Type:	Package
Title:	Network Structural Equation Modeling
Description:	The network structural equation modeling conducts a network statistical analysis on a data frame of coincident observations of multiple continuous variables [1]. It builds a pathway model by exploring a pool of domain knowledge guided candidate statistical relationships between each of the variable pairs, selecting the 'best fit' on the basis of a specific criteria such as adjusted r-squared value. This material is based upon work supported by the U.S. National Science Foundation Award EEC-2052776 and EEC-2052662 for the MDS-Rely IUCRC Center, under the NSF Solicitation: NSF 20-570 Industry-University Cooperative Research Centers Program [1] Bruckman, Laura S., Nicholas R. Wheeler, Junheng Ma, Ethan Wang, Carl K. Wang, Ivan Chou, Jiayang Sun, and Roger H. French. (2013) <doi:10.1109/ACCESS.2013.2267611>.
Version:	0.6.2
Depends:	R (≥ 3.1.0)
Imports:	DiagrammeR (≥ 0.9.2), DiagrammeRsvg (≥ 0.1), htmlwidgets (≥ 1.2), knitr (≥ 1.20), magrittr (≥ 1.5), MASS (≥ 7.3-47), rsvg (≥ 1.1), svglite (≥ 1.2.1), png (≥ 0.1-7), segmented (≥ 0.5-3.0), gtools (≥ 3.5.0)
License:	GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
LazyData:	true
Encoding:	UTF-8
Suggests:	rmarkdown, testthat (≥ 3.0.0)
VignetteBuilder:	knitr
RoxygenNote:	7.2.3
Config/testthat/edition:	3
NeedsCompilation:	no
Packaged:	2023-09-06 14:46:15 UTC; hxh483
Author:	Wei-Heng Huang [aut], Nicholas R. Wheeler [aut], Addison G. Klinke [aut], Yifan Xu [aut], Wenyu Du [aut], Amit K. Verma [aut], Abdulkerim Gok [aut], Devin A. Gordon [ctb], Yu Wang [ctb], Sameera Nalin Venkat [ctb], HeinHtet Aung [ctb], Yeajin Jo [ctb], Xuanji Yu [ctb], Kemal Ozdemirli [ctb], Jonathan Gordon [ctb], Jayvic Cristian Jimenez [ctb], Jiqi Liu [ctb], Alan J. Curran [ctb], Justin S. Fada [ctb], Xuan Ma [ctb], Jennifer L. Braid [ctb], Jennifer L. W. Carter [ctb], Laura S. Bruckman [aut, cre], Roger H. French [aut, cph]
Maintainer:	Laura S. Bruckman <lsh41@case.edu>
Repository:	CRAN
Date/Publication:	2023-09-06 15:50:11 UTC

netSEM: Network Structural Equation Modeling

Description

The network structural equation modeling conducts a network statistical analysis on a data frame of coincident observations of multiple continuous variables [1]. It builds a pathway model by exploring a pool of domain knowledge guided candidate statistical relationships between each of the variable pairs, selecting the 'best fit' on the basis of a specific criteria such as adjusted r-squared value. This material is based upon work supported by the U.S. National Science Foundation Award EEC-2052776 and EEC-2052662 for the MDS-Rely IUCRC Center, under the NSF Solicitation: NSF 20-570 Industry-University Cooperative Research Centers Program [1] Bruckman, Laura S., Nicholas R. Wheeler, Junheng Ma, Ethan Wang, Carl K. Wang, Ivan Chou, Jiayang Sun, and Roger H. French. (2013) doi:10.1109/ACCESS.2013.2267611.

The R package 'netSEM' conducts a net-SEM statistical analysis (network structural equation modeling) on a dataframe of coincident observations of multiple continuous variables.

