NA NA Grazing_T =~ GrazingT 1.0000 NA NA NA Burning_T =~ BurningT 1.0000 NA NA NA PlantDiv =~ Plant_1 0.9390 NA NA NA PlantDiv =~ Plant_2 1.0211 NA NA NA InvertDiv =~ Invert_1 0.7219 NA NA NA InvertDiv =~ Invert_2 0.8224 NA NA NA FunDiv =~ Fun_1 1.2236 NA NA NA FunDiv =~ Fun_2 0.4595 NA NA NA Biodiversity =~ PlantDiv 0.5896 NA NA NA Biodiversity =~ InvertDiv -0.0881 NA NA NA Biodiversity =~ FunDiv -0.2279 NA NA NA
Estimated weights:
Weight Estimate Std. error t-stat. p-value Pasture_type <~ Pasturetype 1.0000 NA NA NA Grazing_T <~ GrazingT 1.0000 NA NA NA Burning_T <~ BurningT 1.0000 NA NA NA PlantDiv <~ Plant_1 0.4840 NA NA NA PlantDiv <~ Plant_2 0.5264 NA NA NA InvertDiv <~ Invert_1 0.5234 NA NA NA InvertDiv <~ Invert_2 0.5962 NA NA NA FunDiv <~ Fun_1 0.7998 NA NA NA FunDiv <~ Fun_2 0.3004 NA NA NA Biodiversity <~ PlantDiv 0.8607 NA NA NA Biodiversity <~ InvertDiv -0.1125 NA NA NA Biodiversity <~ FunDiv -0.3746 NA NA NA
Estimated construct correlations:
Correlation Estimate Std. error t-stat. p-value Pasture_type ~~ Grazing_T 0.0263 NA NA NA Pasture_type ~~ Burning_T 0.0263 NA NA NA Grazing_T ~~ Burning_T -0.0263 NA NA NA
------------------------------------ Effects -----------------------------------
Estimated total effects:
Total effect Estimate Std. error t-stat. p-value Biodiversity ~ Pasture_type -0.7293 NA NA NA Biodiversity ~ Grazing_T 0.3921 NA NA NA Biodiversity ~ Burning_T 0.2413 NA NA NA