Search results

  1. noetsi

    What is this time series coding doing

    (fit<-auto.arima(uschange[,"Consumption],xreg=uschange[,"Income])) It is what is in the brackets that I am asking about I don't know what it is doing. It is figure 9.1 in the link below. https://otexts.com/fpp2/regarima.html
  2. noetsi

    Observational Study

    "In an observational study of more than 96,000 COVID-19 patients at 671 hospitals on six continents, the malaria drug hydroxychloroquine was tied to an increased risk of death, researchers reported on Friday. It was not clear whether taking the drug provided patients with any benefit, according...
  3. noetsi

    Graphs or formal tests

    I was considering this in the context of stationarity (unit roots) but it applies to many things. I used to assume that formal tests were the way to go. Say the ADF for stationarity. But I was reading through an author I have a lot of respect for, and he focused on graphs to make these...
  4. noetsi

    Problem with package

    I tried to install tidyverse. I thought it worked then got this library(tidyverse) Error: package or namespace load failed for ‘tidyverse’ in loadNamespace(i, c(lib.loc, .libPaths()), versionCheck = vI[]): namespace ‘rlang’ 0.4.5 is already loaded, but >= 0.4.6 is required I have the most...
  5. noetsi

    Univariate versus multivariate time series

    If all you care about is forecasting, and for this purpose that is all I care about, which works best univariate and multivariate time series. I predict spending, among other things, if that matters. I had read that univariate models were nearly always more accurate, but that was written...
  6. noetsi

    Time series regression

    What is the best and simplest form of time series regression. I have looked at lots and there are major issues with complexity and how to deal with variables when one is stationary and the other is not. I want to know how two or more predictors are influencing Y over time. I am not concerned...
  7. noetsi

    time series objects

    I am trying to create a time series object. The data is in a folder "S:\\CIU\\A2_Routine Reports Library\\R\\DataforTS.xlsx" I run fts<-ts("S:\\CIU\\A2_Routine Reports Library\\R\\DataforTS.xlsx"[,2],start=c(2014,12),frequency=12) and get Error in "S:\\CIU\\A2_Routine Reports...
  8. noetsi

    Installing Rstudio

    What is the simplest way to install this... There are a lot of sites that have installation and I am not sure if they are all the same. Or if some charge. I would appreciate a link to install a free version for windows 10.
  9. noetsi

    How to improve forecasting

    I forecast monthly spending two years into the future. While our error is generally acceptable (5 percent or so a year out) I want to improve on that. I run exponential smoothing models (six of which I pick the best 3, best being defined by a MAPE from a hold out data set). I am trying to add an...
  10. noetsi

    What is percent difference really doing.

    This is (a1-b1)/ ((a1+B1)/2) and is a way a former poster suggested I use to compare two numbers. I have done so a lot for years, but this week I began to wonder how wise that is. The problem is that really huge differences seem to be understated. For example numbers that are 3 times as large...
  11. noetsi

    What package to install

    I am trying to install the necessary packages to run ARIMA for r. It says what package does this (I think) on page 10/11 of the link (this is page 5/6 in the actual book). I can't figure out what package you are supposed to install...
  12. noetsi

    Best form of time series regression

    If you want to know if an X influences a Y at some point in the future, or several points, which is the best type of time series regression to run. I have looked at many none of which seem to work. I want to focus on the best one. All I really want to know is 1) which predictors have the most...
  13. noetsi

    Best correlation approach for likert scale data

    I have a set of four point likert scale measures (highly satisfied, somewhat satisfied, not satisfied, highly dissatisfied). I have to run correlations between these. Last time I looked at polychoric correlations and spearman rho, I was wonder which of these is better for this type of data or if...
  14. noetsi

    ARIMA models

    I have two models. One applies a seasonal difference, one applies a seasonal and non seasonal difference. The latter is stationary according to the ADF test, the former is not. But the former passes the Box Ljung test, meaning there is no serial correlation, and later one (the one that is...
  15. noetsi

    PROC ARIMA

    My data is clearly non-stationary (by both graphical and formal tests). So I ran code to difference it. When you do that you should retest the differenced data to see if the results need to be differenced again. I am not sure, I can't find in the documentation, how you do that. I assume you test...
  16. noetsi

    Generating Empirical Bayses estimates in PROC MIXED

    I have found various suggestions this be done, it shrinks estimates to the grand mean based on reliability. But I can not find anywhere in the SAS documentation how to request these.
  17. noetsi

    Structural equation models.

    I know SAS does this, Proc Calis. But I have heard doubts raised about how good that product is. Anyone know how good SAS is for structural equation models (L Learned it with Mplus, but there is no way we can use that here, they do not sell to the state).
  18. noetsi

    Controlling for something that does not vary :)

    We are supposed to negotiate with a federal agency. Part of the process is finding variables that explains the results that are not known (or used anyhow) by the agency in question. The problem is that they control for a variety of variables some of which are economic (these are tied to the...
  19. noetsi

    Fixed effects regression

    I work with a federal agency that has not provided many details of their analysis (we ask, they don't provide it). When we asked what method they were using for a statistical control they responded 'Fixed effect model?" I understand the difference between random and fixed effects regression, but...
  20. noetsi

    sas macro

    There is a sas macro for bootstrapping when running multilevel analysis with a categorical dependent variable. It is used when the number of second level units is so small that you need to run non-parametric bootstrapping. I have the macro that does this with interval data, but not categorical...