plot_fit_2

object

An admix variable name (remember quotation marks).

resolution

Should the function plot the number of statistics where the graph fits
the data instead of the <code><a rd-options="" href="/link/cost_function?package=admixturegraph&version=1.0.2" data-mini-rdoc="admixturegraph::cost_function">cost_function</a></code>?

show_fit

If <code>show_fit</code> is <code>TRUE</code> then each statistic is considered fitted
if the difference between a prediction and the observation statistics is no
more than $D*\sigma/(2*Z)$. Notice that even when plotting the number of
fitted statistics, we have no guarantee that the chosen variables maximize
this number as the fitting function still optimizes <code><a rd-options="" href="/link/cost_function?package=admixturegraph&version=1.0.2" data-mini-rdoc="admixturegraph::cost_function">cost_function</a></code>.

sigma

Should the figure be plotted in grayscale or in colour?

grayscale

Additional parameters passed to the plotting function
<code><a rd-options="" href="/link/contour?package=admixturegraph&version=1.0.2" data-mini-rdoc="admixturegraph::contour">contour</a></code>.


A contour plot of the cost function with respect to two admix variables specified by the user.


Implements tools for building and visualising admixture graphs
and for extracting equations from them. These equations can be compared to f-
statistics obtained from data to test the consistency of a graph against data --
for example by comparing the sign of f_4-statistics with the signs predicted by
the graph -- and graph parameters (edge lengths and admixture proportions) can
be fitted to observed statistics.

Thomas Mailund

admixturegraph

Admixture Graph Manipulation and Fitting

plot_fit_2 function

Should the function plot the number of statistics where the graph fits
the data instead of the <code><a rd-options='' href='cost_function'>cost_function</a></code>?

If <code>show_fit</code> is <code>TRUE</code> then each statistic is considered fitted
if the difference between a prediction and the observation statistics is no
more than $D*\sigma/(2*Z)$. Notice that even when plotting the number of
fitted statistics, we have no guarantee that the chosen variables maximize
this number as the fitting function still optimizes <code><a rd-options='' href='cost_function'>cost_function</a></code>.

Additional parameters passed to the plotting function
<code><a rd-options='' href='contour'>contour</a></code>.

plot_fit_2: A contour plot of the cost function.

Description

Usage

Arguments

Value

See Also