Missing Values and Optimal Selection of an Imputation Method and Classification Algorithm to Improve the Accuracy of Ubiquitous Computing Applications

Table 7

Factors influencing accuracy (RMSE) for each algorithm (standard beta coefficient): group mean imputation.

Data characteristic	trees.J48	BayesNet	SMO	Regression	Logistic	IBk
N_attributes	−.068^**	−.072^**	−.179^**	−.068^**	.115^**	.010
N_cases	−.082^**	−.050^**	.011	−.018	−.034^*	−.047^**
C_imbalance	.115^**	.228^**	.260^**	.517^**	.156^**	.197^**
R_missing	.050^**	.085^**	.043	.084^**	.095^**	.066^**
SE_HS	.230^**	.268^**	.178^**	.273^**	.300^**	.248^**
SE_VS	−.008	−.012	−.006	−.013	−.013	−.010
Spread	−.296^**	−.439^**	−.264^**	−.443^**	−.476^**	−.382^**
P_missing_dum1	−.043	−.032	−.034	−.035	−.035	−.041
P_missing_dum2	.002	.024	.004	.016	.021	.013

Note  1: N_attributes: number of attributes, N_cases: number of cases, C_imbalance: degree of class imbalance, R_missing: missing data ratio, SE_HS: horizontal scatteredness, SE_VS: vertical scatteredness, spread: missing data spread, and missing patterns: univariate (P_missing_dum1 = 1, P_missing_dum2 = 0), monotone (P_missing_dum1 = 0, P_missing_dum2 = 1), and arbitrary (P_missing_dum1 = 1, P_missing_dum2 = 1)
Note  2: RMSE indicates error; therefore, lower values are better.
Note  3: ^* < 0.05, ^** < 0.01.