• Journal of the Korean Data and Information Science Society
• /
• v.25 no.4
• /
• pp.893-901
• /
• 2014

A certain number of products are sold each month and some of them are returned for repair. In this study both return rate and cumulative return rate are shown on the graph to show the general trend of how many products are returned as time goes by. Next this type of summary data can be considered as a conglomeration of both left and right censored data. So reliability analysis is attempted for this type of summary data. Lastly, left censored data can be traced to find the exact time period during which the product has been claimed. In that case the left censored data can be taken as failure data. So similar type of reliability analysis is attempted for the resulting right censored data.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.4
• /
• pp.755-764
• /
• 2011

In many companies field failure data is used to predict the future number of failures, especially when an unexpected failure mode happens to be a problem. It is because they want to predict the number of spare parts needed and the future quality warranty cost associated with the part based on the predictions of the future number of failures. In this paper field summary data is used to predict the future number of failures based on an appropriate distribution. Other types of data are also investigated to identify the appropriate distribution.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.1
• /
• pp.11-19
• /
• 2015

A certain number of products are transported to be sold each month and some of them are returned for repair. In this study we first assume that the transported products are the ones that have been sold, Then nonparametric approach is applied to the warranty returns data to see how the reliability decreases over time. Parametric approach such as Weibull distribution is applied to the same data and the results for both nonparametric and parametric approaches are compared. Next we assume that there is a time lag between shipment and sale. Then both nonparametric and parametric approaches are applied to the time-lag data and the results are compared.