東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

A Comparison of Tests for Online Experiments.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	A Comparison of Tests for Online Experiments./
作者:	Dsouza, Alan.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
面頁冊數:	38 p.
附註:	Source: Masters Abstracts International, Volume: 83-12.
Contained By:	Masters Abstracts International83-12.
標題:	Statistics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29215455
ISBN:	9798819378168

A Comparison of Tests for Online Experiments.
Dsouza, Alan.

A Comparison of Tests for Online Experiments. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 38 p.

Source: Masters Abstracts International, Volume: 83-12.

Thesis (M.A.S.)--University of California, Los Angeles, 2022.

This item must not be sold to any third party vendors.

Online experiments have grown in popularity but the techniques used to evaluate them have not adapted to the continuous stream of results. The goal of this review is to analyze the limitations of current online experiment tests and evaluate newer techniques that are better suited for continuous assessment. Conducting tests on simulated experiments showed that peeking at results can cause 3 times as many false-positives when using t-test's. The conservative nature of multiple comparison adjustments led to rejecting over 50% of winning ideas. Mixture Sequential Probability Ratio Tests (mSPRT) resulted in few Type-I errors even when monitoring results continuously. Using mSPRT led to 1/6th as many Type-I errors. There are known downsides to mSPRT including implementation complexity and computation costs, but these are likely smaller than the value created from having a more reliable analysis technique.

ISBN: 9798819378168Subjects--Topical Terms:

517247
Statistics.
Subjects--Index Terms:

A/B test

A Comparison of Tests for Online Experiments.
LDR:02003nmm a2200373 4500 001 2350759
005 20221020130439.5
008 241004s2022 ||||||||||||||||| ||eng d
020 $a 9798819378168
035 $a (MiAaPQ)AAI29215455
035 $a AAI29215455
040 $a MiAaPQ $c MiAaPQ
100 1 $a Dsouza, Alan. $3 3690268
245 1 0 $a A Comparison of Tests for Online Experiments.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 38 p.
500 $a Source: Masters Abstracts International, Volume: 83-12.
500 $a Advisor: Xu, Hongquan.
502 $a Thesis (M.A.S.)--University of California, Los Angeles, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a Online experiments have grown in popularity but the techniques used to evaluate them have not adapted to the continuous stream of results. The goal of this review is to analyze the limitations of current online experiment tests and evaluate newer techniques that are better suited for continuous assessment. Conducting tests on simulated experiments showed that peeking at results can cause 3 times as many false-positives when using t-test's. The conservative nature of multiple comparison adjustments led to rejecting over 50% of winning ideas. Mixture Sequential Probability Ratio Tests (mSPRT) resulted in few Type-I errors even when monitoring results continuously. Using mSPRT led to 1/6th as many Type-I errors. There are known downsides to mSPRT including implementation complexity and computation costs, but these are likely smaller than the value created from having a more reliable analysis technique.
590 $a School code: 0031.
650 4 $a Statistics. $3 517247
650 4 $a Educational tests & measurements. $3 3168483
650 4 $a Educational technology. $3 517670
650 4 $a Web studies. $3 2122754
650 4 $a Educational evaluation. $3 526425
653 $a A/B test
653 $a Online experiments
653 $a Sequential tests
690 $a 0463
690 $a 0288
690 $a 0443
690 $a 0646
690 $a 0710
710 2 $a University of California, Los Angeles. $b Statistics 0891. $3 2095317
773 0 $t Masters Abstracts International $g 83-12.
790 $a 0031
791 $a M.A.S.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29215455