Science topics: StatisticsTime Series
Science topic
Time Series - Science topic
Explore the latest questions and answers in Time Series, and find Time Series experts.
Questions related to Time Series
Hi everyone, I would appreciate to guide me on this?
I have the study design as a serial cross-sectional study with ten years of data, the goal is: to Identify changes in the workload of activities performed by providers over the past 10 years.
The workload or amount of work encompasses nature of activities like lab test and etc or number of patients.
I am not sure can I apply time series? because it is "repeated cross sectional, so there may be different sample each year, how to do this analyze? time series is correct?
Thanks
1.1. Background of the Study
Financial development plays a crucial role in driving economic growth by facilitating various functions such as financial intermediation, reducing transaction costs, and enabling diversification. It encompasses the effective mobilization of domestic savings for productive investments, which is particularly significant for developing nations in alleviating poverty and fostering economic progress (Levine, 2005; Ellahi, 2011). The development of the financial system is vital for the accumulation of capital, efficient allocation of resources, and technological advancements, all of which are fundamental ingredients for sustained economic growth (Nkoro & Uko, 2013).
The relationship between financial development and economic growth has been a subject of theoretical and empirical analysis. Two opposing theories, namely the supply-leading theory and the demand-following theory, present divergent perspectives on the causal link between financial development and economic growth. The supply-leading theory posits that financial development precedes economic development, as the financial sector supplies the necessary financing for productive investments. In contrast, the demand-following theory argues that economic expansion drives the development of the financial sector, as financing and credit are derived from the demands of the economy (Malarvizhi et al., 2019).
Moreover, the impact of money supply on economic growth is another crucial aspect of financial development. Expansionary monetary policies leading to an increase in the money supply can result in lower interest rates, increased lending and investment, and ultimately, higher gross output and economic growth (Arfanuzzaman, 2014). In this context, the measurement of financial depth, particularly through broad money (M2), becomes significant as it includes the components of narrow money and reflects changes in the overall money supply.
The financial crisis of 2008/2009 demonstrated the critical role of the financial system in the real economy. The United Kingdom, as one of the most highly developed financial systems globally, experienced severe repercussions from the crisis, highlighting the interconnectedness of financial activities with economic performance. The growth of the UK's banking sector and its contribution to the country's gross value added and employment further underscore the importance of a robust financial system for economic vitality (Tyler, 2015; World Bank, 2012).
Additionally, attracting foreign direct investment (FDI) has been a significant policy goal for many developing countries. FDI brings potential benefits such as productivity gains, technology transfers, managerial skills, and access to markets. Identifying factors that impede or induce foreign capital flows into host countries is crucial for policymakers seeking to leverage FDI for economic growth (Aitken & Harrison, 1999; World Bank, 1997a, b).
Cameroon harbors the Bank of Central African States (BEAC), which is the central bank of all the member states of the Economic Community of Central Africa States (CEMAC) to which, Commercial banks, postal banks (CAMPOST), insurance companies, non-banking financial institutions are under the supervision of this central bank (Puatwoe, J. T., & Piabuo, S. M. 2017). The banking sector plays a major role in the financial sector of Cameroon; it accounted for about 84.4% of the total assets of the financial sector in 2005, and contributed 19.6% to GDP, which is still in infancy operates with very limited amount of financial instruments and constitutes mostly of banks as the main arm, with an underdeveloped financial marke. (Puatwoe, J. T., & Piabuo, S. M. 2017).
In Nigeria, the financial sector has grown steadily in recent times, albeit, the socio-economic peculiarities of the country, occasioned by weak institutional quality, poor governance, corruption and insurgency in some parts of the country, among others (Akintola, A. A., Oji-Okoro, I., & Itodo, I. A. 2020).
