Questions tagged [change-point]

Methods that attempt to detect when a change occurs in a distribution, process, or function.

311 questions
Filter by
Sorted by
Tagged with
21 views

Issues with Detecting Negative Change in AR(1) Model Using CPAT Library

I'm currently working on evaluating the empirical power of the CUSUM, Rényi CUSUM, and Erdős-Darling tests for detecting change points in AR(1) models, specifically focusing on changes in the mean. ...
28 views

Optimal Timing for Structural Break Analysis in Price Transmission Modeling

I am investigating the price transmission between two inflation indices within the same sector but at different stages of processing. For example, I might be looking at the relationship between raw ...
43 views

How to test if change-point in b-spline is statistically significant?

I'm interested in testing if the difference between 2 slopes one either side of a knot is statistically significant. Ignoring the model assumption violations with this example, how would one see if ...
• 1,641
1 vote
30 views

Literature for a supervised task on time series

I was introduced to the following project at my company. We have $n$ time series coming from $n$ sensors. Each sensor has monitored a physical signal at a specific location. For each time series, a ...
1 vote
15 views

Statistical test to find critical value where IV has effect on DV

Let's say I have an independent variable, that has an influence on a dependent variable, that is only really has an effect if a critical mass/quantity/value of the independent variable is reached. For ...
88 views

Finding the corners of noisy polygons

I have some polygons that look for example like this: If I zoom in very close on one side, you can see the noise. The data is a list of x coordinates and a corresponding list of y coordinates. I ...
• 239
37 views

Testing geometrical trend in a tail

I have a collection of values x1,x2,..., xm, ... xn, with n>>1. It has been observed that at 1<<m<n the points start following a geometric trend, i.e log(xi) -> linear. I need a ...
302 views

Determining a significant breakpoint in a slope

I am trying to find the point where the slope of my data changes significantly. I want to determine a single point (in this case a value for days) in order to use it as an argument in a model I try to ...
• 33
1 vote
18 views

What test for a structural break in a VEC model?

Does anyone know which test to use for structural break in VEC model? I thought to use a CUSUM AND CUSUM-sq, but it seems like CUSUM-sq always return results outside the critical bounds. Any help ...
50 views

Detecting a single change point within an interval with a certain probability

I have a dataset $D$ of binary values, with length $|D|$. There is some unknown $d \in \left[1,2,\ldots,|D|\right]$ (usually, $d$ will be somewhere in the middle) such that, for any $i<d$, $D_i$ ...
• 227
97 views

Is Changepoint Detection valid if the process is not piecewise stationary?

I have seen these two definitions: Let us consider a multivariate non-stationary random process $y=\left\{y_1, \ldots, y_T\right\}$ that takes value in $\mathbb{R}^d(d \geq 1)$ and has $T$ samples. ...
1 vote
98 views

Changepoints vs Structural Breaks

I am looking at this source: It defines changepoint and changepoint detection the following way: 1 Change point detection A particular change point test seeks to identify the specific period of time ...
18 views

External shocks and their effects on stock time series

I have to identify 4 different points in time per stock price. I have several thousand stock prices, which are available as a monthly time series, so I need an automated calculation of the points in ...
• 1
20 views

Structural break test, individual regressors

Say I have an equation $y=\alpha_0+\alpha_1 x_1 + \alpha_2 x_2$ and I'm testing for a structural break (SB) in one of the slope coefficients. How would I discriminate between the breaks. For example ...
• 11
166 views

Estimating Coin Flip Probabilities with Missing Information

I am trying to create an example that shows how the quality of estimation is impacted by incomplete information (e.g. deliberately neglecting the Markov Property) and wrong assumptions about the data ...
31 views

Finding significant changepoints using Segneigh method

I am analyzing changes in the data set in time as mentioned below. To find significant changepoints in time, I am using the 'changepoint package', cptmeanvar function, SegNeigh method, and AIC as the ...
1 vote
66 views

Bayesian change detection (sampling the posterior of a Poisson distribution)

I'm trying to work out how the posterior of a Poisson distribution is derived to enable me to detect changepoints. I'm trying to follow the example here. $Y_i$ (events per year) is modelled using two ...
1 vote
55 views

Trending time-series and structural breaks

I am looking to find structural breaks in a time series, using the strucchange breakpoints function in R. I wonder whether I ...
• 11
33 views

Before-after intervention variation: difference in-difference or broken-stick regression?

I am trying to figure out which analysis would best answer our research question. Our study aimed to find out whether the variation in surgical rate decreases in a group of hospitals after an ...
1 vote
26 views

How to forecast changepoints from Gas Concentration Data?

So I'm trying to predict when gas concentrations change from sensor conductivity readings over a day. The gases randomly change concentrations around every 80-120 seconds and are kept constant between ...
1 vote
25 views

Is new value coming from the distribution of the previous points?

I have a set of 30 data points, measuring percent of acknowledgement of an event that should not happen. So ideal value is 0.0 but we are getting some values greater than that, of order $10^{-5}$. It ...
• 173
42 views

DCC as a model of dynamic conditional autocorrelation?

Is it a good idea to use DCC to estimate dynamic conditional autocorrelation? So far I was using the indirect method for detecting changes in autocorrelation - in R strucchange package by Score-CUSUM ...
45 views

Change Points in Cox Model

I have trained a Cox model on my dataset, which comprises patients entering the study at various time points. I suspect there might be multiple change points indicating shifting effects over time. My ...
• 277
25 views

How to detect moments of state change in boolean time series?

