Structural Equation Modeling

(SEM)

Kassa T. (PhD)
Email: [email protected]
Tel: +251911346214

6/10/2021 Kassa T. Alemu (PhD) 1

What is SEM?
• SEM is a multivariate technique that involves
simultaneously estimating and testing a series of
hypothesised inter-related dependency relationships
between a set of latent (unobserved) constructs,
each measured by one or more manifest
(observed) variables (Reisinger & Mavondo, 2006)

• SEM is also known by other names such as covariance

structure analysis, latent variable analysis, path
analysis and causal modelling.
6/10/2021 Kassa T. Alemu (PhD) 3
6/10/2021 Kassa T. Alemu (PhD) 4
Why SEM?
• SEM facilitates the discovery and confirmation
of relationships among multiple variables.
• incorporates abstract and unobservable
constructs (latent variables) measured by
indicators (also called items, manifest variables
or observed measures).
• Simultaneously model relationships among
multiple predictors (independent or
exogenous) and criterion (dependent or
endogenous) variables.
• The intricate causal networks enabled by SEM
characterise real world processes better than
simple correlation- based models.
• This capability for intricate simultaneous
analysis greatly differs from first-generation
multivariate methods (e.g., linear regression,
logit, etc.) which analyse only one layer of the
linkages between independent and dependent
variables at a time
Role of theory in SEM:
• A theory serves as a conceptual foundation for
developing a model
• Theory is defined as a conceptual scheme based on
fundamental statements, that are assumed to be true.
• It is very important that SEM model be based on a
theory because all relationships must be specified
before the SEM model can be estimated.
• Theory is needed to specify relationships in both
measurement and structural models,
modifications to the proposed relationships, and many
other aspects of estimating a model.
• Theory also helps in establishing causation.
Model
• A model is representation of a theory
• Theory can be thought of as a systematic set of relationships
providing a consistent and comprehensive explanation of
phenomena.
• SEM model consists of the measurement model and the
structural model.
• The measurement model depicts how the observed
(measured) variables represent constructs
• A structural model shows how the constructs are interrelated
to each other, often with multiple dependence relationships
• Structural model specifies whether a relationship exists or
doesn’t exist. If a relationship is hypothesised by the theory,
then an arrow is drawn, otherwise not.
• A model is portrayed in a graphical form known as a path
diagram
Exogenous Vs Endogenous relationships
• Exogenous is the latent, multi-item equivalent of
an independent variable in traditional multivariate
analysis. An exogenous construct is determined
by factors outside of the model, and it cannot be
explained by any other construct or variable in
the model.
• Endogenous is the latent, multi-item equivalent
of a dependent variable. It is determined by
constructs or variables within the model and
thus it is dependent on other constructs.
 Exogenous Endogenous
Variable Variable

6/10/2021 Kassa T. Alemu (PhD) 16

Dependence and correlational
relationships
• A dependence relationship is shown by straight
arrows.
• The arrows flow from the antecedent
(independent) to the subsequent effect
(dependent) measured variable or latent construct.
• A correlational relationship, also called
covariance relationship, specifies a simple
correlation between exogenous constructs.
• A correlational relationship is depicted by a two
headed curved arrow.
Six steps in SEM:
Step 1-4 (Measurement Model)
• Step 1: Defining individual constructs
• Step 2: Developing the overall measurement model
• Step 3: Designing a study to produce empirical results
• Step 4: Assessing the measurement model validity

Stage 5-6 (Structural Model)

• Step 5: Specifying the structural model
• Step 6: Assessing structural model validity
Mediation Analysis
• Mediation occurs when an independent variable
(X), is postulated to exert an effect on an outcome
variable (Y), through one or more intervening
variables called mediators(M) in an intervening
variable model.

• Direct effects are relationships that link two

constructs with a single arrow
• Indirect effects are those relationships that involve
a sequence of relationships with at least one
intervening construct involved.
 Study Effectiveness

Effort

Student intelligence Class Performance

Performance
Managerialism
 Illustration with example:
• Assume Dashin Beer Factory is facing the problem of
attracting and keeping productive employees. The cost
of replacing and retaining employees is high. Dashin
management wants to understand the factors
contributing to employee retention. The company wants
to test a measurement model made of factors that affect
employees attitudes and behaviours remaining within the
factory. Five constructs were observed:
- Job satisfaction (JS)
- Organisational commitment (OC)
- Staying intentions (SI)
- Environmental perceptions(EP)
- Attitude toward co-workers (AC)
 Obtain a copy of the data here:
https://drive.google.com/file/d/1VoCnQtPCEw7fWalv_57m-
kvKJG9WIuHk/view

https://www.youtube.com/watch?v=8R7aV7eKf-4
Model 1
Mastery goals is a significant
positive predictor of interest
(b=.79, s.e.=.087, p<.001;
β=.591).

β;
Standardized
path
coefficient
The path coefficient from
performance goals to interest was
negative, but not significant (b=-
.006, s.e.=.005, p=.300; β= -.071)

β;
Standardized
path
coefficient
The path coefficient from
performance goals to anxiety was
not significant (b=.0099,
s.e.=.007, p=.162; β= .117)

β;
Standardized
path
coefficient
Interest was a positive and
significant predictor of
achievement (b=.364, s.e.=.0517,
p<.001; β= .513)

β;
Standardized
path
coefficient
Anxiety was a negative and
significant predictor of
achievement (b=-.106, s.e.=.055,
p=.055, one-tailed; β= -.1396)

β;
Standardized
path
coefficient
 Correlation
between
mastery and
performance
goals

Covariance between
mastery and performance
goals is -6.25 (p=.008).
[Correlation is -.229.]
Use Postestimation tools in order to obtain fit indices to evaluate the global fit for
the model.
Good square goodness of fit test.
Significance is considered an
indicator of poor model fit.