Also the link between finance and economic growth discussed by many Scholars in Africa in different times. For example Chandang Kurarathe (2001) conclude financial sector development, total private credit extension to GDP and value added ratio were used as a proxy for it, has positive direct effect on per capita GDP or improved financial intermediation and increased liquidity promotes economic growth in South Africa. In the same manner Torroam J.tabor and Chiang(2013) by using stoke of money supply, domestic credits, foreign real credit, inflation and exchange rate as a proxy to financial deepening and applied co- integration and error correction model for the period 1990- 2011 in Nigeria. They conclude the financial sector development has essential role in Nigerian economy.
Murcy et al. (2015) examine the relationship between financial development and economic growth in Kenya using annual time series data. They employed autoregressive distributed lag (ARDL) so as to accommodate small sample data series and to address the problem of endogeneity and found that financial development has a positive and statistically significant effect on economic growth in Kenya in long-run and short-run hence confirmed supply leading hypothesis.Furthermore, Odhiambo (2008) investigated the causality between finance and economic growth in Kenya during 1969-2005 periods. It employed the dynamic multivariate Granger causality test and error correction model. He found that there was only one way causality from economic to finance. The finding indicated that finance act minor role in contribution to economic growth.
Prior to the 1991 reform period, Ethiopia's financial system was governed by the central government, just like that of many other developing nations. In particular, all private banks were nationalized from 1974 until 1991, the duration of the socialist Derg administration. The two government-owned banks, Development Bank of Ethiopia (DBE) and Commercial Bank of Ethiopia (CBE), were the dominating banks during this time (Alemayehu, 2006).
During the years 1981 to 1990, the Commercial Bank of Ethiopia (CBE) was the leading loan provider, sharing 50% (percent) of the total credit, followed by the Development Bank of Ethiopia (DBE) at 40%. The Ethiopian Construction Bank, on the other hand, only covered 10% of the whole credit financial service. The banking and insurance industries were opened to private sector participation by Proclamation No. 84/1994. The declaration signaled the start of a new era in Ethiopia's financial sector, although restricting it to citizens of Ethiopia alone. Private banking and insurance firms proliferated throughout the nation after this declaration (Alemayehu, 2006). Now financial sector consists of about 31 microfinance institutions, 18 insurance firms, and 30 banks with 5311 branches (NBE, 2022/23).
It is evident that both private and public credit has increased throughout the recent period in the country but literature on the relationship and impact of financial depth and Economic growth in Ethiopia is very scant. Therefore, The purpose of this study is to examine the relationship between financial development and economic growth in Ethiopia. Financial development is a multidimensional concept that encompasses the establishment of efficient financial institutions, the deepening of financial markets, and the expansion of financial services. It is widely recognized as a crucial driver of economic growth in both developed and developing countries.
The study aims to investigate the causal relationship between financial depth, measured by indicators such as the size of the banking sector, stock market capitalization, and credit to the private sector, and economic growth in Ethiopia. By analyzing this relationship, the study seeks to provide insights into the specific mechanisms through which financial development influences economic growth in the Ethiopian context.
To conduct this study, a comprehensive dataset covering the relevant financial and economic variables will be collected for the period from 1991 to 2023. The data will include indicators of financial development, such as the ratio of bank credit to GDP, the number of bank branches, and the stock market turnover. Economic growth will be measured by real GDP growth rates.
The study will employ econometric techniques, such as panel data analysis, to estimate the causal relationship between financial development and economic growth. Controlling for other factors that can influence economic growth, such as human capital, infrastructure, and institutional quality, the study will assess the specific impact of financial depth on economic growth in Ethiopia.
The findings of this study are expected to provide valuable insights for policymakers, financial regulators, and other stakeholders in Ethiopia. Understanding the relationship between financial development and economic growth will help inform policy decisions aimed at promoting sustainable and inclusive economic growth in the country. Additionally, the study will contribute to the existing literature on the subject by providing empirical evidence from the Ethiopian context, which has been relatively underexplored in previous studies.
Hi,
I've got myself totally confused and need some help.
I have two univariate time series that represent the area of land (in m2) changing from natural to non-natural at both yearly and quarterly intervals over a 12 year period [12 observations in one - 48 in another]. My interest is to identify whether a change in the area occurred following a shift in policy.
