Timeline for The $z$-test vs the $\chi^2$-test for comparing the odds of catching a cold in 2 groups
Current License: CC BY-SA 3.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 26, 2019 at 14:05 | comment | added | Scortchi♦ | (+1) But it's worth noting that you don't need to simulate: the distribution of your test statistic follows a hypergeometric distribution under the null hypothesis (& conditioning on the marginal totals). This is Fisher's Exact Test. | |
| Jan 15, 2014 at 8:56 | vote | accept | tomka | ||
| Jan 12, 2014 at 9:54 | comment | added | tomka | Thanks @jbowman -- in addition you conducted a one sided test, I see. I think this makes more sense then the two sided tests I used. If the normal approximation is done one sided, the p values is .023 above. I like the poit about independence. Probably students also were not isolated when they held their feet into the water, so that's also a way of transmitting a cold. | |
| Jan 12, 2014 at 4:09 | history | answered | jbowman | CC BY-SA 3.0 |