�ݺ�ߣshows by User: WayneLee9

�ݺ�ߣshows by User: WayneLee9 / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: WayneLee9 / Thu, 23 Feb 2017 07:42:20 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: WayneLee9 Feature selection can hurt model inference /slideshow/feature-selection-can-hurt-model-inference/72491263 lessonsfromdynamictreatmentregimes-170223074221
An example showing how even with A/B testing data, fancy modeling can lead to wrong inference]]>
An example showing how even with A/B testing data, fancy modeling can lead to wrong inference]]> Thu, 23 Feb 2017 07:42:20 GMT /slideshow/feature-selection-can-hurt-model-inference/72491263 WayneLee9@slideshare.net(WayneLee9) Feature selection can hurt model inference WayneLee9 An example showing how even with A/B testing data, fancy modeling can lead to wrong inference <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lessonsfromdynamictreatmentregimes-170223074221-thumbnail.jpg?width=120&height=120&fit=bounds" /> An example showing how even with A/B testing data, fancy modeling can lead to wrong inference

Feature selection can hurt model inference from Wayne Lee

]]> 548 4 https://cdn.slidesharecdn.com/ss_thumbnails/lessonsfromdynamictreatmentregimes-170223074221-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

1 Explaining the Basics of Mean Field Variational Approximation for Statisticians /slideshow/variational-method/42615820 variationalmethod-141211124938-conversion-gate01
Explaining "Explaining Variational Approximation" by JT Ormerod and MP Wand (2010). I wanted to learn variational methods since its speed for Bayesian inference is just so fast! Here's my condensed version of the paper without the cool examples...you should really try the examples out if you want a better understanding of this method! This presentation assumes some knowledge or experience with Bayesian methods.]]>
Explaining "Explaining Variational Approximation" by JT Ormerod and MP Wand (2010). I wanted to learn variational methods since its speed for Bayesian inference is just so fast! Here's my condensed version of the paper without the cool examples...you should really try the examples out if you want a better understanding of this method! This presentation assumes some knowledge or experience with Bayesian methods.]]> Thu, 11 Dec 2014 12:49:38 GMT /slideshow/variational-method/42615820 WayneLee9@slideshare.net(WayneLee9) Explaining the Basics of Mean Field Variational Approximation for Statisticians WayneLee9 Explaining "Explaining Variational Approximation" by JT Ormerod and MP Wand (2010). I wanted to learn variational methods since its speed for Bayesian inference is just so fast! Here's my condensed version of the paper without the cool examples...you should really try the examples out if you want a better understanding of this method! This presentation assumes some knowledge or experience with Bayesian methods. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/variationalmethod-141211124938-conversion-gate01-thumbnail.jpg?width=120&height=120&fit=bounds" /> Explaining "Explaining Variational Approximation" by JT Ormerod and MP Wand (2010). I wanted to learn variational methods since its speed for Bayesian inference is just so fast! Here's my condensed version of the paper without the cool examples...you should really try the examples out if you want a better understanding of this method! This presentation assumes some knowledge or experience with Bayesian methods.

Explaining the Basics of Mean Field Variational Approximation for Statisticians from Wayne Lee

]]> 956 1 https://cdn.slidesharecdn.com/ss_thumbnails/variationalmethod-141211124938-conversion-gate01-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

1 What is bayesian statistics and how is it different? /slideshow/what-isbayesianstatistics/42459635 what-is-bayesian-statistics-141208015302-conversion-gate01
Gentle intro to Bayesian Statistics and how it's different from classical frequentist statistics. Assumes you have basic statistical knowledge. Why "Am I pregnant?" is a question more suitable for Bayesian techniques and not actually suitable at all for Frequentist techniques!]]>
Gentle intro to Bayesian Statistics and how it's different from classical frequentist statistics. Assumes you have basic statistical knowledge. Why "Am I pregnant?" is a question more suitable for Bayesian techniques and not actually suitable at all for Frequentist techniques!]]> Mon, 08 Dec 2014 01:53:02 GMT /slideshow/what-isbayesianstatistics/42459635 WayneLee9@slideshare.net(WayneLee9) What is bayesian statistics and how is it different? WayneLee9 Gentle intro to Bayesian Statistics and how it's different from classical frequentist statistics. Assumes you have basic statistical knowledge. Why "Am I pregnant?" is a question more suitable for Bayesian techniques and not actually suitable at all for Frequentist techniques! <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/what-is-bayesian-statistics-141208015302-conversion-gate01-thumbnail.jpg?width=120&height=120&fit=bounds" /> Gentle intro to Bayesian Statistics and how it's different from classical frequentist statistics. Assumes you have basic statistical knowledge. Why "Am I pregnant?" is a question more suitable for Bayesian techniques and not actually suitable at all for Frequentist techniques!

