Sample size for 10,000 people
10,000 people — a mid-size CRM base, a large company's workforce, a town: at this scale the finite population correction still helps, but modestly. You need 370 respondents for ±5% at 95% confidence, versus 385 for an infinite population. The saving is real (15 respondents) but we're entering the zone where population size stops being a lever.
That's this page's practical lesson: between 10,000 and infinity, the required sample varies by less than 4%. If your base is 'around 10,000', don't bother measuring it precisely — the error is negligible. Invest instead in recruitment representativeness, which weighs far more on final quality.