Dollarizing emotional payoff (MRE), Dystopian Catharsis delivers about +$2.23M per film (PaM) during financial stress, while box-office staples like Heroic Escapism sit closet to (~+$1.09M)—evidence that when wallets tighten, catharsis and comfort win, and oversupplying heavy tones dilutes yield even when they “feel” successful. Across tones, Average Gross Estimate (AGE)—the predicted five-week gross lift under stress for a typical film—ranges from roughly +$0.3M to +$9.0M (e.g., Dystopian Catharsis ≈ +$9.0M vs. Heroic Escapism ≈ +$4.3M). Controlling for release scale and sentiment, emotional valence explains meaningful variance in five-week real gross during high-stress months.
We performed data ingestion and cleaning by reading the master CSV, standardizing column names, coercing types, and filtering out missing values to ensure dataset consistency—establishing a clean dataset for analysis.
raw_df <- read_csv("/Users/jasonclark/Downloads/master_movie_datav1.csv", show_col_types = FALSE) %>%
clean_names()
df <- raw_df %>%
mutate(
release_date = mdy(release_date),
sentiment_at_release = as.numeric(sentiment_at_release),
nber = as.integer(nber),
five_week_real_gross = parse_number(x5_week_real_gross),
opening_theaters = as.numeric(opening_theaters)
) %>%
filter(!is.na(five_week_real_gross))
# Preview
kable(
df %>% select(year, title, five_week_real_gross, opening_theaters) %>% slice_head(n = 5),
caption = "Sample of cleaned box office data",
booktabs = TRUE
)| year | title | five_week_real_gross | opening_theaters |
|---|---|---|---|
| 2000 | How the Grinch Stole Christmas | 378499047 | 3134 |
| 2000 | Mission: Impossible II | 316822028 | 3653 |
| 2000 | Gladiator | 250066150 | 2938 |
| 2000 | The Perfect Storm | 280759344 | 3407 |
| 2000 | Meet the Parents | 205876597 | 2614 |
We created two variables to enable stratified analysis:
nber_flag: Factor for NBER recession status.stress_level: Factor classifying periods as “Normal”,
“Elevated”, or “Stress” based on recession and sentiment.df <- df %>%
mutate(
nber_flag = factor(nber, levels = c(0, 1),
labels = c("Non-recession", "Recession")),
stress_level = factor(
case_when(
nber == 1 ~ "Stress",
sentiment_at_release <= 80 ~ "Stress",
sentiment_at_release <= 85 ~ "Elevated",
TRUE ~ "Normal"
),
levels = c("Normal", "Elevated", "Stress")
),
primary = factor(qc_primary_classification)
)
kable(
df %>% count(stress_level),
caption = "Count of films by stress level",
booktabs = TRUE
)| stress_level | n |
|---|---|
| Normal | 2021 |
| Elevated | 443 |
| Stress | 1623 |
We computed counts and distributional statistics of five-week real gross by primary emotion and stress level to identify over- and under-performing emotional tones under stress.
primary_summary <- df %>%
group_by(primary, stress_level) %>%
summarise(
films = n(),
median_gross = median(five_week_real_gross, na.rm = TRUE),
iqr_gross = IQR(five_week_real_gross, na.rm = TRUE),
.groups = "drop"
)
primary_summary %>%
arrange(desc(films)) %>%
slice_head(n = 5) %>%
kable(
caption = "Top 5 emotion–stress combinations by film count",
booktabs = TRUE,
digits = 0
)| primary | stress_level | films | median_gross | iqr_gross |
|---|---|---|---|---|
| Humorous Escape | Normal | 473 | 48359377 | 79421155 |
| Dark Empathy | Normal | 421 | 14159049 | 36878588 |
| Dark Empathy | Stress | 402 | 12189890 | 39243084 |
| Humorous Escape | Stress | 357 | 46218546 | 74529148 |
| Heroic Escapism | Normal | 307 | 69767243 | 134011088 |
We quantified the relationship between opening theaters and five-week real gross via a Pearson correlation (r ≈ 0.58, p < .001), setting expectations for how scale predicts revenue prior to stress interactions.
cor_test <- cor.test(df$opening_theaters, df$five_week_real_gross)
broom::tidy(cor_test) %>%
select(estimate, p.value, conf.low, conf.high) %>%
kable(
caption = "Release Scale ↔ Gross Correlation (r, p-value, CI)",
digits = 3,
booktabs = TRUE
)| estimate | p.value | conf.low | conf.high |
|---|---|---|---|
| 0.578 | 0 | 0.557 | 0.598 |
We fit a linear model with stress-level interactions, confirming that theatrical scale yields diminishing returns under economic strain (opening_theaters × stress level interaction, ≈ –$4.7K per theater, p = 0.02). Emotional tone also emerged as a statistically significant factor in how films perform under pressure (p < 0.05 across several interactions). When economic stress weakens the financial impact of scale, which emotional tones help steady outcomes—and which make things worse?
