Home > Back-end >  Running anova on multiple column condition
Running anova on multiple column condition

Time:04-10

Here is what my subset of dataframe looks like .

a <- dput(head(mrna.pcs))
structure(list(Mouse.ID = c("DO.0661", "DO.0669", "DO.0670", 
                            "DO.0673", "DO.0674", "DO.0676"), Sex = structure(c(1L, 1L, 1L, 
                                                                                1L, 1L, 1L), .Label = c("F", "M"), class = "factor"), fAge = structure(c(2L, 
                                                                                                                                                         3L, 2L, 3L, 2L, 2L), .Label = c("6", "12", "18"), class = "factor"), 
               Index = structure(c(21L, 24L, 11L, 20L, 12L, 19L), .Label = c("AR001", 
                                                                             "AR002", "AR003", "AR004", "AR005", "AR006", "AR007", "AR008", 
                                                                             "AR009", "AR010", "AR011", "AR012", "AR013", "AR014", "AR015", 
                                                                             "AR016", "AR018", "AR019", "AR020", "AR021", "AR022", "AR023", 
                                                                             "AR025", "AR027"), class = "factor"), Lane = structure(c(6L, 
                                                                                                                                      2L, 4L, 5L, 5L, 4L), .Label = c("1", "2", "3", "4", "5", 
                                                                                                                                                                      "6", "7", "8"), class = "factor"), Gen = structure(c(1L, 
                                                                                                                                                                                                                           1L, 1L, 1L, 1L, 1L), .Label = c("8", "9", "10", "11", "12"
                                                                                                                                                                                                                           ), class = "factor"), PC1 = c(-23.147618298858, -23.004329868562, 
                                                                                                                                                                                                                                                         -17.0024755772689, -23.9178589007844, -56.7766982399411, 
                                                                                                                                                                                                                                                         -34.3969872418573), PC2 = c(40.5243564641241, 2.99206119995141, 
                                                                                                                                                                                                                                                                                     -61.4176842149059, 7.10965422446634, 7.28461966315024, -64.1955797075099
                                                                                                                                                                                                                                                         ), PC3 = c(-17.0598627155672, -22.1038475592448, -6.25238299099893, 
                                                                                                                                                                                                                                                                    23.500307567532, 53.4553992426852, -20.1077749520339), PC4 = c(-5.37605681469604, 
                                                                                                                                                                                                                                                                                                                                   28.8757760174757, 1.96723351126677, 10.1757811517044, 7.63553142427313, 
                                                                                                                                                                                                                                                                                                                                   -0.61083387825962), PC5 = c(2.49156058897602, -2.2801673669604, 
                                                                                                                                                                                                                                                                                                                                                               -5.45494631567109, -5.44682692111089, -7.21616736676726, 
                                                                                                                                                                                                                                                                                                                                                               -11.0786655194642), PC6 = c(-11.625850369587, 1.54093546690149, 
                                                                                                                                                                                                                                                                                                                                                                                           -4.87370378395642, -22.0735137415442, -2.44337914021456, 
                                                                                                                                                                                                                                                                                                                                                                                           0.619440592140127), PC7 = c(7.20873385839409, -17.719801994905, 
                                                                                                                                                                                                                                                                                                                                                                                                                       -0.811301497692041, 7.55418040146638, -4.68437054723712, 
                                                                                                                                                                                                                                                                                                                                                                                                                       1.1158744957288), PC8 = c(-7.19678837565302, 6.24827779166403, 
                                                                                                                                                                                                                                                                                                                                                                                                                                                 0.224651092284126, 6.10960416152842, -14.6615234719377, -0.410198021192528
                                                                                                                                                                                                                                                                                                                                                                                                                       )), row.names = c(NA, -6L), class = c("tbl_df", "tbl", "data.frame"
                                                                                                                                                                                                                                                                                                                                                                                                                       ))

The dataframe

Mouse.ID Sex   fAge  Index Lane  Gen     PC1    PC2    PC3    PC4    PC5     PC6     PC7     PC8
  <chr>    <fct> <fct> <fct> <fct> <fct> <dbl>  <dbl>  <dbl>  <dbl>  <dbl>   <dbl>   <dbl>   <dbl>
1 DO.0661  F     12    AR022 6     8     -23.1  40.5  -17.1  -5.38    2.49 -11.6     7.21   -7.20 
2 DO.0669  F     18    AR027 2     8     -23.0   2.99 -22.1  28.9    -2.28   1.54  -17.7     6.25 
3 DO.0670  F     12    AR011 4     8     -17.0 -61.4   -6.25  1.97   -5.45  -4.87   -0.811   0.225
4 DO.0673  F     18    AR021 5     8     -23.9   7.11  23.5  10.2    -5.45 -22.1     7.55    6.11 
5 DO.0674  F     12    AR012 5     8     -56.8   7.28  53.5   7.64   -7.22  -2.44   -4.68  -14.7  
6 DO.0676  F     12    AR020 4     8     -34.4 -64.2  -20.1  -0.611 -11.1    0.619   1.12   -0.410

My objective is to run anova between my Principal components and the variables which are here Sex,fAge,Index,Lane,Gen .

