time series

  1. T

    Time series Analysis

    I have 4 time series.One of them is stationary and rest of them are not.I need to find relation between them.I will use AIC to decide lag length.Should I use VAR or VECM to find relation between them? Will VAR or VECM give me relation in terms of equation which can be used for forecasting? Do I...
  2. T

    Interpreting ADF Test result

    I have imported csv into R.CSV has 530 rows and one column.I tested it with 3 stationary tests and I got 3 different results. 1) > sapply(mydata,ur.df) $X765 ############################################################### # Augmented Dickey-Fuller Test Unit Root / Cointegration Test #...
  3. T

    Cointegration and granger's causality test in Excel

    I have following data: A -> 100 150 123 145 167 200 250 300 270 B-> 290 300 280 276 234 234 288 345 399 How can I perform stationarity,cointegration,Granger's test in Excel?
  4. R

    Durbin-Watson statistic below 2, fixed effect model

    Hello I am asking for your advice. I am working with unbalanced panel data set. Sample contains data about 11 largest Finnish insurance companies, time period is 13 years. Dependent variable is profitability indicator ratio; independent variables are concentration measured by HHI index and...
  5. N

    Longitude Latitude Time Series Plot

    Hi All! I have been looking to find a package that will allow to plot time series longitude/latitude in a map with density and connecting lines. For example, if t=1 for (lon1,lat1) then circle of diameter 1 is plotted at lon1, lat1. if t=3 for (lon2,lat2) then circle of diameter 3 is plotted at...
  6. C

    ARMA one step ahead forecast and forecast error

    For a ARMA(1,1) process with constant \theta is X_t=\alpha X_{t-1}+\theta +Z_t+\beta Z_{t-1} where Z_T is white noise with mean 0 and variance\sigma ^2. 1)Find the one step ahead forecast 2)Find the expected value and variance of one step ahead forecast error Here's what I did...
  7. K

    Predicting the near-future values using an unevenly sampled time-series data

    Hi there, I need help with predicting the near-future values using an unevenly sampled time-series data. Data is collected as events, and is converted to time series. I have tried out a few approached which have not been successful. Please let me know if there is anything I can do around...
  8. K

    Moving average with replicate X values

    Hello, I would like to calculate the moving average and confidence intervals of time series data. Alternatively, use a smoothing function (like loess). For some years I have upwards of 15 data points, for some years I have none. I cannot figure out a way to calculate a moving average when...
  9. K

    Plotting many time series on same graph (50+)

    Hello, Thank you for taking the time to read my question. I have a LOT of time series data that I would like to plot all on the same graph. My data looks like this: Year Region1 Region2 ... 1990 3.24 5.60 1991...
  10. K

    Summarizing time series data

    Hello, Thank you very much for taking the time to read this! I have many (~70) time series showing the average body size (kg) for the ~50 years. Each time series is for the same species but from a different region/area. I would like to look at the change in body size over time and how...
  11. E

    Regression model with no constant term & more

    Hi guys, There are a bunch of things that I'm getting confused about and while I've researched online for resources to get clarification, I'm still not certain about the answers. So hoping to get some assistance from the experts 1.) can we manually select a regression model that has no...
  12. C

    Time-Series with UKgas

    Hello, i have a problem with the seasonal component. y <- UKgas p <- 4 if(!p%%2==1) { x <- filter(y,rep(1/p,p)) } else { x <- filter(y,c(0.5,rep(1,p-1),0.5)/p) #Berechnung der geglätteten Zeitreihe } d_t <- y-x #Trendbereinigte Zeitreihe f <- matrix(d_t, 27, 4, byrow=TRUE)...
  13. N

    Cointegration in Non-linear time series

    I have the following problem: In*non-linear time series regression yt = g(xt)+et, if xt is non-stationary (i.e. I(1)) and yt is stationary (i.e. I(0)), how to test that this relationship is cointegrated and not spurious? Would it be enough to use KPSS test for unit root on residuals et...
  14. M

    Prediction using Support Vector (SV) method

    Dear Friends, I came to know that using SVM method we can predict the future value more accurately than other normal methods (like ARIMA). My question is how do we give the future index value (let's say 101 when we have 100 values in a time series) so that we can get the predicted value for the...
  15. G

    How can I model a "multiplier effect" in time series data?

    I currently have data corresponding to how often a certain set of songs were downloaded. Each song has a release date, and then the number of downloads per day going forward to today. It would look like...
  16. S

    Box Cox Transformation on time series

    Hi, I want to apply box cox transformation on my time series. I was just wondering can I apply the transformation on any time series or do i have to fix up the time series prior to. I have a non stationary time series with deterministic trends.. would i have to make it stationary first or no...
  17. S

    Correlation between two non stationary time series

    Hey everyone, I'm trying to figure out if there is significant correlation between two non stationary time series (e.g. temperature on a a given day and icecream sales). Could someone please propose a method. There are so many different methods i read about online im not sure which to go...
  18. A

    Please help

    Dear forum guys! I've got a issue with a simple regression in excel (or maybe it's a Z-test problem, that is what I was told). There is a time series data and I have to find out is the fluctuation at certain date is statistically significant. I am not advanced in stats so is there anyone...
  19. K

    Autocorrelation of discrete time series

    I am currently planning on calculating the autocorrelation for various lags given a time series. However, my elements of the time series are "discrete" and abstract classes; i.e., no integers. For example, my series could look like: class A, class B, class A, class A ... Of course I...
  20. L

    Time series question

    Hi, If I have a time series that has a normal distribution of error from the mean is there a technique that lets me forecast the next period based a stronger weighting for recent months. I suppose I can work it up but wondered if anything exists. Thanks in advance.