A Neural Network Approach for Amplifying Random Samples to Stratified Psychometrical Population

The research proposes a neural network approach, learning vector quantization (LVQ), in amplifying random samples to infer their original psychometrical population. To demonstrate the efficiencies of the neural network approach (LVQ), results of two traditional methods, i.e., list-wise deletion (LWD), and non-amplified (NA) are compared with LVQ outcomes. The accomplishments of proposed LVQ method can be significant for sociological and psychological surveys in properly inferring the targeted populations. In the numerical simulation study, successes of LVQ in amplifying samples to infer the original population are further examined by experimental factors of sampling sizes, missing rates, and disproportion rates. The experimental design is to reflect practical research and under these conditions it shows the neural network approach is more accurate and reliable than its competitors.