One-factorial ANOVA assessing intensity-dependent bias

Description

This function performs an one-factorial analysis of variance assessing intensity-dependent bias for a single array. The predictor variable is the average logged intensity of both channels and the response variable is the logged fold-change.

Usage

anovaint(obj,index,N=10)

Arguments

Details

The function anovaint performs a one-factorial ANOVA for objects of class “marrayRaw” or “marrayNorm”. The predictor variable is the average logged intensity of both channels A=0.5*(log2(Ch1)+log2(Ch2)). Ch1,Ch2 are the fluorescence intensities of channel 1 and channel 2, respectively. The response variable is the logged fold-change M=(log2(Ch2)-log2(Ch1)). The A-scale is divided in N intervals generating N levels of factor A. Note that N should divide the total number of spots approx. equally. The null hypothesis is the equality of mean(M) of the different levels (intervals). The model formula used is M ~ (A - 1) (without an intercept term).

Value

The return value is a list of summary statistics of the fitted model as produced by summary.lm. For example, the squared multiple correlation coefficient R-square equals the proportion of the variation of M that can be explained by the variation of A (based on the chosen ANOVA model.)

Author(s)

Matthias E. Futschik (http://itb.biologie.hu-berlin.de/~futschik)

See Also

anova, summary.lm, anovaspatial, marrayRaw, marrayNorm

Examples

# CHECK RAW DATA FOR INTENSITY-DEPENDENT BIAS
data(sw)
print(anovaint(sw,index=1,N=10))


# CHECK  DATA NORMALISED BY OLIN FOR INTENSITY-DEPENDENT BIAS
data(sw.olin)
print(anovaint(sw.olin,index=1,N=10))

Results

R version 3.3.1 (2016-06-21) -- "Bug in Your Hair"
Copyright (C) 2016 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> library(OLIN)
Loading required package: locfit
locfit 1.5-9.1 	 2013-03-22
Loading required package: marray
Loading required package: limma
> png(filename="/home/ddbj/snapshot/RGM3/R_BC/result/OLIN/anovaint.Rd_%03d_medium.png", width=480, height=480)
> ### Name: anovaint
> ### Title: One-factorial ANOVA assessing intensity-dependent bias
> ### Aliases: anovaint
> ### Keywords: models regression
> 
> ### ** Examples
> 
> 
> # CHECK RAW DATA FOR INTENSITY-DEPENDENT BIAS
> data(sw)
> print(anovaint(sw,index=1,N=10))

Call:
lm(formula = Mo ~ intensityint - 1)

Residuals:
     Min       1Q   Median       3Q      Max 
-2.75953 -0.36669 -0.02131  0.34523  2.52124 

Coefficients:
               Estimate Std. Error t value Pr(>|t|)    
intensityint1  -0.60288    0.02944 -20.480  < 2e-16 ***
intensityint2  -0.33124    0.02944 -11.252  < 2e-16 ***
intensityint3  -0.07640    0.02944  -2.595 0.009481 ** 
intensityint4   0.03213    0.02944   1.091 0.275185    
intensityint5   0.09345    0.02944   3.174 0.001513 ** 
intensityint6   0.15532    0.02944   5.276 1.39e-07 ***
intensityint7   0.12948    0.02944   4.399 1.12e-05 ***
intensityint8   0.08188    0.02944   2.781 0.005436 ** 
intensityint9   0.10551    0.02944   3.584 0.000342 ***
intensityint10  0.14017    0.02965   4.727 2.35e-06 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 0.6055 on 4214 degrees of freedom
Multiple R-squared:  0.1344,	Adjusted R-squared:  0.1323 
F-statistic: 65.41 on 10 and 4214 DF,  p-value: < 2.2e-16

> 
> 
> # CHECK  DATA NORMALISED BY OLIN FOR INTENSITY-DEPENDENT BIAS
> data(sw.olin)
> print(anovaint(sw.olin,index=1,N=10))

Call:
lm(formula = Mo ~ intensityint - 1)

Residuals:
    Min      1Q  Median      3Q     Max 
-3.2905 -0.1697  0.0106  0.1822  2.5434 

Coefficients:
                Estimate Std. Error t value Pr(>|t|)
intensityint1  -0.015516   0.018714  -0.829    0.407
intensityint2   0.013669   0.018714   0.730    0.465
intensityint3  -0.011883   0.018714  -0.635    0.525
intensityint4   0.013454   0.018714   0.719    0.472
intensityint5  -0.000450   0.018714  -0.024    0.981
intensityint6  -0.003763   0.018714  -0.201    0.841
intensityint7   0.006463   0.018714   0.345    0.730
intensityint8   0.002680   0.018714   0.143    0.886
intensityint9  -0.013360   0.018714  -0.714    0.475
intensityint10  0.009326   0.018848   0.495    0.621

Residual standard error: 0.3849 on 4214 degrees of freedom
Multiple R-squared:  0.0007295,	Adjusted R-squared:  -0.001642 
F-statistic: 0.3076 on 10 and 4214 DF,  p-value: 0.9795

> 
> 
> 
> 
> 
> 
> 
> 
> dev.off()
null device 
          1 
>