How to cite this document: Demir, E. (2026). Exploratory and confirmatory factor analysis: A theoretical and practical guide with R [Online document]. RPubs. https://rpubs.com/Symrna/EFA_CFA_guide

Introduction

This guide introduces exploratory factor analysis (EFA) and confirmatory factor analysis (CFA), two of the most widely used techniques for studying the structure of latent variables in education, psychology and the social sciences. It combines theoretical background with hands-on application in R. Each section ends with a few self-check questions. You can move on even if some answers are not correct, and you will see feedback after each check. At the end, a worked example applies both techniques to the same dataset, step by step.

The guide is written for students, researchers and practitioners. No prior experience with factor analysis is assumed, but basic knowledge of correlation, variance and regression will help. Each section can be read on its own, so readers who are already familiar with EFA may move directly to the CFA or worked example sections.

Note on data collection. This page records anonymous usage data (for example, which sections are opened, answers to self-check questions and time spent) to improve the material. No personal information is collected unless you choose to fill in the optional form below. The data are used only in aggregate form, to see which parts of the guide are most useful and which questions are most difficult.

About You (Optional)

You may leave these fields empty and still use the whole guide. The information is used only to describe who uses the guide. No individual answers are reported with names or email addresses.

Section 1. Foundations of Factor Analysis

1.1 What Is Factor Analysis?

Factor analysis is a family of multivariate techniques that explain the correlations among a set of observed variables through a smaller number of unobserved variables called factors. Many constructs in the behavioural sciences, such as anxiety, motivation or mathematical ability, cannot be measured directly. We observe responses to items, test scores or ratings, and assume that these observed variables share variance because they are influenced by the same underlying construct (Hair et al., 2019; Pituch & Stevens, 2016; Tabachnick & Fidell, 2019). The idea goes back to Spearman (1904), and Thurstone (1947) extended it to several factors.

1.2 Observed and Latent Variables

An observed (manifest) variable is something we measure directly, such as the response to a questionnaire item. A latent variable is a construct that is not measured directly but is inferred from several observed variables. The dimensions obtained in the analysis are called factors or components, depending on the extraction method. They are called factors when a common factor method such as principal axis factoring or maximum likelihood is used, and components when principal component analysis is used. Strictly speaking, components are weighted sums of the observed variables rather than latent variables, as explained in Section 2.2.

1.3 The Common Factor Model

The common factor model assumes that the variance of each observed variable has two parts. The common variance is shared with other variables and explained by the factors. The unique variance is specific to that variable and includes measurement error. In matrix form, the observed correlation (or covariance) matrix is reproduced by the factor loadings, the factor correlations and the unique variances (Brown, 2015).

For a single item, the model can be written as

x = λ ξ + δ

where x is the observed score, λ is the factor loading, ξ is the latent factor and δ is the unique part. The loading λ shows how strongly the item reflects the factor, and the larger it is, the larger the common part of the item’s variance. With several factors and items the same idea is written in matrix form, with one row of loadings for each item.

1.4 Classification of Factor Analytic Techniques

Factor analysis is not a single technique but a family of related methods. These methods can be classified from several points of view, and one analysis usually belongs to several classes at once. For example, a CFA of ordinal Likert items with a second-order factor is confirmatory, uses a common factor model, is an item-level factor analysis and has a higher-order structure.

Basis of classification Types Main idea
Purpose of the analysis Exploratory (EFA), confirmatory (CFA), hybrid (ESEM) Whether the structure is explored from the data, tested as specified in advance, or tested while allowing cross-loadings
Variance analysed Component analysis (PCA), common factor analysis (PAF, ML, minres and others) Whether total variance is summarised or only the variance shared among the variables is modelled
What is correlated R-type, Q-type R-type analyses correlations among variables across persons, which is the usual case, while Q-type analyses correlations among persons to group similar people (Hair et al., 2019)
Type of observed variables Linear factor analysis, item factor analysis Continuous variables are analysed with Pearson correlations, while ordinal or binary items are analysed with polychoric or tetrachoric correlations and suitable estimators (Flora & Curran, 2004)
Structure of the model First-order, higher-order, bifactor Whether the factors explain only the items, are themselves explained by a general factor, or appear alongside a general factor (Reise, 2012)
Groups and levels Single-group, multigroup, multilevel Whether one model is fitted to one sample, compared across groups, or estimated for nested data such as students within schools
Estimation framework Frequentist, Bayesian Whether parameters are treated as fixed values estimated from the data or as random variables with prior and posterior distributions (Muthén & Asparouhov, 2012)

The most important distinctions for this guide are the purpose of the analysis and the variance analysed. Sections 2 and 3 discuss exploratory and confirmatory factor analysis in detail, including the classification of extraction methods and CFA model types. The hybrid and Bayesian approaches are introduced briefly in Section 4.

1.5 How EFA and CFA Differ

EFA and CFA are both based on the common factor model, yet they differ in several important ways. The table below summarises the main differences. Most of these points are discussed in more detail in Sections 2 and 3.

Feature EFA CFA
Prior theory Not required, the structure is explored Required, a hypothesised structure is tested
Number of factors Decided from the data Fixed in advance by the researcher
Loadings Every item loads on every factor Only specified loadings are estimated, others are fixed (usually to zero)
Identification Rotational indeterminacy, rotation is often used to aid interpretation Identified by fixing a loading or the factor variance
Estimation Extraction methods such as principal axis, maximum likelihood, minimum residual Maximum likelihood, robust ML, WLSMV and others
Main outputs Loadings, communalities, eigenvalues, explained variance Parameter estimates, standard errors, model-data fit indices, residuals
Error covariances Not modelled Can be specified
Typical role Theory building, early instrument development Theory testing, construct validity, measurement invariance

1.6 The Process at a Glance

The flowchart shows how EFA and CFA fit together in one research process. When theory does not yet specify the structure, EFA explores it on one part of the sample, and the resulting structure is then tested with CFA on another part. When the structure is already known from theory, the researcher can go directly to CFA, and a poorly fitting model leads back to revision or further exploration.

1.7 Self-Check Questions

You can try each question up to three times. After a correct answer, or after the third attempt, the correct answer and a short explanation are shown. Your answers do not affect your access to the next section.

1.Which statement best describes a latent variable?
2.In the common factor model, which part of an item's variance includes measurement error?
3.What is the main difference between principal component analysis and common factor analysis?
4.A researcher analyses five-point Likert items with polychoric correlations. Which class of factor analysis does this belong to?
5.Which situation calls for a confirmatory rather than an exploratory approach?

Section 2. Exploratory Factor Analysis (EFA)

EFA is used when the researcher does not have a firm hypothesis about how many factors underlie a set of variables or which variables belong to which factor. Every variable is allowed to load on every factor, and the structure is estimated from the data (Fabrigar et al., 1999; Tabachnick & Fidell, 2019). In this sense EFA is a data-driven technique, although the researcher still makes many decisions, such as the extraction method, the number of factors and the rotation. These decisions are described in the following subsections.

2.1 When and Why We Use EFA

Exploring an unknown structure. When a construct is new or poorly understood, EFA shows how many dimensions the items form and how they group together. For example, a researcher who writes 40 items on teacher burnout can use EFA to see whether the items reflect one general burnout dimension or several related dimensions. The results then guide how the construct is defined and how the scale is scored.

Data reduction. Many correlated variables can be summarised by a few factors. Instead of analysing 30 separate attitude items, a researcher can work with three or four factor scores that keep most of the shared information. This simplifies later analyses, such as regression or group comparisons, and reduces problems caused by highly correlated predictors.

Instrument development and item selection. In the early stages of developing a test or questionnaire, EFA helps identify items that load weakly, load on more than one factor, or do not fit the intended structure. These items are revised or removed before the instrument is tested further. The aim is a shorter instrument whose items clearly represent the intended dimensions.

Checking dimensionality before other analyses. Many models, such as unidimensional item response theory models, assume a single dominant dimension. EFA is often used to check this assumption before fitting such models. If a single factor explains most of the common variance, the unidimensionality assumption is considered reasonable.

Generating hypotheses for CFA. The structure found with EFA can be stated as a model and tested with CFA, preferably on a different sample (see Section 5). In this way EFA generates a hypothesis and CFA tests it. Using the same sample for both steps makes the test less convincing, because the model was already shaped by those data.

2.2 Classification of Extraction Methods

The extraction method determines how the factors are estimated from the correlation matrix. Fabrigar et al. (1999) recommend maximum likelihood when the data are close to multivariate normal and principal axis factoring when this assumption is clearly violated. In practice, different common factor methods usually give similar results when the data are of good quality. The main families of methods are summarised in the table below.

Method Main idea Notes
Principal axis factoring (PAF) Analyses only the common variance by placing communality estimates on the diagonal No distributional assumption, widely used
Maximum likelihood (ML) Finds the parameters most likely to have produced the observed correlations Assumes multivariate normality, gives a chi-square test and fit indices
Minimum residual (minres) or unweighted least squares (ULS) Minimises the residual correlations Robust, works well with polychoric correlations
Generalised least squares (GLS) Weights residuals by the inverse of the correlation matrix Less common in practice
Alpha factoring and image factoring Maximise reliability of factors or analyse the image (shared) part of each variable Mainly of historical interest
Principal component analysis (PCA) Summarises the total variance with weighted composites A component method, not a common factor model (see the note below)

A note on PCA. PCA is often listed together with EFA, and many software packages run it by default. However, PCA analyses the total variance of the variables and makes no distinction between common and unique variance. Its components are exact linear combinations of the observed variables, whereas factors are latent variables that explain only the shared variance. PCA is therefore a data reduction technique, while EFA is a model for latent constructs. When the aim is to understand latent constructs, common factor methods are preferred (Costello & Osborne, 2005; Fabrigar et al., 1999).

The choice of correlation matrix also matters. Pearson correlations suit continuous variables. For ordinal items, such as five-point Likert items, polychoric correlations usually give more accurate results, and tetrachoric correlations are used for dichotomous items.

2.3 Key Terminology in EFA

Term Meaning
Factor loading The relationship between a variable and a factor. In an orthogonal solution it is the correlation between them
Communality (h²) The proportion of a variable’s variance explained by all factors together
Uniqueness (u²) The part of variance not explained by the factors, equal to 1 − h²
Eigenvalue The amount of variance explained by a factor across all variables
Explained variance The percentage of total variance accounted for by each factor and by all factors together
Pattern matrix Unique contribution of each factor to a variable, used for interpretation in oblique solutions
Structure matrix Simple correlations between variables and factors in oblique solutions
Factor correlation matrix (Φ) Correlations among factors after an oblique rotation
Simple structure A pattern in which each variable loads strongly on one factor and weakly on the others (Thurstone, 1947)
Cross-loading A variable with a substantial loading on more than one factor
Heywood case An improper solution in which a communality reaches or exceeds 1

2.4 Rotation Methods

When more than one factor is extracted, the initial solution can be rotated to make it easier to interpret. Rotation turns the factor axes so that each variable loads highly on as few factors as possible, which Thurstone (1947) called simple structure. It does not change the communalities or the fit of the model, and the same rotations are used to interpret principal components (Browne, 2001).

Rotation methods fall into two families. Orthogonal rotations keep the factors uncorrelated, so the loadings can be read as correlations between variables and factors. Oblique rotations allow the factors to correlate, and their results are read from the pattern matrix, the structure matrix and the factor correlation matrix.

Method Family Main idea When to use
Varimax Orthogonal Maximises the variance of the squared loadings within each factor, so each factor has a few high and many near-zero loadings (Kaiser, 1958) Uncorrelated factors are expected, or uncorrelated component scores are needed, as in PCA for data reduction
Quartimax Orthogonal Simplifies the rows, so that each variable loads mainly on one factor A strong general factor is expected, because quartimax tends to produce one
Equamax Orthogonal A compromise between varimax and quartimax Rarely needed, tried when neither varimax nor quartimax gives a clear solution
Direct oblimin (quartimin when δ = 0) Oblique Minimises the cross-products of loadings, and the δ parameter controls how strongly the factors may correlate The default oblique choice in most software, suitable when the factors are expected to correlate
Promax Oblique Starts from a varimax solution and raises the loadings to a power to obtain an oblique target (Hendrickson & White, 1964) Large data sets, because it is fast and usually gives results close to oblimin
Geomin Oblique or orthogonal Minimises the geometric mean of the squared loadings in each row, which tolerates some cross-loadings Complex structures with expected cross-loadings, and the default rotation in ESEM
Target (Procrustes) Oblique or orthogonal Rotates the solution towards a pattern specified by the researcher, with some loadings set to zero Partial prior theory, as a bridge between EFA and CFA
Bifactor (bi-quartimin, bi-geomin) Oblique or orthogonal Rotates towards one general factor and several specific factors (Jennrich & Bentler, 2011) A general factor and specific factors are both expected

In practice an oblique rotation is a good first choice, because most constructs in education and psychology are related (Costello & Osborne, 2005; Fabrigar et al., 1999). Tabachnick and Fidell (2019) suggest that if the factor correlations stay below about .32, an orthogonal solution is also justified, and the two solutions will then be very similar. In R, the rotation is chosen with the rotate argument of fa() and principal() in the psych package, and the GPArotation package provides the oblique and target rotations.