Author(s)

Maintainer: Laura S. Bruckman lsh41@case.edu (ORCID)

Authors:

• Wei-Heng Huang wxh272@case.edu (ORCID)

• Nicholas R. Wheeler nrw16@case.edu (ORCID)

• Addison G. Klinke agk38@case.edu (ORCID)

• Yifan Xu yxx218@case.edu (ORCID)

• Wenyu Du wxd97@case.edu (ORCID)

• Amit K. Verma aak126@case.edu (ORCID)

• Abdulkerim Gok axg515@case.edu (ORCID)

• Roger H. French rxf131@case.edu (ORCID) [copyright holder]

Other contributors:

• Devin A. Gordon dag109@case.edu (ORCID) [contributor]

• Yu Wang yxw880@case.edu (ORCID) [contributor]

• Sameera Nalin Venkat sxn440@case.edu (ORCID) [contributor]

• HeinHtet Aung hxh483@case.edu (ORCID) [contributor]

• Yeajin Jo yxj414@case.edu (ORCID) [contributor]

• Xuanji Yu xxy530@case.edu (ORCID) [contributor]

• Kemal Ozdemirli kxo146@case.edu [contributor]

• Jonathan Gordon jgordon5@bowdoin.edu (ORCID) [contributor]

• Jayvic Cristian Jimenez jxj440@case.edu (ORCID) [contributor]

• Jiqi Liu jxl1763@case.edu (ORCID) [contributor]

• Alan J. Curran ajc269@case.edu (ORCID) [contributor]

• Justin S. Fada jsf77@case.edu (ORCID) [contributor]

• Xuan Ma xxm115@case.edu (ORCID) [contributor]

• Jennifer L. Braid jlb269@case.edu (ORCID) [contributor]

• Jennifer L. W. Carter jwc137@case.edu (ORCID) [contributor]

References

1. Bruckman, Laura S., Nicholas R. Wheeler, Junheng Ma, Ethan Wang, Carl K. Wang, Ivan Chou, Jiayang Sun, and Roger H. French. "Statistical and Domain Analytics Applied to PV Module Lifetime and Degradation Science." IEEE Access 1 (2013): 384-403. doi:10.1109/ACCESS.2013.2267611

2. Bruckman, Laura S., Nicholas R. Wheeler, Ian V. Kidd, Jiayang Sun, and Roger H. French. "Photovoltaic Lifetime and Degradation Science Statistical Pathway Development: Acrylic Degradation." In SPIE Solar Energy+ Technology, 8825:88250D-8. International Society for Optics and Photonics, 2013. doi:10.1117/12.2024717

IV features data

Description

The dataset contains current-voltage (I-V) curve scans and the I-V features data obtained by the I-V features extraction algorithm of the ddiv R package. These extracted I-V features are for the brand A photovoltaic (PV) modules exposed to damp heat indoor accelerated test conditions of 85 degrees C and 85 The measurement step-wise through time at 500 hour time intervals. The raw data is provided by the SunEdison company. The I-V features include max power (Pmp), short circuit current (Isc), current at max power(Imp), fill factor (FF), series resistance (Rs), shunt resistance (Rsh), open circuit voltage (Voc), and voltage at max power (Vmp). The shunt resistance (Rsh) is too noisy to use for netSEM modeling. After checking the correlation between Isc, Imp, Voc, Vmp, FF, Rs. FF, Rs, Vmp are highly correlated, so we randomly select one to be contained in the model. Here we choose Isc, Imp, Rs and Voc to be contained in the model and these four I-V features show no indication of high correlation. The trend of the I-V features are related to the mechanisms of PV degradation. The variable 'dy' is time that has been converted into decimal year in which 1 means 1 year. We would use this dataet to buit <S|M|R> models with time as the stressor, and four I-V features as tracking variables of the degradation mechanisms and max power as the reponse.

Usage

data(IVfeature)

Format

A data frame with 20 rows and 9 variables:

Pmp

max power at the measurement step

dy

the exposure time after been converted into decimal year

Isc

short circuit current

Imp

current at max power

Rs

series resistance

Voc

open circuit voltage

Author(s)

Jiqi Liu, Alan Curran, Justin S. Fada, Xuan Ma, Wei-Heng Huang, Jennifer L. Braid, Roger H. French

Source

Solar Durability and Lifetime Extension (SDLE) Research Center, Case Western Reserve University

Dataframe for PV module degradation under Damp Heat Exposure

Description

In this example, full size PV modules were exposed to damp heat conditions (relative humidity of 85% and a chamber temperature of 85 deg C) for 4000 hours and the degradation in PV power output was measured at specific time intervals, or time steps. In addition, some modules were withdrawn from the study at these time steps, to produce a retained sample library with samples available for each time step. These retained samples were dismantled destructively in order to determine the changes occurred in the module materials. In the resulting netSEM model, time was used as a proxy for damp heat exposure stress (S) variable and $P_max$ (maximum power generated by the modules) was used as the performance level response ($R$) variable, several mechanistic variables ($M$) were obtained through chemical evaluation methods, including FTIR and TGA on EVA encapsulant. This example also demonstrate how to add latent variables.

