This function computes predictions based on fitted linear quantile models.

# S3 method for class 'rq.counts'
predict(object, newdata, offset,
  na.action = na.pass, type = "response",
  namevec = NULL, ...)

Arguments

object

an rq.counts object.

newdata

an optional data frame in which to look for variables with which to predict. If omitted, the fitted values are used.

offset

an offset to be used with newdata.

na.action

function determining what should be done with missing values in newdata. The default is to predict NA.

type

the type of prediction required. The default "response" is on the scale of the response variable, i.e. the values are back-transformed using the inverse of the transformation \(h^{-1}(Xb)\); the alternative "link" is on the scale of the linear predictors \(h(y) = Xb\); finally, predictions for marginal effects are given with "maref".

namevec

character giving the name of the covariate with respect to which the marginal effect is to be computed. If type = "maref", this argument is required. See maref.rq.counts.

...

not used.

Value

a vector or a matrix or an array of predictions.

Author

Marco Geraci

Examples


# Esterase data
data(esterase)

# Fit quantiles 0.25 and 0.75
fit <- rq.counts(Count ~ Esterase, tau = 0.5, data = esterase, M = 50)
cbind(fit$fitted.values, predict(fit, type = "response"))
#>          [,1]      [,2]
#> 1    125.0841  125.0841
#> 2    141.4248  141.4248
#> 3    144.9417  144.9417
#> 4    147.0938  147.0938
#> 5    147.8182  147.8182
#> 6    149.2779  149.2779
#> 7    157.5686  157.5686
#> 8    159.1250  159.1250
#> 9    159.1250  159.1250
#> 10   159.9089  159.9089
#> 11   160.6967  160.6967
#> 12   162.2840  162.2840
#> 13   163.8870  163.8870
#> 14   163.8870  163.8870
#> 15   165.5059  165.5059
#> 16   167.1409  167.1409
#> 17   168.7920  168.7920
#> 18   171.2995  171.2995
#> 19   178.1702  178.1702
#> 20   179.9306  179.9306
#> 21   180.8174  180.8174
#> 22   182.6040  182.6040
#> 23   183.5040  183.5040
#> 24   184.4084  184.4084
#> 25   185.3173  185.3173
#> 26   186.2306  186.2306
#> 27   189.9295  189.9295
#> 28   189.9295  189.9295
#> 29   191.8064  191.8064
#> 30   194.6568  194.6568
#> 31   196.5806  196.5806
#> 32   199.5020  199.5020
#> 33   201.4738  201.4738
#> 34   201.4738  201.4738
#> 35   204.4682  204.4682
#> 36   204.4682  204.4682
#> 37   206.4892  206.4892
#> 38   206.4892  206.4892
#> 39   210.5915  210.5915
#> 40   211.6298  211.6298
#> 41   211.6298  211.6298
#> 42   212.6732  212.6732
#> 43   213.7218  213.7218
#> 44   214.7755  214.7755
#> 45   217.9681  217.9681
#> 46   220.1229  220.1229
#> 47   220.1229  220.1229
#> 48   220.1229  220.1229
#> 49   222.2990  222.2990
#> 50   224.4967  224.4967
#> 51   226.7161  226.7161
#> 52   226.7161  226.7161
#> 53   226.7161  226.7161
#> 54   233.5073  233.5073
#> 55   234.6588  234.6588
#> 56   235.8161  235.8161
#> 57   235.8161  235.8161
#> 58   236.9790  236.9790
#> 59   240.5024  240.5024
#> 60   246.4918  246.4918
#> 61   247.7075  247.7075
#> 62   248.9292  248.9292
#> 63   253.8766  253.8766
#> 64   256.3872  256.3872
#> 65   261.4832  261.4832
#> 66   270.6466  270.6466
#> 67   273.3234  273.3234
#> 68   276.0266  276.0266
#> 69   294.2626  294.2626
#> 70   294.2626  294.2626
#> 71   298.6395  298.6395
#> 72   298.6395  298.6395
#> 73   298.6395  298.6395
#> 74   300.1129  300.1129
#> 75   304.5770  304.5770
#> 76   307.5899  307.5899
#> 77   313.7056  313.7056
#> 78   313.7056  313.7056
#> 79   318.3722  318.3722
#> 80   332.7933  332.7933
#> 81   336.0858  336.0858
#> 82   341.0858  341.0858
#> 83   344.4605  344.4605
#> 84   346.1604  346.1604
#> 85   353.0442  353.0442
#> 86   356.5374  356.5374
#> 87   360.0652  360.0652
#> 88   370.8596  370.8596
#> 89   370.8596  370.8596
#> 90   376.3777  376.3777
#> 91   403.2361  403.2361
#> 92   409.2367  409.2367
#> 93   413.2866  413.2866
#> 94   419.4369  419.4369
#> 95   447.1647  447.1647
#> 96   447.1647  447.1647
#> 97   476.7277  476.7277
#> 98   488.6122  488.6122
#> 99   560.8607  560.8607
#> 100  606.8504  606.8504
#> 101  703.4973  703.4973
#> 102  717.4976  717.4976
#> 103  735.3906  735.3906
#> 104  787.9023  787.9023
#> 105  803.5835  803.5835
#> 106  815.5489  815.5489
#> 107  835.8889  835.8889
#> 108  959.5400  959.5400
#> 109  983.4733  983.4733
#> 110 1064.1475 1064.1475
#> 111 1388.5712 1388.5712
#> 112 1395.4311 1395.4311
#> 113 1416.2147 1416.2147