Recent content by consuli

  1. consuli

    [Simple R crawling for stock]

    An API-Interface is much more reliable than webscraping. You will find much more API Interfaces to financial databases in Python, especially when you are using financial algorithm backtesting portals like Quantopian.com. And the best thing is: You can still use R in Python by the RPY2 library...
  2. consuli

    [Simple R crawling for stock]

    I guess, the more pertinent terms for what you are for would be Stock Screening with [R] Stock Selection with [R] Quantitative Stock Selection with [R] As free R-API-Access to financial portals are in a dynamic change (and I temporarily do not have such a project), I currently cannot recommend...
  3. consuli

    Looking for RPy2 Referent

    Lecture in clear and normal speed English is fine, I guess. But you would have to travel to Germany (Cologne most probably). Consuli
  4. consuli

    Trump has introduced steel and alu tariffs, that economically do not make any sense. The...

    Trump has introduced steel and alu tariffs, that economically do not make any sense. The increase of metal prices for the whole economy will counteract the benfits for the metal producers a multiple times. So buen provecho!
  5. consuli

    Looking for RPy2 Referent

    The German R Forum is planning an R conference, in which - among others - Rpy2 may be a topic. Therefore we are looking for an Rpy2 referent. He/ she should have the following skills: Knowledge of RPy2 Being familiar with understanding problems of R migrators, e.g. due to own migration path...
  6. consuli

    Do you use R in power BI?

    Power BI is that limited, it is not used in statistics, usually.
  7. consuli

    Do you use `return`

    Do not understand why C is releveant here. However, I include return() most of the time.
  8. consuli

    How to choose best robust regression model?

    Hello. There are several robust regression methods like LAR-(aka LAV-, LAD-, L1-Norm-)Regression, Quantil-Regression, M-Estimator, ... They are assumed to be especially appropriate for data, that does not fulfill the 5 OLS conditions. The major part of the robust regression literature (I read)...
  9. consuli

    What does Python offer that R can't?

    Ease of learning for beginners. Graphical user interfaces. Sorted libraries instead of uncontrolled package rank growth. THOUSANDS more API interfaces to other applications, e.g. Webserver, Nvidia CUDA, ... Future safety. Python will still be serviced for decades. Summarizing, good numerical...
  10. consuli

    3 Lines Matlab Code to R Code (Generating autocorrelated random values)

    Hello, I have found the following Matlab Code for generating autocorrelated random values, with a defined autocorrelation on lag 1. Source: http://www.mathworks.com/matlabcentral/newsreader/view_thread/102939 a1=0.5; A=[1,-a1]; # A=[1,-a1] <=> A= c(1, -a1) x=filter(A,1,randn(1000,1)); #...
  11. consuli

    How to generate an autocorrelated random variable?

    Hi, I know I can generate two correlated random variables x1 an x2 using x1= z1 x2= c* z1 + sqrt(1- c^2)* z2 Where z1: standardnormal random variable z2: standardnormal random variable c= Correlation(x1, x2) But how can I generate an autocorrelated variable x, autocorrelated on x(t-1) ?
  12. consuli

    Transformation of a Uniform Distribution needed

    Hello, I have got a crazy distributed p4. (See file attachment). How can I transform a uniform distribution into the one of p4? Probit Transformation?