Regression Basicsy= b0 + b1 *X ‘regression line we want to fit’The method of least squares minimizes the squared distance between the line ‘y’ andindividual data observations yi. That is minimize: ∑ ei2 = ∑ (yi - b0 - b1 Xi...
Monthly Archives: November 2011
Gradient Descent in R
In a previous post I discussed the concept of gradient descent. Given some recent work in the online machine learning course offered at Stanford, I'm going to extend that discussion with an actual example using R-code (the actual code...
Dealing with Non-Positive Definite Matrices in R
Last time we looked at the Matrix package and dug a little into the chol(), Cholesky Decomposition, function. I noted that often in finance we do not have a positive definite (PD) matrix. The chol() function in both the Base and Matrix...
Cleaning time-series and other data streams
The need to analyze time-series or other forms of streaming data arises frequently in many different application areas. Examples include economic time-series like stock prices, exchange rates, or unemployment figures, biomedical data sequences like electrocardiograms or electroencephalograms, or industrial process operating data sequences like temperatures, pressures or concentrations. As a specific example, the figure below shows four data sequences:...
GTA R Users Group – Using R for Data Mining Competitions
Here are the presentation slides I used for my talk on “Using R for Data Mining Competitions” at Ryerson University as part of the Greater Toronto Area (GTA) R User’s Meetup Group. Presentation (Prezi) Presentation (PDF) Meetup Event page Special thanks to Anthony Goldbloom from Kaggle and various competition winners for sharing their code and
Analytics using R: Most active in my Twitter list
I follow some 80 odd people/ news sources on my twitter account. For a while I wondered which of these sources are most active on twitter. I picked a simple metric '# of status messages posted to twitter' as the measure of activity. Using R I quickly wrote a program to generate my top 10 most active...
Putting it all together: concise code to make dotplots with weighted bootstrapped standard errors
I analyze a lot of experiments and there are many times when I want to quickly look at means and standard errors for each cell (experimental condition), or the same for each cell and individual-level attribute level (e.g., Democrat, Independent, … Continue reading →
..A Quick Geo-Trick for GoogleMaps in R (using dismo)
... I thought this geocoding-bit might be worth to share (found HERE when searching the web for dismo-documentation).Read more »
Comparing StackOverflow and the R-help mailing list
Only recently I discovered StackOverflow. I know, as a nerd already programming for many years that is quite late. For those who are not familiar with StackOverflow (aka SO), it is a Question and Answer site for programmers. It is… See more ›
Count different positions between two strings of equal length
This is another pretty simple function, written to help me solve the simplest representation of a trivial but tedious task. Most biologist are probably familiar with this task. How many nucleotide differences exist between two given sequences? I only faced the easiest part of the problem, i.e. I do not perform alignment, I just assume that 
Zero Inflated Models and Generalized Linear Mixed Models with R.
Zuur, Saveliev, Ieno (2012).
