以åããåæ§ã®ææã¯æ§ã ãªåéããæ§ã ãªäººã ãæ§ã ãªå½¢ã§åºãã¦ãã¦ãã¾ããããã¢ã¡ãªã«çµ±è¨å¦ä¼ã以ä¸ã®ãããªæ示çãªå£°æããã®3æ7æ¥ï¼ç¾å°æéï¼ã«çºè¡¨ããã¨ãããã¨ã§æ³¨ç®ãéãã¦ããããã§ãã
AMERICAN STATISTICAL ASSOCIATION RELEASES STATEMENT ON STATISTICAL SIGNIFICANCE AND P-VALUES
Provides Principles to Improve the Conduct and Interpretation of Quantitative Science
https://www.amstat.org/newsroom/pressreleases/P-ValueStatement.pdf
The ASA's statement on p-values: context, process, and purpose
http://amstat.tandfonline.com/doi/abs/10.1080/00031305.2016.1154108
- P-values can indicate how incompatible the data are with a specified statistical model.
- P-values do not measure the probability that the studied hypothesis is true, or the probability that the data were produced by random chance alone.
- Scientific conclusions and business or policy decisions should not be based only on whether a p-value passes a specific threshold.
- Proper inference requires full reporting and transparency.
- A p-value, or statistical significance, does not measure the size of an effect or the importance of a result.
- By itself, a p-value does not provide a good measure of evidence regarding a model or hypothesis.
ï¼ç§è¨³ï¼
- på¤ã¯ããã®ãã¼ã¿ãããç¹å®ã®çµ±è¨ã¢ãã«ã¨ã©ããããé©åããªãããã示ãå¾ã
- på¤ã¯ããã®ä»®èª¬ãçã§ãã確çãã¯ä¸ããªãããã©ã³ãã ãªå¶ç¶ã ããããã®ãã¼ã¿ãå¾ããã確çããä¸ããªã
- ç§å¦ççµè«åã³ãã¸ãã¹ã»æ¿çä¸ã®ææ決å®ã¯ãpå¤ãããç¹å®ã®é¾å¤ãåã£ããã©ãããã ãã«æ ãã¹ãã§ã¯ãªã
- é©åãªæ¨è«ã¯å®å ¨ãªï¼ãã¼ã¿åã³ã¢ãã«ã«é¢ããï¼ã¬ãã¼ãã£ã³ã°ã¨éææ§ãè¦ããã¹ãã§ãã
- åä¸ã®på¤ãããã¯çµ±è¨çæææ§ã¯ãã®çµæã®å¹æãéè¦æ§ã®å¤§ããã測ããã®ã§ã¯ãªã
- på¤ãã®ãã®ã ãã§ã¯ã¢ãã«ã仮説ã«é¢ããã¨ããã³ã¹ã®è¯ãææ¨ããå¾ãªã
ãã®ããã¥ã¡ã³ãã®ä¸ã§ã¢ã¡ãªã«çµ±è¨å¦ä¼ã®presidentã§ããJessica Uttsææãèªã£ã¦ãã¾ããããpå¤åé主義ã«å¯¾ãã決å¥ãçµ±è¨å¦è ã®ã³ãã¥ããã£ããã®ä¼é·ã¨boardã®åã«ããã¦å®£è¨ãããã®ã¯æããå²ä¸åãã¦ã®ãã¨ã§ã¯ãªããã¨æããã¾ããããã¦ãã®å£°æã®åãã¾ã¨ãå½¹ã§ãããASAã®executive directorãåããRon Wassersteinå士ã¯ãè¯ãåå³ãããçµ±è¨å¦ä¸ã®è°è«ã¨ã¯ãã²ã¨ã¤ã®æ°åãã©ãã¨ããã®æ°åãããæ£æçãªé¾å¤ãè¶ ãã¦ãããã©ãããªã©ã¨ãã以ä¸ã®å 容ãå«ããã®ã ãããã®ASAã®å£°æã¯ï¼çµ±è¨å¦ãç¨ããï¼ç 究ã®èµãããã¹ãp < 0.05æ代ãã¸ã¨åããããã®ã ãã¨ã¾ã§è¨ã£ã¦ãã¾ãã