# Impute missing openings and drop helper column
model_df <- df %>%
group_by(year) %>%
mutate(
med_openings = median(opening_theaters, na.rm = TRUE),
opening_theaters = if_else(is.na(opening_theaters), med_openings, opening_theaters)
) %>%
ungroup() %>%
select(-med_openings)
# Fit interaction model
general_model <- lm(
five_week_real_gross ~ opening_theaters * stress_level +
primary * stress_level +
sentiment_at_release,
data = model_df
)
# Extract emotional tone × stress interactions from gross model
gross_terms <- tidy(general_model) %>%
filter(str_detect(term, "primary") & str_detect(term, "stress_levelStress")) %>%
mutate(primary = str_remove_all(term, "primary|:stress_levelStress")) %>%
select(primary, gross_estimate = estimate)
# Extract and rename key coefficient for stress interaction
tidy(general_model) %>%
filter(term == 'opening_theaters:stress_levelStress') %>%
transmute(
Term = term,
`Estimated Impact ($)` = estimate,
StdError = std.error,
TValue = statistic,
PValue. = p.value
) %>%
kable(
caption = "Stress-Level Impact on Theater Scale",
booktabs = TRUE,
digits = 2
)| Term | Estimated Impact ($) | StdError | TValue | PValue. |
|---|---|---|---|---|
| opening_theaters:stress_levelStress | -4699.26 | 2006.2 | -2.34 | 0.02 |
We built a supply-bias matrix of release counts and median grosses—grouped by year and emotional tone—to examine whether studios’ releases under stress actually reflected audience needs. By pairing release frequency with median gross, we disentangle what was offered from what resonated under economic stress. Some tones like Heroic Escapism dominate output, while others appear only sporadically but profitable—revealing an early hint of under-served potential.
# Create supply-bias matrix and preview Dark Empathy
supply_bias <- df %>%
group_by(year, primary) %>%
summarise(
count_releases = n(),
median_gross = median(five_week_real_gross, na.rm = TRUE),
.groups = 'drop'
) %>%
pivot_wider(
names_from = primary,
values_from = c(count_releases, median_gross)
)
# Show a clean sample for one tone
supply_bias %>%
select(year, `count_releases_Dark Empathy`, `median_gross_Dark Empathy`) %>%
slice_head(n = 5) %>%
kable(
caption = "Supply Matrix Sample: Dark Empathy (First 5 Years)",
booktabs = TRUE
)| year | count_releases_Dark Empathy | median_gross_Dark Empathy |
|---|---|---|
| 2000 | 38 | 18411472 |
| 2001 | 37 | 21468625 |
| 2002 | 32 | 12733431 |
| 2003 | 30 | 7811404 |
| 2004 | 35 | 14691340 |
We combined our Section 5 regression results with actual release
counts during stress periods to identify which emotional tones were both
scarce and high-performing. By ranking tones on modeled
stress-interaction effects and matching those ranks to observed release
counts, we expose a clear mismatch: the very tones audiences most needed
under economic pressure were the ones studios under-invested in.
This raises a critical question—are we celebrating true audience
resonance, or simply rewarding what made it to screen?
