Presentation	2021-03-04 ［招待講演］実験計画法による実験方法の設計 ,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Experimental design (also known as the Design of experiments) is a systematic methodology for designing experiments to collect data efficiently, and then analyzing the data using appropriate statistical methods according to the design to draw objective conclusions. The design of experiments was conceived and developed by R.A. Fisher in the 1920s. Fisher wrote "The Arrangement of Field Experiments (1926)" and "The Design of Experiments (1935)" and proposed the idea to the world. In 1950, W. W. Hoffman published his first book, The Arrangement of Field Experiments (1926).In 1950, W.G. Cochran and G.M. Cox published a standard textbook entitled "Experimental Designs", and the design of experiments was applied to many fields. The basis of experimental design is based on Fisher's three principles of "replication", "randomization", and "local control". In the framework of scientific precision experiments proposed around the 16th century, when testing the effect of a factor of interest on a characteristic, the conditions are controlled as closely as possible. In this way, the variation caused by other factors should be suppressed, and the experiment should be conducted under conditions in which the change in the characteristic appears only as an effect of the factor of interest. In other words, it is intended to measure the effect of the factor of interest by not mixing the effects of the factor of interest with those of other factors. However, in many applied fields such as agriculture, engineering, and medicine, it is often practically impossible to control other factors as homogeneously as possible. Therefore, after admitting that we have to give up the strict control of other factors in the design of experiments, we try to cope with the uncontrolled errors and uncertainties (random errors) by correctly handling them with statistical methods. For this purpose, we are required to design experiments based on the three principles mentioned earlier. Although the design of experiments is now quite a classic, its methodology is still in use. Of course, there are many newer and more advanced methods that have been proposed since then, but understanding the idea of the design of experiments will be helpful in understanding and using such methods in any field. Finally, I would like to emphasize that although the design of experiments has its origins in agricultural testing, it is not a unique technology developed for each research field or subject, but a common technology for efficiently conducting experimental research and obtaining an objective conclusion. Regardless of the field of research, I believe that it is useful, but not useless, to be exposed to this concept at least once.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Experimental design / Research design / Analysis of variance
Paper #	IBISML2020-52
Date of Issue	2021-02-23 (IBISML)

Conference Information
Committee	IBISML
Conference Date	2021/3/2(3days)
Place (in Japanese)	(See Japanese page)
Place (in English)	Online
Topics (in Japanese)	(See Japanese page)
Topics (in English)	Organized and general sessions on machine learning
Chair	Ichiro Takeuchi(Nagoya Inst. of Tech.)
Vice Chair	Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo)
Secretary	Masashi Sugiyama(AIST) / Koji Tsuda(NTT)
Assistant	Atsuyoshi Nakamura(Hokkaido Univ.) / Shigeyuki Oba(Miidas)

Paper Information
Registration To	Technical Committee on Infomation-Based Induction Sciences and Machine Learning
Language	JPN-ONLY
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)
Sub Title (in English)
Keyword(1)	Experimental design
Keyword(2)	Research design
Keyword(3)	Analysis of variance
1st Author's Name
1st Author's Affiliation	()
Date	2021-03-04
Paper #	IBISML2020-52
Volume (vol)	vol.120
Number (no)	IBISML-395
Page	pp.pp.71-71(IBISML),
#Pages	1
Date of Issue	2021-02-23 (IBISML)