CLUSTER {unknown} | R Documentation |

## CLUSTER Method for Detecting Pulse Locations.

### Description

Detect pulse locations using the CLUSTER method

### Usage

CLUSTER(x, y, data, sd=.07*mean(y), nnadir=2, npeak=3, alpha)

### Arguments

`x` |
a vector of observation time points. |

`y` |
a vector of hormone concentrations. |

`data` |
a data frame containing the variables occurring in the `x`
and `y` arguments. If this option is not specified, the variables
should be on the search list. Missing values are not allowed. |

`sd` |
standard deviation for the pooled $t$ test. Default is 7% of the
mean response. |

`nnadir` |
number of nadir points used in the $t$ statistics. Default is 2. |

`nnpeak` |
number of peak points used in the $t$ statistics. Default is 3. |

`alpha` |
Significance level of the $t$ statistics. |

### Details

CLUSTER uses $t$ test between two overlapping consecutive
sets of points to identify significant increases and decreases in
observations. The default for the standard deviation `sd` is by
no means standard. Users are recommended to provide an accurate estimate
instead of using the default.

### Value

A vector of pulse locations.

### Author(s)

Yu-Chieh Yang, Anna Liu, Yuedong Wang

### References

Veldhuis, J. D. and Johnson, M. L. (1986), Cluster analysis:
a simple versatile and robust algorithm for endocrine pulse detection,
*American Journal of Physiology*, **250**, E486-E493.

### See Also

`pulini`

### Examples

pl4 <- CLUSTER(time, conc, data=acth, sd=.05*mean(acth$conc), alpha=.2)