2.5 Steps of EFA

  1. Screen the data. Check missing values, outliers, linearity and, if ML is used, multivariate normality. Decide on the sample size. MacCallum et al. (1999) showed that the required sample size depends on communalities and on how many variables represent each factor, so simple rules such as ten cases per item are only rough guides.
  2. Check factorability. Inspect the correlation matrix for enough correlations above about .30. The Kaiser-Meyer-Olkin (KMO) measure should preferably exceed .60, and Kaiser (1974) described values in the .90s as marvellous and values below .50 as unacceptable. Bartlett’s (1950) test of sphericity should be significant, showing that the correlation matrix is not an identity matrix.
  3. Choose the correlation matrix and extraction method. Use Pearson or polychoric correlations depending on the data, and select PAF, ML or minres (Section 2.2).
  4. Decide the number of factors. Combine several criteria rather than relying on one. The Kaiser rule (eigenvalues greater than 1) is simple but tends to overestimate the number of factors. The scree plot (Cattell, 1966) is useful but subjective. Parallel analysis (Horn, 1965) compares observed eigenvalues with those from random data and is among the most accurate methods. Velicer’s (1976) minimum average partial (MAP) test is another reliable option. It removes the first component, then the first two, and so on, and after each step computes the average squared partial correlation among the remaining variables. As long as common variance is being removed, this average decreases, and once only unique variance is left it starts to increase again, so the number of components at the minimum of the curve is taken as the number of factors to retain. Theory and interpretability should always be considered alongside these criteria.
  5. Rotate the solution if needed. The available rotation methods are summarised in Section 2.4. Rotation is not mandatory, and with a single factor there is nothing to rotate. With more than one factor, rotation redistributes the explained variance so that the solution is closer to simple structure and easier to interpret. It does not change the fit of the model. Orthogonal rotations (varimax, quartimax, equamax) keep the factors uncorrelated. Oblique rotations (oblimin, promax, geomin) allow the factors to correlate. Because most constructs in education and psychology are related, oblique rotations are usually recommended, and if the factors turn out to be nearly uncorrelated the result will be close to an orthogonal one (Costello & Osborne, 2005).
  6. Interpret and refine. Examine loadings (often values of at least .30 or .40 are considered salient), cross-loadings, communalities and factor correlations. Remove problematic variables one at a time and rerun the analysis, keeping in mind the content coverage of the construct. This procedure is described in more detail in Section 2.6.
  7. Estimate reliability. Report internal consistency for each factor, preferably McDonald’s omega together with Cronbach’s alpha (McDonald, 1999).
  8. Report the results. Describe the decisions taken at each step, the final pattern matrix, communalities, explained variance and factor correlations.

2.6 Selecting Items and Re-running the Analysis

The first EFA is rarely the final one. In instrument development and in data reduction, variables that do not fit the structure are identified and removed, and the analysis is run again with the remaining variables. This applies equally to items, manifest variables and indicators, and to PCA when components are used as summary scores.

Several criteria are commonly used to identify problematic variables. They should always be weighed together with the content of the variables, because removing an item only for statistical reasons can narrow the meaning of a construct. The most common criteria are listed below.

  • Low loadings. A variable without a salient loading on any factor, usually at least .30 to .40, does not represent the factors well.
  • Cross-loadings. A variable with similar loadings on two or more factors, for example with a difference of less than about .10 between its two highest loadings, is hard to assign to one factor.
  • Low communality. A variable with a very low communality shares little variance with the other variables (Costello & Osborne, 2005).
  • Weak factors. A factor with fewer than three salient variables is usually unstable and difficult to interpret (Costello & Osborne, 2005).
  • Content and redundancy. Items that are worded almost identically, or that do not match the definition of the construct, may be removed even when their loadings are acceptable.

Variables are removed one at a time, starting with the most problematic one, because removing one variable changes all the other loadings. After each removal the number of factors, the loadings and the explained variance are checked again. The process stops when the structure is clear and stable, and every removed variable is reported together with the reason for its removal.

When the aim is data reduction, the final solution is estimated once more with the retained variables only. Factor or component scores are then computed from this final solution and used in later analyses, such as regression or group comparisons. The code below shows the general pattern, using the calibration sample of Section 5 and one item as an example of a removed variable.

# remove a problematic item and re-run the analysis
keep <- setdiff(names(calib), "O4")
efa_final <- fa(calib[, keep], nfactors = 5, fm = "minres", rotate = "oblimin", cor = "poly")
print(efa_final$loadings, cutoff = .30, sort = TRUE)

# scores for data reduction, from the final EFA or from a PCA
fs_final  <- factor.scores(calib[, keep], efa_final, method = "regression")$scores
pca_final <- principal(calib[, keep], nfactors = 5, rotate = "varimax", scores = TRUE)
head(pca_final$scores)

2.7 Self-Check Questions

You can try each question up to three times. After a correct answer, or after the third attempt, the correct answer and a short explanation are shown. Your answers do not affect your access to the next section.

1.Which method is a component method rather than a common factor method?
2.A KMO value of .48 indicates that
3.Which method compares observed eigenvalues with eigenvalues from random data?
4.Does rotation improve the fit of an EFA model?
5.Which rotation is usually recommended when the factors are expected to correlate?
6.An item loads .28 on every factor in an EFA. What is the usual next step?

Section 3. Confirmatory Factor Analysis (CFA)

CFA tests whether a structure specified in advance fits the observed data. The researcher decides the number of factors, which indicators load on which factor, whether factors correlate and whether any residuals covary, all based on theory or previous research (Brown, 2015; Jöreskog, 1969). In this sense CFA is a theory-driven technique, and the result is a judgement about how well the specified model reproduces the observed covariances. The following subsections describe when CFA is used, the types of models and the steps of the analysis.

3.1 When and Why We Use CFA

Testing a hypothesised structure. CFA checks whether data collected with an instrument support the structure proposed by theory or by earlier studies. For example, a researcher using a published five-dimension motivation scale in a new population can test whether the five-factor structure still holds. A good fit supports using the scale in that population, while a poor fit suggests that the structure needs to be examined further.

Gathering construct validity evidence. CFA provides evidence of convergent validity (indicators of the same factor load strongly on it) and discriminant validity (factors that should be distinct are not too highly correlated). Standardised loadings, average variance extracted and factor correlations are the main sources of this evidence. These indices are described in Section 3.6.

Comparing competing models. Alternative structures, such as one factor versus several correlated factors, can be compared formally with fit indices and difference tests. The aim is to find the model that explains the data well with as few parameters as possible. Comparing models in this way is often more informative than testing a single model.

Testing measurement invariance. Multigroup CFA examines whether an instrument measures the same construct in the same way across groups, such as gender, language or country. This is a prerequisite for meaningful group comparisons. Invariance is usually tested in steps, from configural to metric, scalar and strict invariance.

Building the measurement model of SEM. Before testing relationships among latent variables, the measurement part of the model is established with CFA (Section 3.2). If the measurement model fits poorly, the results of the structural model cannot be interpreted with confidence. For this reason the measurement model is always checked first.

Modelling method effects. CFA can include correlated residuals, for instance among negatively worded items, which EFA cannot do directly. Such method effects occur when items share wording or format rather than content. Ignoring them can distort the loadings and lead to poor model fit.

3.2 CFA and Structural Equation Modeling

CFA is a special case of structural equation modeling (SEM). An SEM has two parts. The measurement model links the latent variables to their indicators, and this part is a CFA. The structural model specifies directional paths among the latent variables, such as motivation predicting achievement. A CFA model is therefore an SEM in which the latent variables are only allowed to correlate, with no directional paths among them. For this reason CFA and SEM share the same software, estimators, identification rules and fit indices (Kline, 2023). Anderson and Gerbing (1988) recommended a two-step approach, in which the measurement model is first tested with CFA and the structural model is tested only after an acceptable measurement model has been obtained. The LISREL program developed by Jöreskog and Sörbom (1993) played a key role in making both CFA and SEM widely available.

3.3 Classification of CFA Models

Model Description Typical use
One-factor (unidimensional) model All indicators load on a single factor Testing unidimensionality
Correlated first-order factors Several factors, each measured by its own indicators, with correlations among factors The most common CFA model
Orthogonal first-order factors As above, but factor correlations are fixed to zero Rarely realistic, used for comparison
Second-order (higher-order) model First-order factors are themselves explained by a more general factor When correlated factors share a common general construct
Bifactor model Every indicator loads on a general factor and on one specific factor, which are uncorrelated Separating general and specific variance (Reise, 2012)
Multigroup CFA The same model is fitted in several groups with increasing equality constraints Measurement invariance
MIMIC model Covariates predict the latent factors and, optionally, the indicators Group differences and differential item functioning
Congeneric, tau-equivalent and parallel models Loadings and error variances are free, loadings equal, or both equal Testing assumptions behind reliability coefficients

3.4 Path Diagram Notation

CFA and SEM models are usually presented as path diagrams. A path diagram shows the variables of a model and the relationships among them with a small set of symbols, so that the whole model can be read at a glance. The figure below shows a two-factor model with three indicators per factor, drawn in the classical LISREL notation (Jöreskog & Sörbom, 1993).

Symbol Name Meaning
Oval or circle Latent variable An unobserved construct, such as a factor, inferred from its indicators
Rectangle or square Manifest (observed) variable or indicator A variable measured directly, such as an item score
Single-headed straight arrow Path A directional relationship, pointing from the cause to the effect
Value on a single-headed arrow (λ) Path coefficient The size of a directional effect, which is a factor loading in CFA
Two-headed curved arrow between two variables (φ) Covariance or correlation A non-directional relationship, shown as a correlation in the standardised solution
Two-headed curved arrow on one variable Variance The variance of a latent variable or of an error term
Small circle pointing to an indicator (δ or ε) Error term The unique part of an indicator that is not explained by its factor
Value attached to an error term (θ) Error (residual) variance The variance of the error term, which equals 1 minus the squared loading for a standardised indicator of one factor
Latent variable with no arrows pointing to it Exogenous variable A variable whose causes are not part of the model
Latent variable with arrows pointing to it (ζ) Endogenous variable and disturbance A variable explained by other variables in the model, with its unexplained part called the disturbance

In a CFA all factors are usually exogenous, and they are connected only by two-headed arrows. Directional arrows between factors, and therefore endogenous factors with disturbances, appear only when the model is extended to a full structural equation model (Section 3.2). The path diagrams of the worked example in Section 5.6 use the same symbols.

3.5 Key Terminology in CFA

Term Meaning
Indicator An observed variable used to measure a latent factor
Factor loading The regression coefficient of an indicator on its factor, reported in unstandardised and standardised form
Residual (error) variance Indicator variance not explained by the factor
Free, fixed and constrained parameters Parameters that are estimated, set to a value, or forced to equal other parameters
Scaling the factor Giving each latent variable a metric by fixing one loading to 1 (marker variable) or the factor variance to 1
Identification Whether a unique solution exists. Models can be under-identified, just-identified or over-identified
Degrees of freedom Number of observed variances and covariances, p(p + 1)/2, minus the number of free parameters
Model-implied covariance matrix The covariance matrix reproduced by the model parameters
Model-data fit How closely the model-implied matrix reproduces the observed matrix
Residual matrix Differences between observed and model-implied covariances or correlations
Modification index Expected decrease in chi-square if a fixed parameter were freed
Nested models Models where one can be obtained from the other by constraining parameters