# Filter to stress period records only
stress_period <- df %>%
filter(stress_level == "Stress")
# Summarize observed supply and performance under stress
stress_supply <- stress_period %>%
group_by(primary) %>%
summarise(
releases_stress = n(),
median_stress_gross = median(five_week_real_gross, na.rm = TRUE),
.groups = "drop"
)
# Extract model terms for tone × stress interactions
tone_interactions <- tidy(general_model) %>%
filter(str_detect(term, "stress_levelStress:primary")) %>%
mutate(primary = str_remove(term, "stress_levelStress:primary")) %>%
select(primary, estimate)
# Merge with observed supply
missed_df <- stress_supply %>%
left_join(tone_interactions, by = "primary") %>%
arrange(releases_stress, desc(estimate))
# Preview top 5 under-supplied but high-performing tones
missed_df %>%
slice_head(n = 5) %>%
kable(
caption = "Top 5 Missed Opportunities: Low Supply, High Estimated Performance Under Stress",
booktabs = TRUE
)| primary | releases_stress | median_stress_gross | estimate |
|---|---|---|---|
| Collective Resilience | 85 | 27819517 | NA |
| Dystopian Catharsis | 97 | 41342497 | 26695134 |
| Comfort Nostalgia | 98 | 30435885 | 23189931 |
| Intelligent Rebellion | 103 | 16904685 | 20735755 |
| Redemptive Grit | 227 | 13295759 | 19443971 |
While box office tells one story, emotional payoff tells another. We measure that payoff under stress across IMDb (audience), Rotten Tomatoes (hybrid), and Metascore (critic). Mean Rating Effect (MRE) puts everything in dollars: we convert each platform’s PaM—predict-at-median covariates, the modeled Stress–Normal difference holding opening scale and release sentiment at their medians—into expected gross using per-point betas, then average those dollarized ratings with the PaM gross delta for a typical film. Higher MRE signals deeper emotional resonance under stress; in our results, Comfort Nostalgia and Dark Empathy rise across platforms, Redemptive Grit connects more than it earns, and Heroic Escapism often sells tickets yet under-connects emotionally. The table highlights the top five tones by this blended uplift alongside their PaM gross
# Section 8: PaM (Stress − Normal) effects — gross, ratings, and MRE_pred
stopifnot(exists("df"))
# Fit general_model if missing (uses your Section 2 variables as-is)
if (!exists("general_model")) {
dat2 <- df %>%
dplyr::group_by(year) %>%
dplyr::mutate(
med_openings = median(opening_theaters, na.rm = TRUE),
opening_theaters = if_else(is.na(opening_theaters), med_openings, opening_theaters)
) %>%
dplyr::ungroup() %>% dplyr::select(-med_openings)
general_model <- lm(
five_week_real_gross ~ opening_theaters * stress_level +
primary * stress_level + sentiment_at_release,
data = dat2
)
}
# Levels from your data/model (handles three-level stress, we use only Normal/Stress for deltas)
prim_levels <- levels(df$primary)
stress_levels_model <- levels(df$stress_level) # e.g., c("Normal","Elevated","Stress")
stress_use <- c("Normal","Stress")
# Representative (median) covariates
median_open <- median(df$opening_theaters, na.rm = TRUE)
median_sent <- median(df$sentiment_at_release, na.rm = TRUE)
# ---- PaM gross predictions (median covariates) ----
newdata_g <- expand.grid(
primary = prim_levels,
opening_theaters = median_open,
sentiment_at_release = median_sent,
stress_level = stress_use,
KEEP.OUT.ATTRS = FALSE,
stringsAsFactors = FALSE
)
newdata_g$primary <- factor(newdata_g$primary, levels = prim_levels)
newdata_g$stress_level <- factor(newdata_g$stress_level, levels = stress_levels_model)
preds_g <- newdata_g %>%
dplyr::mutate(pred = as.numeric(predict(general_model, newdata = newdata_g))) %>%
dplyr::select(primary, stress_level, pred) %>%
tidyr::pivot_wider(names_from = stress_level, values_from = pred)
pam_gross <- preds_g %>%
dplyr::transmute(
primary,
gross_normal = Normal,
gross_stress = Stress,
gross_estimate_pred = Stress - Normal
)
# ---- PaM rating deltas (Stress − Normal) ----
# IMDb
df_imdb <- df %>%
