Parameter estimation

I am doing project in which I need to estimate weibull parameters for car part failures ( I know data follows weibull ). I have 1000 cars data (part failure data). Now the problem is suppose some part fails after 6 year( from date of manufacturing) . But i have data of only first three year. Now in this three years data this particular part may have failed in very few cars. Since I am taking miles driven as cycle to estimate parameters. So all the samples( very few) I am gonna have will be less than some threshold.So when i estimate parameters based on these sample. It gives me wrong results. Can anyone help me how to do this.


TS Contributor
Two different cases to clarify first:

If you actually have some data which does not know the exact value, but do know that it is greater than 3, then it is called censored data.

If those data greater than 3 are actually missed, i.e. you do not know the "sample size" and you are unaware of those data, then you are facing a truncated data.

In either cases you may use MLE or any other reasonable / specially devised method for weibull to estimate the parameters.