Cumulative logit and probit models

Described in Chapter 7 "The rxc Table"

Cumulative_models_for_rxc(n, linkfunction = "logit", alpha = 0.05)

Arguments

n: the observed table (an rxc matrix) with at least 3 columns
linkfunction: either "logit" or "probit"
alpha: the nominal level, e.g. 0.05 for 95% CIs

Value

An object of the contingencytables_result class, basically a subclass of base::list(). Use the utils::str() function to see the specific elements returned.

Examples

Cumulative_models_for_rxc(table_7.5)
#> 
#> Testing the fit of a proportional odds model
#>   Pearson goodness of fit:     P =  0.04223, X2 = 11.505 (df=5)
#>   Likelihodd ratio (deviance): P =  0.04594, D  = 11.289 (df=5)
#> 
#> Testing the effect in a proportional odds model
#>   Likelihood ratio             P =  0.02354, T = 12.983 (df=5)
#> 
#> Comparing the rows                  Statistic   P-value
#> --------------------------------------------------------
#> Wald (Z-statistic) row 2 vs row 1    -0.682     0.495121
#> Wald (Z-statistic) row 3 vs row 1    -3.482     0.000499
#> Wald (Z-statistic) row 4 vs row 1    -0.385     0.700454
#> Wald (Z-statistic) row 5 vs row 1    -0.330     0.741356
#> Wald (Z-statistic) row 6 vs row 1    -0.062     0.950912
#> --------------------------------------------------------
#> 
#> Comparing the rows     Estimate (95% Wald CI)     Odds ratio (95% Wald CI)
#> --------------------------------------------------------------------------
#> row 2 vs row 1:      -0.189 (-0.732 to  0.354)     0.828 (0.481 to 1.425)
#> row 3 vs row 1:      -1.742 (-2.722 to -0.761)     0.175 (0.066 to 0.467)
#> row 4 vs row 1:      -0.156 (-0.954 to  0.641)     0.855 (0.385 to 1.898)
#> row 5 vs row 1:      -0.086 (-0.599 to  0.427)     0.917 (0.549 to 1.532)
#> row 6 vs row 1:      -0.023 (-0.744 to  0.698)     0.978 (0.475 to 2.011)
#> --------------------------------------------------------------------------
Cumulative_models_for_rxc(table_7.6)
#> 
#> Testing the fit of a proportional odds model
#>   Pearson goodness of fit:     P =  0.36225, X2 =  2.031 (df=2)
#>   Likelihodd ratio (deviance): P =  0.33912, D  =  2.163 (df=2)
#> 
#> Testing the effect in a proportional odds model
#>   Likelihood ratio             P =  0.00832, T =  9.579 (df=2)
#> 
#> Comparing the rows                  Statistic   P-value
#> --------------------------------------------------------
#> Wald (Z-statistic) row 2 vs row 1    -0.185     0.853517
#> Wald (Z-statistic) row 3 vs row 1    -2.614     0.008960
#> --------------------------------------------------------
#> 
#> Comparing the rows     Estimate (95% Wald CI)     Odds ratio (95% Wald CI)
#> --------------------------------------------------------------------------
#> row 2 vs row 1:      -0.080 (-0.934 to  0.773)     0.923 (0.393 to 2.166)
#> row 3 vs row 1:      -1.170 (-2.047 to -0.293)     0.310 (0.129 to 0.746)
#> --------------------------------------------------------------------------