Outlier detection of time series data in R

r detection outliers
growth_hacker picture growth_hacker · Jul 15, 2014 · Viewed 15.7k times · Source

What are the steps needed to detect outliers in business sales data (which means there might be trends and seasonality) in R?

I have learnt about ACF, PACF, residual, ARIMA model (basically, time series analysis and modelling). Can I use this knowledge to help me identify outliers?

Is it also possible to ask R to pinpoint which point of data is outlier?

Thank you very much.

Answer

javlacalle picture javlacalle · Jul 15, 2014

You may have a look at the following packages available in R.

The R package forecast uses loess decomposition of time series to identify and replace outliers.

The R package tsoutliers implements the Chen and Liu procedure for detection of outliers in time series. A description of the procedure and the implementation is given in the documentation attached to the package. You may also see this post.

Related questions

Remove rows with all or some NAs (missing values) in data.frame

I'd like to remove the lines in this data frame that: a) contain NAs across all columns. Below is my example data frame. gene hsap mmul mmus rnor cfam 1 ENSG00000208234 0 NA NA NA NA 2 ENSG00000199674 0 2 2 2 2 3 ENSG00000221622 0 NA NA NA NA 4 …

Read More
Drop data frame columns by name

I have a number of columns that I would like to remove from a data frame. I know that we can delete them individually using something like: df$x <- NULL But I was hoping to do this with …

Read More
Changing column names of a data frame

I have a data frame called "newprice" (see below) and I want to change the column names in my program in R. > newprice Chang. Chang. Chang. 1 100 36 136 2 120 -33 87 3 150 14 164 In fact this is what am doing: names(newprice)[1]<-paste("premium") …

Read More