Armando B. Mendes

khanacademy – aulas de probabildade

Posted by Armando Brito Mendes | Filed under estatística, materiais ensino, videos

Boas aulas de video em pt sobre probabilidade

Vídeo original: Compound Probability of Independent Events (https://www.khanacademy.org/math/trigonometry/prob_comb/independent_events_precalc/v/compound-probability-of-independent-events) A Khan Academy Portugal disponibiliza explicações online de Matemática gratuitas desde o 1º até ao 12º ano de escolaridade. Este vídeo foi produzido pela Khan Academy e traduzido para português pela Fundação Portugal Telecom (ver todos os vídeos disponíveis em http://fundacao.telecom.pt/khanac

Tags: inferência

Read more | Comments off | May 10th, 2014

Exponential water tank

Posted by Armando Brito Mendes | Filed under estatística, materiais ensino, visualização

Uma excelente forma de perceber a distribuição exponencial

Hibai Unzueta, based on a paper by Albert Bartlett, demonstrates exponential growth with a simple animation. It depicts a man standing in a tank with finite capacity and water rising slowly, but at an exponential rate.

Our brains are wired to predict future behaviour based on past behaviour (see here). But what happens when something growths exponentially? For a long time, the numbers are so little in relation to the scale that we hardly see the changes. But even at moderate growth rates exponential functions reach a point where the numbers grow too fast. Once we confirm that our predictions about the future have failed, very little time to react may be left.

All looks safe at first, because the water rises so slowly, but it seems to rise all of a sudden. Oh, the suspense. What will happen to cartoon pixel man?

Tags: definição, inferência

Read more | Comments off | April 2nd, 2014

SPSS Macros on the Internet

Posted by Armando Brito Mendes | Filed under estatística, materiais para profissionais, software

Alguns sites com macros para SPSS

What sources of SPSS macros are available on the Internet?

Here are a few that I know about; I hope other people will tell us about ones that should be listed but aren’t.

An obvious starting point is SPSS Inc’s own Macro Library at http://www.spss.com/tech/stat/macros/ (it doesn’t contain very many, though, and they are statistical rather than utilities). If you are planning to adapt or write macros, it’s also worth seeing what’s in SPSS Inc’s AnswerNet Solutions. Go to http://www.spss.com/tech/answer/, specify Product; SPSS Base and Free Text: macro, then click on the page’s Search button.Raynald Levesque’s site http://pages.infinit.net/rlevesqu/ includes many pages on macros (including examples and some tutorial materials). But you should also look at the examples in his pages on syntax, as some of these are based on macros.

Newsgroups are also a useful source of macros. Searches of their archives can be very rewarding if you can get your search terms right (see our Other Internet Resources page).

Confidence intervals for proportions, differences between proportions and related quantities. See Dr Robert G. Newcombe’s home page at http://www.uwcm.ac.uk/uwcm/ms/Robert.html. Note that these are SPSS programs rather than macros, despite being described as macros by the author.

Polytomous logistic regression (of particular interest to users of SPSS 8.0 and earlier). For macros by John Hendrickx and Prof. Dr. Steffen Kühnel see http://www.sls.wau.nl/bk/bedrijfskunde/jhendrickx/spss/mlogist/

Regression: evaluating collinearity in models with interactions or non-linear terms. For a macro by Ben Pelzer, Manfred te Grotenhuis, Jan Lammers, John Hendrickx, see http://www.sls.wau.nl/bk/bedrijfskunde/jhendrickx/spss/perturb/perturb.html

Tags: Estat Descritiva, IBM SPSS Statistics, inferência, software estatístico

Read more | Comments off | March 17th, 2014

Posted by Armando Brito Mendes | Filed under estatística, materiais para profissionais

Um bom texto sobre erros cometidos por profissionais no uso da estatística

Alex Reinhart, a PhD statistics student at Carnegie Mellon University, covers some of the common analysis mistakes in Statistics Done Wrong.

Statistics Done Wrong is a guide to the most popular statistical errors and slip-ups committed by scientists every day, in the lab and in peer-reviewed journals. Many of the errors are prevalent in vast swathes of the published literature, casting doubt on the findings of thousands of papers. Statistics Done Wrong assumes no prior knowledge of statistics, so you can read it before your first statistics course or after thirty years of scientific practice.

The text is available for free online, and there’s a physical book version on the way.

Tags: análise de dados, data mining, decisão médica, inferência

Read more | Comments off | January 2nd, 2014

Why Predictive Modelers Should be Suspicious of Statistical Tests

Posted by Armando Brito Mendes | Filed under estatística

Um excelente exemplo de correlações espúrias

Well, the danger is really not the statistical test per se, it the interpretation of the statistical test.

Yesterday I tweeted (@deanabb) this fun factoid: “Redskins predict Romney wins POTUS #overfit. if Redskins lose home game before election => challenger wins (17/18) http://www.usatoday.com/story/gameon/2012/11/04/nfl-redskins-rule-romney/1681023/” I frankly had never heard of this “rule” before and found it quite striking. It even has its own Wikipedia page (http://en.wikipedia.org/wiki/Redskins_Rule).

For those of us in the predictive analytics or data mining community, and those of us who use statistical tests to help out interpreting small data, 17/18 we know is a hugely significant finding. This can frequently be good: statistical tests will help us gain intuition about value of relationships in data even when they aren’t obvious.

Tags: data mining, IBM SPSS Statistics, inferência, software estatístico

Read more | Comments off | December 18th, 2013

Advanced Statistics

Posted by Armando Brito Mendes | Filed under estatística, materiais ensino, software, visualização

Bons slides e outros materiais sobre clusters, AFE, SEM, reg logistica, meta-análise, MANOVA, Reliability

Welcome to Malbowges, the part of Nether Hell dominated by thieves, counsellors of Fraud (or should that just be counsellors), falsifiers and sowers of discord. It’s not a nice place for Sunday lunch. You must wade through rivers of Lucifer’s sputum to reach the answers you seek, and when you find those answers, you’ll probably wish you hadn’t bothered. Revenge is mine, ah ha ha, yah ha ha, ya ha ha ha ha ha ha ha ha ha …

Tags: captura de conhecimento, data mining, decisão médica, IBM SPSS Statistics, inferência, software estatístico

Read more | Comments off | January 9th, 2013

Introductory Statistics

Posted by Armando Brito Mendes | Filed under estatística, materiais ensino, videos, visualização

Muito boas aulas e slides sobre testes não paramétricos e SPSS

Welcome to Limbo, where the lustful, gluttonous and wrathful wander in endless torment. Here you can uncover the searing agony of SPSS, the stomach churning fear of central tendency and the rancid bile of z-scores. Good luck, you’ll need it.

Tags: análise de dados, captura de conhecimento, data mining, decisão médica, Estat Descritiva, IBM SPSS Statistics, inferência, inquéritos, software estatístico

Read more | Comments off | January 9th, 2013

Intermediate Statistics

Posted by Armando Brito Mendes | Filed under estatística, materiais ensino, software, videos

Muito boas aulas e slides sobre ANOVA, ANCOVA e regressão

Welcome to the wood of suicides (is anyone getting all these Dante references or am I just wasting my time here?), where self flagellation is the name of the game. You will experience the bowel-evacuating effect of multiple regression, the bone-splintering power of ANOVA and the nose-hair pulling torment of factor analysis. Can you cope: I think not, mortal filth. Be warned, your brain will be placed in a jar of cerebral fluid and I will toy with it at my leisure.

Tags: decisão médica, IBM SPSS Statistics, inferência, software estatístico

Read more | Comments off | January 9th, 2013