tag:blogger.com,1999:blog-3850643599457806204.comments2021-03-10T02:30:37.963-05:00Engora Data BlogMike Woodwardhttp://www.blogger.com/profile/16922188923191611428noreply@blogger.comBlogger17125tag:blogger.com,1999:blog-3850643599457806204.post-57691272879251595682021-03-10T02:27:32.893-05:002021-03-10T02:27:32.893-05:00This comment has been removed by the author.dotvisionanalyticshttps://www.blogger.com/profile/01720216646538914310noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-28537036264813492022020-12-31T03:01:43.069-05:002020-12-31T03:01:43.069-05:00This comment has been removed by a blog administrator.digitalhtshttps://www.blogger.com/profile/14859107785119426989noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-50559138647943992172020-12-31T03:01:14.487-05:002020-12-31T03:01:14.487-05:00This comment has been removed by a blog administrator.digitalhtshttps://www.blogger.com/profile/14859107785119426989noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-9231327165679029212020-12-12T17:36:26.879-05:002020-12-12T17:36:26.879-05:00This comment has been removed by a blog administrator.the ishttps://www.blogger.com/profile/00819670457700045197noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-4191772960386812852020-11-09T08:10:33.542-05:002020-11-09T08:10:33.542-05:00Thanks for your comment. I'm going to talk abo...Thanks for your comment. I'm going to talk about Bayesian methods later. To be honest, I'm not a huge fan of null hypothesis testing; it feels overly complex and reliant on magic numbers. It does work, but... To me, it feels like going to a bad restaurant, yes, the meal fills you up, but you can't help but think another restaurant would have been tastier. Mike Woodwardhttps://www.blogger.com/profile/16922188923191611428noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-40989873579030270892020-11-04T13:29:45.182-05:002020-11-04T13:29:45.182-05:00Hi Mike!
Here is a simple way to grasp the meanin...Hi Mike!<br /><br />Here is a simple way to grasp the meaning of the null hypothesis.<br /><br />Specifying a hypothesis as "the null hypothesis" is a way to specify that it is supported by lots of "prior data" (data from past experiments that are not directly considered in the present test). <br /><br />Example: You have a medication that has been tested on 1 million patients over many years, and it is effective with probability 0.99. You do a small test on 100 people, and the drug seems ineffective 10% of the time. Would you reject the hypothesis that the drug is 99% effective? Of course not. (You should first try to replicate your result and identify biases in your test.)<br /><br />More precisely,<br /><br />if prob(ineffective in your test) > alpha <br />then retain the drug<br />else reject the drug,<br /><br />where alpha = your estimate of probability of rejecting H0 when H0 is true. <br /><br />The most obvious weakness of this method is that your estimate of alpha does not quantify how much prior testing you rely on. Some methods, including Bayesian methods, count the number of prior trials and combine that number with the number of trials in your test. Anonymoushttps://www.blogger.com/profile/18068160194400919196noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-55958176141986167322020-10-08T20:41:08.736-04:002020-10-08T20:41:08.736-04:00I just saw your talk about USA elections, great ta...I just saw your talk about USA elections, great talk !! I am only commenting, you can try https://panel.holoviz.org/, it's built on top of bokeh and it has the same power and speed development than tableau...nghttps://www.blogger.com/profile/16440691925669479572noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-33043087908009694382020-07-13T18:28:55.723-04:002020-07-13T18:28:55.723-04:00Thanks for the tip Todd! I'm adding this to my...Thanks for the tip Todd! I'm adding this to my reading list.Mike Woodwardhttps://www.blogger.com/profile/16922188923191611428noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-86985027992391699082020-07-12T16:46:08.385-04:002020-07-12T16:46:08.385-04:00I would suggest the book How to Speak How to Liste...I would suggest the book How to Speak How to Listen by M. Adler. That book was the one that sent me on my own journey. Toddhttps://www.blogger.com/profile/01894355437177208274noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-3623383301759670682020-02-19T18:48:29.234-05:002020-02-19T18:48:29.234-05:00I heard the story about a new CEO who was attempti...I heard the story about a new CEO who was attempting to reform the company. There were a group of men sitting on a wall. He though they were wasting company time, so he went up to them, fired them, gave them cash in compensation, and walked them off the site. Only trouble was, they were contractors waiting to begin work and the CEO had just given them several weeks' wages in cash to not do the work the company wanted done...<br />I heard this story in several forms about several companies. It's an entertaining story, but not true either.Mike Woodwardhttps://www.blogger.com/profile/16922188923191611428noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-91445733735696538112020-02-19T11:09:05.093-05:002020-02-19T11:09:05.093-05:00There’s a story in Hewlett-Packerd that an enginee...There’s a story in Hewlett-Packerd that an engineer needed at part from the storeroom out of hours but it was locked. Supposedly Bill Hewlett cut the padlock off with a bolt cutter. It always sounded implausible to me.ColinWhttps://www.blogger.com/profile/07648477899511773662noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-85263874012631557682020-02-16T16:33:43.958-05:002020-02-16T16:33:43.958-05:00Hi Colin, thank you for your comment. This is the ...Hi Colin, thank you for your comment. This is the basis of a statistical test called the z-test. I know some people are probably howling out 't-test' right now, but if the coin is only slightly biased, the number of samples needed to differentiate it from an unbiased coin is so great we're into z-test territory. The z-test is used in things like A/B testing to tell the difference between two normal distributions. (As an aside, if you are looking for a difference between two non-normal distributions, then you use the Kolmogorov–Smirnov test.) I might do a future blog post about these kinds of tests if anyone is interested.Mike Woodwardhttps://www.blogger.com/profile/16922188923191611428noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-2788532582398591542020-02-16T15:35:55.906-05:002020-02-16T15:35:55.906-05:00Thanks, Mike. Here’s a thought... what if you had ...Thanks, Mike. Here’s a thought... what if you had a nearly fair coin? Maybe the heads side sticks out more and the center of gravity is a bit off or something. Anyway, it tosses heads 0.5 + delta. How many tosses does it take to determine the rate is not 0.5 to a certain degree of confidence?ColinWhttps://www.blogger.com/profile/07648477899511773662noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-6353243352525261832020-02-13T12:56:49.008-05:002020-02-13T12:56:49.008-05:00Great advice. I haven't thought about it from ...Great advice. I haven't thought about it from this particular perspective before.Anonymoushttps://www.blogger.com/profile/08276684620600096574noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-53709991277233937212020-02-12T20:17:34.447-05:002020-02-12T20:17:34.447-05:00Well said Mike. I must take a close look at the cu...Well said Mike. I must take a close look at the current state of my footwear.Anonymoushttps://www.blogger.com/profile/02461219339436420812noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-80010470098252637662020-01-26T23:23:14.305-05:002020-01-26T23:23:14.305-05:00Hi Colin, you're correct. I've gone back t...Hi Colin, you're correct. I've gone back to the original text and I'd misread what Huff said. His language was a bit convoluted but I should still have checked better. I've corrected my bog. Thank you!Mike Woodwardhttps://www.blogger.com/profile/16922188923191611428noreply@blogger.comtag:blogger.com,1999:blog-3850643599457806204.post-86935865970204380092020-01-26T15:26:37.995-05:002020-01-26T15:26:37.995-05:00Hey Mike, gotta question your arithmetic on that d...Hey Mike, gotta question your arithmetic on that diagram. A 50% increase on top of a 50% increase is a 125% increase, not 150%. 1.5*1.5=2.25 ;-)ColinWhttps://www.blogger.com/profile/07648477899511773662noreply@blogger.com