# Dr G

less info
reputation
59
bio website location age member for 3 years, 4 months seen Sep 21 at 18:17 profile views 38

# 39 Actions

 Jul29 awarded Enlightened Jul29 awarded Nice Answer Jan19 awarded Enlightened Jan19 awarded Nice Answer Oct24 awarded Yearling Jun8 awarded Constituent Jun8 awarded Caucus Feb5 comment Particle filter in R – trivial code example IMHO you are better off coding the filter yourself... Oct7 comment Hidden Markov model (forward algorithm) in R Actually, despite the title, that book has virtually nothing to do with R. Oct5 comment What is the difference between Kalman filter and moving average? Difficult to say, if you can spare the time I'd argue state space models can be a useful technique to learn. Oct5 revised What is the difference between Kalman filter and moving average? deleted 3 characters in body Oct5 comment What is the difference between Kalman filter and moving average? The equivalence holds only for certain models, e.g. random walk + noise ~ EWMA or local linear trend ~ holt-winters EWMA. State space models are a lot more general than custom smoothers. Also initialization has sounder theoretical bases. If you want to stick to random walk + noise, and you are not familiar with the Kalman filter, then you might be better off with EWMAs. Oct4 answered What is the difference between Kalman filter and moving average? Sep21 answered How do you show that two populations are statistically similar? Aug23 comment What is a minimum sample size for a paired t-test and what is a non-parametric equivalent if data is non-normal? In R you can get the same results using the more user friendly power.t.test, that gives you flexibility on what you keep fixed. E.g. the example above becomes for (k in 0:11){cat(sprintf("%f %f\n", k/2, power.t.test(n=4, delta=k/2, sd=1, type="paired")\$power))} Aug23 comment Is the order important when applying unit root tests? The order of the observations should not matter. Can you post a reproducible example? If you are using R consider debugging the kpss function of your choice or try a different one (e.g. kpss.test in tseries or ur.kpss in urca). Aug16 awarded Critic Jul27 awarded Yearling Jul21 comment Can I use Kolmogorov-Smirnov to compare two empirical distributions? In R you can also do a bootstrapped KS test sekhon.berkeley.edu/matching/ks.boot.html which gets rid of the continuity requirement Jul14 answered Is there an R optimization package that can handle integer constraints and non-linear objective functions?