3.6 Steps of CFA

  1. Specify the model. State the number of factors, the indicators of each factor, factor correlations and any residual covariances based on theory or previous findings. Drawing the model as a path diagram is good practice.
  2. Check identification. The model must have zero or positive degrees of freedom, and every latent variable must be scaled. Brown (2015) recommends at least three indicators per factor.
  3. Estimate the model. Maximum likelihood is the default for continuous, approximately normal data. Robust ML (MLR) corrects standard errors and the chi-square for non-normality. For ordinal items with few categories, weighted least squares estimators based on polychoric correlations, such as WLSMV, are recommended (Flora & Curran, 2004).
  4. Evaluate global fit. Report several indices together. The table below lists commonly used guidelines, which should be applied with judgement rather than as strict rules.
  5. Evaluate local fit. Check the size, sign and significance of loadings, residual correlations and modification indices. Free a parameter only when there is a clear theoretical reason, since changes driven only by modification indices capitalise on chance (MacCallum et al., 1992).
  6. Compare alternative models. Nested models are compared with the chi-square difference test (scaled versions for robust estimators). Non-nested models are compared with information criteria such as AIC and BIC.
  7. Assess reliability and validity. Report composite reliability (omega) for each factor. Average variance extracted (AVE) and the Fornell-Larcker criterion (Fornell & Larcker, 1981), or the heterotrait-monotrait ratio (Henseler et al., 2015), are used for convergent and discriminant validity.
  8. Report the results. Present the model, estimator, fit indices, standardised loadings, factor correlations and any modifications with their justification.
Index Full name Type Good fit Acceptable fit Source
χ² Chi-square test of exact fit Absolute p > .05 Sensitive to sample size, interpreted together with other indices Kline (2023)
χ²/df Normed (relative) chi-square Absolute ≤ 2 ≤ 3 (some authors accept ≤ 5) Schermelleh-Engel et al. (2003)
GFI Goodness-of-Fit Index Absolute ≥ .95 ≥ .90 Jöreskog and Sörbom (1993); Schermelleh-Engel et al. (2003)
AGFI Adjusted Goodness-of-Fit Index Absolute ≥ .90 ≥ .85 Schermelleh-Engel et al. (2003)
RMR Root Mean Square Residual Absolute, residual-based Close to 0 Depends on the scale of the variables Jöreskog and Sörbom (1993)
SRMR Standardized Root Mean Square Residual Absolute, residual-based ≤ .05 (≤ .08 in Hu and Bentler) ≤ .10 Hu and Bentler (1999); Schermelleh-Engel et al. (2003)
WRMR Weighted Root Mean Square Residual Absolute, residual-based (WLS estimators) ≤ 1.0 Experimental, used with caution Yu (2002)
RMSEA Root Mean Square Error of Approximation Absolute, parsimony-adjusted ≤ .05 (≤ .06 in Hu and Bentler) ≤ .08 (.08 to .10 mediocre) Steiger (1990); Browne and Cudeck (1993); Hu and Bentler (1999)
PCLOSE p value for test of close fit (RMSEA ≤ .05) Absolute > .05 > .01 Browne and Cudeck (1993)
NFI Normed Fit Index Incremental ≥ .95 ≥ .90 Bentler and Bonett (1980)
NNFI (TLI) Non-Normed Fit Index (Tucker-Lewis Index) Incremental ≥ .95 ≥ .90 Tucker and Lewis (1973); Bentler and Bonett (1980); Hu and Bentler (1999)
CFI Comparative Fit Index Incremental ≥ .95 ≥ .90 Bentler (1990); Hu and Bentler (1999)
RFI Relative Fit Index Incremental ≥ .95 ≥ .90 Bollen (1986)
IFI Incremental Fit Index Incremental ≥ .95 ≥ .90 Bollen (1989)
PGFI Parsimony Goodness-of-Fit Index Parsimony Higher is better ≥ .50 Mulaik et al. (1989)
PNFI Parsimony Normed Fit Index Parsimony Higher is better ≥ .50 James et al. (1982); Mulaik et al. (1989)
CN Hoelter’s Critical N (at α = .05 or .01) Sample adequacy ≥ 200 Below 200 suggests the sample may be too small for the model Hoelter (1983)
AIC Akaike Information Criterion Information criterion Smaller is better No cut-off, used to compare models Akaike (1987)
BIC Bayesian Information Criterion Information criterion Smaller is better No cut-off, used to compare models Schwarz (1978)
ECVI Expected Cross-Validation Index Information criterion Smaller than the saturated and independence models No cut-off, used to compare models Browne and Cudeck (1993)

Absolute indices assess how well the model reproduces the observed data. Incremental indices compare the model with a baseline model in which all variables are uncorrelated. Parsimony indices penalise complex models, and information criteria are used to compare competing models fitted to the same data. Cut-off values are guidelines rather than strict rules, and they depend on sample size, model complexity, the estimator and the type of data (Hu & Bentler, 1999; Marsh et al., 2004). Several indices from different families should therefore be reported together. In R, fitMeasures(fit) in the lavaan package returns most of these indices.

Hoelter’s critical N depends on the significance level chosen for the χ² test. It is the largest sample size at which the χ² test would not reject the model, and it is usually reported for α = .05 and α = .01, which correspond to 95% and 99% confidence. Values of 200 or more are commonly taken to show that the sample is large enough for the model (Hoelter, 1983).

3.7 Self-Check Questions

You can try each question up to three times. After a correct answer, or after the third attempt, the correct answer and a short explanation are shown. Your answers do not affect your access to the next section.

1.In a CFA model, a loading that is not specified by the researcher is usually
2.Which part of a structural equation model is a CFA?
3.A model with 6 indicators has how many observed variances and covariances?
4.In a path diagram, what does a two-headed curved arrow between two factors represent?
5.Should every parameter with a large modification index be freed?

Section 4. Recent Developments in Factor Analysis

The classical distinction between EFA and CFA has been extended by several newer approaches. This section gives a short overview. Each approach deserves a detailed treatment of its own.

4.1 Bayesian Factor Analysis

In the Bayesian approach, model parameters such as loadings, factor correlations and residual variances are treated as random variables with prior distributions. The data update these priors into posterior distributions, which are usually approximated with Markov chain Monte Carlo (MCMC) methods. Results are reported as posterior means or medians with credible intervals rather than point estimates with p values.

A key idea is the use of small-variance priors (Muthén & Asparouhov, 2012). In classical CFA, cross-loadings and residual covariances are fixed to exactly zero, which is often too strict. Bayesian SEM replaces these exact zeros with approximate zeros by giving the parameters priors centred at zero with a small variance. Model fit is evaluated with posterior predictive checks, such as the posterior predictive p value. In R, Bayesian CFA can be estimated with the blavaan package (Merkle & Rosseel, 2018).

A separate, detailed document on Bayesian factor analysis is in preparation.

4.2 Exploratory Structural Equation Modeling (ESEM)

ESEM combines features of EFA and CFA. Like EFA, it allows all cross-loadings and uses rotation, and like CFA and SEM, it provides standard errors, fit indices and the possibility of including the factors in larger structural models (Asparouhov & Muthén, 2009). ESEM is especially useful for multidimensional instruments, such as personality inventories, where strict CFA models with zero cross-loadings often show poor fit and inflated factor correlations (Marsh et al., 2014).

4.3 Exploratory Graph Analysis (EGA)

EGA comes from network psychometrics. It estimates a network of partial correlations among the items and uses a community detection algorithm to identify clusters of items, which correspond to dimensions. Simulation studies showed that EGA performs comparably to or better than parallel analysis in estimating the number of dimensions (Golino & Epskamp, 2017). EGA is available in the EGAnet package in R.

4.4 Regularized Factor Analysis

Regularization adds a penalty, such as the lasso, to the estimation so that small loadings are shrunk towards zero. This produces a simpler structure without fixing parameters to zero in advance and offers an alternative to rotation and to modification-index-driven model changes (Jacobucci et al., 2016). Regularized SEM is available in packages such as regsem and lslx.

4.5 Machine Learning Approaches

Machine learning methods are increasingly used for decisions in factor analysis. The factor forest approach trains a machine learning model on many simulated datasets with known structures and then predicts the number of factors for new data from features such as eigenvalues and sample size (Goretzko & Bühner, 2020). Neural network models such as autoencoders are also discussed as nonlinear extensions of factor analytic ideas. These approaches belong to the growing field of psychometric data science, which connects classical measurement models with data-driven methods.

4.6 Self-Check Questions (Optional)

You can try each question up to three times. After a correct answer, or after the third attempt, the correct answer and a short explanation are shown. Your answers do not affect your access to the next section.

1.In Bayesian SEM, cross-loadings are typically
2.Which approach estimates the number of dimensions with community detection in a network?
3.Which approach allows cross-loadings while providing fit indices like CFA?

Section 5. Worked Example with the Big Five Inventory

In this section EFA and CFA are applied in order to the same dataset, so that the connection between the two techniques can be followed step by step. The structure is first explored on one half of the sample and then tested on the other half. Each code block is followed by an interpretation of its output.

An earlier, shorter application with the SPSS Anxiety Questionnaire (SAQ) from Field (2018), including PCA, EFA, a second-order CFA and model modifications, is available in Demir (2022), at rpubs.com/Symrna/EFA_CFA. Readers who would like a second example can work through that document as well. Comparing the two examples shows how the same steps apply to a teaching dataset and to an established personality model.

5.1 The Dataset

The five-factor model of personality is one of the most widely supported models in psychology (McCrae & John, 1992). The bfi dataset in the psychTools package contains responses of 2,800 participants to 25 items from the International Personality Item Pool (Goldberg, 1999), collected as part of the SAPA project (Revelle et al., 2010). Each item is answered on a six-point scale from very inaccurate (1) to very accurate (6), and five items measure each of the five factors. The dataset also contains gender, education and age.

Factor Items Reverse-keyed items
Agreeableness A1 to A5 A1
Conscientiousness C1 to C5 C4, C5
Extraversion E1 to E5 E1, E2
Neuroticism N1 to N5 none
Openness O1 to O5 O2, O5

The items. The wording of all 25 items is stored in the bfi.dictionary object of the psychTools package. Each item is a short statement that participants rate for how accurately it describes them. Items marked with −1 are reverse keyed, so a higher response means a lower level of the trait named in the Big6 column.

Item Wording Trait (Big6) Aspect (Little12) Keying
A1 Am indifferent to the feelings of others. Agreeableness Compassion −1
A2 Inquire about others’ well-being. Agreeableness Compassion 1
A3 Know how to comfort others. Agreeableness Compassion 1
A4 Love children. Agreeableness Compassion 1
A5 Make people feel at ease. Agreeableness Compassion 1
C1 Am exacting in my work. Conscientiousness Orderliness 1
C2 Continue until everything is perfect. Conscientiousness Orderliness 1
C3 Do things according to a plan. Conscientiousness Orderliness 1
C4 Do things in a half-way manner. Conscientiousness Industriousness −1
C5 Waste my time. Conscientiousness Industriousness −1
E1 Don’t talk a lot. Extraversion Sociability −1
E2 Find it difficult to approach others. Extraversion Sociability −1
E3 Know how to captivate people. Extraversion Assertiveness 1
E4 Make friends easily. Extraversion Sociability 1
E5 Take charge. Extraversion Assertiveness 1
N1 Get angry easily. Emotional Stability Balance −1
N2 Get irritated easily. Emotional Stability Balance −1
N3 Have frequent mood swings. Emotional Stability Balance −1
N4 Often feel blue. Emotional Stability Balance −1
N5 Panic easily. Emotional Stability Balance −1
O1 Am full of ideas. Openness Intellect 1
O2 Avoid difficult reading material. Openness Intellect −1
O3 Carry the conversation to a higher level. Openness Intellect 1
O4 Spend time reflecting on things. Openness Openness 1
O5 Will not probe deeply into a subject. Openness Openness −1

Columns of the item dictionary. Typing bfi.dictionary[1:25, ] in R shows seven columns for each item. ItemLabel is the code of the item in the SAPA item pool (for example q_146 for A1), and Item is the wording shown to the participants. Giant3 groups the traits into three broad factors, with Agreeableness as Cohesion, Conscientiousness and Neuroticism as Stability, and Extraversion and Openness as Plasticity.

Big6 gives the trait each item belongs to, and Little12 gives the narrower aspect within that trait, such as Orderliness and Industriousness within Conscientiousness. Keying shows the direction of the item, with 1 for positively keyed and −1 for reverse keyed items. IPIP100 refers to the scale of the 100-item IPIP Big Five markers from which the item was taken, for example B5:A for Agreeableness.

The dictionary names the fifth trait Emotional Stability, which is the opposite pole of Neuroticism. For this reason all five N items are marked −1, because they are keyed relative to Emotional Stability. In this guide the factor is interpreted as Neuroticism, so the N items are not reversed and only A1, C4, C5, E1, E2, O2 and O5 are reverse scored. Note also that the Giant3 grouping differs from the higher-order model in Section 5.5, which places Agreeableness under stability following DeYoung (2006) and Digman (1997).

The role of EFA with an established model. The Big Five is an established theory, and the items are not being developed here. EFA therefore does not serve to select items or redefine the scale. Its role is to check whether the expected five-factor structure emerges from the data without imposing it, and to see where the data depart from simple structure, for example through cross-loadings. CFA then tests the theoretical model formally. This is a common and legitimate sequence when an instrument is used in a new sample.

5.2 Packages and Data Preparation

The analyses use the psych package (Revelle, 2026) for EFA, lavaan (Rosseel, 2012) for CFA, semTools (Jorgensen et al., 2026) for reliability and validity, and semPlot (Epskamp, 2015) for path diagrams. All packages are freely available on CRAN and can be installed with the first line of the code below.