Usage

data(PVmodule)

Format

A 16 by 4 data frame of continuous variables

Pmax

Maximum power generated by PV modules

Time

Time in decimal years for exposure of PV modules to damp heat conditions

IREVA

Infrared signal measurement that tracks hydrolysis of EVA encapsulant

TGA

Thermogravimetric analysis of PV module to track formation of acetic acid

Author(s)

Menghong Wang, Abdulkerim Gok, Roger H. French

Source

Solar Durability and Lifetime Extension (SDLE) Research Center, Case Western Reserve University

A data frame of an acrylic polymer degradation experiment

Description

This data set is from a study of photodegradation of acrylic polymer. In this work, polymeric samples were exposed to different levels of light exposures and resulting optical changes were determined through optical spectroscopy. *IrradTot* (total applied irradiance) is the main exogenous variable and *YI* (yellowness index) is the endogenous variable (response). The other columns in the data set (*IAD1*, *IAD2*, *IAD2p*, and *IAD3*) are induced absorbance to dose values extracted from optical absorbance spectra as single metrics and used as intermediate unit level endogenous (response) variables in the netSEM analysis. Photodegradation in a stress and response framework: poly(methyl methacrylate) for solar mirrors and lens. Doi: 10.1117/1.JPE.2.022004

Usage

data(acrylic)

Format

A 357 by 6 data frame of continuous variables

YI

Yellowness index of acrylic sample

IrradTot

Total applied solar irradiance

IAD1

Induced Absorbance to Dose of the Fundamental Absorption Edge - Optical absorbance at 275 nm

IAD2

Induced Absorbance to Dose of the Tinuvin light stabilizer doublet peak at 298 nm

IAD2p

Induced Absorbance to Dose of the Tinuvin light stabilizer doublet peak at 339 nm

IAD3

Induced Absorbance to Dose in the yellowing region, at 440 nm

Author(s)

Myles P. Murray, Laura S. Bruckman, Roger H. French

Source

Solar Durability and Lifetime Extension (SDLE) Research Center, Case Western Reserve University

Backsheet PET/PET/EVA Degradation

Description

A backsheet is a mulit-layer polymer laminate used as the back surface of a crystalline silicon photovoltaic (PV) module that is designed to protect the inner components of the PV module. Typical backsheets consist of three layers of polymers to control diffusion of water and oxygen, as well as to protect human beings from electrical shock. It is critical that your PV module solar panel has a backsheet that is of high quality and can withstand various environmental elements for its 25 year expected product lifetime. Poly(ethylene-terephthalate) (PET) is an important material, and it mainly used as the core (middle) layer of a backsheets to provide mechanical stability and electrical isolation. It is sometimes also used as the outer, or air side, layer of a backsheet. However, Backsheets using PET air side layers are highly susceptible to moisture and ultraviolet (UV) irradiance. Degradation of PV module backsheets can cause severe safety issues and economic losses. Indoor accelerated exposures are used to study backsheets degradation using higher irradiance and shorter exposure times so as to predict the performance of backsheets exposed to the real world conditions.

Usage

data(backsheet)

Format

A data frame with 110 rows and 5 variables:

YI

Yellowness index of PET outer layer measured at every exposure step

Hours

Exposure time of PET in Damp Heat condition

oxidation

Formation of conjugated structures in the polymer during oxidation (FTIR peak at 1552 cm-1)

hydrolysis

Formation of acid and alcohol structures during hydrolysis (FTIR peak 2900 - 3300 cm-1)

crystallization

Crystallinity calculated as the ratio of FTIR peak at 1340 cm-1 to 1370 cm-1

Details

PV module backsheet degradation can be characterized by changes in the yellowness index (YI), which represents the color change of polymer and is associated with chemical change due to irradiance, high temperature and other process. The YI value of a PV backsheet also relates to the module efficiency. In addition, the Fourier-transform infrared spectroscopy (FTIR) is an effective method to study the chemical change of polymers. This non-destructive FTIR measurement enables researchers to obtain qualitative information about polymer functional groups and the relative contribution of each group in the sample to degradation.

