Run a Wald tests on discrete and continuous components
hypothesis can be one of a character giving complete factors or terms to be dropped from the model, CoefficientHypothesis giving names of coefficients to be dropped, Hypothesis giving contrasts using the symbolically, or a contrast matrix, with one row for each coefficient in the full model, and one column for each contrast being tested.
waldTest(object, hypothesis)LMlike or subclass
the hypothesis to be tested. See details.
array giving test statistics
fit
lrTest
lht
#see ZlmFit-class for examples
example('ZlmFit-class')
#>
#> ZlmFt-> data(vbetaFA)
#>
#> ZlmFt-> zlmVbeta <- zlm(~ Stim.Condition+Population, subset(vbetaFA, ncells==1)[1:10,])
#>
#> Done!
#>
#> ZlmFt-> #Coefficients and standard errors
#> ZlmFt-> coef(zlmVbeta, 'D')
#> (Intercept) Stim.ConditionUnstim PopulationCD154+VbetaUnresponsive
#> B3GAT1 -4.1795641 0.63282096 -1.162182250
#> BAX -0.9330077 0.02794714 -0.162052054
#> BCL2 -3.9226304 -2.20112377 1.332228054
#> CCL2 -3.8309742 0.54760417 0.147212758
#> CCL3 -2.3287704 -1.94930881 -0.567152079
#> CCL4 -2.9386008 -1.06755978 -0.003368973
#> CCL5 -1.2350667 0.09455937 -0.484094746
#> CCR2 -4.1050742 1.37877860 1.504033462
#> CCR4 -0.1126440 -0.21758890 -0.839917265
#> CCR5 -2.7417205 -1.20694083 0.521925468
#> PopulationCD154-VbetaResponsive PopulationCD154-VbetaUnresponsive
#> B3GAT1 -1.14875333 -0.16659777
#> BAX 0.45518519 -0.46291603
#> BCL2 -1.29400053 -0.39116499
#> CCL2 0.84204812 0.14680392
#> CCL3 -0.14648827 -0.60189062
#> CCL4 0.02118041 -1.25132594
#> CCL5 -0.65755684 -0.41313077
#> CCR2 0.40289360 0.39925195
#> CCR4 -0.24604817 -0.68742757
#> CCR5 -0.16103855 0.02099718
#> PopulationVbetaResponsive PopulationVbetaUnresponsive
#> B3GAT1 -1.8211123 -0.53512412
#> BAX 0.5582425 0.53846239
#> BCL2 2.0919143 1.91118512
#> CCL2 -0.7797822 -2.02874891
#> CCL3 -0.7669146 -2.46844725
#> CCL4 -2.1491640 -2.15309456
#> CCL5 -0.8123545 -0.94068157
#> CCR2 -0.4731219 0.18547502
#> CCR4 -0.1364576 -0.01272681
#> CCR5 -0.5077805 -0.12742084
#>
#> ZlmFt-> coef(zlmVbeta, 'C')
#> (Intercept) Stim.ConditionUnstim PopulationCD154+VbetaUnresponsive
#> B3GAT1 18.19441 -1.7969063 NA
#> BAX 17.67008 -0.6534516 -0.2356154
#> BCL2 18.73554 1.3286670 -1.3753715
#> CCL2 23.94679 -7.3355989 -3.6985974
#> CCL3 19.86182 NA 3.2750181
#> CCL4 19.54785 NA 1.2579223
#> CCL5 20.07363 0.4504418 -0.2026483
#> CCR2 15.27429 -1.2269270 4.1759840
#> CCR4 18.03446 -0.3702826 -0.1011834
#> CCR5 16.28993 0.9461661 1.1537964
#> PopulationCD154-VbetaResponsive PopulationCD154-VbetaUnresponsive
#> B3GAT1 NA -0.5500307
#> BAX -0.19649762 -0.2783088
#> BCL2 NA -3.1850947
#> CCL2 -7.04188444 -3.9220153
#> CCL3 -0.04812137 -0.6043503
#> CCL4 2.77190815 -2.5532715
#> CCL5 -0.84757938 -1.5303864
#> CCR2 3.19304135 4.0151403
#> CCR4 -0.57583680 -0.7602052
#> CCR5 -0.51211945 -0.6646556
#> PopulationVbetaResponsive PopulationVbetaUnresponsive
