```{r}
#| label: tbl-724
#| tbl-cap: "Integrated Results Matrix for the Effect of
#|           Topic Familiarity on Reliance on Author Expertise"
#| apa-note: "We integrated quantitative data (whether
#|            students selected a card about nuclear power
#|            or about climate change) and qualitative data
#|            (interviews with students) to provide a more
#|            comprehensive description of students’ card
#|            selections between the two topics."

tibble(
  `Quantitative result` = c(
    paste("When the topic was more (climate change) and", 
          "cards were more relevant, participants placed", 
          "less value on author expertise."),
    paste("When the topic is less familiar (nuclear power)", 
          "and cards were more relevant, participants", 
          "placed more value on author expertise.")),
   `Qualitative result` = c(
     paste("When an assertion was considered to be more", 
          "familiar and to be general knowledge,", 
          "participants perceived less need to rely on", 
          "author expertise."),
     paste("When an assertion was considered to be less", 
          "familiar and not general knowledge,", 
          "participants perceived more need to rely on", 
          "offer as brief expertise author expertise.")),
  `Example quote` = c(
    paste("Participant 144: \"I feel that I know more", 
          "about climate, and there are several things", 
          "on climate cards that are obvious, and that", 
          "if I sort of know it already, then the source", 
          "is not so critical... whereas with nuclear", 
          "energy. I don't know so much, so then I may", 
          "be more interested in who says what.\""),
    paste("Participant 3: \"[Nuclear power], which I know", 
          "much, much less about, I would back up my", 
          "arguments more with what I trust from the", 
          "professors.\""))
) |> 
  mutate(
    `Quantitative result` = hanging_indent(
      `Quantitative result`, width = 25),
    `Qualitative result` = hanging_indent(
      `Qualitative result`, width = 25),
    `Example quote` = hanging_indent(
      `Example quote`, width = 32)) |>
  apa_flextable(line_spacing = 1.5, font_size = 12) |>
  align() |>
  width(width = c(2,2,2.5))
```

```{r}
#| label: tbl-721
#| tbl-cap: "Results of Confirmatory Factor Analysis for the 
#|   Relationships Among Three Types of Intelligence"
#| apa-note: 
#|   - "Structural equation modeling was used for the analysis. 
#|     NFI = normed fit index; 
#|     CFI = comparative fit index; 
#|     RMSEA = root-mean-square error of 
#|     approximation."
#|   - "^a ^In Model A, all 57 items of social 
#|    intelligence, emotional intelligence, and cultural 
#|    intelligence were loaded onto one factor. ^b ^In
#|    Model B, the 21 items of social intelligence were 
#|    loaded onto one factor, and the 16 items of emotional 
#|    intelligence and the 20 items of cultural intelligence 
#|    were loaded onto another factor. ^c ^In Model C, 
#|    the 21 items of social intelligence were loaded onto one 
#|    factor, the 16 items of emotional intelligence were 
#|    loaded onto a second factor, and the 20 items of 
#|    cultural intelligence were loaded onto a third factor."
#|   - "^\\*\\*\\*^*p* < .001."
tibble(
  Model = c(
    "A: One-intelligence model^&thinsp;a^",
    "B: Two-intelligences mode^&thinsp;b^",
    "C: Three-intelligences model^&thinsp;c^"),
  Chi2 = c(10994.664, 10091.236, 8640.066),
  df = c(1539L, 1538L, 1536L),
  NFI = c(0.296, 0.354, 0.447),
  CFI = c(0.326, 0.39, 0.494),
  RMSEA = c(0.115, 0.109, 0.1),
  p = .0001
) |> 
  add_star_column(Chi2, merge = TRUE) |> 
  select(-p) |> 
  apa_flextable(column_formats = column_formats(
    accuracy = 0.001),
    layout = "fixed") |>
  width(width = c(2.15, 1.15, rep(3.2 / 4, 4)))
```

```{r}
#| label: tbl-719
#| tbl-cap: "Comparison of Fit Indices in Models Fitted to Simulated Data Across Longitudinal Mediation Model Types"
#| apa-note: "AIC and BIC differences are relative to the simplex 
#|   lagged model. RMSEA = root-mean-square error of 
#|   approximation; CI = confidence interval; 
#|   AIC = Akaike information criterion; 
#|   BIC = Bayesian information criterion."