I therefore, have looked at using an Interrupted Time Series approach to investigate. Initially I just compared segmented linear regressions as a way of getting an indicator of whether change occurred. However, my data is non-stationary and I am aware, therefore unsuitable for regression in its current format.
Whilst I understand that I can de-trend the data to make it stationary, I worry that such would damage the output. My issue is really confusion around stationarity.........I believe that I am trying to measure the trend and assume that by making the data stationary, the trend [thing i am trying to assess] will no longer be accounted for......
Could someone help to explain to me how stationary data would allow the identification of a change in the trends during the periods both prior to and after the implementation of the policy?
I have analyzed a time series with MFDFA algorithm. But the general Hurst exponent is from 0.015 to 0.04, quite near to 0. And the width of the multifractal spectrum I got is about 0.04, very narrow. So I wonder whether this time series is fractal or multifracal? And what does general Hurst expoent equal to 0 mean?
I am a doctorate degree student, working on mt thesis.
how can i calculate time delay and embeded dimention in Mackey-Glass chaotic time series is more important?
and how can we get it in mathlab?
Here is the case, as I said, I am working on how Macroeconomic variables affect REIT Index Return. To understand how macroeconomic variables affect REIT which tests or estimation method should I use.
I know I can use OLS but is there any other method to use? All my time series are stationary at I(0).
Hi!
I want to use the ADL model for my data analysis. However, after performing a stationary test, dependent and 6/8 independent variables are stationary only in differences. The other two are stationary in levels.
Is the cointegration test always necessary?
If so, I found on the Internet that I can only use the Pesaran Bounds test because I have a mix of I(0) and I(1) variables.
Is it true? I am not sure.
And how do you perform that test?
Thanks a lot for your suggestions.
I'm currently in a research project on wavelet transform denoising. Due to lack of statistical knowledge, I'm not able to do research on thresholding method, so I'm curious if there are any other research directions(more prefer an engineering project), thank you for your answer.
For Example the sales of Mobile Phones is increasing in a country. If we want to study that does introduction of a new technology in mobile phones change/shift the growth trend in sales of mobile phones? Which statistical tools are best suited for this type of study.
I want to know the time-series characteristics of demand for manufactured products. Is there a good paper to know the state-of-the-art research on how the demand of manufactured goods fluctuates or grows? If there is no such paper, do you know any papers that treated or questioned related problems?
Dear Academics,
I have two times series with 12 observations for each. Both are yearly quantitive data for last 12 years. I presented as graphs and it seems they have negative correlation.
How can I show the relationship between them statistically (first series effect on second or at least correlation)? Which tests should I perform?
Datas are non-stationary.
Hello guys
I want to employ FMRI for conducting research.
At first step, I want to know FMRI data is an image like MRI.
Or I should behave with FMRI like time-series when it comes to analyzing data
thank you
I've fitted a latent growth mixture model to time series data. It consists of a value (population prevalence) at 11 time points for a sample of 150 areas. Said model was fitted using the lcmm package in R and identified a two class model as optimal - reflecting an hlme model as follows:
gmm2 <- gridsearch(rep = 1500, maxiter = 50, minit = gmm1, hlme(Value ~ jrtime, subject = "ID", random=~jrtime, ng = 2, data = rec, mixture = ~ jrtime, nwg=T))
Said model uses the "Value"/prevalence data for each area as the primary variable. However, the original "Value" column within the data also relates to 95% confidence intervals (reflecting different sample sizes which contributed to the observations at each time point and for each area). Under the current approach all observations of "Value" are treated equally. Should I (and is there a good method through which to) account for the differing levels of uncertainty in "Value" as part of my lcmm?
I wondered if such could be coded into the package, but this does not appear to be the case. Therefore I wondered whether a manual account could be taken (such as adding the CI range as a covariate)? However, I also wondered whether there was scope to add such as part of the prior setting if applying an alternative Bayesian approach.
Any advice/links to relevant literature (or shareable code) would be hugely appreciated.
Hello everyone!