What is bayesian statistics and how is it different? from Wayne Lee

]]> 1520 6 https://cdn.slidesharecdn.com/ss_thumbnails/what-is-bayesian-statistics-141208015302-conversion-gate01-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

1 R merge-tutorial /slideshow/r-mergetutorial/40698337 r-merge-tutorial-141024164450-conversion-gate02
merg( ): SQL like JOINs in R]]>
merg( ): SQL like JOINs in R]]> Fri, 24 Oct 2014 16:44:50 GMT /slideshow/r-mergetutorial/40698337 WayneLee9@slideshare.net(WayneLee9) R merge-tutorial WayneLee9 merg( ): SQL like JOINs in R <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/r-merge-tutorial-141024164450-conversion-gate02-thumbnail.jpg?width=120&height=120&fit=bounds" /> merg( ): SQL like JOINs in R

R merge-tutorial from Wayne Lee

]]> 503 2 https://cdn.slidesharecdn.com/ss_thumbnails/r-merge-tutorial-141024164450-conversion-gate02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

1 The Key to Blind Dates - Data Snooping /slideshow/data-snooping/33230174 xlntcartoonmultiplehyptestingscript-140407113801-phpapp01
Overall, if you ask enough questions about the data, measure enough metrics, and/or fit enough models, you'll likely find one that moves in your favor. Data snooping is heavily tied to the problem of multiple testing which is elegantly demonstrated through this xkcd cartoon. There is unfortunately no golden rule to prevent data snooping given the pressure to deploy new features, discover new results, and publish interesting findings. Asking product managers/scientists to formulate hypotheses before performing the analysis can be quite difficult. This is where a data scientist should step in and help iterate between the original hypotheses and data. How would you deal with data snooping?]]>
Overall, if you ask enough questions about the data, measure enough metrics, and/or fit enough models, you'll likely find one that moves in your favor. Data snooping is heavily tied to the problem of multiple testing which is elegantly demonstrated through this xkcd cartoon. There is unfortunately no golden rule to prevent data snooping given the pressure to deploy new features, discover new results, and publish interesting findings. Asking product managers/scientists to formulate hypotheses before performing the analysis can be quite difficult. This is where a data scientist should step in and help iterate between the original hypotheses and data. How would you deal with data snooping?]]> Mon, 07 Apr 2014 11:38:01 GMT /slideshow/data-snooping/33230174 WayneLee9@slideshare.net(WayneLee9) The Key to Blind Dates - Data Snooping WayneLee9 Overall, if you ask enough questions about the data, measure enough metrics, and/or fit enough models, you'll likely find one that moves in your favor. Data snooping is heavily tied to the problem of multiple testing which is elegantly demonstrated through this xkcd cartoon. There is unfortunately no golden rule to prevent data snooping given the pressure to deploy new features, discover new results, and publish interesting findings. Asking product managers/scientists to formulate hypotheses before performing the analysis can be quite difficult. This is where a data scientist should step in and help iterate between the original hypotheses and data. How would you deal with data snooping? <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/xlntcartoonmultiplehyptestingscript-140407113801-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> Overall, if you ask enough questions about the data, measure enough metrics, and/or fit enough models, you'll likely find one that moves in your favor. Data snooping is heavily tied to the problem of multiple testing which is elegantly demonstrated through this xkcd cartoon. There is unfortunately no golden rule to prevent data snooping given the pressure to deploy new features, discover new results, and publish interesting findings. Asking product managers/scientists to formulate hypotheses before performing the analysis can be quite difficult. This is where a data scientist should step in and help iterate between the original hypotheses and data. How would you deal with data snooping?