# Make data
d <- tibble(
             Model = c("Simplex lagged",
                       "Simplex contemporaneous",
                       "Latent growth",
                       "Modified latent change"),
  `&chi;^2^_Value` = c(63.3, 58, 65, 26.2),
     `&chi;^2^_df` = c(28L, 29L, 33L, 33L),
      `&chi;^2^_p` = c(1e-04, 0.001, 1e-04, 0.79),
       RMSEA_Value = c(0.044, 0.04, 0.039, 0),
    `RMSEA_95% CI` = c("[.030, .059]", "[.024, .054]",
                       "[.025, .053]", "[.000, .020]"),
           RMSEA_p = c(0.72, 0.87, 0.9, 0.999),
               AIC = c(13479, 13472, 13471, 13432),
               BIC = c(13658, 13646, 13627, 13588),
      `deltaAIC` = c(NA, -7L, -8L, -47L),
      `deltaBIC` = c(NA, -12L, -31L, -70L)
) 

# Format data
d_formatted <- d |> 
  mutate(RMSEA_Value = align_chr(
    RMSEA_Value, 
    accuracy = .001, 
    trim_leading_zeros = TRUE))

# Make table
d_formatted |> 
  apa_flextable(font_size = 11) |> 
  width(width = c(1.80, .45, .35, .45, .05, .40, 
                   .85, .35, .50, .50, .40, .40)) 
```

```{r}
#| label: tbl-718
#| tbl-cap: "Hierarchical Regression: Results for Well-Being"
#| apa-note: 
#|   - "CI = confidence interval; *LL* = lower limit; 
#|   *UL* = upper limit; familismo = the collective 
#|   importance of family unity that emphasizes interdependence
#|   and solidarity; Mex Am margin = Mexican 
#|   American marginalization."
#|   - "^\\*^*p* < .05. ^\\*\\*^*p* < .01. ^\\*\\*\\*^*p* < .001."
set.seed(123)
# Make coefficients
d_coefficients <- tibble::tribble(
  ~Step,                ~Variable, ~beta,    ~b,
     1L, "Perceived social class",  0.31,  0.45,
     1L,       "Generation level", -0.01, -0.01,
     2L,              "Familismo",  0.23,  0.37,
     2L,          "Acculturation",  0.05,  0.11,
     2L,          "Enculturation",  0.24,  0.35,
     2L,        "Mex {Am} margin", -0.17, -0.23,
     3L,   "Masculinity ideology", -0.18, -0.05
  ) |> 
  mutate(vname = snakecase::to_any_case(
    Variable, 
    case = "parsed") |> fct_inorder(),
    Variable = fct_inorder(Variable))

# Make data
d <- d_coefficients |> 
  unite(vname, c(beta, vname), 
        sep = " * ") |> 
  pull(vname) |> 
  paste(collapse = " + ") |> 
  {
    \(x) paste0("y ~ ", x)
    }() |> 
  simulateData(standardized = TRUE, sample.nobs = 125) |> 
  mutate(y = y + 4) |> 
  as_tibble()

# Rescale data
for (i in seq_len(nrow(d_coefficients))) {
  d[,d_coefficients[i,]$vname] <- d[,d_coefficients[i,]$vname] * 
    d_coefficients[i,]$beta / 
    d_coefficients[i,]$beta
}

# Analyze data
d_analysis <- d_coefficients |>
  select(Step, vname) |>
  crossing(Model = 1:3) |>
  arrange(Model, Step) |>
  filter(Step <= Model) |>
  select(-Step) |>
  summarise(f = paste0(vname, collapse = " + "), 
            .by = Model) |>
  mutate(
    eq = paste0("y ~ ", f) |> map(formula),
    fit = map(eq, lm, data = d),
    Model = paste("Model", Model)
  )

# Format data
d_formatted <- d_analysis |>
  mutate(
    parameters = map(fit, model_parameters),
    std_parameters = map(fit, 
                         model_parameters, 
                         standardize  = "basic") |> 
      map(\(d) select(d, Std_Coefficient))
  ) |>
  select(Model, parameters, std_parameters) |>
  unnest(c(parameters, std_parameters)) |>
  select(-CI, -t, -df_error) |>
  rename(pp = p) |>
  relocate(SE, .before = Std_Coefficient) |>
  apa_format_columns() |>
  rename(`95% CI for *B*_*LL*` = LL,
         `95% CI for *B*_*UL*` = UL) |>
  as_grouped_data("Model") |>
  left_join(
    d_analysis |>