dplyr::mutate(im_db_rating = suppressWarnings(as.numeric(im_db_rating))) %>%
dplyr::filter(!is.na(im_db_rating))
m_imdb <- if (nrow(df_imdb) > 0) lm(im_db_rating ~ primary * stress_level, data = df_imdb) else NULL
# Rotten Tomatoes
df_rt <- df %>%
dplyr::mutate(
rotten_tomatoes = stringr::str_remove(rotten_tomatoes, "%"),
rotten_tomatoes = suppressWarnings(as.numeric(rotten_tomatoes)),
rotten_tomatoes = dplyr::if_else(rotten_tomatoes <= 1, rotten_tomatoes * 100, rotten_tomatoes)
) %>% dplyr::filter(!is.na(rotten_tomatoes))
m_rt <- if (nrow(df_rt) > 0) lm(rotten_tomatoes ~ primary * stress_level, data = df_rt) else NULL
# Metascore
df_meta <- df %>%
dplyr::mutate(metascore = suppressWarnings(as.numeric(metascore))) %>%
dplyr::filter(!is.na(metascore))
m_meta <- if (nrow(df_meta) > 0) lm(metascore ~ primary * stress_level, data = df_meta) else NULL
# Helper to get Stress−Normal by primary from a fitted rating model
rating_delta <- function(mod, colname) {
if (is.null(mod)) return(tibble::tibble(primary = prim_levels, !!colname := NA_real_))
pr <- expand.grid(primary = prim_levels, stress_level = stress_use, stringsAsFactors = FALSE)
pr$primary <- factor(pr$primary, levels = prim_levels)
pr$stress_level <- factor(pr$stress_level, levels = stress_levels_model)
pred <- pr %>%
dplyr::mutate(pred = as.numeric(predict(mod, newdata = pr))) %>%
dplyr::select(primary, stress_level, pred) %>%
tidyr::pivot_wider(names_from = stress_level, values_from = pred) %>%
dplyr::transmute(primary, !!colname := Stress - Normal)
pred
}
imdb_est <- rating_delta(m_imdb, "imdb_estimate")
rt_est <- rating_delta(m_rt, "rt_estimate")
meta_est <- rating_delta(m_meta, "meta_estimate")
# ---- Assemble console-aligned table + QC lock on PaM gross ----
final_tbl <- pam_gross %>%
dplyr::left_join(imdb_est, by = "primary") %>%
dplyr::left_join(rt_est, by = "primary") %>%
dplyr::left_join(meta_est, by = "primary") %>%
dplyr::mutate(
mean_rating_effect_pred = rowMeans(
dplyr::across(c(imdb_estimate, rt_estimate, meta_estimate, gross_estimate_pred)),
na.rm = TRUE
)
)
# QC: re-compute PaM gross deltas from preds_g and confirm exact match
delta_check <- preds_g %>% dplyr::transmute(primary, delta = Stress - Normal)
qc <- final_tbl %>% dplyr::left_join(delta_check, by = "primary") %>%
dplyr::mutate(diff = abs(gross_estimate_pred - delta))
if (any(qc$diff > 1e-6, na.rm = TRUE)) stop("QC failed: PaM gross deltas drifted from locked values.")
# Print console-style table in the doc (top 5 rows)
knitr::kable(
final_tbl %>%
dplyr::arrange(dplyr::desc(mean_rating_effect_pred)) %>%
dplyr::transmute(primary, gross_normal, gross_stress, gross_estimate_pred, mean_rating_effect_pred) %>%
dplyr::slice_head(n = 5),
caption = "Top 5 tones by PaM mean rating effect (MRE_pred) alongside PaM gross lift for a median-scale film.",
booktabs = TRUE,
digits = c(NA, 2, 2, 2, 2)
)| primary | gross_normal | gross_stress | gross_estimate_pred | mean_rating_effect_pred |
|---|---|---|---|---|
| Dystopian Catharsis | 55872821 | 62711587 | 6838766 | 1709691.6 |
| Heroic Escapism | 105205723 | 109335615 | 4129893 | 1032473.0 |
| Comfort Nostalgia | 78308680 | 81642243 | 3333563 | 833394.1 |
| Humorous Escape | 68936233 | 71899114 | 2962880 | 740720.7 |
| Dark Empathy | 72092548 | 72989726 | 897178 | 224295.6 |
Top 5 tones by PaM mean rating effect (MRE_pred) alongside PaM gross lift for a median-scale film.
The data tells a subtle truth: When the economy falters, audiences crave more than distraction—they hunger for stories that mirror their own uncertainty. Big, wide releases aren’t the ones that automatically resonate. Sometimes it’s the films unafraid to confront hardship that linger—and discover meaning in the dark.
Emotional payoff is powerful—but is it predictable?
Some tones show high average returns, but their success is erratic. This
section explores emotional volatility under economic stress, revealing
which tones offer safe emotional returns—and which are wild cards.
