I'm doing ARIMA with several variables on a time series.
Arima value decimalvar1 decimalvar2, ar(1)
Decimalvar1 and decimalvar2 end up being really close to value. Decimalvar1 coefficient is like 30 000 while value let's say 70 000.
I get them in the results as coefficients in the same box as the constant. The lags are in a different box showing decimal values. I'm supposed to get the decimalvars
as decimal values aswell. More like 1.01 rather than 30 000
THe decimalvars are a list of changes from normal I think? It's supposed to show interest based on how many searched for it, and it starts with 0. It shows values like. -0.01 0.03 - 0.12. Almost all of them negative
So my question is, should I format these decimalvars to something else before the regression? for example with start value 1, then 0,99? Or how?
Related Posts with Regression using variable given in decimal change
Looking for a way to save sums and load into a table similar to estimate tableI apologize if this has been asked before, but I looked around and couldn't find an answer. For a r…
Tabulate With Weights In StataI have a variable "education" which is 3-level and ordinal and I have a binary variable "urban" whic…
Creating a graph with counts of IDs using 2 different requirementsHi everyone, Hoping to get some advice on how t ocreate a graph for my longitudinal patient panel t…
Fuzzy match across multiple variables within a datasetI have a dataset of about 15000 observations of different patients, many of which are duplicates. Th…
Hypothesis Test on Goodman-Kruskal Gamma StatisticHi---looking for some help with whether there is an option to run a hypothesis test/compute a p-valu…
Subscribe to:
Post Comments (Atom)
0 Response to Regression using variable given in decimal change
Post a Comment