# install.packages(c("psych", "psychTools", "GPArotation", "lavaan", "semTools", "semPlot"))
library(psych)        # EFA, PCA, polychoric correlations, KMO, Bartlett's test, parallel analysis, reliability
library(psychTools)   # example datasets (bfi) and item dictionaries
library(GPArotation)  # rotation methods such as oblimin and geomin
library(lavaan)       # CFA, SEM and ESEM estimation, fit indices, factor scores
library(semTools)     # composite reliability (omega), AVE and other SEM tools
library(semPlot)      # path diagrams of CFA and SEM models

col1 <- "#1F6F8B"; col2 <- "#E07A5F"; col_title <- "#123F52"   # colours used in the figures

head(bfi)
Show output
      A1 A2 A3 A4 A5 C1 C2 C3 C4 C5 E1 E2 E3 E4 E5 N1 N2 N3 N4 N5 O1 O2 O3 O4 O5 gender
61617  2  4  3  4  4  2  3  3  4  4  3  3  3  4  4  3  4  2  2  3  3  6  3  4  3      1
61618  2  4  5  2  5  5  4  4  3  4  1  1  6  4  3  3  3  3  5  5  4  2  4  3  3      2
61620  5  4  5  4  4  4  5  4  2  5  2  4  4  4  5  4  5  4  2  3  4  2  5  5  2      2
61621  4  4  6  5  5  4  4  3  5  5  5  3  4  4  4  2  5  2  4  1  3  3  4  3  5      2
61622  2  3  3  4  5  4  4  5  3  2  2  2  5  4  5  2  3  4  4  3  3  3  4  3  3      1
61623  6  6  5  6  5  6  6  6  1  3  2  1  6  5  6  3  5  2  2  3  4  3  5  6  1      2
      education age
61617        NA  16
61618        NA  18
61620        NA  17
61621        NA  17
61622        NA  17
61623         3  21
bfi.dictionary[1:25, ]   # item wording
Show output
   ItemLabel                                      Item     Giant3                Big6
A1     q_146 Am indifferent to the feelings of others.   Cohesion       Agreeableness
A2    q_1162         Inquire about others' well-being.   Cohesion       Agreeableness
A3    q_1206               Know how to comfort others.   Cohesion       Agreeableness
A4    q_1364                            Love children.   Cohesion       Agreeableness
A5    q_1419                 Make people feel at ease.   Cohesion       Agreeableness
C1     q_124                   Am exacting in my work.  Stability   Conscientiousness
C2     q_530     Continue until everything is perfect.  Stability   Conscientiousness
C3     q_619            Do things according to a plan.  Stability   Conscientiousness
C4     q_626           Do things in a half-way manner.  Stability   Conscientiousness
C5    q_1949                            Waste my time.  Stability   Conscientiousness
E1     q_712                         Don't talk a lot. Plasticity        Extraversion
E2     q_901     Find it difficult to approach others. Plasticity        Extraversion
E3    q_1205             Know how to captivate people. Plasticity        Extraversion
E4    q_1410                      Make friends easily. Plasticity        Extraversion
E5    q_1768                              Take charge. Plasticity        Extraversion
N1     q_952                         Get angry easily.  Stability Emotional Stability
N2     q_974                     Get irritated easily.  Stability Emotional Stability
N3    q_1099                Have frequent mood swings.  Stability Emotional Stability
N4    q_1479                          Often feel blue.  Stability Emotional Stability
N5    q_1505                             Panic easily.  Stability Emotional Stability
O1     q_128                         Am full of ideas. Plasticity            Openness
O2     q_316         Avoid difficult reading material. Plasticity            Openness
O3     q_492 Carry the conversation to a higher level. Plasticity            Openness
O4    q_1738          Spend time reflecting on things. Plasticity            Openness
O5    q_1964     Will not probe deeply into a subject. Plasticity            Openness
          Little12 Keying IPIP100
A1      Compassion     -1    B5:A
A2      Compassion      1    B5:A
A3      Compassion      1    B5:A
A4      Compassion      1    B5:A
A5      Compassion      1    B5:A
C1     Orderliness      1    B5:C
C2     Orderliness      1    B5:C
C3     Orderliness      1    B5:C
C4 Industriousness     -1    B5:C
C5 Industriousness     -1    B5:C
E1     Sociability     -1    B5:E
E2     Sociability     -1    B5:E
E3   Assertiveness      1    B5:E
E4     Sociability      1    B5:E
E5   Assertiveness      1    B5:E
N1         Balance     -1    B5:N
N2         Balance     -1    B5:N
N3         Balance     -1    B5:N
N4         Balance     -1    B5:N
N5         Balance     -1    B5:N
O1       Intellect      1    B5:O
O2       Intellect     -1    B5:O
O3       Intellect      1    B5:O
O4        Openness      1    B5:O
O5        Openness     -1    B5:O
items <- bfi[, 1:25]
colSums(is.na(items))     # missing values per item
Show output
A1 A2 A3 A4 A5 C1 C2 C3 C4 C5 E1 E2 E3 E4 E5 N1 N2 N3 N4 N5 O1 O2 O3 O4 O5 
16 27 26 19 16 21 24 20 26 16 23 16 25  9 21 22 21 11 36 29 22  0 28 14 20 
items <- na.omit(items)   # listwise deletion for simplicity
nrow(items)
Show output
[1] 2436
# Reverse score the negatively keyed items (six-point scale)
rev_items <- c("A1", "C4", "C5", "E1", "E2", "O2", "O5")
items[rev_items] <- 7 - items[rev_items]

describe(items)
Show output
   vars    n mean   sd median trimmed  mad min max range  skew kurtosis   se
A1    1 2436 4.59 1.41      5    4.78 1.48   1   6     5 -0.84    -0.28 0.03
A2    2 2436 4.80 1.18      5    4.97 1.48   1   6     5 -1.12     1.01 0.02
A3    3 2436 4.60 1.31      5    4.79 1.48   1   6     5 -1.01     0.46 0.03
A4    4 2436 4.69 1.49      5    4.92 1.48   1   6     5 -1.02     0.02 0.03
A5    5 2436 4.54 1.27      5    4.70 1.48   1   6     5 -0.84     0.13 0.03
C1    6 2436 4.53 1.24      5    4.66 1.48   1   6     5 -0.87     0.32 0.03
C2    7 2436 4.37 1.32      5    4.50 1.48   1   6     5 -0.74    -0.15 0.03
C3    8 2436 4.30 1.29      5    4.41 1.48   1   6     5 -0.68    -0.15 0.03
C4    9 2436 4.45 1.38      5    4.59 1.48   1   6     5 -0.61    -0.59 0.03
C5   10 2436 3.69 1.63      4    3.74 1.48   1   6     5 -0.06    -1.23 0.03
E1   11 2436 4.02 1.63      4    4.14 1.48   1   6     5 -0.37    -1.09 0.03
E2   12 2436 3.85 1.61      4    3.93 1.48   1   6     5 -0.23    -1.15 0.03
E3   13 2436 3.98 1.35      4    4.05 1.48   1   6     5 -0.47    -0.46 0.03
E4   14 2436 4.41 1.47      5    4.58 1.48   1   6     5 -0.82    -0.32 0.03
E5   15 2436 4.39 1.34      5    4.53 1.48   1   6     5 -0.78    -0.11 0.03
N1   16 2436 2.94 1.58      3    2.84 1.48   1   6     5  0.37    -1.02 0.03
N2   17 2436 3.52 1.53      4    3.52 1.48   1   6     5 -0.08    -1.06 0.03
N3   18 2436 3.22 1.59      3    3.17 1.48   1   6     5  0.14    -1.18 0.03
N4   19 2436 3.20 1.57      3    3.14 1.48   1   6     5  0.20    -1.09 0.03
N5   20 2436 2.97 1.62      3    2.85 1.48   1   6     5  0.38    -1.07 0.03
O1   21 2436 4.81 1.13      5    4.96 1.48   1   6     5 -0.90     0.46 0.02
O2   22 2436 4.32 1.55      5    4.47 1.48   1   6     5 -0.62    -0.76 0.03
O3   23 2436 4.45 1.21      5    4.57 1.48   1   6     5 -0.77     0.32 0.02
O4   24 2436 4.93 1.19      5    5.13 1.48   1   6     5 -1.24     1.18 0.02
O5   25 2436 4.53 1.32      5    4.68 1.48   1   6     5 -0.76    -0.18 0.03

A note on warning messages. When you run the code yourself, R may print warning messages that are not shown on this page. For example, the polychoric correlations can produce warnings about empty response categories, and lavaan warns when a solution contains negative variances. Such warnings do not stop the analysis, but they should be read, and the lavaan warning for the higher-order model is discussed in Section 5.5.

Listwise deletion is used here to keep the example simple. In applied work, full information maximum likelihood or multiple imputation is usually preferable when data are missing. In this dataset the proportion of missing values is small, so listwise deletion has little effect on the results.

Interpretation. Of the 2,800 participants, 364 have at least one missing item response, so 2,436 complete cases remain for the analyses. After reverse scoring, higher scores on every item indicate a higher level of the trait it measures. The results reported in this section were obtained with the seed 2026 and may differ slightly with other R or package versions.

5.3 Splitting the Data

When EFA and CFA are run on the same data, the CFA is not a real test of the model. The EFA has already shaped the model to fit that particular sample, including its random fluctuations, so a good CFA fit is partly circular. This problem is known as capitalising on chance (MacCallum et al., 1992).

The solution is cross-validation. The sample is randomly divided into two halves. The first half, the calibration sample, is used for EFA. The second half, the validation sample, is used for CFA. If the structure found in the first half also fits well in the second half, there is stronger evidence that it is not specific to one sample (Worthington & Whittaker, 2006). Three practical points should be considered.

  • Each half must be large enough for its own analysis. With about 2,400 complete cases, each half has around 1,200 cases.
  • The split must be random, and a seed should be set so that the results can be reproduced.
  • The two halves should be compared on basic descriptive statistics to confirm that they are similar.

Ideally, the final model should also be confirmed in a completely new sample. Cross-validation within one sample is a useful first step, but it cannot replace replication in an independent study. Results that hold across different samples and populations provide the strongest evidence.

set.seed(2026)
n <- nrow(items)
idx <- sample(seq_len(n), size = floor(n / 2))
calib <- items[idx, ]    # EFA
valid <- items[-idx, ]   # CFA

round(cbind(calib = colMeans(calib), valid = colMeans(valid)), 2)
Show output
   calib valid
A1  4.58  4.61
A2  4.79  4.80
A3  4.59  4.61
A4  4.70  4.68
A5  4.54  4.55
C1  4.56  4.49
C2  4.38  4.36
C3  4.34  4.26
C4  4.51  4.39
C5  3.80  3.59
E1  3.99  4.05
E2  3.85  3.84
E3  3.98  3.99
E4  4.39  4.43
E5  4.40  4.38
N1  2.91  2.97
N2  3.46  3.57
N3  3.19  3.26
N4  3.16  3.25
N5  2.95  2.99
O1  4.83  4.79
O2  4.34  4.29
O3  4.47  4.43
O4  4.92  4.93
O5  4.57  4.49

Interpretation. Each half contains 1,218 cases. The largest difference between the item means of the two halves is 0.22 points on the six-point scale, and most differences are much smaller, so the two halves are comparable. Any differences in the results of the two analyses are therefore not caused by systematic differences between the halves.

5.4 EFA on the Calibration Sample

Working on this part only? Show the setup code

This code is optional and only needed if you start with the EFA part in a new R session, without running the earlier sections. It loads the packages and creates the objects that this part uses. The results are the same as when the whole guide is run in order.

library(psych); library(psychTools); library(GPArotation)
library(lavaan); library(semTools); library(semPlot)
col1 <- "#1F6F8B"; col2 <- "#E07A5F"; col_title <- "#123F52"   # colours used in the figures

# data preparation (Section 5.2)
items <- na.omit(bfi[, 1:25])
rev_items <- c("A1", "C4", "C5", "E1", "E2", "O2", "O5")
items[rev_items] <- 7 - items[rev_items]

# splitting the data (Section 5.3)
set.seed(2026)
idx <- sample(seq_len(nrow(items)), size = floor(nrow(items) / 2))
calib <- items[idx, ]    # EFA
valid <- items[-idx, ]   # CFA

Factorability and number of factors.

R <- polychoric(calib)$rho
KMO(R)
Show output
Kaiser-Meyer-Olkin factor adequacy
Call: KMO(r = R)
Overall MSA =  0.85
MSA for each item = 
  A1   A2   A3   A4   A5   C1   C2   C3   C4   C5   E1   E2   E3   E4   E5   N1   N2   N3   N4 
0.80 0.83 0.87 0.89 0.91 0.86 0.80 0.87 0.83 0.87 0.84 0.89 0.91 0.88 0.89 0.77 0.77 0.87 0.88 
  N5   O1   O2   O3   O4   O5 
0.87 0.88 0.79 0.83 0.77 0.78 
cortest.bartlett(R, n = nrow(calib))
Show output
$chisq
[1] 12162.82

$p.value
[1] 0

$df
[1] 300
fa.parallel(calib, cor = "poly", fm = "minres", fa = "fa")

Show output
Parallel analysis suggests that the number of factors =  6  and the number of components =  NA 
map_res <- vss(calib, n = 8, cor = "poly", plot = FALSE)   # includes Velicer's MAP
round(map_res$map, 3)
Show output
[1] 0.033 0.027 0.025 0.021 0.017 0.018 0.021 0.024
plot(1:8, map_res$map, type = "b", pch = 19, col = col1, lwd = 2.5, bty = "l", las = 1,
     xlab = "Number of components removed", ylab = "Average squared partial correlation",
     main = "Velicer's MAP test", col.main = col_title)
k <- which.min(map_res$map)
points(k, map_res$map[k], pch = 21, cex = 2.2, col = col2, lwd = 2)
text(k, map_res$map[k], paste("minimum at", k), pos = 1, offset = 1.2, col = col2)

How to read the MAP test. The vss() output reports the average squared partial correlation after 1, 2, 3 and more components have been removed. In this sample the values are .033, .027, .025, .021, .017, .018, .021 and .024 for one to eight components, so the curve falls until five components and rises again from six. The minimum at five components means that removing a sixth component no longer takes away common variance among the items, and the MAP test therefore suggests five factors. Unlike the Kaiser rule and parallel analysis, the MAP test tends to underestimate rather than overestimate the number of factors when it errs, so the two criteria complement each other.

