# lfa: Logistic factor analysis In lfa: Logistic Factor Analysis for Categorical Data

## Description

Fit a factor model of dimension d for binomial data. Returns logistic factors.

## Usage

 `1` ```lfa(X, d, adjustments = NULL, override = FALSE, safety = FALSE) ```

## Arguments

 `X` a matrix of SNP genotypes, i.e. an integer matrix of 0's, 1's, and 2's. Sparse matrices of class Matrix are not supported (yet). `d` number of logistic factors, including the intercept `adjustments` a matrix of adjustment variables to hold fixed during estimation. `override` optional boolean to bypass Lanczos bidiagonalization SVD. Usually not advised unless encountering a bug in the SVD code. `safety` optional boolean to bypass checks on the genotype matrices, which require a non-trivial amount of computation.

## Details

This function performs logistic factor analysis on SNP data. As it stands, we follow the convention where d=1 is intercept only, and for d>1 we compute d-1 singular vectors and postpend the intercept.

## Value

matrix of logistic factors, with the intercept at the end.

## Note

Genotype matrix is expected to be a matrix of integers with values 0, 1, and 2. Note that the coding of the SNPs does not affect the algorithm.

## Examples

 ```1 2 3``` ```LF <- lfa(hgdp_subset, 4) dim(LF) head(LF) ```

### Example output

``` 159   4
[,1]       [,2]         [,3] [,4]
[1,] -0.03635636 0.10431465 -0.026157330    1
[2,] -0.04618695 0.10283828 -0.014107285    1
[3,] -0.02800495 0.09071295 -0.030261474    1
[4,] -0.03513497 0.08332765 -0.002122198    1
[5,] -0.03064114 0.07938743 -0.021696325    1
[6,] -0.02442314 0.06953981 -0.005312549    1
```

lfa documentation built on Nov. 8, 2020, 7:30 p.m.