To calculate the margin of error for the given poll, we can use the formula for the margin of error in a proportion, which is:
\[ ME = z \times \sqrt{\frac{p(1-p)}{n}} \]
Where:
- \( ME \) is the margin of error,
- \( z \) is the z-score corresponding to the desired confidence level (for a 95% confidence level, \( z \approx 1.96 \)),
- \( p \) is the proportion of respondents who selected a particular answer (0.39 in this case),
- \( n \) is the total number of respondents (350).
First, we calculate \( p(1-p) \):
\[ p = 0.39 \quad \text{and} \quad 1 - p = 1 - 0.39 = 0.61 \]
\[ p(1-p) = 0.39 \times 0.61 = 0.2379 \]
Next, we calculate the standard error (SE):
\[ SE = \sqrt{\frac{0.2379}{350}} \approx \sqrt{0.000678} \approx 0.026 \]
Now, we compute the margin of error:
\[ ME = 1.96 \times 0.026 \approx 0.0511 \]
To express this as a percentage:
\[ ME \approx 0.0511 \times 100 \approx 5.11% \]
Considering rounding, the closest answer in the provided options to the calculated margin of error (5.11%) is 5.3%.
Thus, the final answer is:
5.3%