# === Emotional Volatility Under Economic Stress ===
volatility_df <- df %>%
filter(stress_level == "Stress") %>%
group_by(primary) %>%
summarise(
n_titles = n(),
median_gross = median(five_week_real_gross, na.rm = TRUE),
sd_gross = sd(five_week_real_gross, na.rm = TRUE),
.groups = "drop"
) %>%
arrange(desc(sd_gross))
volatility_df %>%
slice_head(n = 5) %>%
kable(
caption = "Top 5 Most Volatile Emotional Tones (Standard Deviation of Gross Under Stress)",
booktabs = TRUE,
digits = 0
)| primary | n_titles | median_gross | sd_gross |
|---|---|---|---|
| Heroic Escapism | 254 | 74587978 | 137734453 |
| Collective Resilience | 85 | 27819517 | 90252420 |
| Dystopian Catharsis | 97 | 41342497 | 78612312 |
| Humorous Escape | 357 | 46218546 | 73221154 |
| Comfort Nostalgia | 98 | 30435885 | 70887268 |
Most films in the dataset are not anchored by a single emotional identity. While our primary analyses isolate tone-level effects to maintain clean attribution and frame the emotional identity of a film, nearly every film carries a secondary emotional resonance that shapes its nuance.
By summarizing average gross and IMDb performance for each Primary × Secondary pairing during high-stress periods, we explore how emotional blends shape audience connection.This analysis evaluates tone pairings during high-stress periods, revealing how secondary emotions amplify—or dilute—the commercial and emotional impact of the primary. By calculating each pairing’s relative lift, we surface combinations that consistently outperform expectations.
This table highlights the top-performing emotional tone pairings under stress, sorted by average 5-week real gross. It complements our primary-only models by revealing how layered emotional architecture—through secondary tones—shaped both audience resonance and box office impact.
# Filter to only films released during stress periods
combo_summary <- df %>%
filter(stress_level == "Stress") %>%
mutate(
gross = five_week_real_gross,
imdb = as.numeric(im_db_rating),
primary = as.factor(primary),
secondary = as.factor(qc_secondary_classification)
) %>%
group_by(primary, secondary) %>%
summarise(
n = n(),
avg_gross_pairing = mean(gross, na.rm = TRUE),
avg_imdb = mean(imdb, na.rm = TRUE),
.groups = "drop"
)
# Calculate average gross per primary tone
primary_avg <- combo_summary %>%
group_by(primary) %>%
summarise(
avg_gross_primary = mean(avg_gross_pairing, na.rm = TRUE),
.groups = "drop"
)
# Join and calculate relative lift
combo_with_lift <- combo_summary %>%
left_join(primary_avg, by = "primary") %>%
mutate(
relative_lift = avg_gross_pairing / avg_gross_primary
) %>%
arrange(desc(relative_lift))
# Display top 5 by relative lift
combo_with_lift %>%
slice_max(relative_lift, n = 5) %>%
kable(
caption = "Top 5 Emotional Tone Pairings by Relative Lift (Stress Periods)",
booktabs = TRUE,
digits = 2
)| primary | secondary | n | avg_gross_pairing | avg_imdb | avg_gross_primary | relative_lift |
|---|---|---|---|---|---|---|
| Dystopian Catharsis | Redemptive Grit | 2 | 241964308 | 6.35 | 86743551 | 2.79 |
| Intelligent Rebellion | Heroic Escapism | 6 | 96396068 | 6.65 | 41029590 | 2.35 |
| Dark Empathy | Heroic Escapism | 12 | 99986956 | 6.78 | 47270442 | 2.12 |
| Heroic Escapism | Comfort Nostalgia | 6 | 261126740 | 6.57 | 127264344 | 2.05 |
| Redemptive Grit | Heroic Escapism | 10 | 68332673 | 6.51 | 39114134 | 1.75 |
Below is a summary of all R-generated CSV files used in the final analysis and Tableau visualizations.
