WordGPT

Margin of error for n = 400 at 99% confidence

With a sample of 400 the margin of error at 99% confidence is about ±6.44 percentage points (worst case, p = 0.5).

How to work it out

  1. 1

    The margin of error for a proportion is z* times the standard error.

    E=z∗p(1−p)nE = z^{*}\sqrt{\frac{p(1-p)}{n}}
  2. 2

    For 99% confidence z* = 2.576. Use p = 0.5 for the worst case.

    E=2.5760.5×0.5400=0.06440E = 2.576\sqrt{\frac{0.5 \times 0.5}{400}} = 0.06440
  3. 3

    As a percentage:

    E=±6.44%E = \pm 6.44\%
  4. 4

    Quadrupling the sample size only halves the margin of error, because n is under a square root.

LaTeX source of the formulas on this page
\[ E = z^{*}\sqrt{\frac{p(1-p)}{n}} = 6.44\% \]
\[ E = z^{*}\sqrt{\frac{p(1-p)}{n}} \]
\[ E = 2.576\sqrt{\frac{0.5 \times 0.5}{400}} = 0.06440 \]
\[ E = \pm 6.44\% \]

Margin of error for n = 400 by proportion

Proportion pMargin of error
0.5±6.44%
0.4±6.31%
0.3±5.90%
0.2±5.15%
0.1±3.86%
0.05±2.81%

Margin of error for n = 400 at other confidence levels

ConfidenceMargin of error (p = 0.5)
80%±3.20%
90%±4.11%
95%±4.90%
98%±5.82%
99%±6.44%

Questions

What is the margin of error for 400 respondents?

About ±6.44 percentage points at 99% confidence.

How does the margin of error change with sample size?

It is proportional to 1/√n: a sample four times as large has half the margin of error.

What does a margin of error of ±6.4% mean?

If the poll were repeated many times, 99% of the intervals p̂ ± 6.4% would contain the true proportion.

Other sample sizes

Other confidence levels

    Margin of error for a sample of 400 at 99% confidence: ±6.44% | WordGPT