We find that the chi-square

goodness of fit test is significant,
χ²(4)=37.568, p<.001, suggesting
poor fit of the model to the data.

One thing to keep in mind is that

nowadays researchers do not rely
heavily on this test (although it is
still conventionally reported). A key
reason is that SEM is a large
sample procedure. Hence, this test
is often overpowered even in
circumstances when there is only
minor misspecification.

Typically, researchers report on

many of the other fit indices
reported in this table.
The lowest possible RMSEA is 0.
Values < .05 are considered
indicative of close fit. Values up to
.08 are considered acceptable
(Pituch & Stevens, 2016).

The pclose is a test of whether the

model departs significantly from one
that is a close-fit to the data (i.e.,
RMSEA< or = .05).

-----------------------------------------------
------------------

We see that the RMSEA value

(.245) is quite large (>.08) and the
pclose test is significant (p<.001).
Both findings indicate poor model fit
to the data.
The CFI and TLI are both
incremental fit indices. Values >
.95 for these indices indicate
very good fit (Schumaker &
Lomax, 2016). Values .90 or
above are considered evidence
of acceptable fit (Pituch &
Stevens, 2016).

SRMR values up to .05 are

considered indicative of a close-
fitting model. Values between .05
up to .10 suggest acceptable fit
(Pituch & Stevens, 2016).

-------------------------------------------
----------------------

We see that the CFI (.771) and

TLI (.485) values are very low
(both < .90), whereas the SRMR
(.124) was high (i.e., > .10),
relative to conventional
thresholds for acceptable model
fit.
The AIC and BIC are information
indices. These are not useful for
evaluating the fit of one specific
model (as we were doing with
the other indices in this table).
However, they are useful for
identifying the best fitting model
out of a candidate set. The better
fitting model(s) out of a
candidate set of models (2 or
more models) are those with AIC
or BIC values that are lowest
(i.e., lower is better).

These indices are generally most

useful for identifying the best
fitting model out of a candidate
set of non-nested models.
However, they can also be useful
when identifying fit even with
nested models (although
candidate nested models are
most often evaluated using
likelihood ratio chi-square tests).
Matrix of standardized covariance
residuals. Values > 1.96 in the off-
diagonal elements suggest more
substantial areas of model
misspecification (Pituch & Stevens,
2016)
Modification indices (MI) are
suggestions for potential model
specifications (through the
inclusion of additional parameters)
that may result in an increase in
model fit.

The MI value indicates the degree

of the chi-square goodness of fit
value is expected to decrease as
a result of adding a suggested
parameter (NOTE: smaller chi-
square values are associated with
increased fit). A value > 3.84
(p=.05) suggests that including a
suggested parameter will result in
a significant improvement in
model fit. The P>MI column is the
projected p-value for the
increment in fit as a result of
adding in the suggested
parameter.
EPC (expected parameter
change) and Standard EPC
provide an indication of the
expected value of a parameter
should you choose to re-specify
your model with a given
parameter estimated (Pituch &
Stevens, 2016).

EPC = unstandardized parameter

estimate.
Standard EPC = standardized
estimate.

---------------------------------------------
-------------------
NOTE: It is worth mentioning that
not all recommendations
necessarily make sense!
You can clear out the
estimates in the path
diagram
Model 2
 β;
Standardized
path
coefficient

Mastery goals is a positive and significant predictor of interest (b=.770, s.e.=.085,

p<.001; β=.607).
 β;
Standardized
path
coefficient

Mastery goals is a negative and significant predictor of anxiety (b=-.399, s.e.=.094,

p<.001; β=-.337).
We see that interest (b=.1999, s.e.=.059, p=.001; β=.279) and mastery goals
(b=.3256, s.e.=.078, p<.001; β=.359) are positive and significant predictors of
achievement. Performance goals is a negative and significant (b=-.009, s.e. = .004,
p=.034; β=-.143) predictor of achievement.
 Correlation
between
mastery and
performance
goals

The covariance between mastery goals and performance goals is -6.2537 (p=.008).
[The correlation is -.229.]
 Correlation
between
disturbance
terms

The covariance between the disturbances for interest and anxiety is .0185 (p=.920).
[The correlation between disturbances was .008.]
The chi-square goodness of
fit test was not significant,
χ²(2) = 1.351, p=.509.

The RMSEA was 0 and the

pclose test was not
significant (p=.616).

The CFI and TLI were both >

.95, while the SRMR was
.021.

All of these indices suggest a

very good fitting model.
 All standardized
covariance residuals
fell < 1.96

Notice too that no suggested modifications were provided.

If you want to obtain R-
square values associated
with each of your
endogenous variables,
you can use the Equation-
Level Goodness of fit
option under
Postestimation tools.
 References

Pituch, K. A., & Stevens, J. P. (2016). Applied multivariate statistics for the social
sciences (6th edition). Routledge: New York.

Schumacker, R. E., & Lomax, R. G. (2016). A beginner’s guide to structural

equation modeling (4th edition). Routledge: New York.