#> B3GAT1 NA NA
#> BAX -0.04213554 -0.01140701
#> BCL2 -1.58527659 -2.32150932
#> CCL2 NA NA
#> CCL3 0.45944273 NA
#> CCL4 NA NA
#> CCL5 -1.61445447 -1.33608326
#> CCR2 3.31403666 2.07650762
#> CCR4 -0.26166401 -0.75331686
#> CCR5 -1.26236131 -1.52747203
#>
#> ZlmFt-> se.coef(zlmVbeta, 'C')
#>
#> X1 (Intercept) Stim.ConditionUnstim PopulationCD154+VbetaUnresponsive
#> B3GAT1 1.1195139 1.9390550 NA
#> BAX 0.2289293 0.2625570 0.4158706
#> BCL2 1.1852624 1.2983899 1.3686231
#> CCL2 2.5224874 4.3690763 4.3690763
#> CCL3 1.4009323 NA 3.1325799
#> CCL4 1.7441805 NA 3.2630629
#> CCL5 0.4951370 1.0038683 1.0106941
#> CCR2 1.1047933 1.2757054 1.2757054
#> CCR4 0.2983985 0.4372988 0.6361878
#> CCR5 0.6656093 2.1048414 0.9984140
#>
#> X1 PopulationCD154-VbetaResponsive PopulationCD154-VbetaUnresponsive
#> B3GAT1 NA 1.9390550
#> BAX 0.3643741 0.3574157
#> BCL2 NA 1.6762142
#> CCL2 3.5673358 3.5673358
#> CCL3 2.6825812 2.4264860
#> CCL4 3.2630629 4.2723522
#> CCL5 1.0847908 0.7768348
#> CCR2 1.5624136 1.3530899
#> CCR4 0.5532457 0.4774376
#> CCR5 1.2452410 0.9413137
#>
#> X1 PopulationVbetaResponsive PopulationVbetaUnresponsive
#> B3GAT1 NA NA
#> BAX 0.3211103 0.3241627
#> BCL2 1.2670988 1.2983899
#> CCL2 NA NA
#> CCL3 3.1325799 NA
#> CCL4 NA NA
#> CCL5 1.0362222 0.9807059
#> CCR2 1.8596442 1.5624136
#> CCR4 0.4777267 0.4725825
#> CCR5 1.6304032 1.0869354
#>
#> ZlmFt-> #Test for a Population effect by dropping the whole term (a 5 degree of freedom test)
#> ZlmFt-> lrTest(zlmVbeta, 'Population')
#> Refitting on reduced model...
#>
#> Done!
#> , , metric = lambda
#>
#> test.type
#> primerid cont disc hurdle
#> B3GAT1 0.000000 3.293892 3.293892
#> BAX 1.072472 10.728081 11.800553
#> BCL2 5.443797 20.567934 26.011731
#> CCL2 4.103765 4.775242 8.879007
#> CCL3 1.523584 7.006491 8.530076
#> CCL4 1.516648 8.444875 9.961523
#> CCL5 5.572644 5.389674 10.962318
#> CCR2 12.540757 4.640800 17.181557
#> CCR4 4.607460 8.728194 13.335653
#> CCR5 7.136405 1.526627 8.663031
#>
#> , , metric = df
#>
#> test.type
#> primerid cont disc hurdle
#> B3GAT1 0 5 5
#> BAX 5 5 10
#> BCL2 4 5 9
#> CCL2 3 5 8
#> CCL3 4 5 9
#> CCL4 3 5 8
#> CCL5 5 5 10
#> CCR2 5 5 10
#> CCR4 5 5 10
#> CCR5 5 5 10
#>
#> , , metric = Pr(>Chisq)
#>
#> test.type
#> primerid cont disc hurdle
#> B3GAT1 1.00000000 0.6547769674 0.65477697
#> BAX 0.95651117 0.0570459966 0.29862654
#> BCL2 0.24471407 0.0009773063 0.00203398
#> CCL2 0.25047521 0.4439211826 0.35260548
#> CCL3 0.82245576 0.2201579879 0.48173135
#> CCL4 0.67843337 0.1333623010 0.26773693
#> CCL5 0.35004597 0.3701952302 0.36046135
#> CCR2 0.02808429 0.4612686366 0.07044188
#> CCR4 0.46563569 0.1204092082 0.20550576
#> CCR5 0.21069179 0.9099767975 0.56435354
#>
#> attr(,"test")
#> [1] "Population"
#>
#> ZlmFt-> #Test only if the VbetaResponsive cells differ from the baseline group
#> ZlmFt-> lrTest(zlmVbeta, CoefficientHypothesis('PopulationVbetaResponsive'))
#> Refitting on reduced model...
