The Control Chart Patterns Recognition (CCPR) is one of important tools in Statistical Process Control (SPC). The performance of CCPR depend on many factors, one of those the prediction algorithm. Furthermore, when data is substantially missing, the rate of false alarms and misclassification is high. This paper reported an investigation of five classifiers namely, Decision Tree, ANN, Linear Support Vector Machine, Gaussian Support Vector Machine, and KNN-5 with ensemble classifier.  The results is compare with perfect sample pattern (without missing data) and sample patterns with missing data 5%, 10%, 15%, 20%, 30%, 40% and 50%. Two datasets having normal ± 3 Sigma shifting range, and small shifting range less than ± 1.5 Sigma was investigated. The results show that the ensemble classifier have higher recognition accuracy for sample patterns without missing data 99.55% and 98.64% for sample patterns with 20% missing data.