Two ways to handle it:
You can make interpolation for missing values. For instance, one value is for 1990 and second for 1995. One way is to take growth of these two values, by adding the growth value with the value of 1990 you will get value for 1991 and similarly add growth value with 1991 and so on......
The problem should be treated in a deeper manner:
(1) How large is the sample size, and what is the share of missing values?
(2) What is the type of your time series? In which field is your approach?
(3) What is the time measure? Intra-day?, dayli, monthly, sub-annual, etc.?
(4) Where are the missing values situated? At the begining, at the end of the time serie?
After you answer on these questions you may search for an appropriate method of inputation, like Chuck and Mirajul already mentioned.
Omitting the entire record containing the missing information may not help, rather it complicate the issues. The main reason is that the time series may not be a series of observations collected at equal intervals of time. Hence, adopting methods of interpolation is suggested.
Use the "Interpolation method" if any values for a variable in your data set are missing. There are numerous different interpolation techniques, including linear, polynomial, spline, piecewise constant, etc. The linear one is typically used. However, if the start and end values between any two dates are available, only then you can use the method.
The Interpolation methods are widely available in Excel and EViews.
Use 'forward fill' method to deal with missing values by using the value directly prior to fill the missing values. You can also use mean imputation method.
- Badges
- Science topic
- Similar topics
- Engineering
- Modeling