#>
#> Done!
#> , , metric = lambda
#>
#> test.type
#> primerid cont disc hurdle
#> B3GAT1 0.00000000 2.2974635 2.2974635
#> BAX 0.01776885 2.5081546 2.5259234
#> BCL2 1.80508046 9.4881861 11.2932665
#> CCL2 0.00000000 0.6678630 0.6678630
#> CCL3 0.02425584 1.1530015 1.1772574
#> CCL4 0.00000000 3.8914009 3.8914009
#> CCL5 2.54893181 3.3702326 5.9191644
#> CCR2 3.99053248 0.1406114 4.1311439
#> CCR4 0.30752656 0.1884803 0.4960069
#> CCR5 0.73461509 0.3702349 1.1048500
#>
#> , , metric = df
#>
#> test.type
#> primerid cont disc hurdle
#> B3GAT1 0 1 1
#> BAX 1 1 2
#> BCL2 1 1 2
#> CCL2 0 1 1
#> CCL3 1 1 2
#> CCL4 0 1 1
#> CCL5 1 1 2
#> CCR2 1 1 2
#> CCR4 1 1 2
#> CCR5 1 1 2
#>
#> , , metric = Pr(>Chisq)
#>
#> test.type
#> primerid cont disc hurdle
#> B3GAT1 1.0000000 0.129585466 0.129585466
#> BAX 0.8939563 0.113258489 0.282815165
#> BCL2 0.1790995 0.002067992 0.003529379
#> CCL2 1.0000000 0.413797670 0.413797670
#> CCL3 0.8762357 0.282921705 0.555087964
#> CCL4 1.0000000 0.048533925 0.048533925
#> CCL5 0.1103689 0.066384383 0.051840572
#> CCR2 0.0457566 0.707673921 0.126745777
#> CCR4 0.5792020 0.664184477 0.780357269
#> CCR5 0.3913913 0.542876237 0.575552395
#>
#> attr(,"test")
#> [1] "PopulationVbetaResponsive"
#>
#> ZlmFt-> # Test if there is a difference between CD154+/Unresponsive and CD154-/Unresponsive.
#> ZlmFt-> # Note that because we parse the expression
#> ZlmFt-> # the columns must be enclosed in backquotes
#> ZlmFt-> # to protect the \quote{+} and \quote{-} characters.
#> ZlmFt-> lrTest(zlmVbeta, Hypothesis('`PopulationCD154+VbetaUnresponsive` -
#> ZlmFt-+ `PopulationCD154-VbetaUnresponsive`'))
#> Warning: Some levels contain symbols. Be careful to escape these names with backticks ('`') when specifying contrasts.
#> Refitting on reduced model...
#>
#> Done!
