The simplest way to generate
random walks with RandomWalker is using the automatic function
rw30().
RandomWalker provides rw30() as a quick way to generate
random walks without specifying any parameters. This is perfect for:
The rw30() function: 1. Generates 30 random
walks 2. Each with 100 steps 3. Using
normal distribution (mean = 0, sd = 1) 4. Starting at
0 5. Returns a tidy tibble
It’s equivalent to:
rw30()
#> # A tibble: 3,000 × 3
#> walk_number step_number y
#> <fct> <int> <dbl>
#> 1 1 1 0
#> 2 1 2 -0.365
#> 3 1 3 -0.383
#> 4 1 4 -0.276
#> 5 1 5 -0.917
#> 6 1 6 -0.717
#> 7 1 7 -1.66
#> 8 1 8 -2.66
#> 9 1 9 -3.80
#> 10 1 10 -3.96
#> # ℹ 2,990 more rowsColumns: - walk_number: Factor (1-30)
identifying each walk - step_number: Integer (1-100) for
each step - y: The random walk values
Note: Cumulative columns such as cum_sum,
cum_prod, cum_min, cum_max, and
cum_mean are not included by default. You can add them
using rand_walk_helper() or tidyverse operations if
needed. ## Understanding the Output
Each walk consists of 100 steps:
Since steps are drawn from N(0,1):
The function stores metadata:
# Overall statistics
rw30() |> summarize_walks(.value = y) |>
head()
#> Warning: There was 1 warning in `dplyr::summarize()`.
#> ℹ In argument: `geometric_mean = exp(mean(log(y)))`.
#> Caused by warning in `log()`:
#> ! NaNs produced
#> # A tibble: 1 × 16
#> fns fns_name dimensions mean_val median range quantile_lo quantile_hi
#> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 rw30 Rw30 1 1.54 1.25 54.7 -11.6 15.3
#> # ℹ 8 more variables: variance <dbl>, sd <dbl>, min_val <dbl>, max_val <dbl>,
#> # harmonic_mean <dbl>, geometric_mean <dbl>, skewness <dbl>, kurtosis <dbl>
# By walk
rw30() |>
summarize_walks(.value = y, .group_var = walk_number) |>
head(10)
#> Warning: There were 29 warnings in `dplyr::summarize()`.
#> The first warning was:
#> ℹ In argument: `geometric_mean = exp(mean(log(y)))`.
#> ℹ In group 1: `walk_number = 1`.
#> Caused by warning in `log()`:
#> ! NaNs produced
#> ℹ Run `dplyr::last_dplyr_warnings()` to see the 28 remaining warnings.
#> # A tibble: 10 × 17
#> walk_number fns fns_name dimensions mean_val median range quantile_lo
#> <fct> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 1 rw30 Rw30 1 5.80 5.91 18.1 -1.84
#> 2 2 rw30 Rw30 1 -0.899 -1.20 9.98 -5.28
#> 3 3 rw30 Rw30 1 -2.81 -1.06 15.9 -13.4
#> 4 4 rw30 Rw30 1 6.07 6.52 16.4 -2.52
#> 5 5 rw30 Rw30 1 4.93 5.19 15.2 -2.08
#> 6 6 rw30 Rw30 1 -8.66 -9.58 21.5 -18.9
#> 7 7 rw30 Rw30 1 2.56 3.20 13.8 -3.63
#> 8 8 rw30 Rw30 1 3.18 3.16 9.22 -0.845
#> 9 9 rw30 Rw30 1 -5.92 -5.90 10.9 -10.6
#> 10 10 rw30 Rw30 1 1.47 1.26 9.19 -2.14
#> # ℹ 9 more variables: quantile_hi <dbl>, variance <dbl>, sd <dbl>,
#> # min_val <dbl>, max_val <dbl>, harmonic_mean <dbl>, geometric_mean <dbl>,
#> # skewness <dbl>, kurtosis <dbl># Custom analysis
rw30() |>
group_by(walk_number) |>
summarize(
final_value = last(y),
max_value = max(y),
min_value = min(y),
volatility = sd(y)
) |>
head(10)
#> # A tibble: 10 × 5
#> walk_number final_value max_value min_value volatility
#> <fct> <dbl> <dbl> <dbl> <dbl>
#> 1 1 -4.67 1.70 -18.1 5.35
#> 2 2 -16.2 2.77 -18.5 6.70
#> 3 3 -17.9 2.74 -20.2 7.41
#> 4 4 -4.36 3.83 -5.28 2.14
#> 5 5 -1.88 0.131 -12.5 3.06
#> 6 6 1.23 10.0 -1.41 2.70
#> 7 7 5.64 10.1 0 2.61
#> 8 8 5.14 6.87 -6.82 2.99
#> 9 9 11.6 17.1 -0.0186 4.60
#> 10 10 -9.30 0.423 -16.3 4.13# Walk that went highest
max_walk <- rw30() |>
subset_walks(.value = "y", .type = "max")
# Walk that went lowest
min_walk <- rw30() |>
subset_walks(.value = "y", .type = "min")
# Visualize extremes
max_walk |> visualize_walks()walks <- rw30()
# Get only first 10 walks
walks |>
filter(walk_number %in% as.character(1:10)) |>
visualize_walks()# Show variability
walks <- rw30()
# Distribution of final positions
walks |>
group_by(walk_number) |>
slice_max(step_number) |>
