| Title | Author | Created | Published | Tags |
| ------------------------ | ---------- | ----------------- | ----------------- | -------------------------------------------------- |
| Inferences in Population | Jon Marien | November 20, 2025 | November 20, 2025 | [[#classes\|#classes]], [[#MATH26367\|#MATH26367]] |
# Inferences
$ \hat{p}-z_{\alpha/2}\sqrt{\frac{\hat{p}\hat{q}}n}<p<\hat{p}+z_{\alpha/2}\sqrt{\frac{\hat{p}\hat{q}}n}$
$\hat{p}$ is the sample proportion -- that is, the proportion of a specific outcome or characteristic observed in a sample of data.
$ \hat{p}=\frac xn$
$\hat{q}$ represents the sample proportion of failures — that is, the proportion of the sample that does not have the specific characteristic or outcome you are measuring. It is the complement of $\hat{p}$.
$ \hat{q}=1-\hat{p}$
Error:
$E=CI-\sqrt{\frac{\hat{p}\hat{q}}n}$
Minimum sample size:
$n=\hat{p}\hat{q}\Bigg(\frac{z_{\alpha_2}}{E}\Bigg)^2$
If necessary, round up to obtain a whole number. This formula can be found by solving the margin of error value for $n$:
$(2E=z_{\alpha/2}\sqrt{\frac{\hat{p}\hat{q}}n})$
$ \begin{array}{ccc}\hat{p}&\hat{q}&\hat{p}\hat{q}\\\\\hline0.1&0.9&0.09\\0.2&0.8&0.16\\0.3&0.7&0.21\\0.4&0.6&0.24\\0.5&0.5&0.25\\0.6&0.4&0.24\\0.7&0.3&0.21\\0.8&0.2&0.16\\0.9&0.1&0.09\end{array}$
# Example
![[image-1042.png]]Home Broadband Internet
A researcher wants to estimate with 98% confidence the proportion of Canadians who have high-speed Internet connection at home. A previous study showed that 52% of Canadian homes had have high-speed Internet connection at home. The researcher wants to be accurate within 3% of the true proportion. Find the minimum sample size necessary.
Solution:
$\text{Since z}_{\alpha/2}=2.33,\text{E}=0.03,\:\hat{p}=0.52,\hat{q}=0.48$
$ n=\hat{p}\hat{q}\Bigg(\frac{z_{\alpha/2}}E\Bigg)^2=0.48(0.52)\Bigg(\frac{2.33}{0.03}\Bigg)^2=1505.6$
which, when rounded up, indicates that **1506 homes** need to be sampled.