In general, a trend is an observable pattern in the data.

learn more… | top users | synonyms

2
votes
1answer
51 views

When using a limited data set, how can I use excel to forecast future values?

To preface, I am a statistics novice, but I am faced with a problem that I cannot seem to be able to satisfactorily resolve. The problem is as follows: I am working to forecast future sales for one ...
0
votes
0answers
22 views

Regression or time series model to predict trend

DATA I have the following data at hand: data about internet usage, per hour, per user, per part of the day (morning, afternoon, evening); the category of websites visited and their duration; ...
0
votes
2answers
54 views
0
votes
0answers
13 views

Correct for trend and drift in my regression model

I am running unit-root tests (xtunitroot, dfuller: stata)on the variables in my panel data. The default specification of the test includes a constant term. On some ...
0
votes
0answers
12 views

Question about trend stationarity

I am using Matlab in order to test stationarity of macroeconomic time series such as GDP, PCI or population. My first question is the following: I start by testing the stationarity of the data: I ...
0
votes
0answers
21 views

How to extend the separated trend line to predict future time series values in R?

We have data from border router devices that depict the bits per second from the past 4 years. There are some missing values or values too low when backup devices were in use. Every day has a BPS ...
0
votes
0answers
24 views

Booking Pickup reservation problem

I am solving a reservation forecasting problem, where I need to predict what will be the reservations at a given point (say 31 Dec 2016) and also how will it pick up in 60 days prior to the given date....
0
votes
0answers
7 views

assessing slope of proportions across time

I have a list of proportions for 2 groups (values range from 0 to 1) that are associated with Years (2002-2011, coded as 0 to 9 ; 10 observations, with years having equal scoring for a linear trend). ...
0
votes
0answers
3 views

Confront % changes over time in a time series split by categories

I am working with a problem where I have a time series of sales data and I can look at this data across different categories (for example I can look at sales data over time categorized by products). ...
0
votes
0answers
13 views

Selection of additive/multiplicative trend/error/seasonality in ETS

Forecasting: principles and practice. This book tells about 30 different types of ETS models. It describes about additive models and multiplicative model. I would like to know on what basis do we ...
1
vote
0answers
29 views

Time trend in DF unit root test

I have a couple of questions concerning the time trend (βt) in an augmented Dickey-Fuller test for panel data: 1) From what I understand there is no clear rule/standard or test as to when to include ...
0
votes
0answers
45 views

P for trend for quartiles in linear regression in SAS

I am using PROC GLM in SAS to run a linear regression model and have a continuous exposure variable that for a secondary analysis I have categorized into quartiles. I know I can use a contrast ...
0
votes
0answers
9 views

Data analysis method for seasonality due to independent variable and trend

I have historical average temperature data for each day for about 30 years. I also have historical data for each hour population of certain kind of microbe. The microbe growth rate is about same as ...
0
votes
0answers
12 views

Trend break in panel data

I have a panel of countries (N= 30) over four decades (T= 40). I would like to test the impact of a policy by analyzing whether it led to a change in the trend in the outcome variable. Note: The ...
0
votes
0answers
29 views

Removing seasonality when timeseries includes negative or zero values

I am using an x13-arima-seats based solution to remove seasonality and detect data trends. However, many of the series I need to observe trends on contain zero and negative values, which my solution ...
1
vote
2answers
38 views

Testing trend in proportions?

Simple question: I have a sequence of 10 proportions $(p_1,\dots,p_{10})$ (indexed by time), $p_j\in(0,1)$, that seems to have an increasing trend. How can I test this trend?
1
vote
1answer
60 views

Fitting a nonlinear regression $Y=1 - a^{-bx}$

I have the following dataset: where X:Y 1:0.81 2:0.86 4:0.9 6:0.93 8:0.96 10:0.98 12:0.99 14:0.99 16:1 18:1 20:1 ..:1 Since the limit of the regression ...
0
votes
0answers
22 views

How we can find trend of time series and turning points?

