You might want to consider exponential smoothing models such as Holt's
(Double Exponential Smoothing).
This method continually updates the trend parameter, and you can
monitor the most recent value (for sign, or magnitude, or both).
In R, some choices to fit the Holt model:
1. stats::HoltWinters(
Colleagues,
Thanks all for the responses.
I am monitoring the daily total number of defects per sample unit.
I need to know whether this daily defect proportion is trending upward (a bad
thing for a manufacturing process).
My first thought was to use either a u or a u' control chart for this.
Às 14:23 de 07/09/2023, Thomas Subia via R-help escreveu:
Colleagues
Consider
smokers <- c( 83, 90, 129, 70 )
patients <- c( 86, 93, 136, 82 )
prop.trend.test(smokers, patients)
Output:
Chi-squared Test for Trend inProportions
data: smokers out of patients ,
using scores: 1
The example is the example in the documentation for the method. There were no
details.
https://www.rdocumentation.org/packages/stats/versions/3.6.2/topics/prop.trend.test
More documentation would be useful. Answering questions like what are these
numbers?
As shown, I see a cluster of three valu
Dear Thomas
Are you looking for more than
smokers / patients
Michael
On 07/09/2023 14:23, Thomas Subia via R-help wrote:
Colleagues
Consider
smokers <- c( 83, 90, 129, 70 )
patients <- c( 86, 93, 136, 82 )
prop.trend.test(smokers, patients)
Output:
Chi-squared Test for Trend
Colleagues
Consider
smokers <- c( 83, 90, 129, 70 )
patients <- c( 86, 93, 136, 82 )
prop.trend.test(smokers, patients)
Output:
Chi-squared Test for Trend inProportions
data: smokers out of patients ,
using scores: 1 2 3 4
X-squared = 8.2249, df = 1, p-value = 0.004132
# trend
I like many packages. They give me working code that it would take a long time
for me to write (and debug). In some cases I am fairly sure that the effort
would be a full time job on top of my regular workload. The packages use less
of my time.
I hate packages because of Richard's point #3. I h
Dear R users,
I have encountered some error in finding factor scores/ person ability in
item response theory.
I tried a few times using ltm and mirt package but it still gave me error.
#TRY #1 - Fit GPCM model using ltm
> irt_model <- gpcm(response_matrix)
> irt_person_abilities <- fscores(ir
The Data Colada blog has some articles about the groundhog package.
See particular https://datacolada.org/95
and especially https://datacolada.org/100
I now have three reasons for preferring to stick with the core library
packages as much as possible.
1) It's just better style to do more with less
I'm a little confused, because the sample code does something that
none of the suggestions does.
x1 <- c(116,0,115,137,127,0,0)
x2 <- c(0,159,0,0,0,159,127)
[You] want : xx <- c(116,115,137,127,159, 127)
Assuming that there should have been two copies of 159 in xx, this is
xx <- c(x1[x1 != 0], x2[
10 matches
Mail list logo
