Fit Penalized Generalized Linear Models with an Offset — glmnet_offset • offsetreg

This function is a wrapper around glmnet::glmnet() that uses a column from x as an offset.

Usage

glmnet_offset(
  x,
  y,
  family,
  offset_col = "offset",
  weights = NULL,
  lambda = NULL,
  alpha = 1
)

Arguments

x

Input matrix

y

Response variable

family

A function or character string describing the link function and error distribution.

offset_col

Character string. The name of a column in data containing offsets.

weights

Optional weights to use in the fitting process.

lambda

A numeric vector of regularization penalty values

alpha

A number between zero and one denoting the proportion of L1 (lasso) versus L2 (ridge) regularization.

alpha = 1: Pure lasso model
alpha = 0: Pure ridge model

Value

A glmnet object. See glmnet::glmnet() for full details.

Details

Outside of the tidymodels ecosystem, glmnet_offset() has no advantages over glmnet::glmnet() since that function allows for offsets to be specified in its offset argument.

Within tidymodels, glmnet_offset() provides an advantage because it will ensure that offsets are included in the data whenever resamples are created.

The x, y, family, lambda, alpha and weights arguments have the same meanings as glmnet::glmnet(). See that function's documentation for full details.

See also

glmnet::glmnet()

Examples

us_deaths$off <- log(us_deaths$population)
x <- model.matrix(~ age_group + gender + off, us_deaths)[, -1]
glmnet_offset(x, us_deaths$deaths, family = "poisson", offset_col = "off")
#> 
#> Call:  glmnet::glmnet(x = x, y = y, family = family, weights = weights,      offset = offsets, alpha = alpha, lambda = lambda) 
#> 
#>    Df  %Dev Lambda
#> 1   0  0.00 159700
#> 2   1 19.30 145600
#> 3   1 29.40 132600
#> 4   1 35.78 120800
#> 5   1 40.18 110100
#> 6   2 44.76 100300
#> 7   2 52.46  91410
#> 8   2 58.11  83290
#> 9   2 62.41  75890
#> 10  2 65.75  69150
#> 11  2 68.40  63010
#> 12  3 70.59  57410
#> 13  4 73.19  52310
#> 14  4 76.34  47660
#> 15  4 78.94  43430
#> 16  4 81.10  39570
#> 17  4 82.91  36050
#> 18  4 84.42  32850
#> 19  4 85.70  29930
#> 20  4 86.77  27270
#> 21  5 87.80  24850
#> 22  5 88.77  22640
#> 23  6 89.91  20630
#> 24  6 91.14  18800
#> 25  6 92.19  17130
#> 26  6 93.08  15610
#> 27  6 93.85  14220
#> 28  6 94.50  12960
#> 29  6 95.05  11810
#> 30  6 95.52  10760
#> 31  6 95.92   9802
#> 32  6 96.27   8931
#> 33  6 96.56   8138
#> 34  6 96.80   7415
#> 35  6 97.01   6756
#> 36  6 97.19   6156
#> 37  6 97.34   5609
#> 38  7 97.48   5111
#> 39  7 97.75   4657
#> 40  7 98.00   4243
#> 41  7 98.21   3866
#> 42  7 98.39   3523
#> 43  7 98.55   3210
#> 44  7 98.69   2925
#> 45  7 98.81   2665
#> 46  7 98.91   2428
#> 47  7 99.00   2212
#> 48  6 99.08   2016
#> 49  6 99.13   1837
#> 50  6 99.17   1674
#> 51  6 99.21   1525
#> 52  6 99.24   1389
#> 53  6 99.26   1266
#> 54  6 99.29   1153
#> 55  6 99.30   1051
#> 56  6 99.32    958
#> 57  6 99.33    873
#> 58  7 99.36    795
#> 59  7 99.38    724
#> 60  7 99.41    660
#> 61  7 99.42    601
#> 62  7 99.44    548
#> 63  7 99.45    499
#> 64  7 99.46    455
#> 65  7 99.47    414
#> 66  7 99.48    378
#> 67  7 99.49    344
#> 68  7 99.49    314
#> 69  7 99.50    286
#> 70  7 99.50    260
#> 71  7 99.51    237
#> 72  7 99.51    216
#> 73  7 99.51    197
#> 74  7 99.51    179
#> 75  7 99.52    164