I have a statistical maths problem where I have a rather large dataset consisting of a timestamp (rows) and a quantity of - lets say detections - per each day (columns for each location). Currently I have two challenges with the data:
Some of the data is missing, and I need to replace the missing values on some days or periods by a certain estimation based on earlier values. Is there a way to do this in Libreoffice/Matlab/Octave etc. tool, or what could be the best mathematical method to look into?
Second issue is that the data in a visualised form seems to follow a certain pattern, but the amount of detections is increasing gradually by time. Is it possible to average the whole dataset so that instead of increasing by time, the dataset would be more stagnant but still shows the same patterns periodically? This could be referred as to histogram equalization from image processing.
It would be great to have just possible statistical methods and/or tools to push to the right direction, so that I could do more research on the area and on the dataset on my own. :)