Parallel analysis may suggest more factors than the theory predicts. This is a good opportunity to discuss why the number of factors should not be decided by a single criterion. The results of all criteria are interpreted together below.

Interpretation. The overall KMO value is .85, which Kaiser (1974) describes as meritorious, and the lowest item-level value is .77 (N2), so every item is suitable for factor analysis. Bartlett’s test is significant, χ²(300) = 12,162.82, p < .001, so the correlation matrix is clearly different from an identity matrix. Both checks therefore support continuing with factor analysis.

Rpoly <- polychoric(calib)$rho
pal_r <- colorRampPalette(c(col2, "#F7F7F7", col1))(101)
par(mar = c(4, 4, 3, 6))
image(1:25, 1:25, Rpoly[, 25:1], col = pal_r, zlim = c(-1, 1), axes = FALSE,
      xlab = "", ylab = "", main = "Polychoric correlations among the 25 items",
      col.main = col_title)
axis(1, at = 1:25, labels = colnames(Rpoly), las = 2, tick = FALSE, cex.axis = 0.75)
axis(2, at = 1:25, labels = rev(colnames(Rpoly)), las = 1, tick = FALSE, cex.axis = 0.75)
abline(v = c(5.5, 10.5, 15.5, 20.5), h = c(5.5, 10.5, 15.5, 20.5), col = "white", lwd = 2.5)
par(xpd = TRUE)
for (i in 1:100) rect(26.2, 3 + (i - 1) * 0.19, 27.0, 3 + i * 0.19, col = pal_r[i], border = NA)
text(27.3, c(3, 12.5, 22), c("-1", "0", "1"), adj = 0, cex = 0.8)

par(xpd = FALSE)

Figure 1. Polychoric correlations among the 25 items in the calibration sample, with blue for positive and red for negative correlations. The five darker blocks along the diagonal show that items of the same trait correlate more strongly with each other than with items of other traits. The correlations range from −.40 to .78, and the negative values come mostly from Neuroticism items, which relate inversely to the other traits.

The criteria for the number of factors do not fully agree. Two criteria suggest six factors and two suggest five, as summarised in the table below. Such disagreement is common in practice, especially with large samples.

Criterion Suggested number of factors
Kaiser rule (eigenvalues 5.94, 2.90, 2.23, 2.01, 1.69, 1.06, 0.81) 6
Parallel analysis 6
Velicer’s MAP test 5
Theory (five-factor model) 5

The sixth eigenvalue (1.06) is only slightly above 1. Because both the five- and six-factor solutions are plausible, both are examined below and the decision is made by looking at the content of the factors. A solution with more factors should be preferred only if the extra factor is meaningful and interpretable.

pa <- fa.parallel(calib, cor = "poly", fm = "minres", fa = "fa", plot = FALSE)
Show output
Parallel analysis suggests that the number of factors =  6  and the number of components =  NA 
x <- 1:12
plot(x, pa$fa.values[x], type = "b", pch = 19, col = col1, lwd = 2.5,
     ylim = c(-0.3, max(pa$fa.values) + 0.3), xaxt = "n", bty = "l", las = 1,
     xlab = "Factor number", ylab = "Eigenvalue (common factor)",
     main = "Scree plot and parallel analysis", col.main = col_title)
axis(1, at = x)
lines(x, pa$fa.sim[x], type = "b", lty = 2, pch = 1, col = col2, lwd = 2)
abline(v = 5.5, col = "grey55", lty = 3)
legend("topright", c("Observed data", "Random data (parallel analysis)"),
       col = c(col1, col2), lty = c(1, 2), pch = c(19, 1), lwd = 2, bty = "n")

Figure 2. Scree plot of the observed eigenvalues and the eigenvalues from random data. Factors whose observed eigenvalue lies above the random-data line are retained by parallel analysis. The observed line drops sharply after the fifth factor, and the sixth factor lies only just above the random-data line.

PCA and EFA compared. To show the difference discussed in Section 2.2, the same data are analysed with PCA and with common factor analysis. Five components and five factors are extracted, so that only the method differs. The communalities of the two solutions are then compared.

pca5 <- principal(calib, nfactors = 5, rotate = "varimax")
efa5 <- fa(calib, nfactors = 5, fm = "minres", rotate = "oblimin", cor = "poly")

round(cbind(PCA = pca5$communality, EFA = efa5$communality), 2)
Show output
    PCA  EFA
A1 0.48 0.28
A2 0.63 0.61
A3 0.63 0.62
A4 0.45 0.38
A5 0.54 0.53
C1 0.52 0.44
C2 0.59 0.51
C3 0.48 0.38
C4 0.57 0.55
C5 0.56 0.53
E1 0.43 0.34
E2 0.61 0.62
E3 0.52 0.48
E4 0.63 0.62
E5 0.51 0.47
N1 0.68 0.70
N2 0.66 0.64
N3 0.63 0.60
N4 0.59 0.55
N5 0.50 0.44
O1 0.48 0.43
O2 0.44 0.31
O3 0.58 0.56
O4 0.43 0.35
O5 0.45 0.33

PCA communalities are usually higher, because PCA analyses total variance and does not separate unique variance from common variance. The difference is expected to be largest for items with low communalities.

Interpretation. The mean communality is .54 for PCA and .49 for EFA. The difference is largest for the weaker items, for example A1 (.48 in PCA versus .28 in EFA) and O5 (.45 versus .33). PCA attributes part of the unique variance of these items to the components, so it presents them as better measures than they really are.

The EFA solution.

print(efa5$loadings, cutoff = .30, sort = TRUE)
Show output

Loadings:
   MR2    MR3    MR1    MR4    MR5   
N1  0.837                            
N2  0.795                            
N3  0.754                            
N4  0.525 -0.387                     
N5  0.555                            
E1         0.543                     
E2         0.712                     
E4         0.669                     
C1                0.628              
C2                0.713              
C3                0.605              
C4                0.672              
C5                0.617              
A1                       0.505       
A2                       0.763       
A3                       0.720       
A4                       0.515       
A5                       0.538       
O1                              0.593
O3                              0.685
O5                              0.553
E3         0.461                0.319
E5         0.486                     
O2                              0.481
O4        -0.350                0.447

                 MR2   MR3   MR1   MR4   MR5
SS loadings    2.809 2.307 2.294 2.170 1.849
Proportion Var 0.112 0.092 0.092 0.087 0.074
Cumulative Var 0.112 0.205 0.296 0.383 0.457
efa5$Phi                 # factor correlations
Show output
            MR2        MR3        MR1         MR4         MR5
MR2  1.00000000 -0.2211914 -0.2060865 -0.07909413 -0.01872189
MR3 -0.22119142  1.0000000  0.2437765  0.30758261  0.15422096
MR1 -0.20608654  0.2437765  1.0000000  0.23578124  0.18916657
MR4 -0.07909413  0.3075826  0.2357812  1.00000000  0.20611943
MR5 -0.01872189  0.1542210  0.1891666  0.20611943  1.00000000
fa.diagram(efa5)

# Alternative solution suggested by the criteria, if different
efa6 <- fa(calib, nfactors = 6, fm = "minres", rotate = "oblimin", cor = "poly")
print(efa6$loadings, cutoff = .30, sort = TRUE)
Show output

Loadings:
   MR6    MR2    MR3    MR4    MR5    MR1   
N1  0.893                                   
N2  0.876                                   
N3  0.692                                   
E1         0.568                            
E2         0.744                            
E4         0.651                            
C1                0.624                     
C2                0.763                     
C3                0.591                     
C4                0.646               -0.366
C5                0.579                     
A1                       0.596              
A2                       0.801              
A3                       0.694              
O1                              0.611       
O3                              0.694       
O5                              0.541 -0.341
A4                       0.480              
A5                       0.481              
E3         0.430                0.351       
E5         0.487                            
N4  0.435 -0.439                            
N5  0.449                                   
O2                              0.460 -0.306
O4        -0.385                0.451       

                 MR6   MR2   MR3   MR4   MR5   MR1
SS loadings    2.572 2.415 2.262 2.123 1.881 0.778
Proportion Var 0.103 0.097 0.090 0.085 0.075 0.031
Cumulative Var 0.103 0.199 0.290 0.375 0.450 0.481

Check whether each item loads mainly on its expected factor, which items show cross-loadings, and whether an extra factor is substantively meaningful or only a minor method or content factor. The pattern loadings and factor correlations are used for interpretation, because the solution is oblique. The six-factor solution is examined in the same way.

Interpretation of the five-factor solution. The five factors correspond clearly to the Big Five traits. Neuroticism (N1 to N5, loadings .53 to .84), Extraversion (E1, E2, E4, E5 and E3, loadings .46 to .71), Conscientiousness (C1 to C5, .61 to .71), Agreeableness (A1 to A5, .51 to .76) and Openness (O1, O2, O3, O5 and O4, .45 to .69) are recovered without any item loading mainly on the wrong factor. Together the five factors explain 45.7% of the total variance.

L <- unclass(efa5$loadings)
# order the factor columns by the trait whose items load highest on them
ord <- sapply(c("N", "E", "C", "A", "O"), function(p)
  which.max(colMeans(abs(L[grep(paste0("^", p), rownames(L)), ]))))
L <- L[, ord]
colnames(L) <- c("Neuroticism", "Extraversion", "Conscientiousness",
                 "Agreeableness", "Openness")
rows <- c(paste0("N", 1:5), paste0("E", 1:5), paste0("C", 1:5),
          paste0("A", 1:5), paste0("O", 1:5))
L <- L[rows, ]
pal <- colorRampPalette(c("#B23A48", "#F7F7F7", col1))(101)
par(mar = c(9.5, 4, 3, 1))
image(1:5, 1:25, t(L)[, 25:1], col = pal, zlim = c(-1, 1), axes = FALSE,
      xlab = "", ylab = "", main = "EFA pattern loadings (five factors)",
      col.main = col_title)
axis(2, at = 1:25, labels = rev(rows), las = 1, tick = FALSE)
axis(1, at = 1:5, labels = colnames(L), las = 2, tick = FALSE)
for (i in 1:5) for (j in 1:25) {
  v <- t(L)[i, 26 - j]
  text(i, j, sprintf("%.2f", v), cex = 0.75, font = ifelse(abs(v) >= .30, 2, 1),
       col = ifelse(abs(v) >= .30, "black", "grey55"))
}
abline(h = c(5.5, 10.5, 15.5, 20.5), col = "white", lwd = 3)

Figure 3. Pattern loadings of the five-factor EFA solution. Darker blue cells show stronger positive loadings, red cells show negative loadings, and loadings of at least .30 are printed in bold. Each block of five items loads mainly on its own trait, and the few bold values outside the blocks are the cross-loadings discussed below.

Three items have cross-loadings of at least .30. E3 (“Know how to captivate people”) loads on Extraversion (.46) and Openness (.32), N4 (“Often feel blue”) loads on Neuroticism (.53) and negatively on Extraversion (−.39), and O4 (“Spend time reflecting on things”) loads on Openness (.45) and negatively on Extraversion (−.35). These items share content with more than one trait, which is common in personality inventories.

The factor correlations are small to moderate. The highest is between Extraversion and Agreeableness (.31), and Neuroticism correlates negatively with the other traits (−.22 to −.02). Since the factors are correlated, the oblique rotation was the right choice.

Interpretation of the six-factor solution. The sixth factor explains only 3.1% of the variance and is defined by negative loadings of C4 (−.37), O5 (−.34) and O2 (−.31), which are all reverse-keyed items. It therefore reflects the wording of the items rather than a substantive trait, a so-called method factor. The five-factor solution is retained, in line with the MAP test and with theory. This example shows why the number of factors should be decided by combining statistical criteria with the content of the factors.