In this example, a dataset containing the YI of PET based backsheets (PET/PET/EVA) exposed to 1,500 hours of Damp Heat with no irradiance and a relative humidity (RH) of 85% and a chamber temperature of 85 degree celsius. The PET samples were removed from the exposure chamber every 500 hours and the YI measurement was conducted at every time step. The stress variable is exposure time with unit of hours. Mechanistic variables from FTIR are included to track chemical changes in the materials related to polymer chain scission due to hydrolysis, crystallinity change and oxidation.

Author(s)

Yu Wang, Wei-heng Huang, Laura S. Bruckman, Roger H. French

Source

Solar Durability and Lifetime Extension (SDLE) Research Center, Case Western Reserve University

Crack Quantification for Photovoltaic Backsheets

Description

A dataset containing the average normalized crack depth for photovoltaic backsheets with inner layers of either ethylene-vinyl acetate or polyethylene exposed to 4,000 hours of continuous UVA irradiance with an intensity of 1.55 w/m2 at 340 nm and a chamber temperature of 70 deg C. Mechanistic variables from Fourier transform infrared spectroscopy are included to track chemical changes in the materials related to cracking. See the journal article titled 'A Non-Destructive Method for Crack Quantification in Photovoltaic Backsheets Under Accelerated and Real-World Exposures' in Polymer Degradation and Stability for more details. Doi: 10.1016/j.polymdegradstab.2018.05.008

Usage

data(crack)

Format

A data frame with 97 rows and 5 variables:

dAvgNorm

Average crack depth normalized by the backsheet's inner layer thickness

uva360dose

Integrated, cumulative photodose for all wavelengths less than 360 nm

crys730

Percent crystallinity calculated from the ratio of CH2 rocking peaks at 731 and 720 cm-1

carb1715

Ketone carbonyl index calculated as the ratio of intensities at 1715 and 2851 cm-1

carbPC1

1st principal component score from the carbonyl region (1500-1800 cm-1)

Author(s)

Addison G. Klinke, Abdulkerim Gok, Laura S. Bruckman, Roger H. French

Source

Solar Durability and Lifetime Extension (SDLE) Research Center, Case Western Reserve University

Generate initial values for nls function

Description

Generate multiple initial vectors for the nls function in netSEM().

Usage

genInit(bounds = list(a1 = c(-3, 3), a2 = c(-3, 3), a3 = c(-3, 3)), k = 50)

Arguments

Details

Currently the non-linearizable function included in netSEM() is y = a + b * exp(c * x), where a, b and c are coefficients to be estimated. Thus an initial vector contains three values. The random initial values are generated by a uniform distribution between the bounds.

Value

a data frame. Each column corresponds to a coefficient. Each row corresponds to a random initial vector.

Examples

genInit(list(a1 = c(0,2), a2 = c(4,5), a3 = c(-1, -0.5)), k = 20 )

Aluminum Gradient Material for Metal's Design

Description

Functional graded materials (FGM) are a class of materials with engineered continuous compositional gradients through the plate thickness. This work applies the netSEM approach on an aluminum FGM, produced via sequential alloy casting using planar solidification, to quantify the < Processing | Microstructure | Performance > relationships. The material has a continuous gradient in zinc (Zn) and magnesium (Mg) concentrations through the plate thickness. This subsequently produces a gradient in strengthening mechanisms from a dominant precipitate-strengthened aluminum alloy (AA) (Zn-based AA-7055) to a dominant strain-hardenable aluminum alloy (Mg-based AA-5456). Therefore, the material is simultaneously strengthened via solid solution strengthening and precipitation strengthening.

