Analisis Eksploratif Faktor-Faktor yang Berkaitan dengan Jumlah Tujuan Disposisi Surat Masuk di PT Perkebunan Nusantara I Regional 1

Abstract

The internship program at PT Perkebunan Nusantara I Regional 1 provided an opportunity to observe the administration of incoming mail, particularly the determination of disposition destinations as part of the company's document management process. Since the number of disposition destinations varies across letters, statistical analysis is needed to identify the factors associated with this variation. This study aimed to analyze the association between letter origin, the number of incoming letters per day, and letter type with the number of disposition destinations. The dataset consisted of 315 incoming letters collected during July 2024. The response variable was positive count data without zero values, while categorical predictors were transformed into dummy variables. Data were analyzed using a Zero-Truncated Poisson regression model, and model selection was based on the Akaike Information Criterion (AIC). The results showed that the number of incoming letters per day was significantly associated with the number of disposition destinations (p = 0.0389), with an Incidence Rate Ratio (IRR) of 0.983 and a 95% confidence interval of 0.967–0.999. This finding indicates that each additional incoming letter per day was associated with an approximately 1.7% decrease in the expected number of disposition destinations. In contrast, letter origin and letter type were not significantly associated with the response variable. The Zero-Truncated Poisson model provided a better fit than the standard Poisson model and was therefore selected as the final model.