Jump to content

File:Interaction between sample size, effect size, and statistical power.svg

Page contents not supported in other languages.
This is a file from the Wikimedia Commons
From Wikipedia, the free encyclopedia

Original file (SVG file, nominally 1,152 × 960 pixels, file size: 366 KB)

Summary

Description
English: Distributions of sample means under the null (θ=0) and alternative hypotheses are shown. The shaded red area represents Type I error (α), held constant at 0.05, while the shaded green area represents statistical power (1-β). As the sample size increases, the distributions narrow, leading to clearer separation between the hypotheses and higher power. Similarly, a larger effect size increases the distance between the distributions, resulting in greater power.

```python import numpy as np import matplotlib.pyplot as plt from scipy.stats import norm

  1. Parameters

alpha = 0.05 # Significance level

  1. Create subplots

xmin, xmax = -0.4, 0.6 ns = [10, 30, 100] thetas = [0.1, 0.3, 0.5] fig, axes = plt.subplots(len(ns), len(thetas), figsize=(12, 10))

  1. Loop through different scenarios

for i, n in enumerate(ns): # Sample sizes

   for j, theta in enumerate(thetas):  # Effect sizes
       # Calculate parameters
       sigma = 1 / np.sqrt(n)
       z_alpha = norm.ppf(1 - alpha)
       threshold = z_alpha * sigma
       power = 1 - norm.cdf(z_alpha - theta / sigma)
       # Generate distributions
       x = np.linspace(xmin, xmax, 1000)
       null_dist = norm.pdf(x, 0, sigma)
       alt_dist = norm.pdf(x, theta, sigma)
       # Plot on the corresponding subplot
       ax = axes[i, j]
ax.plot(x, null_dist, label=rf'$H_0\; (\theta = 0)
) ax.plot(x, alt_dist, label=rf'$H_1\; (\theta = {theta})
Source Own work Edit this at Structured Data on Commons
Author

)

       ax.axvline(threshold, color='gray', linestyle='--', label='Threshold')
       ax.fill_between(x, null_dist, where=(x > threshold), color='red', alpha=0.3, label='Significance (α)')
       ax.fill_between(x, alt_dist, where=(x > threshold), color='green', alpha=0.3, label='Power (1-β)')
       # Set subplot title and labels
       ax.set_title(rf'$n={n}, \theta={theta}$ Power$={power:.2f}}})
       ax.set_xlabel('Sample Mean (x̄)')
       ax.set_yticks([])
       ax.set_xlim(xmin, xmax)
       # ax.set_ylabel('Probability Density')
       if i == 0 and j == 0: ax.legend(fontsize='small')

plt.tight_layout() plt.savefig('power_analysis.svg') plt.show() ``` }} |date=2024-07-26 |source=Own work |author=Cosmia Nebula }}

Licensing

I, the copyright holder of this work, hereby publish it under the following license:
w:en:Creative Commons
attribution share alike
This file is licensed under the Creative Commons Attribution-Share Alike 4.0 International license.
You are free:
  • to share – to copy, distribute and transmit the work
  • to remix – to adapt the work
Under the following conditions:
  • attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  • share alike – If you remix, transform, or build upon the material, you must distribute your contributions under the same or compatible license as the original.

Captions

Add a one-line explanation of what this file represents

Items portrayed in this file

depicts

image/svg+xml

375,179 byte

21ee0e509f5fa685a496e95554a3efd3f0601da3

File history

Click on a date/time to view the file as it appeared at that time.

Date/TimeThumbnailDimensionsUserComment
current02:11, 27 July 2024Thumbnail for version as of 02:11, 27 July 20241,152 × 960 (366 KB)Cosmia NebulaUploaded while editing "Replication crisis" on en.wikipedia.org

The following 2 pages use this file:

Metadata