Usage

data(metal)

Format

A data frame with 72 rows and 6 variables:

Hardness

Vickers hardness

Z

the compositional gradient (z-direction)

Mg

the element Zinc

Zn

the element Magnesium

MgZn2

the alloy

Mgexcess

Mg-excess

Author(s)

Amit K. Verma, Roger H. French, Jennifer L. W. Carter

Source

Solar Durability and Lifetime Extension (SDLE) Research Center, Case Western Reserve University

network Structural Equation Modeling (netSEM)

Description

This function carries out netSEM using principle 1

Usage

netSEMp1(
  x,
  exogenous = NULL,
  endogenous = NULL,
  nlsInits = data.frame(a1 = 1, a2 = 1, a3 = 1),
  str = FALSE
)

Arguments

Details

netSEM builds a network model of multiple continuous variables using principle 1. Principle 1 determines the univariate relationships in the spirit of the Markovian process. In this case, the relationship between each pair of system variables, including predictors and the system level response is determined with the Markovian property that assumes the value of the current predictor is sufficient in relating to the next level variable, i.e., the relationship is independent of the specific value of the preceding-level variable to the current predictor, given the current value. Each pair of variables is tested for sensible (in the domain knowledge sense) paring relation chosen from 7 pre-selected common functional forms in linear regression settings. Adjusted R-squared is used for model selection for every pair.

P-values reported in the "res.print" field of the return list contains the P-values of estimators of linear regression coefficients. The P-values are ordered in the common order of coefficients, i.e. in the order of increasing exponents. For example, in the quadratic functional form y ~ b0 + b1x + b2x^2, the three P-values correspond two those of \hatb0, \hatb1 and \hatb2, respectively. If there are less than 3 coefficients to estimate, the extra P-value field is filled with NA's.

Value

An object of class netSEM, which is a list of the following items:

• "table": A matrix. For each row, first column is the endogenous variable, second column is the predictor, the other columns show corresponding summary information: Best functional form, R-squared, adj-R-squared, P-value1, P-value2 and P-value3. The P-values correspond to those of estimators of linear regression coefficients. See details.

• "bestModels": A matrix. First dimension indicates predictors. The second dimension indicates endogenous variables. The i-jth cell of the matrix stores the name of the best functional form corresponding to the j-th endogenous variable regressed on the i-th predictor.

• "allModels": A three dimensional list. The first dimension indicates predictors. The second dimension indicates endogenous variables. Third dimension indicates the fitting results of all 6 functional forms. The i-j-k-th cell of the list stores a "lm" object, corresponding to the j-th endogenous, i-th predictor and the k-th functional form.

The object has two added attributes:

• "attr(res.best, "Step")": A vector. For each variable, it shows in which step it is choosen to be significantly related to endogenous variable.

• "attr(res.best, "diag.Step")": A matrix. First dimension is predictors; second dimension is endogenous variables. Each cell shows in which step the pairwise relation is being fitted.

Examples

## Not run: 
## Load the sample acrylic data set
data(acrylic)

## Run netSEM
ans <- netSEMp1(acrylic)

## End(Not run)

network Structural Equation Modelling (netSEM) - Principle 2

Description

This function builds an netSEM model using principle 2.

Usage

netSEMp2(
  x,
  exogenous = NULL,
  endogenous = NULL,
  str = FALSE,
  criterion = "AIC"
)

Arguments

Details

Principle 2 resembles the multiple regression principle in the way multiple predictors are considered simultaneously. Specifically, the first-level predictors to the system level variable, such as, Time and unit level variables, acted on the system level variable collectively by an additive model. This collective additive model can be found with a generalized stepwise variable selection (using the stepAIC() function in R, which performs variable selection on the basis of AIC or BIC) and this proceeds iteratively.

Data is analysed first using Principle 1 to find the best models. If needed, transformations based on the best models are applied to the predictors. Starting from the system response variable, each variable is regressed on all other variables except for the system response in an additive multiple regression model, which is reduced by a stepwise selection using stepAIC(). Then, for each selected variable, fitted regression for 6 selected functional forms (8 if strength type problem) and pick the best.

Value

A list of the following items:

• "res.print": A matrix. For each row, first column is the endogenous variable, second column is the exogenous variable, the other columns show corresponding summary information.