5.5 CFA on the Validation Sample

Working on this part only? Show the setup code

This code is optional and only needed if you start with the CFA part in a new R session, without running the earlier sections. It loads the packages and creates the objects that this part uses. The results are the same as when the whole guide is run in order.

library(psych); library(psychTools); library(GPArotation)
library(lavaan); library(semTools); library(semPlot)
col1 <- "#1F6F8B"; col2 <- "#E07A5F"; col_title <- "#123F52"   # colours used in the figures

# data preparation (Section 5.2)
items <- na.omit(bfi[, 1:25])
rev_items <- c("A1", "C4", "C5", "E1", "E2", "O2", "O5")
items[rev_items] <- 7 - items[rev_items]

# splitting the data (Section 5.3)
set.seed(2026)
idx <- sample(seq_len(nrow(items)), size = floor(nrow(items) / 2))
calib <- items[idx, ]    # EFA
valid <- items[-idx, ]   # CFA

The theoretical models are now specified in advance and tested on the validation sample. Four models are compared, a one-factor model, five orthogonal factors, five correlated factors, and a higher-order model in which the five traits are explained by two metatraits, stability and plasticity (DeYoung, 2006; Digman, 1997). Because the items are ordinal, the WLSMV estimator is used.

m1 <- paste("general =~", paste(names(items), collapse = " + "))

m5 <- '
  agree =~ A1 + A2 + A3 + A4 + A5
  consc =~ C1 + C2 + C3 + C4 + C5
  extra =~ E1 + E2 + E3 + E4 + E5
  neuro =~ N1 + N2 + N3 + N4 + N5
  open  =~ O1 + O2 + O3 + O4 + O5
'

# Higher-order model with two metatraits (Digman, 1997; DeYoung, 2006)
m5h <- paste(m5, '
  stability  =~ agree + consc + neuro
  plasticity =~ extra + open
')

fit1  <- cfa(m1,  data = valid, ordered = TRUE, estimator = "WLSMV")
fit5o <- cfa(m5,  data = valid, ordered = TRUE, estimator = "WLSMV", orthogonal = TRUE)
fit5  <- cfa(m5,  data = valid, ordered = TRUE, estimator = "WLSMV")
fit5h <- cfa(m5h, data = valid, ordered = TRUE, estimator = "WLSMV")

idx_fit <- c("chisq.scaled", "df.scaled", "cfi.scaled", "tli.scaled",
             "rmsea.scaled", "srmr")
round(rbind(one_factor   = fitMeasures(fit1,  idx_fit),
            orthogonal_5 = fitMeasures(fit5o, idx_fit),
            correlated_5 = fitMeasures(fit5,  idx_fit),
            higher_order = fitMeasures(fit5h, idx_fit)), 3)
Show output
             chisq.scaled df.scaled cfi.scaled tli.scaled rmsea.scaled  srmr
one_factor       8100.837       275      0.498      0.453        0.153 0.143
orthogonal_5     6149.642       275      0.623      0.589        0.132 0.156
correlated_5     3139.112       265      0.816      0.791        0.094 0.085
higher_order     2992.663       269      0.825      0.805        0.091 0.088
lavTestLRT(fit5o, fit5)    # do the factor correlations matter?
Show output

Scaled and Shifted Chi-Squared Difference Test (method = "satorra.2000")

lavaan->lavTestLRT():  
   lavaan NOTE: The "Chisq" column contains standard test statistics, not the robust test 
   that should be reported per model. A robust difference test is a function of two standard 
   (not robust) statistics.

       Df AIC BIC   Chisq Chisq diff   RMSEA Df diff Pr(>Chisq)    
fit5  265          3263.3                                          
fit5o 275         11965.8     1140.9 0.84479      10  < 2.2e-16 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
# standardised loadings, one row per item
std5 <- standardizedSolution(fit5)
subset(std5, op == "=~", select = c(lhs, rhs, est.std, se, pvalue))
Show output
     lhs rhs est.std    se pvalue
1  agree  A1   0.335 0.028      0
2  agree  A2   0.665 0.022      0
3  agree  A3   0.764 0.018      0
4  agree  A4   0.543 0.027      0
5  agree  A5   0.771 0.019      0
6  consc  C1   0.596 0.025      0
7  consc  C2   0.611 0.027      0
8  consc  C3   0.512 0.025      0
9  consc  C4   0.752 0.022      0
10 consc  C5   0.664 0.025      0
11 extra  E1   0.562 0.023      0
12 extra  E2   0.720 0.019      0
13 extra  E3   0.702 0.020      0
14 extra  E4   0.717 0.019      0
15 extra  E5   0.616 0.023      0
16 neuro  N1   0.874 0.011      0
17 neuro  N2   0.816 0.012      0
18 neuro  N3   0.745 0.015      0
19 neuro  N4   0.685 0.021      0
20 neuro  N5   0.527 0.023      0
21  open  O1   0.614 0.030      0
22  open  O2   0.386 0.035      0
23  open  O3   0.875 0.029      0
24  open  O4   0.221 0.040      0
25  open  O5   0.476 0.031      0
# thresholds side by side, one row per item and one column per threshold
th <- subset(parameterEstimates(fit5), op == "|")
round(xtabs(est ~ lhs + rhs, data = th), 2)
Show output
    rhs
lhs     t1    t2    t3    t4    t5
  A1 -1.86 -1.22 -0.77 -0.34  0.41
  A2 -2.15 -1.52 -1.21 -0.50  0.51
  A3 -1.84 -1.34 -0.97 -0.34  0.63
  A4 -1.66 -1.15 -0.86 -0.39  0.26
  A5 -2.04 -1.38 -0.91 -0.22  0.68
  C1 -1.97 -1.36 -0.90 -0.21  0.82
  C2 -1.90 -1.18 -0.77 -0.09  0.87
  C3 -1.81 -1.14 -0.71  0.03  0.96
  C4 -2.01 -1.22 -0.58 -0.12  0.65
  C5 -1.17 -0.52  0.05  0.34  0.99
  E1 -1.38 -0.79 -0.31  0.03  0.70
  E2 -1.32 -0.74 -0.16  0.20  0.94
  E3 -1.59 -1.00 -0.50  0.29  1.17
  E4 -1.68 -1.08 -0.73 -0.25  0.66
  E5 -1.85 -1.16 -0.79 -0.12  0.83
  N1 -0.73 -0.09  0.28  0.83  1.43
  N2 -1.17 -0.53 -0.14  0.49  1.16
  N3 -1.00 -0.27  0.07  0.66  1.35
  N4 -1.03 -0.28  0.11  0.71  1.31
  N5 -0.74 -0.09  0.27  0.83  1.34
  O1 -2.44 -1.66 -1.15 -0.40  0.48
  O2 -1.58 -0.96 -0.47 -0.10  0.55
  O3 -1.93 -1.41 -0.92 -0.07  0.90
  O4 -2.11 -1.58 -1.18 -0.58  0.24
  O5 -1.97 -1.27 -0.74 -0.20  0.62
# factor correlations
round(lavInspect(fit5, "cor.lv"), 2)
Show output
      agree consc extra neuro  open
agree  1.00                        
consc  0.37  1.00                  
extra  0.74  0.38  1.00            
neuro -0.26 -0.28 -0.24  1.00      
open   0.29  0.33  0.49 -0.06  1.00
# the full output can still be printed with
# summary(fit5, standardized = TRUE, fit.measures = TRUE)
compRelSEM(fit5)           # omega for each factor
Show output
$agree

Composite `agree` is composed of observed variables:
    A1, A2, A3, A4, A5
True-score variance is represented by common factor(s):
    agree
Total variance of composite `agree` determined from the unrestricted model.
The proportion attributable to "true" scores is its model-based estimate of reliability ("omega"):

[1] 0.699

$consc

Composite `consc` is composed of observed variables:
    C1, C2, C3, C4, C5
True-score variance is represented by common factor(s):
    consc
Total variance of composite `consc` determined from the unrestricted model.
The proportion attributable to "true" scores is its model-based estimate of reliability ("omega"):

[1] 0.746

$extra

Composite `extra` is composed of observed variables:
    E1, E2, E3, E4, E5
True-score variance is represented by common factor(s):
    extra
Total variance of composite `extra` determined from the unrestricted model.
The proportion attributable to "true" scores is its model-based estimate of reliability ("omega"):

[1] 0.768

$neuro

Composite `neuro` is composed of observed variables:
    N1, N2, N3, N4, N5
True-score variance is represented by common factor(s):
    neuro
Total variance of composite `neuro` determined from the unrestricted model.
The proportion attributable to "true" scores is its model-based estimate of reliability ("omega"):

[1] 0.856

$open

Composite `open` is composed of observed variables:
    O1, O2, O3, O4, O5
True-score variance is represented by common factor(s):
    open
Total variance of composite `open` determined from the unrestricted model.
The proportion attributable to "true" scores is its model-based estimate of reliability ("omega"):

[1] 0.55
AVE(fit5)                  # average variance extracted
Show output
agree consc extra neuro  open 
0.405 0.399 0.444 0.546 0.314 

Interpretation of model fit.

Model χ² (scaled) df CFI TLI RMSEA [90% CI] SRMR
One factor 8,100.84 275 .498 .453 .153 [.150, .156] .143
Five orthogonal factors 6,149.64 275 .623 .589 .132 [.130, .135] .156
Five correlated factors 3,139.11 265 .816 .791 .094 [.091, .097] .085
Higher-order (stability, plasticity) 2,992.66 269 .825 .805 .091 [.088, .094] .088

The one-factor model fits very poorly, so the 25 items cannot be explained by a single general personality factor. Allowing the five factors to correlate improves the fit substantially, and the scaled chi-square difference test confirms this, Δχ²(10) = 1,140.9, p < .001. The five personality traits are therefore related to each other, as expected from previous research.

# the ESEM model is fitted here as well, so that it can be shown in the figure
all_items <- paste(names(items), collapse = " + ")
m_esem <- paste0('efa("b1")*f1 + efa("b1")*f2 + efa("b1")*f3 + efa("b1")*f4 + efa("b1")*f5 =~ ', all_items)
fit_esem <- cfa(m_esem, data = valid, ordered = TRUE, estimator = "WLSMV", rotation = "geomin")
fits <- sapply(list(fit1, fit5o, fit5, fit5h, fit_esem), fitMeasures,
               fit.measures = c("cfi.scaled", "rmsea.scaled"))
models <- c("One factor", "Five orthogonal", "Five correlated",
            "Higher-order (improper)", "ESEM")
bar_col <- c(rep("#9CC3D1", 4), col1)
par(mfrow = c(1, 2), mar = c(4.5, 11, 3, 1))
bp <- barplot(rev(fits[1, ]), horiz = TRUE, names.arg = rev(models), las = 1,
              col = rev(bar_col), border = NA, xlim = c(0, 1.12), xlab = "CFI",
              main = "CFI (higher is better)", col.main = col_title)
abline(v = c(.90, .95), lty = c(3, 2), col = col2, lwd = 2)
text(rev(fits[1, ]), bp, sprintf("%.3f", rev(fits[1, ])), pos = 4, cex = 0.8)
bp <- barplot(rev(fits[2, ]), horiz = TRUE, names.arg = rev(models), las = 1,
              col = rev(bar_col), border = NA, xlim = c(0, 0.20), xlab = "RMSEA",
              main = "RMSEA (lower is better)", col.main = col_title)
abline(v = c(.06, .08), lty = c(2, 3), col = col2, lwd = 2)
text(rev(fits[2, ]), bp, sprintf("%.3f", rev(fits[2, ])), pos = 4, cex = 0.8)

Figure 4. CFI and RMSEA of the CFA models and the ESEM model in the validation sample. The dashed and dotted lines mark the guidelines for good and acceptable fit (Hu & Bentler, 1999). Only the ESEM model reaches the acceptable range on both indices, and the higher-order model is labelled improper because of its Heywood case.

The higher-order model shows slightly better fit indices, but its solution is improper. lavaan warns that some latent variances are negative, and the standardised loading of Extraversion on plasticity is 1.01, which is impossible. This is a Heywood case, which is likely here because each second-order factor has only two or three first-order indicators. An improper solution should not be interpreted, so the five correlated factors model is preferred.

Even this model does not reach the conventional guidelines in Section 3.6 (CFI .816 and TLI .791 are below .90, RMSEA .094 is above .08), although SRMR (.085) is acceptable. If the same model is estimated with ML and the items are treated as continuous, cfa(m5, data = valid, estimator = "ML"), the results are similar, χ²/df = 8.54, GFI = .87, AGFI = .82, NFI = .75, NNFI = .74, CFI = .77, RFI = .72 and IFI = .77. Poor fit of strict CFA models is a well-known finding for personality data (Marsh et al., 2014), and the next steps examine where the misfit comes from.

Interpretation of the parameters. All standardised loadings are significant and range from .22 to .88. The weakest indicators are O4 (.22), A1 (.34), O2 (.39) and O5 (.48), the same items that showed low communalities or cross-loadings in the EFA. The strongest factor correlation is between Agreeableness and Extraversion (.74), followed by Extraversion and Openness (.49), while Neuroticism and Openness are nearly unrelated (−.06).

Interpretation of reliability and validity.

Factor Omega AVE
Agreeableness .70 .41
Conscientiousness .75 .40
Extraversion .77 .44
Neuroticism .86 .55
Openness .55 .31

Omega is acceptable (≥ .70) for four factors, but Openness (.55) is low because of its weak indicators. Only Neuroticism has an AVE above .50, so convergent validity is limited for the other factors. The squared correlation between Agreeableness and Extraversion (.74² = .54) is higher than the AVE of both factors, so by the Fornell-Larcker criterion these two factors are not clearly distinct in this sample. This is not surprising for a short form with five items per trait.

