theta_plot {LongDat}

Plot theta values of negative binomial models versus non-zero count for count data

Description

Plot theta values of negative binomial models versus non-zero count for count data

Arguments

input

A data frame with the first column as "Individual" and all the columns of dependent variables (features, e.g. bacteria) at the end of the table.

test_var

The name of the independent variable you are testing for, should be a character vector (e.g. c("Time")) identical to its column name and make sure there is no space in it.

variable_col

The column number of the position where the dependent variable columns (e.g. bacteria) start in the table

fac_var

The column numbers of the position where the columns that aren't numerical (e.g. characters, categorical numbers, ordinal numbers), should be a numerical vector (e.g. c(1, 2, 5:7))

not_used

The column position of the columns not are irrelevant and can be ignored when in the analysis. This should be a number vector, and the default is NULL.

point_size

The point size for plotting in 'ggplot2'. The default is 1.

x_interval_value

The interval value for tick marks on x-axis. The default is 5.

y_interval_value

The interval value for tick marks on y-axis. The default is 5.

verbose

A boolean vector indicating whether to print detailed message. The default is TRUE.

Details

This function outputs a plot that facilitates the setting of theta_cutoff in longdat_disc() and longdat_cont(). This only applies when the dependent variables are count data. longdat_disc() and longdat_cont() implements negative binomial (NB) model for count data, and if the theta (dispersion parameter) of NB model gets too high, then the p value of it will be extremely low regardless of whether there is real significance or not. Therefore, the highest threshold of theta value is set and any variable beyond the threshold will be excluded from the test. The default value of theta_cutoff is set to 2^20 from the observation that 2^20 is a clear cutoff line for several datasets. Users can change theta_cutoff value to fit their own data.

Value

a 'ggplot' object

Examples

test_theta_plot <- theta_plot(input = LongDat_disc_master_table,
 test_var = "Time_point", variable_col = 7, fac_var = c(1:3))