如何在预测中指定最小或最大可能值? [英] How to specify minimum or maximum possible values in a forecast?
问题描述
在使用ETS/ARIMA模型进行的预测中,是否可以指定最小或最大可能值?
例如,以%预测趋势只能在0%到100%之间.
我正在使用R包forecast
(和功能forecast
).
如果时间序列y
具有自然界线[a, b]
,则应首先进行类似logit"转换:
f <- function (x, a, b) log((x - a) / (b - x))
yy <- f(y, a, b)
然后,所得的yy
在(-Inf, Inf)
上不受限制,适用于高斯误差假设.使用yy
进行时间序列建模,然后在预测/预测上进行反变换:
finv <- function (x, a, b) (b * exp(x) + a) / (exp(x) + 1)
y <- finv(yy, a, b)
请注意,上述变换f
(因此为finv
)是单调的,因此,如果yy
的95%置信区间为[l, u]
,则y
的对应置信区间为[finv(l), finv(u)]
.
如果您的y
仅限于一侧,请考虑类似日志"的转换.
- 在
[a, Inf)
上绑定,请考虑yy <- log(y - a)
; - 在
(-Inf, a]
上绑定,请考虑yy <- log(a - y)
.
哇,我不知道Rob Hyndman拥有博客.感谢 @ulfelder 提供它.我在此处添加了它,以使答案更加扎实:在限制范围内进行预测.>
这个更具体,我没有讨论. 数据需要对数转换但在某处可能需要0时该怎么办.我只是添加一个小的容限,例如说yy <- log(y + 1e-7)
继续.
Is there a way to specify minimum or maximum possible values in a forecast done with ETS/ARIMA models?
Such as when forecasting a trend in % that can only go between 0% and 100%.
I am using R package forecast
(and function forecast
).
If your time series y
has a natural bound [a, b]
, you should take a "logit-alike" transform first:
f <- function (x, a, b) log((x - a) / (b - x))
yy <- f(y, a, b)
Then the resulting yy
is unbounded on (-Inf, Inf)
, suitable for Gaussian error assumption. Use yy
for time series modelling, and take back-transform later on the prediction / forecast:
finv <- function (x, a, b) (b * exp(x) + a) / (exp(x) + 1)
y <- finv(yy, a, b)
Note, the above transform f
(hence finv
) is monotone, so if the 95%-confidence interval for yy
is [l, u]
, the corresponding confidence interval for y
is [finv(l), finv(u)]
.
If your y
is only bounded on one side, consider "log-alike" transform.
- bounded on
[a, Inf)
, consideryy <- log(y - a)
; - bounded on
(-Inf, a]
, consideryy <- log(a - y)
.
Wow, I didn't know Rob Hyndman has a blog. Thanks to @ulfelder for providing it. I added it here to make my answer more solid: Forecasting within limits.
This one is more specific, which I have not covered. What to do when data need a log transform but it can take 0 somewhere. I would just add a small tolerance, say yy <- log(y + 1e-7)
to proceed.
这篇关于如何在预测中指定最小或最大可能值?的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!