My Blog

This post is about Exponential Smoothing method, a prediction method for time series data. There are many forms of Exponential Smoothing method and the most basic ones are Single, Double and Triple (Holt-Winters) Exponential Smoothing. Some of the Exponential Smoothing forms can be written as ARIMA model; some of them can not and vice versa. Compared to ARIMA model, Exponential Smoothing method do not have strong model assumptions and it also can not add explanatory variables in the algorithm.

LDA and QDA are classification methods based on the concept of Bayes’ Theorem with assumption on conditional Multivariate Normal Distribution. And, because of this assumption, LDA and QDA can only be used when all explanotary variables are numeric. This post is my note about LDA and QDA, classification teachniques. All the contents in this post are based on my reading on many resources which are listed in the References part.

This post shows the R code for LDA and QDA by using funtion lda() and qda() in package MASS. To show how to use these function, I created a function, bvn(), to generate bivariate normal dataset based on the assumptions and then used lda() and qda() on the generated datasets. Details Resources for Package ‘MASS’ CRAN - Package ‘MASS’ Package ‘MASS’ - Reference manual Example Code LDA : Suppose our dataset are from \[X_{green}=N(\begin{pmatrix} 0.

Update : 2018-05-06 Yihui Xie has announced a new package blogdown in September 2017. This package include all the features in knitr-jekyll but instead of using Jekyll this time he switched to Hugo. There is a terrific instruction from him, blogdown: Creating Websites with R Markdown. So, if you want to integrate your website with R Markdown, I will definitely recommend you to check that out. I also convert my whole website from Jekyll with knitr-jekyll to Hugo with blogdown.

Naive Bayes Classifier is a simple and intuitive method for the classification. The algorithm is based on Bayes’ Theorem with two assumptions on predictors: conditionally independent and equal importance. This technique mainly works on categorical response and explanatory variables. But it still can work on numeric explanatory variables as long as it can be transformed to categorical variables. This post is my note about Naive Bayes Classifier, a classification teachniques.

This post shows the R code for Naive Bayes Classifier by using funtion naiveBayes() in package e1071. And I use the simple example in my post, Naive Bayes Classifier, to show how to use this function. Details Resources for Package ‘e1071’ CRAN - Package ‘e1071’ Package ‘e1071’ - Reference manual Example Code (e1071::naiveBayes()) Suppose we have a contingency table like this: Q : And, what will be our guess on type if we have a data has X1=“Yes” and X2=“Unsure”?