I want something like this in a time series: Currently I'm using some linear interpolation to find trend and turning points. What other methods can I use to find these turning points in a time ...
0
votes
0answers
22 views

measure trend in time series / event analysis data

I have a data set of people's buying history for 1 year by day. I am interested in predicting if this person will buy a product in the next coming year. My idea is that if someone has a "upward" ...
0
votes
1answer
21 views

Which MA(q) to use for hourly data in Time Series decomposition?

I am trying to do a Time Series decomposition manually (I don't wanna use one of those R packages that give you all already done). I have already removed the mean from my TS by dividing the TS by its ...
3
votes
2answers
37 views

$c(n)$ is trend, $r(n)$ is fluctuation. Should $\text{cov}[c(n),r(n)]/\text{var}[r(n)]$ be close to zero?

Suppose $y(n)$ is a random time series given as function of the discrete-time variable $n$. Suppose we can decompose it into $y(n) = c(n) + r(n)$, where $r(n)$ is a strict stationary residual ...
0
votes
1answer
35 views

Error while decomposing a time series in R

I'm coding to forecast using ARIMA model. The data is one single column in .csv file and it is an annual data. Therefore, the frequency = 1. When I'm trying to decompose my data it gives me an error:...
1
vote
0answers
42 views

Using repeated measures change/trend as a predictor variable

I have repeated measures of happiness for a sample of participants, and a single measure of satisfaction for each of the ...
0
votes
0answers
7 views

Weekly Time Series Detrend

I have weekly time series data that has a unit root problem. When i include a trend (in DF), the unit root is gone. This is 10 years worth of data, with gaps, and there are nearly 400 weeks. My idea ...
2
votes
0answers
12 views

'Level' still seems periodic after Season Decomposition

I've used tbats for this transformation: Exponential smoothing state space model with Box-Cox transformation, ARMA errors, Trend and Seasonal components My (...
1
vote
1answer
77 views

Is a trend-stationary variable I(1) or I(0)?

I am trying to do cointegration analysis between two variables. I first used the standard Dickey-Fuller and Phillips-Perron tests; they concluded my variables were I(1). I then did cointegration and ...
0
votes
1answer
22 views

Huge discrepancy between analytic Mann-Kendall statistic and its block bootstrap estimate

I am analyzing some environmental time series and I use Mann-Kendall test to check for monotonic trends. However, I am a little bit concerned about autocorrelations in my data, since standard Mann-...
3
votes
1answer
48 views

Does stationarity imply absense of upward or downward trend?

I wonder if a time series being stationary implies that there can be no upward or downward trend. It appears to me that such an implication should hold, since in order to be stationary a time series ...
1
vote
1answer
117 views

Change point detection test using Pettitt-Mann-Whitney test?

I am getting two change point with same p-value (or 90.27% probability) in an interval of two years i.e., 1955 and 1958. Here the trend is increasing from 1901-1955 and 1958-2015. How it could be ...
1
vote
0answers
98 views

Interpretation of Mann-Kendall statistics

I am doing a trend analysis for vegetation dynamics using Mann-Kendall test for trend detection and Sen's slope for computing the magnitude of the trend. There are 6 sites inside a conservation area ...
0
votes
0answers
30 views

Is detrending the same as seasonal adjustment?

I have a time series of Twitter tweet counts against time. Inevitably, Tweet count goes up during the morning and lunch time. I am exploring the topic of seasonal adjustment. This would remove this ...
3
votes
2answers
76 views

predict seasonality and trend combined, better approach?

The nature of my problem combines seasonality (yearly repeated) and trend (over all data). I have one observation per month. To simplify, let's say I have this: Which can be perceived as this: So ...
0
votes
2answers
133 views

Trend and Breakout detection in time series

I am working on several types of system metrics which characterizes several components of an application. The metrics range from system metrics like cpu.utilization to network metrics and database ...
2
votes
0answers
17 views

A number that shows trend, especially regression

I apologize for the vague title, I am not quite able to form my question except by giving an example. I am trying to quantify the regression in some aspects of software development process. Take ...
1
vote
0answers
17 views

Statiscal test for ranking time series based on change points and values

I have five time series, each of which consisting of 30 measurements (pressure) from sensors (on three machines located at five different locations). I would like to rank those time series. I run a ...
0
votes
1answer
78 views

How can I represent exogenous I(0) variable in VECM / Cointegrating relationship?

