All Questions
15,082 questions
0
votes
0
answers
19
views
Aggregating Clicks per Impression Signal
I'm training a model to predict the probability of a website event occurring, based on signals about user clicks and impressions calculated across sessions.
As users interact with the website, their ...
- 73
1
vote
0
answers
12
views
Doing a VARMA model but ran into some issues with ECCM and non invertible matrices
Im using the MTS package since I'm basing myself on Tsay (2014). I'm trying to fit a model with mexican unemployment rates and CPI. doing the eccm I get:
0
1
2
3
4
5
6
0
0.0000
0.0052
0.0560
0.0616
...
3
votes
2
answers
79
views
Predicting the Next Event's Timestamp Based on Historical Data with Possible Patterns?
I'm working on a personal project where I aim to predict the time of the next event based on a series of historical timestamps. The dataset I have consists of around 400k timestamps of past events.
...
- 131
1
vote
0
answers
15
views
How to choose a control group in Interrupted Time Series?
I have a dataframe similar to the following:
...
- 11
0
votes
0
answers
26
views
Probability of success changing with time with initial probability of success
The setup for this question is I have some data for events in which the outcome is either a success or fail, and this chance of success depends on time. Broadly, each trial has an immediate non-zero ...
2
votes
1
answer
39
views
Best Practices for Imputing Missing Data in Trade Data (Linear Interpolation and Random Volume)
I am working on a dataset containing trade data, and my goal is to impute the missing data for a period of around 24 hours. Here's a sample of the trade data I'm working with:
timestamp
symbol
price
...
- 21
0
votes
0
answers
10
views
Detecting Volatility Clusters in Time Series, Stock Returns (%) in particular
My primary objective is to detect the presence of volatility clusters in financial time series, stock returns (%) in particular. So, it can be translated into the detection of "conditional ...
- 1
3
votes
3
answers
583
views
How to make two perfectly negatively correlated growing Geometric Brownian Motion (GBM) series? (Impossibility)
Intro
I am self studying in Youtube the course MIT 18.S096 Topics in Mathematics w Applications in Finances and in the following lecture min 34:50 by Dr. Jake Xia is studied the efficient frontier of ...
- 128
0
votes
0
answers
25
views
Using GLMs or GLMMs for diversity metrics
I would appreciate some help in a question regarding statistical analysis. I'm looking at species count data where sampling was carried out over multiple years in repeated sites. So each year was ...
- 63
1
vote
1
answer
18
views
Time-dependent covariates and optimism of results
I have a dataset spanning 2019-2023, and a set of categorical covariates that join by year and zip code. For validation, 2023 is left out, and the covariates for that year are an average of previous ...
- 21
0
votes
0
answers
24
views
Measure of correlation between binary sequences that were generated using a gaussian process
To perform an experiment, I need to construct a collection of $n$ binary sequences of length $T.$
Example consisting of $n=3$ and $T=20$:
$
\begin{bmatrix}
0&1&1&0&0&1&0&1&...
0
votes
0
answers
31
views
Hyperparameter Tuning for Multiple Time Series
I am developing a time-series model utilizing NeuralProphet for forecasting the demand of products by day. I have grouped the products into a number of clusters by features such as average demand, ...
1
vote
0
answers
15
views
Finding the most important daily pattern on a time series
I have multiple hourly time series measurements from different measurement points, for multiple weeks. My goal is to eventually cluster the measurement points into clusters, but to reduce ...
- 11
0
votes
0
answers
54
views
Estimate of mean in semiparametric model. Box-Cox fails for negative mean
I have a time series of positive values $X_t \geq 0$ satisfying the following model:
$$\begin{cases}f_*(X_{t}) = f_*(X_{t-1}) + \mu + \varepsilon_{t}, &\forall t \in \{1,2,\dots,T\},\\
X_0 = 1, &...
- 1
0
votes
0
answers
26
views
On a non-standard application of Kalman filter
These questions arose when I was reading Online Appendix D for the paper Missing Events in Event Studies: Identifying the Effects of Partially-Measured News Surprises by R.S. Gurkaynak, B. Kisacikoglu ...
- 125
0
votes
0
answers
20
views
Conducting multivariate time series prediction with a known future variable
I have a dataset with 71 different variables over an extended time series running monthly from 1960 to 2023 and I want to predict the value of all those variables when one of those variables labelled ...
rcsmith
1
vote
0
answers
26
views
Cross-correlation function using Spearman's correlation
Is it "kosher" to use Spearman's correlation in place of Pearson's in the cross-correlation function?
