---
title: "Simulate data to explore the effect of different parameters"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{Simulate data to explore the effect of different parameters}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

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

```{r setup}
library(lcsm)
```

The functions `sim_uni_lcsm()` and `sim_bi_lcsm()` simulate data based on some some parameters that can be specified.
A full list of parameters that can be specified for the data simulation can be found in the [README](https://github.com/milanwiedemann/lcsm/) file on GitHub.

```{r sim-uni-data}
# Simulate some data 
sim_uni_lcsm(timepoints = 5, 
             model = list(alpha_constant = TRUE, beta = FALSE, phi = TRUE), 
             model_param = list(gamma_lx1 = 21, 
                                sigma2_lx1 = 1.5,
                                sigma2_ux = 0.2,
                                alpha_j2 = -0.93,
                                sigma2_j2 = 0.1,
                                sigma_j2lx1 = 0.2,
                                phi_x = 0.3),
             sample.nobs = 1000,
             na_pct = 0.3)

```


It is also possible to return the lavaan syntax instead of simulating data for further manual specifications.
The modified object could then be used to simulate data using `lavaan::simulateData()`.

```{r, sim-bi-syn}
# Return lavaan syntax based on the following argument specifications
simsyntax <- sim_bi_lcsm(timepoints = 5, 
                         model_x = list(alpha_constant = TRUE, beta = TRUE, phi = FALSE),
                         model_x_param = list(gamma_lx1 = 21,
                                              sigma2_lx1 = .5,
                                              sigma2_ux = .2,
                                              alpha_g2 = -.4,
                                              sigma2_g2 = .4,
                                              sigma_g2lx1 = .2,
                                              beta_x = -.1),
                         model_y = list(alpha_constant = TRUE, beta = TRUE, phi = TRUE),
                         model_y_param = list(gamma_ly1 = 5,
                                              sigma2_ly1 = .2,
                                              sigma2_uy = .2,
                                              alpha_j2 = -.2,
                                              sigma2_j2 = .1,
                                              sigma_j2ly1 = .02,
                                              beta_y = -.2,
                                              phi_y = .1),
                         coupling = list(delta_lag_xy = TRUE, 
                                         xi_lag_yx = TRUE),
                         coupling_param = list(sigma_su = .01,
                                               sigma_ly1lx1 = .2,
                                               sigma_g2ly1 = .1,
                                               sigma_j2lx1 = .1,
                                               sigma_j2g2 = .01,
                                               delta_lag_xy = .13,
                                               xi_lag_yx = .4),
                        return_lavaan_syntax = TRUE)
```

I'm using the function `cat()` here to make the output more readable.
This has no effect on the information that is returned, it is just another way to format the syntax and `lavaan` knows how to read either format as long as it's a string, i.e. surrounded by quotation marks.

```{r, sim-bi-syn-print}
cat(simsyntax)
```