The Key to Blind Dates - Data Snooping from Wayne Lee

]]> 1143 5 https://cdn.slidesharecdn.com/ss_thumbnails/xlntcartoonmultiplehyptestingscript-140407113801-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

1 Crash Course in A/B testing /slideshow/crash-course-in-ab-testing-for-beginners/32045017 abtestingoverview-140307115028-phpapp01
This is a crash course in A/B testing from the statistical view. Focus is placed on the overall idea and framework assuming very little experience/knowledge in statistics.]]>
This is a crash course in A/B testing from the statistical view. Focus is placed on the overall idea and framework assuming very little experience/knowledge in statistics.]]> Fri, 07 Mar 2014 11:50:28 GMT /slideshow/crash-course-in-ab-testing-for-beginners/32045017 WayneLee9@slideshare.net(WayneLee9) Crash Course in A/B testing WayneLee9 This is a crash course in A/B testing from the statistical view. Focus is placed on the overall idea and framework assuming very little experience/knowledge in statistics. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/abtestingoverview-140307115028-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> This is a crash course in A/B testing from the statistical view. Focus is placed on the overall idea and framework assuming very little experience/knowledge in statistics.

Crash Course in A/B testing from Wayne Lee

]]> 1473 10 https://cdn.slidesharecdn.com/ss_thumbnails/abtestingoverview-140307115028-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

1 Introduction to Bag of Little Bootstrap /slideshow/bagoflittlebootstrap/29294131 bagoflittlebootstrap-131217114432-phpapp02
Reading group presentation on Bag of Little Bootstrap (BLB)]]>
Reading group presentation on Bag of Little Bootstrap (BLB)]]> Tue, 17 Dec 2013 11:44:32 GMT /slideshow/bagoflittlebootstrap/29294131 WayneLee9@slideshare.net(WayneLee9) Introduction to Bag of Little Bootstrap WayneLee9 Reading group presentation on Bag of Little Bootstrap (BLB) <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/bagoflittlebootstrap-131217114432-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" /> Reading group presentation on Bag of Little Bootstrap (BLB)

Introduction to Bag of Little Bootstrap from Wayne Lee

]]> 7921 8 https://cdn.slidesharecdn.com/ss_thumbnails/bagoflittlebootstrap-131217114432-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

1 LDA Beginner's Tutorial /slideshow/lda-oct3-2013/26831803 ldaoct32013-131003112438-phpapp01
Introduction to Latent Dirichlet Allocation (LDA). We cover the basic ideas necessary to understand LDA then construct the model from its generative process. Intuitions are emphasized but little guidance is given for fitting the model which is not very insightful.]]>
Introduction to Latent Dirichlet Allocation (LDA). We cover the basic ideas necessary to understand LDA then construct the model from its generative process. Intuitions are emphasized but little guidance is given for fitting the model which is not very insightful.]]> Thu, 03 Oct 2013 11:24:38 GMT /slideshow/lda-oct3-2013/26831803 WayneLee9@slideshare.net(WayneLee9) LDA Beginner's Tutorial WayneLee9 Introduction to Latent Dirichlet Allocation (LDA). We cover the basic ideas necessary to understand LDA then construct the model from its generative process. Intuitions are emphasized but little guidance is given for �fitting the model which is not very insightful. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ldaoct32013-131003112438-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> Introduction to Latent Dirichlet Allocation (LDA). We cover the basic ideas necessary to understand LDA then construct the model from its generative process. Intuitions are emphasized but little guidance is given for �fitting the model which is not very insightful.

LDA Beginner's Tutorial from Wayne Lee

]]> 31137 11 https://cdn.slidesharecdn.com/ss_thumbnails/ldaoct32013-131003112438-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

1 https://cdn.slidesharecdn.com/profile-photo-WayneLee9-48x48.jpg?cb=1668143535 I'm constantly looking for new statistical challenges and learning the classic/novel solutions to these problems. I enjoy working with experts with diverse backgrounds and demystifying statistics. My long term objective is in scalable education for statistics which is I think is a tough challenge for statistics community and important for the general public. http://www.waynetailee.com https://cdn.slidesharecdn.com/ss_thumbnails/lessonsfromdynamictreatmentregimes-170223074221-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/feature-selection-can-hurt-model-inference/72491263 Feature selection can ... https://cdn.slidesharecdn.com/ss_thumbnails/variationalmethod-141211124938-conversion-gate01-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/variational-method/42615820 Explaining the Basics ... https://cdn.slidesharecdn.com/ss_thumbnails/what-is-bayesian-statistics-141208015302-conversion-gate01-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/what-isbayesianstatistics/42459635 What is bayesian stati...