---
title: "Multilevel Models with plssem"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{Multilevel Models with plssem}
  %\VignetteEngine{knitr::rmarkdown}
  \usepackage[utf8]{inputenc}
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

library(plssem)
```

This vignette shows examples of multilevel random slopes and intercept models,
with both continuous and ordinal data.

## Random Slopes Model

```{r slopes-syntax}
slopes_model <- "
  X =~ x1 + x2 + x3
  Z =~ z1 + z2 + z3
  Y =~ y1 + y2 + y3
  W =~ w1 + w2 + w3
  Y ~ X + Z + (1 + X + Z | cluster)
  W ~ X + Z + (1 + X + Z | cluster)
"
```

### Continuous Indicators

```{r slopes-continuous, message=FALSE, warning=FALSE}
fit_slopes_cont <- pls(
  slopes_model,
  data      = randomSlopes,
  bootstrap = TRUE,
  sample    = 50
)
summary(fit_slopes_cont)
```

### Ordered Indicators

```{r slopes-ordered, message=FALSE, warning=FALSE}
fit_slopes_ord <- pls(
  slopes_model,
  data      = randomSlopesOrdered,
  bootstrap = TRUE,
  sample    = 50,
  ordered   = colnames(randomSlopesOrdered) # explicitly specify variables as ordered
)
summary(fit_slopes_ord)
```

## Random Intercepts Model

```{r intercepts-syntax}
intercepts_model <- '
  f =~ y1 + y2 + y3
  f ~ x1 + x2 + x3 + w1 + w2 + (1 | cluster)
'
```

### Continuous Indicators

```{r intercepts-continuous, message=FALSE, warning=FALSE}
fit_intercepts_cont <- pls(
  intercepts_model,
  data      = randomIntercepts,
  bootstrap = TRUE,
  sample    = 50
)
summary(fit_intercepts_cont)
```

### Ordered Indicators

```{r intercepts-ordered, message=FALSE, warning=FALSE}
fit_intercepts_ord <- pls(
  intercepts_model,
  data      = randomInterceptsOrdered,
  bootstrap = TRUE,
  sample    = 50,
  ordered   = colnames(randomInterceptsOrdered) # explicitly specify variables as ordered
)
summary(fit_intercepts_ord)
```