Normalization in Statistical Analysis

Data normalization for statistical analysis

Signal and Noise

Class lecture on signal and noise by University of Geneva

Signal to noise formulations in CCD cameras

Review of S-to-N characteristics in the in photographic images

Alkemade seminal paper on Signal to Noise "A review and tutorial discussion of noise and signal-to-noise ratios in analytical spectrometry-I. Fundamental principles of signal-to-noise ratios*"

Some reminders about stats

A simple explanation about when to use a Z-test, F-test and T-test found here

Parametric Test

- Test for Normality (here)

Non-parametric Tests (for non normal distributed data)

- Spearman Correlation (here)

- Anderson-Darling and Shapiro-Wilk tests (here)

Others

- Stepwise regression in Stata (here)

Plotting them means

Plotting means in R by normal distributions with alpha levels and barplots and styles (here)

Package for plotting means + SD + SEM on Matlab (NotBoxPlots)

All Machine Learning Methods Explained

I found a good tutorial/wiki course about machine learning methods and some code on how to implement them here

Experimental Design

Guide on how to decide which type of statistical analysis to do based on which type of data we have here.

Significant values in correlations in Stata 10

To get a combination of correlations that have P-value < 0.05 and those who have a P-value < 0.01

pwcorr variables , obs sig print(.05) star(0.01)

Computational Statistics with Matlab

found on the net this tutorial by Mark Steyver with matlab code. Great!

Correlating binary and continuous variables

Correlating two nominal variables using Cramers V An example here

Statnotes website

Using SPSS website

Data mining and Machine learning blogs/lecutes

Data mining in matlab

Lecture notes for the Machine Learning course i took at McGill in 2008

Analytics and data mining blog

ANOVA - Linear Models - Experimental Design

A good summary page for different ANOVA models

Journal of Statistical Software - Special Edition: Spectroscopy and Chemometrics in R

Until today i was not aware of the important aids for chemometric research, which i think everyone should know.

1- The Special edition of JSTAR focused on chemometrics sing R. I am now exploring the contents of this Journal

2- Also the extended collection of software implementations offered for the R language for computational Chemistry and Physics

Multivariate Statistics

In the last months I have shifted from Bioinformatics (Genomics) to Chemometrics research. However, one thing that remains to addressed is my poor knowledge of statistics. One way of coping with this lack of knowledge is reading statistics books and books that deals with statistics using a programming language or a package. One of these books i have found and it's totally free (thanks to the Open Text Book initiative) is Multivariate Statistics with R by Paul J. Hewson  which can be downloaded from here.