Extract information stored within a powRICLPM object (internally used by print.powRICLPM and summary.powRICLPM). See "Details" for which pieces of information can be extracted. The information is presented by condition (i.e., sample size, number of time points, and ICC).
Arguments
- from
A
powRICLPMobject- what
A character string, denoting the information to extract, either "conditions", "estimation_problems", "results", or "names".
- parameter
(optional) When
what = "results", a character string denoting the parameter to extract the results for.
Details
The following information can be extracted from the powRICLPM object:
conditions: Adata.framewith the different experimental conditions per row, where each condition is defined by a unique combination of sample size, number of time points and ICC.estimation_problems: The proportion of fatal errors, inadmissible values, or non-converged estimations (columns) per experimental conditions (row).results: The average estimate (average), minimum estimate (minimum), standard deviation of parameter estimates (SD), the average standard error (SEavg), the mean square error (MSE), the average width of the confidence interval (accuracy), the coverage rate (coverage), and the proportion of times the p-value was lower than the significance criterion (power). It requires setting theparameter = "..."argument.names: The parameter names in the condition with the least parameters (i.e., parameter names that apply to each experimental condition).
Examples
# \dontshow{
load(system.file("extdata", "out_preliminary.RData", package = "powRICLPM"))
# }
# Return data frame with number of estimation problems per experimental condition
give(out_preliminary, "estimation_problems")
#> sample_size time_points ICC errors not_converged inadmissible
#> 1 500 3 0.4 0 0 1
#> 2 600 3 0.4 0 0 0
#> 3 700 3 0.4 0 0 0
#> 4 800 3 0.4 0 0 1
#> 5 500 4 0.4 0 0 0
#> 6 600 4 0.4 0 0 0
#> 7 700 4 0.4 0 0 0
#> 8 800 4 0.4 0 0 0
#> 9 500 3 0.6 0 0 0
#> 10 600 3 0.6 0 0 0
#> 11 700 3 0.6 0 0 0
#> 12 800 3 0.6 0 0 0
#> 13 500 4 0.6 0 0 0
#> 14 600 4 0.6 0 0 0
#> 15 700 4 0.6 0 0 0
#> 16 800 4 0.6 0 0 0
# Return data frame with performance measures for "wB2~wA1" per experimental condition
give(out_preliminary, "results", parameter = "wB2~wA1")
#> sample_size time_points ICC population_value average minimum SD SEAvg
#> 1 500 3 0.4 0.2 0.208 0.026 0.076 0.079
#> 2 600 3 0.4 0.2 0.205 0.004 0.071 0.073
#> 3 700 3 0.4 0.2 0.193 -0.005 0.063 0.069
#> 4 800 3 0.4 0.2 0.201 0.060 0.063 0.063
#> 5 500 4 0.4 0.2 0.191 0.078 0.055 0.062
#> 6 600 4 0.4 0.2 0.202 0.079 0.050 0.057
#> 7 700 4 0.4 0.2 0.206 0.072 0.061 0.053
#> 8 800 4 0.4 0.2 0.205 0.042 0.055 0.049
#> 9 500 3 0.6 0.2 0.195 -0.016 0.087 0.097
#> 10 600 3 0.6 0.2 0.188 -0.009 0.095 0.090
#> 11 700 3 0.6 0.2 0.201 0.007 0.088 0.083
#> 12 800 3 0.6 0.2 0.192 0.029 0.074 0.077
#> 13 500 4 0.6 0.2 0.203 0.036 0.068 0.071
#> 14 600 4 0.6 0.2 0.190 0.015 0.072 0.066
#> 15 700 4 0.6 0.2 0.201 0.019 0.065 0.060
#> 16 800 4 0.6 0.2 0.199 0.068 0.048 0.056
#> MSE accuracy coverage power
#> 1 0.006 0.307 0.96 0.74
#> 2 0.005 0.286 0.96 0.82
#> 3 0.004 0.271 0.96 0.85
#> 4 0.004 0.246 0.94 0.82
#> 5 0.003 0.242 0.98 0.87
#> 6 0.002 0.222 1.00 0.95
#> 7 0.004 0.206 0.91 0.96
#> 8 0.003 0.193 0.90 0.99
#> 9 0.008 0.380 0.96 0.53
#> 10 0.009 0.352 0.92 0.52
#> 11 0.008 0.325 0.94 0.68
#> 12 0.005 0.300 0.99 0.64
#> 13 0.005 0.278 0.95 0.77
#> 14 0.005 0.260 0.90 0.81
#> 15 0.004 0.236 0.96 0.92
#> 16 0.002 0.220 0.97 0.96
# Return character vector with parameter names
give(out_preliminary, "names")
#> [1] "RI_A~~RI_A" "RI_B~~RI_B" "RI_A~~RI_B" "wA2~wA1" "wA2~wB1"
#> [6] "wB2~wA1" "wB2~wB1" "wA3~wA2" "wA3~wB2" "wB3~wA2"
#> [11] "wB3~wB2" "wA1~~wA1" "wB1~~wB1" "wA1~~wB1" "wA2~~wA2"
#> [16] "wA3~~wA3" "wB2~~wB2" "wB3~~wB3" "wA2~~wB2" "wA3~~wB3"