If you have a sample with n observations, it's the summation I = 1 to n of xi/n--that's the average.

如果你有n个观测值,对Xi从i=1到n求和再除以n

耶鲁公开课 - 金融市场课程节选

Therefore, the convention among academic researchers is that it is ok, and you can claim your conclusion based on only a sample of observations, as long as the probability that you are wrong is no bigger than 5%.

FORBES: Publication Bias (or, Why You Can't Trust Any of the Research You Read)

Final results of the first research sample of the investigators' observations will be published in late March.

CENTERFORSECURITYPOLICY: New Shariah study documents Islamist threat