See Also

netSEMp1

Examples

## Not run: 
# Using AIC criterion
data(acrylic)
ans <- netSEMp2(acrylic, criterion = "AIC")

# Using AIC criterion
ans <- netSEMp2(acrylic, criterion = "BIC")


# Using simulated data
 s <- runif(100,0,2)
m3 <- 1+2.5*s+rnorm(100,0,0.5)
m1 <- runif(100,1,4)
m2 <- -1-m1+m3+rnorm(100,0,0.3)
 y <- 2+2*exp(m1/3)+(m2-1)^2-m3+rnorm(100,0,0.5)
# Check the pairwise plot 
sim <- data.frame(cbind(y,s,m1,m2,m3))
pairs(sim)
ans <- netSEMp2(sim)


## End(Not run)

Extract Path Model Equation

Description

Extract and display an equation of a pairwise path between two variables.

Usage

path(x, from, to, round = 3)

Arguments

Details

Extract the "best" model from principle 1 between any two variables. The model name and the model equation are printed on screen. The model coefficients, as well as the model R object are also returned.

Value

a list of the following items:

• "model": the best fitted model.

• "model.print": a character string of the model equation.

See Also

netSEMp1

Examples

## Not run: 
## Load the sample acrylic data set
data(acrylic)

# Run netSEM principle one
ans <- netSEMp1(acrylic)

# Extract relations between IrradTot and IAD2
cf <- path(ans, from = "IrradTot", to = "IAD2")
print(cf)

## End(Not run)

Summary of predicted and observed response values along a pathway

Description

Predict response variable values along a pathway in principle 1.

Usage

pathwayPredict(x, path, newdata = NULL)

Arguments

Value

An object of class pathway, which is a list of the following items:

• "pathway": A string form that shows the pathway.

• "RMSE": A value of the root mean squared error.

• "Resp": A matrix. The first column is the observed response values and the second is the predicted response values.

See Also

pathwayRMSE, netSEMp1

Examples

## Not run: 
# Load the sample acrylic data set
data(acrylic)
ans <- netSEMp1(acrylic)
paths <- pathwayRMSE(ans,maxlen=3)
response <- pathwayPredict(ans, paths[10,2])
response

## End(Not run)

Summary of pathway RMSE

Description

Summarize root mean square error (RMSE) for direct and indirect pathway from netSEMp1 result.

Usage

pathwayRMSE(x, maxlen = 2, ...)

Arguments

Details

pathwayRMSE gives a summary about RMSE.

Value

A data frame of result. A summary of RMSE results for all of pathways.

See Also

netSEMp1, pathwayPredict

Examples

## Not run: 
data(acrylic)
ans <- netSEMp1(acrylic)
pathwayRMSE(ans,maxlen=2)

## End(Not run)

A data frame of an degradation experiment of poly(ethylene-terephthalate) films

Description

The data set is a study of photolysis and hydrolysis of poly(ethylene-terephthalate) films that contain an ultraviolet stabilizer additive. In this work, polymeric samples were exposed to UV light and moisture according to ASTM G-154 Cycle 4 standard accelerated weathering conditions. Resulting optical chemical changes were determined through optical and infrared (IR) spectroscopy. *Time* is the main exogenous variable and *YI* (yellowness index) is the endogenous variable (response). The other columns in the data set (*AbsEdge*, *UV.Stab.Bleaching*, *Crystallization*, and *ChainScission*) are values extracted from optical and IR absorbance spectra as single metrics and used as intermediate unit level endogenous (response) variables in the netSEM analysis.

Usage

data(pet)

Format

A 37 by 6 data frame of continuous variables:

YI

Yellowness index of PET film

Time

Time exposed to ASTM G-154 Cycle 4 conditions

AbsEdge

Fundamental Absorption Edge - Optical absorbance at 312 nm

UVStabBleaching

Ultraviolet Stabilizer Bleaching - Optical absorbance at 340 nm

Crystallization

IR spectropscopy peak of relative crystallinity - IR absorbance at 975 wavenumber

ChainScission

IR carbonyl peak - IR absorbance at 1711 wavenumber

Author(s)

Devin A. Gordon, Wei-Heng Huang, Roger H. French, Laura S. Bruckman

Source

Solar Durability and Lifetime Extension (SDLE) Research Center, Case Western Reserve University

Plotting of netSEM diagram

Description

Plot netSEMp1 result plot.netSEMp1 plots a network structural equation network model diagram, fitted under principle 1, based on best functional form for each selected pairwise variable.