åèªèº«ããã¤ã¦ãããä»ç¾å¨ãæã æ©ã¾ãããåé¡ãªã®ã§è³ã®çã話ã§ããããp < 0.05ã§ãªããã°åãå ¥ããããªããã¨ããã«ã«ãã£ã¼ãããããå¼å®³ã¯é常ã«å¤§ããããã§ããããæã¯file-drawer effect*1ã«ã¤ãªãã£ãããããæã¯p-value hacking*2ãdata dredging*3ã«ã¤ãªãã£ãããã¨ããã¼ã¿ããçã«æ義ããç¥è¦ãå¾ããã¨ããæ¬ç¾©ã«æãäºæ ã«ãªããã¨ããããã¨ããã
ï¼æ£è¦åå¸ã®çå´5%åãå³ç¤º*4ãããã®ï¼
ãã®å£°æã®å¾åã«ã¯ãpå¤ã«ä¾æ ããªãæ°ããªã¢ããã¼ãã®ä¾ãã¨ãã¦äºæ¸¬å¤ãéè¦ããã¢ããã¼ã*5ããã¤ã¸ã¢ã³ã¢ããªã³ã°ã決å®çè«çã¢ããã¼ã*6ããã³false discovery rate*7ã¨ãã£ããã®ãç¨ããã¹ããã¨ããã³ã¡ã³ããä»ããã¦ãã¾ããå®ã¯åæ§ã®è©±ã¯[twitter:@KuboBook]å çã®ãã¿ã©ãã¼ããï¼ãã¼ã¿è§£æã®ããã®çµ±è¨ã¢ããªã³ã°å ¥éââä¸è¬åç·å½¢ã¢ãã«ã»é層ãã¤ãºã¢ãã«ã»MCMC (確çã¨æ å ±ã®ç§å¦)ï¼ã§ãææããã¦ãã¦ãããããããããããã¦å ¬ã®ãã®ã¨ãã¦æ¥ã®ç®ãè¦ãã®ããªï¼ã¨æã£ã¦ããã¨ããã§ããããããæå³ã§è¨ãã¨ãå°ãåã«ããã°ã«æ¸ãããã®ä»¶ãã追è¨ãã§åãä¸ãããã¤ã¸ã¢ã³çã¢ããã¼ãã®æ¹ã妥å½ãªã®ããããã¾ãããã
ã¨ããã§ããã®ASAã®å£°æã¯å®é¨ç§å¦ã»ç¤¾ä¼èª¿æ»ã®ç 究ããã¦ãã人ã ã«å¤§ããªæ³¢ç´ãæããããã®ã ããã¨æãã¾ãããä¸ã®ç§è¨³ã§å¤ªåä¸ç·ã«ããããã«ããã¸ãã¹ã»æ¿çä¸ã®ææ決å®ã«ããã¦ããpå¤åé主義ããã®è±å´ãä¿ãã¦ããã¨ãè¨ããåãå«ãããã¸ãã¹å®åã®ç¾å ´ã§ãã¼ã¿åæã«åãçµã人ã ã«ã¨ã£ã¦ãå¿ãã¹ããã®ãªã®ããªã¨åãæ¢ãã¦ãã¾ãããå ¨ã¦ãpå¤ã®ããã«ãããªãèªããã¼ã¿ãã®ãã®ã«deep diveãã¦ç´å¾ã®ããã¨ããã³ã¹ãæ±ãããã¨ããèªã¿æ¹ããããªãã°ãããã¾ã§ä»¥ä¸ã«ãæ¤å®ãã§ã¯ãªããã¢ããªã³ã°ãã¸ã¨ã·ãããã¦ããã¹ããªã®ããªã¨æã次第ã§ãã
*1:p < 0.05ã«éããªãã£ãã¨ããã ãã§è«æèªã®æ»èªããã®ä»ã®å¯©æ»ãééã§ããæ¡æãããªãç 究ãåºã¦ããåé¡
*2:p < 0.05ã«ãããã¨ã ããç®çã¨ãã¦åççãªçç±ããªãçµ±è¨åæææ³ãããããæå½ãã次第ã«è©¦ããã¨
*3:ä¸å¿ è¦ã«å¤§ããªãµã³ãã«ãµã¤ãºã¨å¤ãã®ç¹å¾´éãç¨æãããã¨ã«ãã£ã¦æ¬æ¥ãªãä½ã®é¢é£ããªãã¯ãã®å¤æ°å士ã«é¢é£ããããã®ããã«è¦ãã¦ãã¾ã誤ã£ãçµè«ã«è³ããã¨ã§ãå¤éæ¯è¼ã®æ çµã¿ã§åé¡ã«ãªããã¨ãå¤ãããã
*4:ããæ¹ãã»ã¼å¿ãã¦ããã®ã§ãã¡ããåç §ãã¾ãã http://aaaaushisan.blogspot.jp/2012/04/r_13.html
*5:ããããæ©æ¢°å¦ç¿çãªäº¤å·®æ¤è¨¼ãªã©ãæ³å®ãã¦ããã®ããªã¨
*6:ããããããconfusion matrixã«åºã¥ãå種ã®äºæ¸¬ã¹ã³ã¢è©ä¾¡ãè¨ã£ã¦ããã®ãã
*7:å¤éæ¯è¼è£æ£ã®ä¸ã§ã¯å²ã¨æ°ããææ³