#> , , metric = lambda
#>
#> test.type
#> primerid cont disc hurdle
#> B3GAT1 0.000000000 0.19720610 0.1972061
#> BAX 0.009603320 0.43127916 0.4408825
#> BCL2 2.004979393 2.88482572 4.8898051
#> CCL2 0.003581828 -0.10852740 -0.1049456
#> CCL3 1.389919527 -0.59684167 0.7930779
#> CCL4 0.695474388 1.22446841 1.9199428
#> CCL5 1.643474587 0.01090422 1.6543788
#> CCR2 0.037354159 1.44946742 1.4868216
#> CCR4 0.977322744 0.13931993 1.1166427
#> CCR5 3.776168456 0.50849269 4.2846611
#>
#> , , metric = df
#>
#> test.type
#> primerid cont disc hurdle
#> B3GAT1 0 1 1
#> BAX 1 1 2
#> BCL2 1 1 2
#> CCL2 1 1 2
#> CCL3 1 1 2
#> CCL4 1 1 2
#> CCL5 1 1 2
#> CCR2 1 1 2
#> CCR4 1 1 2
#> CCR5 1 1 2
#>
#> , , metric = Pr(>Chisq)
#>
#> test.type
#> primerid cont disc hurdle
#> B3GAT1 1.00000000 0.65698552 0.65698552
#> BAX 0.92193505 0.51136195 0.80216477
#> BCL2 0.15678342 0.08941768 0.08673459
#> CCL2 0.95227640 1.00000000 1.00000000
#> CCL3 0.23841869 1.00000000 0.67264409
#> CCL4 0.40430856 0.26848550 0.38290384
#> CCL5 0.19984941 0.91683346 0.43727657
#> CCR2 0.84674577 0.22861343 0.47548935
#> CCR4 0.32286067 0.70895803 0.57216874
#> CCR5 0.05198758 0.47579209 0.11738096
#>
#> attr(,"test")
#> [1] "Contrast Matrix"
#>
#> ZlmFt-> waldTest(zlmVbeta, Hypothesis('`PopulationCD154+VbetaUnresponsive` -
#> ZlmFt-+ `PopulationCD154-VbetaUnresponsive`'))
#> Warning: Some levels contain symbols. Be careful to escape these names with backticks ('`') when specifying contrasts.
#> , , metric = lambda
#>
#> test.type
#> primerid cont disc hurdle
#> B3GAT1 NA 2.632691e-01 NA
#> BAX 0.009305455 4.373274e-01 0.446632837
#> BCL2 1.748463371 2.500540e+00 4.249003565
#> CCL2 0.002614910 1.215898e-07 0.002615031
#> CCL3 1.278016527 1.692421e-03 1.279708948
#> CCL4 0.636616606 1.271218e+00 1.907834528
#> CCL5 1.553679693 1.810976e-02 1.571789452
#> CCR2 0.025434721 1.431864e+00 1.457299039
#> CCR4 0.955370495 1.297495e-01 1.085120034
#> CCR5 3.317281808 5.264420e-01 3.843723848
#>
#> , , metric = df
#>
#> test.type
#> primerid cont disc hurdle
#> B3GAT1 1 1 2
#> BAX 1 1 2
#> BCL2 1 1 2
#> CCL2 1 1 2
#> CCL3 1 1 2
#> CCL4 1 1 2
#> CCL5 1 1 2
#> CCR2 1 1 2
#> CCR4 1 1 2
#> CCR5 1 1 2
#>
#> , , metric = Pr(>Chisq)
#>
#> test.type
#> primerid cont disc hurdle
#> B3GAT1 NA 0.6078831 NA
#> BAX 0.92315144 0.5084152 0.7998617
#> BCL2 0.18607002 0.1138073 0.1194925
#> CCL2 0.95921700 0.9997218 0.9986933
#> CCL3 0.25826815 0.9671850 0.5273692
#> CCL4 0.42493864 0.2595383 0.3852290
#> CCL5 0.21259304 0.8929499 0.4557118
#> CCR2 0.87328861 0.2314604 0.4825602
#> CCR4 0.32835604 0.7186919 0.5812583
#> CCR5 0.06855509 0.4681066 0.1463342
#>