The way it is being run now is this

For PC1

anova(lm(PC1 ~ Sex*fAge, data=mrna.pcs))

For PC2

anova(lm(PC2 ~ Sex*fAge, data=mrna.pcs))

For PC3

anova(lm(PC3 ~ Sex*fAge, data=mrna.pcs))

Similarly for other PCs

anova(lm(PC4 ~ Sex*fAge, data=mrna.pcs))
anova(lm(PC5 ~ Sex*fAge, data=mrna.pcs))
anova(lm(PC6 ~ Sex*fAge, data=mrna.pcs))
anova(lm(PC7 ~ Sex*fAge, data=mrna.pcs))
anova(lm(PC8 ~ Sex*fAge, data=mrna.pcs))

So these are only for Sex and Age if i have to run for the rest of the predictors I have to run them individually. Here it is okay since I have small no of PCs but I have data which runs into quite a bit of PCs and other traits/predictors.

So my question is how is there way to set up them to run them in one go such that it can test each PCs vs all the predictors.

For example

PC1 ~ Sex 
PC1 ~ Sex fAge
PC1 ~ Sex fAge Index
PC1 ~ Sex fAge Index Lane
PC1 ~ Sex fAge Index Lane Gen

The same for other PCs as well

CodePudding user response:

As Axeman points out, it's a bad idea to blindly try all possible permutations of a regression. This "fishing expedition" approach is highly likely to lead to spurious results.

That said, here's how you could generate a large number of formulae and then apply these to your data set. Since your sample data set contains only 6 rows, there isn't enough data to actually run the last step, but it should work. Here I use expand.grid to generate many different formulae, then use lapply to run them against the data.

rhs <- c(
  'Sex', 
  'Sex fAge',
  'Sex fAge Index',
  'Sex fAge Index Lane',
  'Sex fAge Index Lane Gen'
)
dv <- paste0('PC', 1:8)
frms <- with(expand.grid(dv, rhs), paste(Var1, Var2, sep = ' ~ '))

models <- lapply(frms, function(x) anova(lm(x, data = mrna.pcs)))
names(models) <- frms # so that you can see which formula belongs to which output

Or rather than working with a predefined set of formulae, you could use combn to generate all possible combinations of predictors from a list of them. From there, the rest of the solution is the same.

iv <- c("Sex", "fAge", "Index", "Lane", "Gen")  
dv <- paste0('PC', 1:8)
rhs <- unlist(sapply(1:length(iv), function(m) apply(combn(iv, m = m), 2, paste, collapse = '   ')))
frms <- with(expand.grid(dv, rhs), paste(Var1, Var2, sep = ' ~ '))

models <- lapply(frms, function(x) anova(lm(x, data = mtcars)))
names(models) <- frms

This use of combn generates 31 formulae from 5 given predictors:

 [1] "Sex"                             "fAge"                           
 [3] "Index"                           "Lane"                           
 [5] "Gen"                             "Sex   fAge"                     
 [7] "Sex   Index"                     "Sex   Lane"                     
 [9] "Sex   Gen"                       "fAge   Index"                   
[11] "fAge   Lane"                     "fAge   Gen"                     
[13] "Index   Lane"                    "Index   Gen"                    
[15] "Lane   Gen"                      "Sex   fAge   Index"             
[17] "Sex   fAge   Lane"               "Sex   fAge   Gen"               
[19] "Sex   Index   Lane"              "Sex   Index   Gen"              
[21] "Sex   Lane   Gen"                "fAge   Index   Lane"            
[23] "fAge   Index   Gen"              "fAge   Lane   Gen"              
[25] "Index   Lane   Gen"              "Sex   fAge   Index   Lane"      
[27] "Sex   fAge   Index   Gen"        "Sex   fAge   Lane   Gen"        
[29] "Sex   Index   Lane   Gen"        "fAge   Index   Lane   Gen"      
[31] "Sex   fAge   Index   Lane   Gen"

Which is then combined with the dependent variables for a total of 248 formulae.

CodePudding user response:

Consider lapply on the PCs, combn on all combinations of non-PC columns, and reformulate for formula build

# RESPONSE AND TRAIT COLUMN VECTORS
PC_cols <- names(mrna.pcs)[grep("PC", names(mrna.pcs))]
traits <- names(mrna.pcs)[grep("PC", names(mrna.pcs)[-1], invert=TRUE)]

# GENERALILZED METHOD TO RUN DYNAMIC MODEL
run_model <- function(PC, traits) {
    fml <- reformulate(traits, response=PC)
    anova(lm(fml, data=mrna.pcs))
}

# NAMED LIST OF ANOVA OBJECTS
anova_list <- sapply(
    PC_cols,
    function(PC) lapply(
        seq_along(traits), 
        function(i) combn(traits, i, FUN=function(t) run_model(PC, t))
    ),
    simplify = FALSE
)

# ACCESS ELEMENTS
anova_list$PC1
anova_list$PC2
anova_list$PC3
...
anova_list$PC8
  • Related