      pull(fit) |>
      apa_performance_comparison(
        starred = "deltaR2", 
        metrics = c("R2", "deltaR2")),
    by = join_by(Model)
  ) |>
  replace_na(list(Model = "", Variable = "")) |>
  unite(Variable, c(Variable, Model), sep = "") |>
  mutate(`&beta;` = ifelse(Variable == "Constant", NA, `&beta;`)) |> 
  add_star_column(c(`*B*`, `&beta;`), p = pp) |> 
  select(-pp) |>
  mutate(Variable = str_replace(Variable, "^Model", "Step") |> 
           snakecase::to_sentence_case() |> 
           str_replace(" am ", " Am "))

# Make table
d_formatted |> 
  apa_flextable(line_spacing = 1.5, 
                layout = "fixed") |>
  padding(i = ~!is.na(`*B*`), 
          j = 1, 
          padding.left = 15) |>
  surround(i = ~is.na(`*B*`), 
           border.top = fp_border_default(color = "gray30")) |> 
  width(width = 6.5 * c(3, .6, .4, 1, 1, 1, 
                           .6, .4, 1, 1) / 10)
```

```{r}
#| label: tbl-717
#| tbl-cap: "Moderator Analysis: Types of Measurement and Study Year"
#| apa-note: 
#|   - "Number of studies = 120, number of
#|     effects = 782, total 
#|     *N* = 52,578. CI = confidence 
#|     interval; *LL* = lower limit; 
#|     *UL* = upper limit."
#|   - "^a ^0 = self-report, 
#|     1 = test. ^b ^ 0 = test, 
#|     1 = grade point average. ^c ^Study 
#|     year was grand centered. ^d ^0 = other, 
#|     1 = yes. ^e ^0 = no, 
#|     1 = yes."

# Make data
d <- tibble(
  effect_type = c(
    "Fixed effects",
    "Fixed effects",
    "Fixed effects",
    "Fixed effects",
    "Fixed effects",
    "Fixed effects",
    "Random effects",
    "Random effects"
  ),
  Effect = c(
    "Intercept",
    "Creativity measurement^&thinsp;a^",
    "Academic achievement measurement^&thinsp;b^",
    "Study year^&thinsp;c^",
    "Goal^&thinsp;d^",
    "Published^&thinsp;e^",
    "Within-study variance",
    "Between-study variance"
  ),
  Estimate = c(0.119, 0.097, -0.039, 2e-04, 
               -0.003, 0.054, 0.009, 0.018),
  SE = c(0.04, 0.028, 0.018, 0.001, 
         0.029, 0.03, 0.001, 0.003),
  `95% CI_*LL*` = c(0.041, 0.042, -0.074, -0.001, 
                    -0.06, -0.005, 0.008, 0.012),
  `95% CI_*UL*` = c(0.198, 0.153, -0.004, 0.002, 
                    0.054, 0.114, 0.011, 0.023),
  p = c(0.003, 0.001, 0.03, 0.76, 
        0.91, 0.07, 9e-04, 9e-04)
) 

# Format data
d_formatted <- d |> 
  mutate(Estimate = align_chr(
    Estimate, 
    accuracy = .0001, 
    drop0trailing = TRUE, 
    trim_leading_zeros = TRUE)) |> 
  mutate(across(c(Estimate:`95% CI_*UL*`), \(x) {
    align_chr(x, 
              accuracy = .001, 
              trim_leading_zeros = TRUE)
  })) |>
  mutate(Effect = hanging_indent(Effect, width = 35)) 

# Make table
d_formatted |> 
  apa_flextable(row_title_column = effect_type) |> 
  align(j = 1) |>
  padding(j = 1, 
          padding.left = c(0, 
                           15, 
                           rep(30, 5), 
                           0, 
                           rep(15, 2))) |> 
  width(width = c(2.5, rep(.8, 5)))
```

```{r}
#| label: tbl-716
#| tbl-cap: "Regressions of Associations Between Marital 
#|           Satisfaction and Average Levels of Marital Behavior"
#| apa-note: "CI = confidence interval; H → H = husband-as-actor 
#|           effect on the husband’s own marital satisfaction; 
#|           W → W = wife-as-actor effect on the wife's own marital 
#|           satisfaction; W → H = wife-as-partner effect on the 
#|           husband’s satisfaction; H → W = husband-as-partner 
#|           effect on the wife's satisfaction."