Basically, I have used the cross-correlation function to determine correlation over a ...
- 391
0
votes
0
answers
37
views
Uncertainty about the auto-correlation of a signal
I have the following signal that represent a supply voltage to an electric motor:
I compute the auto-correlation of that signal as:
...
- 113
2
votes
1
answer
40
views
How to include multiple observations in timeseries multiple linear regression?
I want to know how much variance in signal y can be explained by signals of class x. I have multiple observations of signals of class x. Take the simple multiple linear regression model:
$y = B_0 + ...
- 123
1
vote
0
answers
10
views
Is there a link between a multivariate VAR specification and the bivariate ones arising when combining the variables in groups of two?
Consider $x_t=(x_t^1,x_t^2,x_t^3)$ and a simple Vector Autoregression (VAR) of order one for its dynamics, given by
$$
x_t=\Phi x_{t-1}+\epsilon_t,
$$
where $\phi\in\mathbb{R}^{3x3}$ satisfies the ...
- 349
0
votes
0
answers
31
views
Time Series analysis ACF and stationarity help
basically this is the first time I applied TS analysis to a real dataset. ACF and PACF plots are not as nice as in hypothetical settings. I need help interpreting the results.
I am analysing sales ...
0
votes
0
answers
15
views
Assessing for statistical significance of change in trend rate of events with survival analysis in R
I have data examining the date of an event following a particular procedure among different sampled individuals. I expect that within X days of the procedure, the rates of my event will increase and ...
- 1
0
votes
0
answers
8
views
Posterior probability of cointegration rank
I've been trying to learn Bayesian estimation of VECM. Right now I have troubles figuring how to estimate posterior probabilities of cointegration rank values.
I looked into the bvartools library in R ...
- 1
1
vote
1
answer
32
views
AIC and differencing for time series
I'm teaching an applied time series course and have come up with a question I'm not sure how to answer. Suppose we have a non-stationary time series and we try models using regular differencing, ...
- 277
1
vote
1
answer
26
views
Is there away to compute Index values (base 100) from Year-over-Year % change (YoY) of the variable?
Let's assume I have a time series like this :
Time period
YoY Change (%)
Y2024 _ Q1
7.00
Y2024 _ Q2
4.85
Y2024 _ Q3
5.77
Y2024 _ Q4
5.66
Y2025 _ Q1
6.54
Y2025 _ Q2
6.48
Y2025 _ Q3
6.36
Y2025 ...
- 109
0
votes
0
answers
30
views
a discrepancy between the arima model and plot
I ran the arima model and estimated the fitted values. My constant value in the arima model is 153. Since the time variable (t_centered) was centered at zero, the constant indicates a predicted ...
0
votes
0
answers
9
views
Causal claims with no control group or how can I extract all info available from longitudinal design to have causal claims?
Background: I want to check the effect of an educational intervention. However, I have no control group.
Question 1: how can I have evidence of my intervention effect in this scenario?
Questions 2: ...
- 194
0
votes
1
answer
54
views
Confused about the stationarity assumption in time series analysis
I understand that in time series analysis one important step is to make the time series stationary which will remove trends and is an assumption for models such as ARMA.
One way to make a time series ...
- 1,629
1
vote
1
answer
25
views
ARIMAX time series with different lengths
I'm building an ARIMAX model with two time series: one has been differenced to make it stationary, while the other is already stationary and has more observations. How can I align these two series ...
1
vote
1
answer
13
views
Time series classification, using lagged data, and exogenous time series variables for exploratory features
I have the following pandas dataframe
...
- 531
2
votes
0
answers
15
views
How to determine sample sizes for experiments with ambiguous randomisation units?
I am running an A/B test to compare two bidding strategies in an online auction system, where the goal is to improve Return on Investment (ROI). The two strategies differ in how they bid for ...
- 161
1
vote
1
answer
56
views
Multi-level modelling?
In an instructional study, I have pretest and post-test measures of writing quality--no control condition. There are 110 students nested in 10 classes. I have pretest measures of spelling skill and ...
- 13
1
vote
1
answer
28
views
Identifying equilibrium point of a time series
I am working on a piece of analysis around new product releases, and specifically whether the lifecycle of new product releases has changed over time.
One question I am interested in is statistical ...
