PPubMed30 Dec 2025Cited 1×

Combination of partial least square structural equation modeling scheme of principal component analysis with importance performance analysis ☆ ☆☆

Bambang Widjanarko Otok, Zulfani Alfasanah, Diaz Fitra Aksioma

Abstract

Title: Highlights 1. • PCA is used in the inner weighting scheme of the PLS model to obtain latent variable scores. 2. • PLS-IPA explains the influence between latent variables and indicators while mapping indicators based on importance and performance.

§ The Valyu brief

The paper, in five minutes

Read from the full text via Valyu Contents

A PCA‑enhanced PLS‑SEM combined with Importance‑Performance Analysis identifies key socioeconomic and service factors influencing toddler malnutrition in East Java.

What’s new

i.Introduced PCA as the inner weighting scheme for PLS‑SEM to compute latent variable scores
ii.Integrated Importance‑Performance Analysis with PLS‑SEM to map influence and performance of latent variables
iii.Applied the combined method to secondary 2022 data to assess determinants of toddler malnutrition in East Java
iv.Provided detailed documentation and reproducible workflow for the PCA‑based PLS‑IPA procedure

How they did it

The study used secondary 2022 data from East Java (38 districts) covering socioeconomic, parenting, food security, health services, and malnutrition indicators. For each latent variable, PCA was performed on its indicator block to extract the first component loading as the weight vector, which was used to compute latent scores; these scores fed into a PLS‑SEM estimated by ordinary least squares and bootstrapped (B=2000) for significance. Finally, the estimated path coefficients were plotted on an Importance‑Performance map to guide priority actions.

What they found

Socio‑Economic → Parenting: coefficient 0.464, t = 3.963, p < 0.001 (significant)
Socio‑Economic → Food Security: coefficient 0.720, t = 10.641, p < 0.001 (significant)
Socio‑Economic → Health & Environmental Services: coefficient 0.513, t = 2.103, p = 0.036 (significant)
Parenting → Malnutrition: coefficient ‑0.185, t = 0.851, p = 0.395 (not significant)
Composite reliability values: Socio‑Economic 0.965, Parenting 1.000, Food Security 1.000, Health & Env 0.687 (below 0.70), Malnutrition 0.940

Caveats

✕Cross‑sectional analysis using only aggregate 2022 data, so temporal dynamics are not captured
✕Data quality depends on official statistics surveys, which may have completeness issues
✕Only indirect/underlying factors were modeled; direct causes like dietary intake and infections were omitted
✕PLS‑SEM is exploratory, providing associations rather than definitive causal inference
✕IPA mapping does not incorporate contextual factors such as culture, local policies, or social dynamics

§ The Valyu brief

Reading the full paper and taking notes. This takes a few seconds…

§ Ask this paper

Ask a question about this paper

Valyu reads the full text and answers from what the paper actually says.

§ Related work in other archives

Combination of partial least square structural equation modeling scheme of principal component analysis with importance performance analysis ☆ ☆☆

The paper, in five minutes

Ask a question about this paper

Similar papers in all four archives

The paper, in five minutes

Similar papers in all four archives