# fftper

##### Compute a Periodogram via FFT

Compute a periodogram of the univariate time series via FFT.

- Keywords
- ts

##### Usage

`fftper(y, window = 1, plot = TRUE, …)`

##### Arguments

- y
a univariate time series.

- window
smoothing window type. (0: box-car, 1: Hanning, 2: Hamming)

- plot
logical. If

`TRUE`

(default), smoothed periodogram is plotted.- …
further arguments to be passed to

`plot.spg`

.

##### Details

Hanning Window : | \(W_0\) = 0.5 | \(W_1\) = 0.25 |

##### Value

An object of class `"spg"`

, which is a list with the following
elements:

periodogram (raw spectrum).

smoothed periodogram. If there is not a negative number, logarithm of smoothed periodogram.

if `TRUE`

"smooth the periodogram on log scale.

the name of the univariate time series `y`

.

##### Note

We assume that the length \(N\) of the input time series `y`

is a power
of 2. If \(N\) is not a power of 2, calculate using the FFT by appending 0's
behind the data `y`

.

##### References

Kitagawa, G. (2010)
*Introduction to Time Series Modeling*. Chapman & Hall/CRC.

##### Examples

```
# NOT RUN {
# Yaw rate, rolling, pitching and rudder angle of a ship
data(HAKUSAN)
YawRate <- HAKUSAN[, 1]
fftper(YawRate, window = 0)
# }
```

*Documentation reproduced from package TSSS, version 1.2.3, License: GPL (>= 2)*