So I am doing an econometric study on Bitcoin's USD price. As an exogenous regressor, I have the total number of bitcoins in circulation (nbtc). The graph looks like this: This variable is: ...
0
votes
0answers
17 views

MATLAB regression showing 'overparametrized' error

So, I'm looking at the time series of earth surface temperatures from 1880 to 2015, a total of 1632 data points (Monthly Data). I was trying to find the trend using a polynomial fit. This is what I've ...
1
vote
0answers
28 views

How do I detrend this (non-linear) time series before differencing?

I have a variable that looks like this (after taking natural log): I can't run stationarity tests as there are clearly structural changes in the data. How can I get around this – am I supposed to ...
0
votes
0answers
7 views

Analyzing Average Trend with not matching years

I am working on analyzing census data. Most census data are 5-year average (year 1995 means average of 1991-1995, year 2000 means average of 1996-2000, etc). I am trying to match with other datasets ...
1
vote
0answers
18 views

autocorrelation interpretation (annual bird surveys)

I am following a method used by others (McCrimmon et al. 1997 Ecological Applications 7(2):581-592) to look for trends in the annual count of nesting pairs of birds at 29 nest sites over a 42 year ...
0
votes
0answers
22 views

Testing for a Change in Agreement Between Paired Binary Measurements

I would like to know if there is a change in agreement between paired binary measurements from before to after an event occurred. I have two instruments, which are measuring samples from a population ...
0
votes
0answers
44 views

How do I detrend a GDP time series using country specific deterministic trend?

I am trying to replicate Section 3 of this paper (pdf) which investigates international business cycles. Section 3 is the empirical part whereby they analyze international business cycle transmissions ...
1
vote
1answer
30 views

non-parametric trend analysis with data that is both left and right censored

I am assessing the the presence of monotonic temporal trends in E. coli concentration data using a non-parametric approach. These data are both right and left censored (for example the lower detection ...
0
votes
0answers
29 views

How can I analyze trends in longitudinal NON-panel data?

I want to analyze data from the General Social Survey. The data is longitudinal individual level data but it is not panel data (yes, I know there's a recent implementation of a panel component - I'm ...
-1
votes
1answer
40 views

Why does differencing once remove not only linear but also nonlinear trends?

Applying first differences to a time series removes linear trends. See e.g. Can I detrend and difference to make a series stationary? I can understand the motivation. And also, why you would need to ...
0
votes
0answers
25 views

How to interpret lag vs current variable scatter plots

I'm pretty new to stats and time series, and I was following a tutorial for my time series analysis. So, I'm getting stationary time series with my first difference of data, so I'm not taking any log ...
0
votes
1answer
75 views

How to extract the common trend in Panel data?

I have a panel dataset that contains many cities' real estate information ( floor sold) . Now I want to study the relationship between the cyclicality of floor sold and some other dependent variable. ...
1
vote
1answer
41 views

Nonparametric censored trend analysis: When using cenken (package NADA in R), should I use annual medians or all of data

I am using cenken to perform a nonparametric trend test on concentration data with multiple detection limits (the detection limit changed when a change of labs was made). I have seven years of data ...
0
votes
0answers
29 views

What's the best strategy for testing 100+ Poisson distributions on seasonality and trend in Excel?

I have pooled data which can be divided into 4 categories, and those can be divided in 6-50 groups each. I tested the pooled data and the categories with time series plots. Now I'd like to test all of ...
0
votes
0answers
54 views

Seasonality and trend window in the Forecast functions of R

I have time-series power consumption data for one month. The data is sampled at minutes frequency. Thus, for each day I have 1440 observations and for the month (30 days) I have 4320 observations. On ...