Scribd
Upload
34 views7 pages

Smart PLS

The document outlines the procedures for conducting Confirmatory Factor Analysis (CFA) and validating model fit using PLS SEM algorithms, including parameters such as loading factors, construct reliability, and various validity tests. It also details the assessment of the inner model, including R-squared values and significance testing for hypothesis evaluation. Additionally, it provides rules of thumb for interpreting results and determining the strength of relationships between variables.

Uploaded by

marshandaputriw
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as XLSX, PDF, TXT or read online on Scribd
34 views7 pages

Smart PLS

The document outlines the procedures for conducting Confirmatory Factor Analysis (CFA) and validating model fit using PLS SEM algorithms, including parameters such as loading factors, construct reliability, and various validity tests. It also details the assessment of the inner model, including R-squared values and significance testing for hypothesis evaluation. Additionally, it provides rules of thumb for interpreting results and determining the strength of relationships between variables.

Uploaded by

marshandaputriw
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as XLSX, PDF, TXT or read online on Scribd
You are on page 1/ 7

1.

Outer Model/ Confirmatory Factor analysis (CFA)


Pengujian Parameter
Loading Factor

(Calculate - PLS SEM Algoritm - Start


calculation - Open Report - Outer Loading)
Validitas
Konvergen
Average Variance Extracted (Calculate - PLS
SEM Algoritm - Start calculation - Open Report -
Construct Reliability and Validity)

Cross Loading (Calculate - PLS SEM Algoritm -


Start calculation - Open Report - Discriminant
Validity - Cross Loadings)
Fornell-Larcker (Calculate - PLS SEM Algoritm
Validitas
- Start calculation - Open Report - Discriminant
Diskriminan
Validity - Fornell-Larcker)
Latent Variable Correlation (Calculate - PLS
SEM Algoritm - Start calculation - Open Report -
Latent Variables - Correlation)
Cronbach's Alpha
(Calculate - PLS SEM Algoritm - Start
calculation - Open Report - Construct Reliability
Uji Reliabilitas and Validity)
Composite Reliability (Calculate - PLS SEM
Algoritm - Start calculation - Open Report -
Construct Reliability and Validity)

2. Validasi Model Fit


Pengujian Parameter
SRMR (Calculate - PLS SEM Algoritm - Strat
calculation - Open Report - Model Fit)
d-ULS (Sama diatasnya)
d-G (Sama diatasnya)

Chi Square (Sama diatasnya)

Validasi Model Fit


NFI (Sama diatasnya)
GoF - √rata-rata AVE x rata-rata R-Square
(Calculate - PLS SEM Algoritm - Strat calculation -
Open Report - Construct Reliability and validity)

Q2 Predictive Relevance
(Calculate - PLSPredict - Start calculation - Open
report - LV prediction summary)

3. Inner Model
Pengujian Parameter
R Square (Jika variabel X ≤ 2)

R Square Adjusted (Jika X > 2)


(Calculate - PLS SEM Algoritm - Start calculation -
Open Report - R-Square, dilihat dependennya)

Signifikansi (Pengujian Hipotesis)


(Calculate - Bootstrapping - Start Calculation -
Open Report - Path Coefficient)
Inner Model
Jika sudah mengetahui arah hubungan
positif/negatif (Gunakan one-tailed)

Jika belum mengetahui arah hubungan (Gunakan


two-tailed)

Effect Size (Calculate - PLS SEM Algoritm - Start


calculation - Open Report - F-Square)
dependennya)
Rule of Thumb Sumber
≥ 0.70 (Wiyono, 2020; Savitri et al., 2021)
≥ 0.60 (cukup) (Wiyono, 2020)

≥ 0.50 (Masih dapat diterima) (Haryono, 2016)

≥ 0.50 (Haryono, 2016)

Korelasi antara indikator (instrumen) dengan


konstruksinya (variabel) -> indikator (intrument (Wiyono, 2020; Budhi, 2018)
pada konstruk (variabel) lainnya

Nilai akar AVE korelasi konstruk (variabel) yang


(Savitri et al., 2021; Budhi, 2018)
sama -> korelasi dengan konstruk (variabel) lainnya

Nilai korelasi satu variabel terhadap variabel (Hamid & Anwar, 2019)
lainnya < nilai Akar Kuadrat AVE variabel tersebut
≥ 0.70 (Savitri et al., 2021; Wiyono, 2020)

≥ 0.60 (Budhi, 2018)

≥ 0.70 (Savitri et al., 2021; Wiyono, 2020)

Rule of Thumb Sumber


(Santoso & Rahardjo, 2021; Wiyono, 2020)
Nilai SRMR < 0.10, maka Model Fit
≥ 0.05 (Wiyono, 2020)
≥ 0.05 (Wiyono, 2020)
x2 statistik ≥ X2 tabel (DF total indikator - 1. Chi-
Square Tabel untuk DF = ? Dan signifikansi ? Berapa (Wiyono, 2020)
Chi-Square tabelnya)
Nilai NFI mendekati nilai 1 (Santoso & Rahardjo, 2021)
0.1 (GOF kecil)
0.25 (GOF moderate) (Wiyono, 2020)
0.36 (GOF besar)
Q2 > 0 : Memiliki predictive relevance
(Setiaman, 2023; Savitri et al., 2021;
Wiyono, 2020)
(Setiaman, 2023; Savitri et al., 2021;
Q2 < 0 : Kurang memiliki predictive relevance
Wiyono, 2020)
0.02 (Lemah); 0.15 (Moderate); 0.35 (Kuat)

Rule of Thumb Sumber


Nilai R-Square 0.75 (kuat), 0.50 (Moderat), dan (Savitri et al., 2021)
0.25 (Lemah)

Nilai R-Square Adjusted 0.67 (kuat), 0.33


(Moderat), dan 0.19 (Lemah) (Haryono, 2016)

> 1.65 (Significance level = 10%)


> 1.96 (Significance level = 5%)
> 1.65 (Significance level = 1%)
Khusus Mediasi:
(Santoso & Rahardjo, 2021; Wiyono, 2020)
Jika Pengaruh langsung (X -> Y) signifikan dan
pengaruh tidak langsung (X -> M -> Y) signifikan =
Partial mediation
Jika Pengaruh langsung (X -> Y) tida signifikan dan
pengaruh tidak langsung (X -> M -> Y) signifikan =
Full mediation
< 0.02 (efek kecil)
0.02 - 0.15 (efek sedang) (Savitri et al., 2021)
> 0.35 (efek besar)

You might also like