Journal of Applied Statistics and Information Technology

A negative binomial Erlang-Lindley distribution with applications

Somporn Thepchim — 2024-06-21

In this paper, a new three-parameter negative binomial distribution obtained by mixing the negative binomial distribution and the two-parameter Erlang-Lindley distribution is introduced for modeling count data. Its probability mass function, factorial moment, mean, variance, and index of dispersion have been obtained and discussed. Estimation of the parameters is illustrated using the maximum likelihood method, and the usefulness of the proposed distribution is explained as examples of real data sets, which show that the proposed distribution provides a better fit than the Poisson, negative binomial, and negative binomial-Lindley distributions.

Productivity Improvement on the PCBA Coating Process

Nichanach Katemukda — 2024-06-24

The printed circuit board assembly (PCBA) industry is important for Thailand because it is a high-value export product. Many manufacturers, such as the world-class company, have plants located in Thailand. The research established that the output of the coating process needed to be increased by maintaining the resources. The manufacturer case study needs the printed circuit board to be coated per customer requirement, which is 20–30 microns. The coating machine process is a bottleneck, and only one machine is in place. The data analysis of the production database identifies that the thickness measurement consumed more time per day (76 minutes of performing the coupon and thickness measurement). Three times per day, the thickness is confirmed by a coupon (stainless plate) measurement at the beginning of the shift (morning, afternoon, and night shift). The research aims to prove the coating machine's performance is still maintained all day and can reduce the number of thickness measurements per day. The statistical approach involved applying analysis of variance and concluding that the thickness requirements are still maintained all day and there is no need to measure the thickness for the afternoon and night shifts. The thickness is not different for all three shifts, with 95% confidence. The coating still meets the customer requirements, and the output increased from 103.20 to 118.40 units per day, and productivity improved from 8.60 to 9.87 units per operator, which is 14.77% increasing.

Quality Control Using Statistical Methods to Reduce Costs in Ceramics Industry Factory

Hussaya wongwan — 2024-06-26

This research the objective is to find methods for quality control in the ceramics industry production process using an action research model. From the study problems were found in the production process. Broken and defective ceramic products occur at a high rate. Increasing production costs. The research therefore aims to study quality control methods in the production process of ceramic products. Based on the principles of quality control using statistical methods. To correct and improve the production process Reduce the amount of waste or defects. Tools used to collect data Including production data record inspection sheet and waste generated in the production process. Analyze data to determine the importance of problems with Pareto charts and use fishbone diagrams to analyze the cause of the problem. Create an improvement plan, experiment with using P-type control charts to control the rate of waste that occurs. The research results found that problems that occur within a factory are caused by factors such as people, machines, raw materials, methods, and the working environment. That causes various errors and is the cause of waste within the production process. Before improving the process, waste data that occurred in the production process was found in the amount of 3,928 pieces, accounting for 10.33 percent, with a process efficiency value of 90. When statistical quality control methods are used to improve processes it was found that waste from production was reduced to 1,910 pieces, accounting for 5.03 percent the process efficiency value was 95. From the results of improvement using statistical quality control principles. It shows that the ability of the process to produce work has increased and the waste rate from the production process has actually decreased.