stress_level variables.─ Session info ─────────────────────────────────────────────────────────────── setting value version R version 4.4.3 (2025-02-28) os macOS Sequoia 15.4.1 system aarch64, darwin20 ui X11 language (EN) collate en_US.UTF-8 ctype en_US.UTF-8 tz America/Los_Angeles date 2025-08-14 pandoc 3.4 @ /Applications/RStudio.app/Contents/Resources/app/quarto/bin/tools/aarch64/ (via rmarkdown) quarto 1.6.42 @ /Applications/RStudio.app/Contents/Resources/app/quarto/bin/quarto ─ Packages ─────────────────────────────────────────────────────────────────── package * version date (UTC) lib source backports 1.5.0 2024-05-23 [1] CRAN (R 4.4.1) bit 4.6.0 2025-03-06 [1] CRAN (R 4.4.1) bit64 4.6.0-1 2025-01-16 [1] CRAN (R 4.4.1) broom * 1.0.8 2025-03-28 [1] CRAN (R 4.4.1) bslib 0.9.0 2025-01-30 [1] CRAN (R 4.4.1) cachem 1.1.0 2024-05-16 [1] CRAN (R 4.4.1) cli 3.6.4 2025-02-13 [1] CRAN (R 4.4.1) crayon 1.5.3 2024-06-20 [1] CRAN (R 4.4.1) digest 0.6.37 2024-08-19 [1] CRAN (R 4.4.1) dplyr * 1.1.4 2023-11-17 [1] CRAN (R 4.4.0) evaluate 1.0.3 2025-01-10 [1] CRAN (R 4.4.1) fastmap 1.2.0 2024-05-15 [1] CRAN (R 4.4.1) generics 0.1.3 2022-07-05 [1] CRAN (R 4.4.1) glue 1.8.0 2024-09-30 [1] CRAN (R 4.4.1) hms 1.1.3 2023-03-21 [1] CRAN (R 4.4.0) htmltools 0.5.8.1 2024-04-04 [1] CRAN (R 4.4.1) janitor * 2.2.1 2024-12-22 [1] CRAN (R 4.4.1) jquerylib 0.1.4 2021-04-26 [1] CRAN (R 4.4.0) jsonlite 2.0.0 2025-03-27 [1] CRAN (R 4.4.1) knitr * 1.50 2025-03-16 [1] CRAN (R 4.4.1) lifecycle 1.0.4 2023-11-07 [1] CRAN (R 4.4.1) lubridate * 1.9.4 2024-12-08 [1] CRAN (R 4.4.1) magrittr 2.0.3 2022-03-30 [1] CRAN (R 4.4.1) pillar 1.10.2 2025-04-05 [1] CRAN (R 4.4.1) pkgconfig 2.0.3 2019-09-22 [1] CRAN (R 4.4.1) purrr 1.0.4 2025-02-05 [1] CRAN (R 4.4.1) R6 2.6.1 2025-02-15 [1] CRAN (R 4.4.1) readr * 2.1.5 2024-01-10 [1] CRAN (R 4.4.0) rlang 1.1.5 2025-01-17 [1] CRAN (R 4.4.1) rmarkdown 2.29 2024-11-04 [1] CRAN (R 4.4.1) rstudioapi 0.17.1 2024-10-22 [1] CRAN (R 4.4.1) sass 0.4.9 2024-03-15 [1] CRAN (R 4.4.0) sessioninfo 1.2.3 2025-02-05 [1] CRAN (R 4.4.1) snakecase 0.11.1 2023-08-27 [1] CRAN (R 4.4.0) stringi 1.8.7 2025-03-27 [1] CRAN (R 4.4.1) stringr * 1.5.1 2023-11-14 [1] CRAN (R 4.4.0) tibble 3.2.1 2023-03-20 [1] CRAN (R 4.4.0) tidyr * 1.3.1 2024-01-24 [1] CRAN (R 4.4.1) tidyselect 1.2.1 2024-03-11 [1] CRAN (R 4.4.0) timechange 0.3.0 2024-01-18 [1] CRAN (R 4.4.1) tzdb 0.5.0 2025-03-15 [1] CRAN (R 4.4.1) vctrs 0.6.5 2023-12-01 [1] CRAN (R 4.4.0) vroom 1.6.5 2023-12-05 [1] CRAN (R 4.4.0) withr 3.0.2 2024-10-28 [1] CRAN (R 4.4.1) xfun 0.52 2025-04-02 [1] CRAN (R 4.4.1) yaml 2.3.10 2024-07-26 [1] CRAN (R 4.4.1) [1] /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library * ── Packages attached to the search path. ──────────────────────────────────────────────────────────────────────────────