# Position Leverage

### Description

Provides a rough heuristic for determining the degree to which each position in the DNA matrix affects the resulting tree.

### Usage

1 | ```
position.leverage(data, F, to = NULL, rep = 50, by = 1)
``` |

### Arguments

`data` |
A DNA matrix in |

`F` |
A tree estimation function, accepting a DNA matrix of class |

`to` |
The tree with which distances are measured in respect to, or |

`rep` |
The number of times to replicate the position in question. |

`by` |
The function will perform the calculation on every |

### Details

This function takes a DNA matrix and, for every `by`

-th position,
replicates that position `rep`

times, randomly removing
`rep`

other positions to keep all sequences the same length
other positions to keep all sequences the same length. For each new DNA
matrix created in this way, `F`

is used to estimate the corresponding
tree, and the distance to tree `to`

is computed and stored. This
distance can be thought of as somewhat analogous to the leverage of that
position.

### Value

Returns a numeric vector of distances from tree `to`

for each position
sampled.

### Author(s)

John Chakerian <chakj@stanford.edu>

### References

Chakerian, J. and Holmes, S. P. Computational Tools for Evaluating Phylogenetic and Heirarchical Clustering Trees. arXiv:1006.1015v1.

### See Also

`dist.multiPhylo`

### Examples

1 2 3 | ```
data(woodmouse)
f.est <- function(x) root(nj(dist.dna(x)), "No305", resolve.root=TRUE)
position.leverage(woodmouse, f.est, by=10)
``` |