ggplot(aes(x = y)) +
geom_histogram(bins = 15, fill = "steelblue", alpha = 0.7) +
geom_vline(xintercept = 0, color = "red", linetype = "dashed") +
theme_minimal() +
labs(
title = "Distribution of Final Positions",
subtitle = "30 random walks, 100 steps each",
x = "Final Position",
y = "Count"
)# Test if variance grows linearly with steps
walks <- rw30()
variance_by_step <- walks |>
group_by(step_number) |>
reframe(
variance = var(y),
theoretical = step_number # For N(0,1), var = n
)
ggplot(variance_by_step, aes(x = step_number)) +
geom_line(aes(y = variance, color = "Observed"), linewidth = 1) +
geom_line(aes(y = theoretical, color = "Theoretical"), linewidth = 1, linetype = "dashed") +
scale_color_manual(values = c("Observed" = "blue", "Theoretical" = "red")) +
theme_minimal() +
labs(
title = "Variance Growth in Random Walk",
subtitle = "Observed vs Theoretical (Var = n)",
x = "Step Number",
y = "Variance",
color = ""
)random_normal_walk() insteadrw30() has no parameters, which means:
# ❌ Can't change number of walks
# rw30(.num_walks = 50) # Error!
# ✅ Use random_normal_walk() instead
random_normal_walk(.num_walks = 50)
# ❌ Can't change number of steps
# rw30(.n = 200) # Error!
# ✅ Use random_normal_walk() instead
random_normal_walk(.n = 200)
# ❌ Can't change distribution parameters
# rw30(.mu = 0.1) # Error!
# ✅ Use random_normal_walk() instead
random_normal_walk(.mu = 0.1)rw30() uses normal distribution exclusively:
When rw30() doesn’t fit your needs:
# Generate walks
walks <- rw30()
# Show that mean displacement is zero
walks |>
group_by(step_number) |>
summarize(mean_position = mean(y)) |>
ggplot(aes(x = step_number, y = mean_position)) +
geom_line(color = "blue", linewidth = 1) +
geom_hline(yintercept = 0, linetype = "dashed", color = "red") +
theme_minimal() +
labs(
title = "Mean Position Over Time",
subtitle = "Averages to zero (red line)",
x = "Step",
y = "Mean Position"
)# Show that standard deviation grows as sqrt(n)
walks |>
group_by(step_number) |>
reframe(
sd_position = sd(y),
theoretical = sqrt(step_number)
) |>
ungroup() |>
ggplot(aes(x = step_number)) +
geom_line(aes(y = sd_position, color = "Observed"), linewidth = 1) +
geom_line(aes(y = theoretical, color = "Theoretical"), linewidth = 1, linetype = "dashed") +
scale_color_manual(values = c("Observed" = "blue", "Theoretical" = "red")) +
theme_minimal() +
labs(
title = "Standard Deviation Growth",
subtitle = "Should follow sqrt(n) (red dashed line)",
x = "Step",
y = "Standard Deviation",
color = ""
)# Find when walks first cross a threshold
walks <- rw30()
first_crossing <- walks |>
group_by(walk_number) |>
filter(y >= 5) |>
slice_min(step_number, n = 1) |>
select(walk_number, first_crossing_time = step_number)
# Some walks may never cross
n_crossed <- nrow(first_crossing)
cat(sprintf("%d out of 30 walks crossed 5\n", n_crossed))
#> 22 out of 30 walks crossed 5
# Distribution of first crossing times
if (n_crossed > 0) {
ggplot(first_crossing, aes(x = first_crossing_time)) +
geom_histogram(bins = 20, fill = "steelblue", alpha = 0.7) +
theme_minimal() +
labs(
title = "First Passage Time Distribution",
subtitle = "Time to first cross level 5",
x = "Step Number",
y = "Count"
)
}# Find maximum distance from origin
walks <- rw30()
max_excursion <- walks |>
group_by(walk_number) |>
summarize(
max_positive = max(y),
max_negative = min(y),
max_excursion = max(abs(y))
)
# Visualize
max_excursion |>
ggplot(aes(x = max_excursion)) +
geom_histogram(bins = 15, fill = "steelblue", alpha = 0.7) +
theme_minimal() +
labs(
title = "Distribution of Maximum Excursions",
subtitle = "Maximum absolute distance from origin",
x = "Maximum Excursion",
y = "Count"
)Once you’re comfortable with rw30(), explore:
vignette("getting-started")vignette("home")Ready for more control? Check out the function reference for customizable random walks!