BioF3 FigCode · SCI 绘图代码集

样本量-功效曲线（Power Curve）

导出日期：2026年6月27日

分类：分布可视化 ｜ 依赖包：pwr、ggplot2、tidyr

解决的生物学问题

我要检测 1.5 倍差异需要多少样本？现有样本量能达到 80% power 吗？

应用场景

输入数据格式

参数：effect_size 范围、显著性水平 α、检验类型

关键参数

快速开始

1. 直接在线运行

打开 FigCode 在线绘图，点击本工具卡片的"在线绘图"按钮即可用内置示例数据出图，零环境配置。

2. 本地复现

下载脚本和示例数据，本地 RStudio 运行：

# 下载
curl -O https://<your-site>/figcode/scripts/power-curve.R
curl -O https://<your-site>/figcode/data/power-curve.csv

3. 安装依赖

# CRAN 包
install.packages(c("pwr", "ggplot2", "tidyr"))

# Bioconductor 包（如需）
# BiocManager::install(c())

完整代码

library(pwr)
library(ggplot2)
library(tidyr)

# --- Compute power across n for several effect sizes ---
n_seq <- seq(5, 200, by = 5)
effects <- c(0.2, 0.5, 0.8)   # Cohen's d: small / medium / large

df <- expand.grid(n = n_seq, d = effects)
df$power <- mapply(
  function(n, d) pwr.t.test(n = n, d = d, sig.level = 0.05,
                             type = "two.sample")$power,
  df$n, df$d
)
df$d_label <- factor(
  paste0("d = ", df$d),
  levels = paste0("d = ", effects)
)

# --- Plot ---
ggplot(df, aes(n, power, color = d_label)) +
  geom_line(size = 1.1) +
  geom_hline(yintercept = 0.8, linetype = "dashed", color = "grey50") +
  annotate("text", x = max(n_seq), y = 0.81,
           label = "Power = 0.80", hjust = 1, size = 3.5, color = "grey40") +
  scale_color_manual(values = c("#dc2626", "#059669", "#2563eb"),
                     name = "Effect size") +
  scale_y_continuous(limits = c(0, 1), breaks = seq(0, 1, 0.2)) +
  labs(title = "Two-sample t-test Power",
       x = "Sample size per group", y = "Statistical power") +
  theme_classic()

替换为自己的数据

脚本中以 # --- Demo data --- 标注的段落是示例数据生成代码。替换为自己的数据时，保持列名一致即可：

延伸阅读