Local fit and modifications. Strict CFA models of personality data often show only moderate fit, because items have small cross-loadings and some items share specific content (Marsh et al., 2014). Modification indices show where the model is strained. They estimate how much the chi-square value would decrease if a fixed parameter were freed.

modindices(fit5, sort = TRUE, maximum.number = 10)
Show output
      lhs op rhs      mi    epc sepc.lv sepc.all sepc.nox
299 extra =~  N4 228.849 -0.455  -0.256   -0.256   -0.256
324 neuro =~  O4 211.511  0.297   0.259    0.259    0.259
259 agree =~  N4 181.970 -0.733  -0.245   -0.245   -0.245
315 neuro =~  C5 180.947 -0.325  -0.284   -0.284   -0.284
304 extra =~  O4 166.276 -0.571  -0.321   -0.321   -0.321
312 neuro =~  C2 165.359  0.320   0.279    0.279    0.279
339  open =~  E4 157.504 -0.667  -0.409   -0.409   -0.409
601    N1 ~~  N2 154.634  0.356   0.356    1.268    1.268
279 consc =~  N4 142.070 -0.417  -0.249   -0.249   -0.249
303 extra =~  O3 138.805  0.851   0.479    0.479    0.479
# Free only theoretically defensible residual covariances,
# for example between items of the same factor with similar content
m5m <- paste(m5, 'N1 ~~ N2')
fit5m <- cfa(m5m, data = valid, ordered = TRUE, estimator = "WLSMV")
fitMeasures(fit5m, idx_fit)
Show output
chisq.scaled    df.scaled   cfi.scaled   tli.scaled rmsea.scaled         srmr 
    3015.154      264.000        0.824        0.800        0.093        0.084 

As a safer approach, only residual covariances between items of the same factor with clearly related content are freed, and every modification is reported with its justification. Modifications that are made only to improve fit, without a theoretical reason, are likely to capitalise on chance and may not replicate in another sample.

Interpretation. Most of the largest modification indices refer to cross-loadings, for example Extraversion on N4 (MI = 228.8), Neuroticism on O4 (MI = 211.5) and Agreeableness on N4 (MI = 182.0), the same items flagged in the EFA. The largest residual covariance is between N1 and N2 (MI = 154.6). Both items describe anger (“Get angry easily” and “Get irritated easily”), so freeing this covariance can be justified by their similar content. After the modification the fit hardly changes (CFI = .824, TLI = .800, RMSEA = .093, SRMR = .084). The misfit is therefore spread over many small cross-loadings rather than located in a few parameters, and freeing many parameters one by one would mostly capitalise on chance.

An ESEM model for comparison. Section 4.2 introduced ESEM. It can be fitted with lavaan (version 0.6-13 or later) to see how much fit improves when cross-loadings are allowed. The five factors are rotated with geomin, and all 25 items may load on every factor.

all_items <- paste(names(items), collapse = " + ")
m_esem <- paste0('efa("b1")*f1 + efa("b1")*f2 + efa("b1")*f3 + efa("b1")*f4 + efa("b1")*f5 =~ ', all_items)
fit_esem <- cfa(m_esem, data = valid, ordered = TRUE, estimator = "WLSMV", rotation = "geomin")
fitMeasures(fit_esem, idx_fit)
Show output
chisq.scaled    df.scaled   cfi.scaled   tli.scaled rmsea.scaled         srmr 
     981.269      185.000        0.949        0.917        0.059        0.031 

Interpretation. The ESEM model fits much better than the CFA model, CFI = .949, TLI = .917, RMSEA = .059 and SRMR = .031, and it reaches the acceptable levels in Section 3.6. Allowing small cross-loadings, instead of fixing them to zero, is enough to explain most of the misfit. This result illustrates why ESEM is often recommended for multidimensional personality instruments (Marsh et al., 2014).

5.6 Drawing Path Diagrams

Working on this part only? Show the setup code

This code is optional and only needed if you start with the path diagrams in a new R session, without running the earlier sections. It loads the packages and creates the objects that this part uses. The results are the same as when the whole guide is run in order.

library(psych); library(psychTools); library(GPArotation)
library(lavaan); library(semTools); library(semPlot)
col1 <- "#1F6F8B"; col2 <- "#E07A5F"; col_title <- "#123F52"   # colours used in the figures

# data preparation (Section 5.2)
items <- na.omit(bfi[, 1:25])
rev_items <- c("A1", "C4", "C5", "E1", "E2", "O2", "O5")
items[rev_items] <- 7 - items[rev_items]

# splitting the data (Section 5.3)
set.seed(2026)
idx <- sample(seq_len(nrow(items)), size = floor(nrow(items) / 2))
calib <- items[idx, ]    # EFA
valid <- items[-idx, ]   # CFA

# CFA models (Section 5.5)
m5 <- '
  agree =~ A1 + A2 + A3 + A4 + A5
  consc =~ C1 + C2 + C3 + C4 + C5
  extra =~ E1 + E2 + E3 + E4 + E5
  neuro =~ N1 + N2 + N3 + N4 + N5
  open  =~ O1 + O2 + O3 + O4 + O5
'
m5h <- paste(m5, '
  stability  =~ agree + consc + neuro
  plasticity =~ extra + open
')
fit5  <- cfa(m5,  data = valid, ordered = TRUE, estimator = "WLSMV")
fit5h <- cfa(m5h, data = valid, ordered = TRUE, estimator = "WLSMV")

Path diagrams show the specified model visually, with latent factors as ovals, indicators as rectangles and loadings as arrows. Standardised estimates are shown on the arrows, which makes the relative strength of each loading easy to see. Curved double-headed arrows represent factor correlations and residual variances.

semPaths(fit5, what = "std", whatLabels = "std", layout = "tree", rotation = 2, style = "lisrel",
         fade = FALSE, edge.color = "grey25", edge.label.color = "black",
         edge.label.cex = 0.85, edge.label.position = 0.7,
         sizeMan = 6, sizeMan2 = 3, sizeLat = 10, sizeLat2 = 6, nCharNodes = 0, label.cex = 1.1,
         color = list(lat = "#DCEBF0", man = "white"),
         thresholds = FALSE, intercepts = FALSE, residuals = FALSE, mar = c(2, 6, 4, 6))
title("Five correlated factors, standardized estimates", line = 1)

semPaths(fit5h, what = "std", whatLabels = "std", layout = "tree", rotation = 2, style = "lisrel",
         fade = FALSE, edge.color = "grey25", edge.label.color = "black",
         edge.label.cex = 0.85, edge.label.position = 0.7,
         sizeMan = 6, sizeMan2 = 3, sizeLat = 10, sizeLat2 = 6, nCharNodes = 0, label.cex = 1.1,
         color = list(lat = "#DCEBF0", man = "white"),
         thresholds = FALSE, intercepts = FALSE, residuals = FALSE, mar = c(2, 6, 4, 6))
title("Higher-order model, standardized estimates", line = 1)

# the same model drawn with base R graphics, as shown in the online document
draw_path <- function(fit, col1 = "#1F6F8B", col2 = "#E07A5F", col_title = "#123F52") {
  s <- standardizedSolution(fit)
  lv <- c("agree", "consc", "extra", "neuro", "open")
  lab <- c(agree = "Agreeableness", consc = "Conscientiousness", extra = "Extraversion",
           neuro = "Neuroticism", open = "Openness")
  ld <- s[s$op == "=~", ]; ov <- ld$rhs
  grp <- match(ld$lhs, lv)
  xo <- setNames(seq_along(ov) * 1.15 + (grp - 1) * 1.6, ov)   # gap between trait groups
  xl <- sapply(lv, function(f) mean(xo[ld$rhs[ld$lhs == f]]))
  yl <- 6.4; yo <- 2.2; W <- max(xo) + 1
  par(mar = c(0.3, 0.3, 2.2, 0.3))
  plot(NA, xlim = c(0.2, W), ylim = c(0.4, 11.6), axes = FALSE, xlab = "", ylab = "")
  title("Five correlated factors, standardised estimates", col.main = col_title, cex.main = 1.15)
  fc <- s[s$op == "~~" & s$lhs != s$rhs & s$lhs %in% lv, ]
  fc <- fc[order(abs(xl[fc$rhs] - xl[fc$lhs])), ]
  for (i in seq_len(nrow(fc))) {
    a <- xl[fc$lhs[i]]; b <- xl[fc$rhs[i]]; h <- 0.5 + abs(b - a) / 7.5
    t <- seq(0, pi, length.out = 80); xm <- (a + b) / 2; rr <- abs(b - a) / 2
    xs <- xm - rr * cos(t); ys <- yl + 0.62 + h * sin(t)
    neg <- fc$est.std[i] < 0
    lines(xs, ys, col = adjustcolor(ifelse(neg, col2, "grey45"), 0.85), lwd = 0.6 + 3 * abs(fc$est.std[i]))
    rect(xm - 0.62, yl + 0.62 + h - 0.2, xm + 0.62, yl + 0.62 + h + 0.2, col = "white", border = NA)
    text(xm, yl + 0.62 + h, sprintf("%.2f", fc$est.std[i]), cex = 0.72, col = ifelse(neg, col2, "grey20"))
  }
  for (i in seq_len(nrow(ld))) {
    x0 <- xl[ld$lhs[i]]; x1 <- xo[ld$rhs[i]]
    arrows(x0, yl - 0.62, x1, yo + 0.45, length = 0.06, lwd = 0.6 + 3 * ld$est.std[i], col = adjustcolor(col1, 0.75))
    px <- x0 + (x1 - x0) * 0.78; py <- yl - 0.62 + (yo + 0.45 - yl + 0.62) * 0.78
    rect(px - 0.36, py - 0.17, px + 0.36, py + 0.17, col = "white", border = NA)
    text(px, py, sprintf("%.2f", ld$est.std[i]), cex = 0.64, col = "grey15")
  }
  tt <- seq(0, 2 * pi, length.out = 80)
  for (f in lv) {
    polygon(xl[f] + 2.55 * cos(tt), yl + 0.62 * sin(tt), col = "#DCEBF0", border = col1, lwd = 1.6)
    text(xl[f], yl, lab[f], cex = 0.82, font = 2, col = col_title)
  }
  res <- s[s$op == "~~" & s$lhs == s$rhs & s$lhs %in% ov, ]
  for (v in ov) {
    rect(xo[v] - 0.45, yo - 0.45, xo[v] + 0.45, yo + 0.45, col = "white", border = "grey35")
    text(xo[v], yo, v, cex = 0.74)
    arrows(xo[v], yo - 1.15, xo[v], yo - 0.47, length = 0.04, col = "grey55", lwd = 0.8)
    text(xo[v], yo - 1.38, sprintf("%.2f", res$est.std[res$lhs == v]), cex = 0.6, col = "grey35")
  }
}
draw_path(fit5)

Figure 5. Path diagram of the five correlated factors model with standardised estimates from the validation sample. Straight arrows from the ovals to the boxes are factor loadings, the curved lines above the ovals are factor correlations (red for negative), and the small arrows under the boxes are residual variances. Thicker lines show larger values, so the weak indicators O4 (.22) and A1 (.33) and the strong correlation between Agreeableness and Extraversion (.74) stand out at a glance.

5.7 Factor Scores and Standardised Total Scores

Working on this part only? Show the setup code

This code is optional and only needed if you start with the factor scores in a new R session, without running the earlier sections. It loads the packages and creates the objects that this part uses. The results are the same as when the whole guide is run in order.

library(psych); library(psychTools); library(GPArotation)
library(lavaan); library(semTools); library(semPlot)
col1 <- "#1F6F8B"; col2 <- "#E07A5F"; col_title <- "#123F52"   # colours used in the figures

# data preparation (Section 5.2)
items <- na.omit(bfi[, 1:25])
rev_items <- c("A1", "C4", "C5", "E1", "E2", "O2", "O5")
items[rev_items] <- 7 - items[rev_items]

# splitting the data (Section 5.3)
set.seed(2026)
idx <- sample(seq_len(nrow(items)), size = floor(nrow(items) / 2))
calib <- items[idx, ]    # EFA
valid <- items[-idx, ]   # CFA

# five-factor EFA (Section 5.4)
efa5 <- fa(calib, nfactors = 5, fm = "minres", rotate = "oblimin", cor = "poly")

# CFA models (Section 5.5)
m5 <- '
  agree =~ A1 + A2 + A3 + A4 + A5
  consc =~ C1 + C2 + C3 + C4 + C5
  extra =~ E1 + E2 + E3 + E4 + E5
  neuro =~ N1 + N2 + N3 + N4 + N5
  open  =~ O1 + O2 + O3 + O4 + O5
'
m5h <- paste(m5, '
  stability  =~ agree + consc + neuro
  plasticity =~ extra + open
')
fit5  <- cfa(m5,  data = valid, ordered = TRUE, estimator = "WLSMV")
fit5h <- cfa(m5h, data = valid, ordered = TRUE, estimator = "WLSMV")

Once a structure is accepted, scores for each person on each factor can be obtained in three ways. To compare them fairly, all scores are calculated on the validation sample. The scores are then correlated to see how much the choice of method matters.

# 1. EFA factor scores (weights from the calibration sample)
fs_efa_reg  <- factor.scores(valid, efa5, method = "regression")$scores
fs_efa_bart <- factor.scores(valid, efa5, method = "Bartlett")$scores

# 2. CFA factor scores
fs_cfa <- lavPredict(fit5)

# 3. Standardised total scores (items already reverse scored)
keys <- list(agree = paste0("A", 1:5), consc = paste0("C", 1:5),
             extra = paste0("E", 1:5), neuro = paste0("N", 1:5),
             open  = paste0("O", 1:5))
z_total <- sapply(keys, function(k) scale(rowSums(valid[, k])))

# Compare, for example, neuroticism
cor(cbind(z_total = z_total[, "neuro"], cfa = fs_cfa[, "neuro"]))
Show output
          z_total       cfa
z_total 1.0000000 0.9690501
cfa     0.9690501 1.0000000
plot(z_total[, "neuro"], fs_cfa[, "neuro"],
     xlab = "Standardised total score", ylab = "CFA factor score")

The EFA factor columns are not labelled automatically, so match them to the trait names by looking at the loading pattern before comparing. When loadings within a factor are similar, standardised total scores and factor scores correlate very highly. Large differences in loadings make the weighting of factor scores more important.

