Waht do you expect?

Waht do you expect?

所有跟贴·加跟贴·新语丝读书论坛

送交者: LaoXiao 于 2008-12-17, 11:23:38:

回答: Gyro，方便时，能否再帮我RUN几组数据? 由 JFF 于 2008-12-17, 09:53:33:

By CLT, the distribution can be approximated by Normal distribution as Normal(0.5*N*(a+b), 0.5*(b-a)*sqrt(N/3) ).

Your N>1000, that means the approximation should be very good.

Your only requested a 50 times simulation and "不需保留小数点后面的数", that means the simulation result will be very un-reliable.

What do you expect? Use such a meaningless simulation result to beat a beautiful theoretical approximation?

as you say N>1000, the approximation should be very good. - JFF (122 bytes) 2008-12-17, 11:45:45 (284798)
- I mean the simulation result would be meaningless - LaoXiao (209 bytes) 2008-12-17, 11:51:55 (284803)
  - agreed (无内容) - JFF (0 bytes) 2008-12-17, 11:55:54 (284807)
    - except from the topic (无内容) - JFF (0 bytes) 2008-12-17, 11:58:08 (284809)
- “不需保留小数点后面的数”。指“N个X之和”　（N > 1000) (无内容) - JFF (0 bytes) 2008-12-17, 11:48:03 (284800)
  - Let's try one more time, - LaoXiao (469 bytes) 2008-12-17, 12:11:59 (284821)
    - Let's try one more time, - JFF (263 bytes) 2008-12-17, 12:21:17 (284824)
      - example - LaoXiao (432 bytes) 2008-12-17, 12:46:26 (284839)
        
        "我想整几组直观的数据。" (无内容) - JFF (0 bytes) 2008-12-17, 13:21:45 (284864)
      - reply - LaoXiao (226 bytes) 2008-12-17, 12:33:26 (284833)
  - Put in another way, if you do the simulation 1,000,000 times, - LaoXiao (68 bytes) 2008-12-17, 11:55:18 (284806)