Usage

## S3 method for class 'netSEMp1'
plot(
  x,
  cutoff = c(0.2, 0.5, 0.8),
  latent = NULL,
  plot.save = FALSE,
  filename = NULL,
  style = TRUE,
  ...
)

Arguments

Value

An html style plot of pairwise relationship pathway diagram between exogenous variables and an endogenous variable. Arrows show relationships between each variable with given statistical relations along the connection lines.

See Also

netSEMp1

Examples

# Load acrylic data set
data(acrylic)

# Build a netSEM model
ans <- netSEMp1(acrylic)

# Plot the network model 
plot(ans,cutoff = c(0.3,0.6,0.8))

# Plot the network diagram with latent argument labels
plot(ans, cutoff = c(0.3, 0.6, 0.8), 
     latent = c('IAD1' = 'FundAbsEdge', 
                'IAD2' = 'UVStab', 
                'IAD2p' = 'UVStab', 
                'IAD3' = 'YelMet'))

# Drop relationships lower than minimum cutoff value
plot(ans, cutoff = c(0.3,0.6,0.8), style = FALSE)

## Not run: 
# Save plot 
plot(ans, cutoff = c(0.3, 0.6, 0.8), plot.save = TRUE, filename = 'acrylic-netSEMp1')

## End(Not run)

Plotting of netSEM diagram

Description

Plot netSEMp2 result plot.netSEMp2 plots a network structural equation model diagram, fitted under principle 2, based on best functional form for each selected pairwise variable.

Usage

## S3 method for class 'netSEMp2'
plot(
  x,
  cutoff = c(0.3, 0.6, 0.8),
  latent = NULL,
  plot.save = FALSE,
  filename = NULL,
  style = TRUE,
  ...
)

Arguments

Value

An html style plot of multiple regression relationship pathway diagram between exogenous variables and an endogenous variable. Arrows show relationships between each variable with given statistical relations along the connection lines.

See Also

netSEMp2

Examples

## Not run: 
# Load acrylic data set
data(acrylic)

# Build a netSEMp2 model
ans2 <- netSEMp2(acrylic, criterion = "AIC")
ans2_BIC <- netSEMp2(acrylic, criterion = "BIC")

# Plot the network model 
plot(ans2, cutoff = c(0.3,0.6,0.8))
plot(ans2_BIC , cutoff = c(0.3,0.6,0.8))

# Drop Relationship lower than minimum cutoff
plot(ans2, cutoff = c(0.3,0.6,0.8), style = FALSE)

# plot network model with latent argument labels
plot(ans2, cutoff = c(0.3, 0.6, 0.8), 
     latent = c('IAD1' = 'FundAbsEdge', 
                'IAD2' = 'UVStab', 
                'IAD2p' = 'UVStab', 
                'IAD3' = 'YelMet'))

# plot the network diagram and save file
#plot(ans, cutoff = c(0.3,0.6,0.8), plot.save = TRUE, filename = "acrylic-netSEMp2"))

## End(Not run)

Summary of netSEMp1

Description

summarize netSEMp1 result

Usage

## S3 method for class 'netSEMp1'
summary(object, ...)

Arguments

Details

summary.netSEMp1 gives a summary about the netSEMp1 analysis.

Value

NULL. A summary of data and fitting result is printed on screen.

Examples

data(acrylic)
ans <- netSEMp1(acrylic)
summary(ans)

Summary of netSEMp2

Description

summarize netSEM result

Usage

## S3 method for class 'netSEMp2'
summary(object, ...)

Arguments

Details

summary.netSEMp2 gives a breif summary about the netSEM Principle 2 analysis.

Value

NULL. A summary of data and fitting result is printed on screen.

Examples

data(acrylic)
ans <- netSEMp2(acrylic)
summary(ans)