I'm currently working on a time series of vegetation indices, and a key question I have is which method of atmospheric correction to use. Is it absolutely crucial for achieving accurate results, or is it something I can potentially skip? I would appreciate some insights on this matter.
Thank you!
we only assume that the time series may have one breakpoint in pettitt test, How does the pettitt test work if we have two or more time series breakpoints??
Hey,
I'm pretty new to 3D kinematic analysis in sports, and I'm trying to follow this "protocol", i.e. the exact structure of results as in this article: https://peerj.com/articles/10841/
However, I think I understand how they are calculating the angles at key events and ROM, but I'm not sure how they are calculating the "angular changing rate".
As a data, I have a time series of angular velocity and acceleration. But how do you get just "one number" from time series? Is it also at key events, or can I calculate the "angular changing rate" leading to having just one number from a time series?
Thanks!
Dear Researcher,
I am using SIMHYD hydro logical model. This model requires input in Tarsier daily time series format (.tts). I have all information in excel sheets, kindly guide me how to convert data from excel form to Tarsier daily time series format.
Suppose, I have daily data for a certain time series variable. However, if I want that variable to use quarterly data for research, how should I organize the data?
What is the short new way for you to solve this problem of data analysis in time series?Suppose you have time series data. What steps do you take and how to analyse this data? How to solve it in your work?Follow me and share with me your post and your personal experience.
What is the short new way for you to solve this problem of data analysis in time series? Suppose you have time series data. What steps do you take and how to analyse this data? How to solve it in your work? Follow me and share with me your post and your personal experience.
Hello Everyone !
I am currently analyzing the emissions of around 300 companies over a time spans of +- 20 years (time series data !). I am wondering what is the best way to approach the analysis of this dataset and what methods can I use to draw insights from my dataset.
I was thinking about starting with indexing my dataset (since companies dont have the same volume of emissions) and then average these indexes according to specific characteristics of the companies (ex: size, country, etc...) in order to attempt to pick up trends.
After the descriptive statistic analysis, I was thinking that I could top my analysis with a regression analysis of emissions according to the type of company (inv. company, state-owned, etc...). For that matter, is there a specific statistical test I can do to regress time series data according to a specific independant variable ?
Let me know what you think of this approach...I am listening to your comments !
Cordially,
Diego Spaey
I am interested to study on private investment and its determinants using time series data. want to understand the possible way of adopting time series data below 30 years. Is that possible to use? Thank you for your information.
Hello,
We are trying to analyze data from different patients. Here's the summary for the entire cohort:
1) Each patient will be followed over time.
2) Each patient will be given a starting dose of a compound, and a certain lab readout will be generated for that time point at that starting dose.
3) As time progresses, the dose will be increased/maintained, and a different readout will be generated by then. The dose adjustment will be done on a clinical basis.
Our question is:
We wanted to know whether increasing the dose would significantly change the readout at that certain time point. Two-way ANOVA (or a repeated two-way ANOVA) will erroneously provide us with a result. Which tool/statistical test would be appropriate for this scenario?
Thanks!
For example, There is no doubt that global sea level is rising, and based on the global mean sea level (GMSL)data, we can calculated the trend of the GMSL. However, we all know that that must be some interannual/decadal variations of the GMSL, and even the alising errors of our data. We can get the linear trend of GMSL timeseires based on least-square method. However, how can we estimate the uncertainty range of this trend? 1, GMSL timeseires have autocorrelation; 2, the variations of GMSL timeseries are not the white noises, the standard deviation of GMSL anomalies is not 1.
In time series analysis under what circumstances would the multiplicative model be preferred to additive model
I encountered a problem converting google earth engine data to ASCII format, in order to extract NDVI time series on TimeSat.
I have several IONEX files for multiple GNSS stations, and I would like to calculate the vertical and slant TEC values and store them in a time series data frame. Are there any software packages or reference material available that can help me read those IONEX files please?
I am dealing with a company profile that was established in 2005. For most of the variables, the information is available either till 2021 or 2018.