Interpretation.

Factor Standardised total score with CFA factor score Standardised total score with EFA factor score
Agreeableness .91 .96
Conscientiousness .97 .97
Extraversion .95 .90
Neuroticism .97 .95
Openness .84 .94

The correlations are high for all factors, so in most practical situations standardised total scores rank people very similarly to factor scores. The lowest correlation between the total score and the CFA factor score is for Openness (.84). Its loadings differ the most (from .22 for O4 to above .60 for O3), so weighting items by their loadings changes the scores more than for the other factors.

traits <- c(agree = "Agreeableness", consc = "Conscientiousness", extra = "Extraversion",
            neuro = "Neuroticism", open = "Openness")
par(mfrow = c(2, 3), mar = c(4.5, 4.5, 3, 1))
for (k in names(traits)) {
  r <- cor(z_total[, k], fs_cfa[, k])
  plot(z_total[, k], fs_cfa[, k], pch = 16, col = adjustcolor(col1, 0.3),
       xlab = "Standardised total score", ylab = "CFA factor score", bty = "l", las = 1,
       main = sprintf("%s (r = %.2f)", traits[k], r), col.main = col_title)
  abline(lm(fs_cfa[, k] ~ z_total[, k]), col = col2, lwd = 2)
}
# last panel, the five correlations side by side
rs <- sapply(names(traits), function(k) cor(z_total[, k], fs_cfa[, k]))
bp <- barplot(rs, names.arg = c("A", "C", "E", "N", "O"), ylim = c(0, 1.1), col = col1, border = NA,
              las = 1, ylab = "Correlation", main = "All five traits", col.main = col_title)
text(bp, rs, sprintf("%.2f", rs), pos = 3, cex = 0.9)

Figure 6. Standardised total scores plotted against CFA factor scores for each of the five traits, with the correlations summarised in the last panel. For Conscientiousness, Neuroticism and Extraversion the points lie close to the line, so the two scoring methods are almost interchangeable. For Agreeableness and especially Openness the spread is wider, because their items differ more in how strongly they reflect the factor.

5.8 Interpretation Questions

These questions refer to the output of your own run. Numerical answers are accepted within a small tolerance, because results can differ slightly between R and package versions. As in the other sections, each question can be tried up to three times, and the correct answer is shown with a short explanation at the end.

1.How many factors does parallel analysis suggest for the calibration sample?
2.Which items show cross-loadings of at least .30 in the five-factor EFA? Write the item codes separated by commas.
3.Which model fits best in the validation sample according to CFI, RMSEA and SRMR?
4.Which factor has the lowest omega coefficient?
5.What is the correlation between the standardised total score and the CFA factor score for Neuroticism? Give two decimals.
6.Why were EFA and CFA conducted on different halves of the sample?

Your Results

You have reached the end of the guide. Press the button below to see your total score, your results for each section and a summary of how you worked through the guide, such as the time spent in each section. Your answers were recorded while you worked, so there is nothing to submit.

Clears your saved answers on this device so that you can work through the questions once more.

References

The guide draws on widely used textbooks and methodological articles on factor analysis and structural equation modeling. All sources cited in the text are listed in APA style. Click the button below to open the full list.

Show references

Akaike, H. (1987). Factor analysis and AIC. Psychometrika, 52(3), 317–332.

Anderson, J. C., & Gerbing, D. W. (1988). Structural equation modeling in practice: A review and recommended two-step approach. Psychological Bulletin, 103(3), 411–423.

Asparouhov, T., & Muthén, B. (2009). Exploratory structural equation modeling. Structural Equation Modeling, 16(3), 397–438.

Bartlett, M. S. (1950). Tests of significance in factor analysis. British Journal of Psychology, Statistical Section, 3(2), 77–85.

Bentler, P. M., & Bonett, D. G. (1980). Significance tests and goodness of fit in the analysis of covariance structures. Psychological Bulletin, 88(3), 588–606.

Bentler, P. M. (1990). Comparative fit indexes in structural models. Psychological Bulletin, 107(2), 238–246.

Bollen, K. A. (1986). Sample size and Bentler and Bonett’s nonnormed fit index. Psychometrika, 51(3), 375–377.

Bollen, K. A. (1989). A new incremental fit index for general structural equation models. Sociological Methods & Research, 17(3), 303–316.

Brown, T. A. (2015). Confirmatory factor analysis for applied research (2nd ed.). Guilford Press.

Browne, M. W., & Cudeck, R. (1993). Alternative ways of assessing model fit. In K. A. Bollen & J. S. Long (Eds.), Testing structural equation models (pp. 136–162). Sage.

Browne, M. W. (2001). An overview of analytic rotation in exploratory factor analysis. Multivariate Behavioral Research, 36(1), 111–150.

Cattell, R. B. (1966). The scree test for the number of factors. Multivariate Behavioral Research, 1(2), 245–276.

Costello, A. B., & Osborne, J. W. (2005). Best practices in exploratory factor analysis: Four recommendations for getting the most from your analysis. Practical Assessment, Research, and Evaluation, 10(7), 1–9.

Demir, E. (2022). Example: Exploratory and confirmatory factor analysis in R [Online document]. RPubs. https://rpubs.com/Symrna/EFA_CFA

DeYoung, C. G. (2006). Higher-order factors of the Big Five in a multi-informant sample. Journal of Personality and Social Psychology, 91(6), 1138–1151.

Digman, J. M. (1997). Higher-order factors of the Big Five. Journal of Personality and Social Psychology, 73(6), 1246–1256.

Epskamp, S. (2015). semPlot: Unified visualizations of structural equation models. Structural Equation Modeling, 22(3), 474–483.

Fabrigar, L. R., Wegener, D. T., MacCallum, R. C., & Strahan, E. J. (1999). Evaluating the use of exploratory factor analysis in psychological research. Psychological Methods, 4(3), 272–299.

Field, A. (2018). Discovering statistics using IBM SPSS Statistics (5th ed.). Sage.

Flora, D. B., & Curran, P. J. (2004). An empirical evaluation of alternative methods of estimation for confirmatory factor analysis with ordinal data. Psychological Methods, 9(4), 466–491.

Fornell, C., & Larcker, D. F. (1981). Evaluating structural equation models with unobservable variables and measurement error. Journal of Marketing Research, 18(1), 39–50.

Goldberg, L. R. (1999). A broad-bandwidth, public domain, personality inventory measuring the lower-level facets of several five-factor models. In I. Mervielde, I. Deary, F. De Fruyt, & F. Ostendorf (Eds.), Personality psychology in Europe (Vol. 7, pp. 7–28). Tilburg University Press.

Golino, H. F., & Epskamp, S. (2017). Exploratory graph analysis: A new approach for estimating the number of dimensions in psychological research. PLoS ONE, 12(6), e0174035.

Goretzko, D., & Bühner, M. (2020). One model to rule them all? Using machine learning algorithms to determine the number of factors in exploratory factor analysis. Psychological Methods, 25(6), 776–786.

Hair, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2019). Multivariate data analysis (8th ed.). Cengage.

Hendrickson, A. E., & White, P. O. (1964). Promax: A quick method for rotation to oblique simple structure. British Journal of Statistical Psychology, 17(1), 65–70.

Henseler, J., Ringle, C. M., & Sarstedt, M. (2015). A new criterion for assessing discriminant validity in variance-based structural equation modeling. Journal of the Academy of Marketing Science, 43(1), 115–135.

Hoelter, J. W. (1983). The analysis of covariance structures: Goodness-of-fit indices. Sociological Methods & Research, 11(3), 325–344.

Horn, J. L. (1965). A rationale and test for the number of factors in factor analysis. Psychometrika, 30(2), 179–185.

Hu, L., & Bentler, P. M. (1999). Cutoff criteria for fit indexes in covariance structure analysis: Conventional criteria versus new alternatives. Structural Equation Modeling, 6(1), 1–55.

Jacobucci, R., Grimm, K. J., & McArdle, J. J. (2016). Regularized structural equation modeling. Structural Equation Modeling, 23(4), 555–566.

James, L. R., Mulaik, S. A., & Brett, J. M. (1982). Causal analysis: Assumptions, models, and data. Sage.

Jennrich, R. I., & Bentler, P. M. (2011). Exploratory bi-factor analysis. Psychometrika, 76(4), 537–549.

Jöreskog, K. G., & Sörbom, D. (1993). LISREL 8: Structural equation modeling with the SIMPLIS command language. Scientific Software International.

Jöreskog, K. G. (1969). A general approach to confirmatory maximum likelihood factor analysis. Psychometrika, 34(2), 183–202.

Jorgensen, T. D., Pornprasertmanit, S., Schoemann, A. M., & Rosseel, Y. (2026). semTools: Useful tools for structural equation modeling (R package version 0.5-10). https://CRAN.R-project.org/package=semTools

Kaiser, H. F. (1958). The varimax criterion for analytic rotation in factor analysis. Psychometrika, 23(3), 187–200.

Kaiser, H. F. (1974). An index of factorial simplicity. Psychometrika, 39(1), 31–36.

Kline, R. B. (2023). Principles and practice of structural equation modeling (5th ed.). Guilford Press.

MacCallum, R. C., Roznowski, M., & Necowitz, L. B. (1992). Model modifications in covariance structure analysis: The problem of capitalization on chance. Psychological Bulletin, 111(3), 490–504.

MacCallum, R. C., Widaman, K. F., Zhang, S., & Hong, S. (1999). Sample size in factor analysis. Psychological Methods, 4(1), 84–99.

Marsh, H. W., Hau, K.-T., & Wen, Z. (2004). In search of golden rules: Comment on hypothesis-testing approaches to setting cutoff values for fit indexes and dangers in overgeneralizing Hu and Bentler’s (1999) findings. Structural Equation Modeling, 11(3), 320–341.

Marsh, H. W., Morin, A. J. S., Parker, P. D., & Kaur, G. (2014). Exploratory structural equation modeling: An integration of the best features of exploratory and confirmatory factor analysis. Annual Review of Clinical Psychology, 10, 85–110.

McCrae, R. R., & John, O. P. (1992). An introduction to the five-factor model and its applications. Journal of Personality, 60(2), 175–215.

McDonald, R. P. (1999). Test theory: A unified treatment. Lawrence Erlbaum.

Merkle, E. C., & Rosseel, Y. (2018). blavaan: Bayesian structural equation models via parameter expansion. Journal of Statistical Software, 85(4), 1–30.

Mulaik, S. A., James, L. R., Van Alstine, J., Bennett, N., Lind, S., & Stilwell, C. D. (1989). Evaluation of goodness-of-fit indices for structural equation models. Psychological Bulletin, 105(3), 430–445.

Muthén, B., & Asparouhov, T. (2012). Bayesian structural equation modeling: A more flexible representation of substantive theory. Psychological Methods, 17(3), 313–335.

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

Reise, S. P. (2012). The rediscovery of bifactor measurement models. Multivariate Behavioral Research, 47(5), 667–696.

Revelle, W. (2026). psych: Procedures for psychological, psychometric, and personality research (R package version 2.6.5). Northwestern University. https://CRAN.R-project.org/package=psych

Revelle, W., Wilt, J., & Rosenthal, A. (2010). Individual differences in cognition: New methods for examining the personality-cognition link. In A. Gruszka, G. Matthews, & B. Szymura (Eds.), Handbook of individual differences in cognition (pp. 27–49). Springer.

Rosseel, Y. (2012). lavaan: An R package for structural equation modeling. Journal of Statistical Software, 48(2), 1–36.

Schermelleh-Engel, K., Moosbrugger, H., & Müller, H. (2003). Evaluating the fit of structural equation models: Tests of significance and descriptive goodness-of-fit measures. Methods of Psychological Research Online, 8(2), 23–74.

Schwarz, G. (1978). Estimating the dimension of a model. The Annals of Statistics, 6(2), 461–464.

Spearman, C. (1904). “General intelligence,” objectively determined and measured. The American Journal of Psychology, 15(2), 201–292.

Steiger, J. H. (1990). Structural model evaluation and modification: An interval estimation approach. Multivariate Behavioral Research, 25(2), 173–180.

Tabachnick, B. G., & Fidell, L. S. (2019). Using multivariate statistics (7th ed.). Pearson.

Thurstone, L. L. (1947). Multiple-factor analysis. University of Chicago Press.

Tucker, L. R., & Lewis, C. (1973). A reliability coefficient for maximum likelihood factor analysis. Psychometrika, 38(1), 1–10.

Velicer, W. F. (1976). Determining the number of components from the matrix of partial correlations. Psychometrika, 41(3), 321–327.

Worthington, R. L., & Whittaker, T. A. (2006). Scale development research: A content analysis and recommendations for best practices. The Counseling Psychologist, 34(6), 806–838.

Yu, C.-Y. (2002). Evaluating cutoff criteria of model fit indices for latent variable models with binary and continuous outcomes [Doctoral dissertation, University of California, Los Angeles].