- 391
1
vote
1
answer
78
views
Expectation of the minimum of random variables (Exponential + Erlang)
Consider the following random variable
$$
Z=\min_i\{X_i+Y_i\}
$$
for $-n\leq i\leq n$, where $X_i\overset{\mathrm{iid}}{\sim}\text{Exp}(\lambda)$, $Y_i\overset{\mathrm{iid}}{\sim}\text{Erlang}(|i|,\...
- 150
0
votes
0
answers
32
views
Asymptotic properties of estimators for general time series model
my question concerns the asymptotic properties of estimators in time series analysis. In particular I am interested in the behavior of the estimators for time series NOT being an ARMA time series. So ...
- 315
3
votes
1
answer
85
views
Maximum of two independent gamma variables
Let $X_1$, $X_2$ be two independent random variables with different gamma distributions, and $X = \max\{X_1, X_2\}$.
Are there known results for the distribution of $X$? Actually I only need to know $\...
- 1,191
0
votes
0
answers
35
views
Is Using Floored Dates as a Feature in Predictive Models a Good Idea?
I’m working on a predictive modeling project and considering using a Floored Date Feature to capture broader temporal patterns in my data. The idea is to round the observation date to a specified ...
- 826
0
votes
0
answers
25
views
Linearity of and pointwise equality in expectation of min() function
Consider the expressions $f = c + s*E[min(a/s, X)]$ and $g = E[min(c + a, c+sX)]$ where
c >= 0
0 < s <= 1
a >= 0
X ~ Poisson($\lambda$/s)
I'd like to think that $f = g$, reasoning as ...
2
votes
1
answer
78
views
What does it mean when newey-west standard errors are much larger than other types of standard errors
I am doing a regression using time series data and when I use newey-west standard errors they are 3-4 times as large as other types of standard errors (heteroskedasticity-robust and different ...
- 35
1
vote
1
answer
22
views
Decomposing forecast errors into shape and scale components
I'm working on a time series forecasting problem where I predict hourly demand values for each day (24 hours in total). I measure the error of my predictions at the day-level using the Mean Absolute ...
- 111
1
vote
0
answers
12
views
Test for changing strength of association between two variables across time
I want to test for the weakening association between two variables with longitudinal data.
I have a survey that measures trust in government institutions each year between 2005 and 2020. I also have ...
- 183
0
votes
0
answers
10
views
How to compare Private Equity fund IRRs across time while accounting for varying return patterns?
I have multiple time series of Private Equity (PE) Internal Rate of Returns (IRR), where each fund typically exhibits higher variability in returns at the start, with the bulk of returns realized ...
- 363
1
vote
1
answer
40
views
Good literature for bayesian structural time series
I am currently writing on something about time series analysis, including a chapter about bayesian structural time series. I come from a math background, and understand fundamentals of time series ...
0
votes
1
answer
38
views
How to Model Installment Payments with Different Durations Using Survival Analysis?
I'm working on a problem where I need to model the likelihood of future payments for various installment plans using survival analysis. The data I have consists of installment payment plans (or ...
- 195
0
votes
0
answers
23
views
Testing the predictive power of a time series signal
Given a signal from an unknown source/origins and some financial close price data, what are some straightforward ways to test for the signal's predictive power? Would I need to make both series ...
- 1
0
votes
0
answers
16
views
Holt Winters with binary values
I have a question regarding Holt Winters method.
I have an order history which contains at least the customers and the belonging time when the order was taken. We will skip the rest for now since it ...
- 1
0
votes
0
answers
25
views
Test in R for stationarity (not for unit root) of a time series
I'm teaching a time series analysis course. We discuss stationarity as a concept, and then our textbook explains the Augmented Dickey Fuller test, which in R is carried out by the command ...
- 277
3
votes
1
answer
70
views
Sample mean or James-Stein estimator?
I have a simple practical question, which I posted in Quant Finance SE (posting here as well, as I am not getting an answer(s) for it).
Suppose we have $n\geq3$ financial time series (correlated or ...
- 557
2
votes
1
answer
66
views
Is anomaly forecasting in time series analysis possible?
I am currently working on a univariate time series data and I wanted to know if anomaly forecasting is possible in time series.
I previously worked on anomaly detection which detects the anomaly when ...
0
votes
0
answers
8
views
Suggestions on ranking covariate time series
I have a multivariate time series problem where I need to predict a main time series given many potential covariates. I need to not only choose the best covariates for prediction but also determine if ...
- 145