Scribd
Upload
15 views12 pages

Note 1

Uploaded by

wan dalini
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
15 views12 pages

Note 1

Uploaded by

wan dalini
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 12

SMARTPLS 4 WORKSHOP (PART 1):

BASIC STRUCTURAL EQUATION MODELING


(PLS-SEM) DATA ANALYSIS USING SMARTPLS 4

Prof Dr Chua Yan Piaw


University of Malaya

Contents

• Introduction to SmartPLS 4

• Types of SEM models


• Reflective models
• Formative models

1
Icons for SmartPLS 4

Introduction to SmartPLS 4

Joe F. Hair (2022):

SmartPLS is for latent variable modeling


(structural equation modeling).

It combines state of the art methods (the


newest technology, ideas, and features)
with an easy-to-use graphical user
interface.

2
Buttons used to draw
models and perform
the analysis
Indicators/ items in a
research instrument/
questionnaire
Panel for drawing the
hypothesized model

Indicators / items A latent variable

3
7

Path
coefficient
/
Loadings Beta R-square

4
9

10

5
11

12

6
2nd order
model

1st order
models

Indicators

13

14

7
15

16

8
A SEM Model in SmartPLS

Item 1: Number of R2
students Performance of
institutions
Item 2: Number of
graduates
Regression weight/
Item 1: Friendly Beta/ path coefficient
staff

Item 2: Competence
Service Quality
of staff

Item 3: Motivated
staff

= directly observable variable = latent or unobserved


variable

17

Two kinds of relationship in SEM models


Reflective models and Formative models

A reflective model
Personality item 1

Personality Personality item 2

Personality item 3

Analysis – Consistent PLS-SEM

18

9
A formative model

Peer Influence

Personality Education

Thinking style

Analysis – PLS-SEM

19

Reflective model vs Formative model


Satisfaction Health

Reflective relationship Formative relationship

Item 1 Item 2 Item 3 Item 4 Living Age Smoking Emotion


style habit
The change in the
Health represents an
construct Satisfaction will
emergent construct that
be reflected in a change
is formed from a set of
in all its indicators.
indicators that have
theoretical rationale.
The indicators are
exchangeable. The indicators are not
exchangeable.
20

10
RESEARCH STATISTICS

Reflective relationship

Direction of causality is from construct


(latent variable) to indicators

Measures expected to be correlated.


Indicators are interchangeable, can be
DR CHUA YAN PIAW (UM)

removed is not reliable.


Examples: items for measure
Motivation: motivation item1,
motivation item 2, motivation item 3

21

Formative relationship – direction of


causality is from indicators to the latent
variable.

No reason to expect the indicators are


correlated

Indicators are not interchangeable.


DR CHUA YAN PIAW (UM)

Example: Healthy construct – factors: living


style. gender, races

22

11
12

23

24
RESEARCH STATISTICS DR CHUA YAN PIAW (UM)

You might also like