set.seed(123)
# Make Coefficients
d_coefficients <- tibble::tribble(
        ~Dependent,    ~Group, ~Predictor,     ~b,
  "Angry Behavior",   "Actor",       "H_H",  -98.9,
  "Angry Behavior",   "Actor",       "W_W", -87.11,
  "Angry Behavior", "Partner",       "W_H", -76.18,
  "Angry Behavior", "Partner",       "H_W",  -91.8,
       "Disregard",   "Actor",       "H_H", -38.62,
       "Disregard",   "Actor",       "W_W", -47.54,
       "Disregard", "Partner",       "W_H", -82.81,
       "Disregard", "Partner",       "H_W", -79.36,
      "Distancing",   "Actor",       "H_H", -47.42,
      "Distancing",   "Actor",       "W_W",   3.04,
      "Distancing", "Partner",       "W_H",  -0.05,
      "Distancing", "Partner",       "H_W",  -53.5
  ) 

# Make Model
model <- d_coefficients |> 
  mutate(b = b / 100) |>
  unite(Predictor, c(Group, Predictor)) |> 
  mutate(across(c(Dependent, Predictor), snakecase::to_snake_case)) |> 
  unite(b, c(b, Predictor), sep = " * ") |> 
  summarise(b = paste(b, collapse = " + "), .by = Dependent) |> 
  unite(Model, c(Dependent, b), sep = " ~ ") |> 
  pull(Model) 

# Make data
d_simulated <- lavaan::simulateData(model, sample.nobs = 50) |> 
  as_tibble() |> 
  mutate(id = row_number(), .before = 0) |> 
  pivot_longer(angry_behavior:distancing, 
               values_to = "y", names_to = "Dependent") |> 
  mutate(y = y  * 100) |> 
  nest(data = -Dependent)


# Analyze data
d_analysis <- d_simulated |> 
  mutate(
    fit = map(data, \(d) {
      lm(y ~ ., data = d |> select(-id))
      }),
    tbl = map(fit, parameters::parameters))
  
# Format data
d_formatted <- d_analysis |> 
  select(Dependent, tbl) |> 
  unnest(tbl) |> 
  apa_format_columns() |> 
  filter(Variable != "Constant") |> 
  separate(Variable, c("Type", "i", "d")) |> 
  mutate(across(c(i,d), toupper)) |> 
  unite(Variable, c(i, d), sep = c(" \u2192 ")) |> 
  relocate(`95% CI`, .after = last_col()) |> 
  as_grouped_data(groups = c("Dependent", "Type")) |> 
  mutate(across(c(Type, Variable), \(x) tidyr::replace_na(x, ""))) |> 
  mutate(Variable = paste0(Type, Variable, recycle0 = TRUE),
         Dependent = snakecase::to_sentence_case(Dependent)) |> 
  fill(Dependent) |> 
  filter(Variable != "") |> 
  select(-Type)

# Make Table
d_formatted |> 
  apa_flextable(row_title_column = Dependent, 
                row_title_align = "center",
                line_spacing = 1.5, 
                no_format_columns = Variable) |> 
  padding(j = 1, 
          i = ~`*B*` != "", 
          padding.left = 20) |> 
  width(width = c(1.1, rep(.85, 4), 2)) 
```