Let $A = (X_1, ... X_n)$ be a series consisting of long periods of ones interrupted with shorter periods of zeros, like $$A = 111111111 00000001111111111100000011111111111111.$$ The plot below (left) ...
• 291
29 views

Are there tests on parameter stability for time series rolling OLS?

I have an OLS model implemented in a rolling window scheme. The estimated params $\beta$ do change for each window, and the entire intention is to capture any structural change, but they should not be ...
• 101
12 views

How to handle recent variable change resulting in level-switch in time series modeling?

I developed a script to run time series models on people data, and I re-run the Arima model fitting/forecast reconciliation algorithm monthly as new data comes in. I use the grouped/hierarchical time ...
25 views

Best Approach to Detecting Breakpoints in Continuous Treatment-Outcome Relationship?

I am currently conducting research to understand the relationship between a continuous treatment variable and a continuous outcome variable. To mitigate confounding and selection bias, I am employing ...
45 views

Assumptions in Changepoint analysis (EnvCpt) of Time Series

I'm looking to identify changepoints in my time series data. To begin, I've seasonally adjusted the data using JDemetra+. Next, I'll carry out a changepoint analysis utilizing the EnvCpt function in R....
• 111
85 views

Efficient method to detect large probability shifts in HMM model output

I am using an HMM model, the specifics of which I cannot disclose. However, my objective is to detect significant transitions in the model's output probability distribution. This probability ...
• 90
32 views

Finding the threshold at which events become significantly more frequent

I have two sequences of data: air temperature T and event A. High temperatures can cause Event A, or it can just happen randomly (or other reasons). In the database, some events A are attributed to ...
• 21
69 views

Structural breaks in Survival Analysis

I am currently conducting research using panel data to analyze survival patterns. This involves examining the time-to-event data of a diverse group of participants over multiple years, where the ...
• 277
76 views

Anomaly Detection in Categorical Data

I want to build a system that will detect Anomaly for categorical data. I have a timeseries data like this For metric data these anomalies are calculated Outliers detection Trend Pattern Change I ...
• 33
113 views

How to determine if change in time series is noise or significant?

I am looking at weekly sales data and see that sales last week dropped by x%. I see that weekly sales do fluctuate quite a bit so not sure if this is indeed a problem. What statistical methods can I ...
• 11
1 vote
239 views

Changepoint detection and forecasting

I am seeking to develop a three-staged algorithm that should be able to detect change in Mean Variance Both Mean and Variance simultaneously if they exist. I would be glad if this program can also ...
1 vote
125 views

Period cutoff in Chow test

I am using the Chow test to analyze structural change in time series data potentially caused by a significant event. Since each data point represents a day, the data is broken into two chunks: Chunk 1:...
• 11
1 vote
158 views

How to test if the mean of a time series has significantly shifted at a certain point?

sorry if this has been asked before but I have searched the internet a lot but have not been able to find a satisfactory answer. I have a time series (approximately 25 points) and I have implemented ...
244 views

Detecting Events in a series

I have a series (sensor readings) with different events and I'm trying to segment/detect those events for further analysis using change point detection in python. In general, the series consists of a ...
• 23
655 views

What is a reasonable range of penalty values to try in PELT changepoint analysis?

I have a simulated a time series data set several predictor variables and response class that I created to practice different analytical techniques before I apply methods to my real (very large) ...
• 111
23 views

Structural break near the end of training sample

I have multivariate time series (VAR), and i found a break near the end (84.7%). I wanted to use a dummy variable in this situation, but even if I choose 90% training set, the dummy only trains on 100 ...
• 47
802 views

change point detection of time series

Currently, I am working on a research project that involves forecasting electricity consumption using data mining. In my analysis, I have detected the change point for time series using the ...
• 51
305 views

Is it reasonable to choose a subset of the time series to create a model?

I am new to time series forecasting and would much appreciate your reply. I have an annual housing starts data between1970-2022 shown, below. I want to forecast the next 10 year housing units. If I ...
• 229
80 views

Determine what is the break point for the slope change in R [duplicate]

I am trying to create a plot with 2 linear regression lines for each group (i.e., CAD, and Healthy). One linear regression line ...
• 31
191 views

How to efficiently fit a spline with a linear piece between two constant pieces

I have two dimensional data, to which I'd like to fit a spline function. A spline would be defined as this: y_0 for x<=...
1 vote
136 views

How to deal with VECM with a different structural break for each time series?

I am modelling a VECM with structural breaks. I am following Joyeux (2007) way of doing it with dummy variables, including the different trace and eigenvalue stats for cointegration with structural ...
• 21
157 views

• 223
1 vote
1k views

Poisson Model Interrupted Time Series Analysis

I've run an Interrupted Time Series Analysis on count data, fitting a Poisson Model as below: ...
133 views

From which X value, Y starts to be different?

Here are data about the ventilation response (VE) to exercise (i.e., increase in oxygen consumption or VO2). In normal condition, ventilation increases linearly until a threshold where ...
• 31
1 vote
52 views

Weird results regarding structural break test in R

So I downloaded stock data and differenced it to get log returns. Im trying to split my dataset in a pre-covid and covid period so I try to detect my dataset for structural breaks. I fitted the ...
• 11