Okay, maybe the two samples would be an inch or 2 apart. But it’s less likely that the means of the two samples will be 4 inches apart— and even less likely that there will be a difference of 6 or 8 inches. It turns out that we can calculate a standard error for the difference between two sample means; this standard error gives us a measure of the dispersion we can expea:, on average, when we subtract one sample mean from the other. (As noted earlier, the formula is in the chapter appendix.)