My concern is whether a time series ARDL application for 2005-2018 or 2005-2021 will be enough to report acceptable results or not. Since the company is established recently, there is no other way to increase the time period also. If possible, is there any study or reference that has applied such short time period data for time series analysis?
Thank you in advance for all your suggestions and opinions.
is Toda-yamamoto test used for long or short term ? and what is the difference between long and short term? short term is 5 years? more less? can we apply Toda-yamamoto to 10 years data or not? if not is there any alternative test?
Thank you
Dear Scholars,
In financial time series modelling, the usual practice is to model the financial variable using the log-return. Why can't we model the financial time series using the price? I am looking forward to read your professional responses soon.
#TIA
Good morning,
for my research project, I am using school meal data selection. I would like to investigate the children's food selection patterns using multiple time series using the K-means method. Given the remit of the study, in my data, I have missing data due to data collection during school and bank holidays, weekend generating breaks in food selection values. When you investigate a phenomenon on a daily scale, how do you manage these kinds of missing values? Do you change the temporal scale for example month rather than day, keeping breaks in graphics, or perform an imputation?
In my research study, i have four annual time series and i I want to convert them to monthly series while retaining the wide fluctuations in the original series. knowing that the curves of these annual series are approximately exponential.
my research study is about financial price modeling, i have several times series in which the frequency of some series is monthly, while the frequency of others is annual. my objecyive is to convert the annual series to montjly data but, what is the relevant statistical method in this case?
how can I obtain free precipitation, temperature, and potential evaporation data for a specific lake for the past 20 years?
I have 5 time series data points, of which 3 are absolute values and 2 are percentage terms. After converting the absolute values into log form, can I use ARDL?
kindly provide the answer to my question sir/madam.
Could you please provide me with 2 or 3 Elsevier or Springer articles that utilize this formula:
LST = BT / (1 + w * (BT / p) * ln(e))?
What kind of mining techniques are used in spatial databases and difference between temporal data and time series?
What kind of mining techniques are used in spatial databases and difference between temporal data and time series?
Discussion of issues related to the use of Neural Network Entropy (NNetEn) for entropy-based signal and chaotic time series classification. Discussion about the Python package for NNetEn calculation.
Main Links:
Python package
In my research study, I'm trying to model financial series using two series as data bases: the first series is monthly, and the second series is daily.
I've tried to render the second series monthly as well, by taking the instantaneous average of each month, but I've noticed that the wide fluctuations that make my research so interesting have disappeared.
how can we render a daily time series into a monthly series while retaining the effect of extreme values in the series?
what is the appropriate measure or statistical technique in this case?
My dependent variable consists of cross-sectional data with 8 observations, while the independent variables consist of time series data with 45 observations.
I am looking for time series data collected from sensors (presence, temperature, contact, RFID, etc.) in a Smart building.
I would like to obtain data allowing me to better understand the occupants of a building and to adapt to their rhythm of life and their needs.
I'm expecting to use stock prices from the pre-covid period up to now to build a model for stock price prediction. I doubt regarding the periods I should include for my training and test set. Do I need to consider the pre-covid period as my training set and the current covid period as my test set? or should I include the pre-covid period and a part of the current period for my training set and the rest of the current period as my test set?
I want to extract patent indices in the field of solar energy and analyze them with the time series method
Does anyone know which patent indicators can be analyzed in the context of time series?
thank you
My article focuses on the changes in Land surface temperature, vegetation, and waterbodies over a long time in an area by using Landsat and Modis data with a new methodology.
how to deal with missing values in times series data?
I am doing Trend analysis. When I was doing Homogeneity tests ( Pettitt, SNHT test, Buishand, von Neumann) on Precipitation and Temperature time series using XLSTAT, I found that a great number of my Temperature data are inhomogeneous. Can anybody tell me How can I make them homogeneous data?
The available memory keeps changing even if no file is open. The files that I want to open are large files of around 7-10 GB
Hello,
I have two time-series, A and B; what test can I apply to check if they differ?
I could compare the values between A and B at specific time points; for instance, is there a difference between the measures for A and B at t=24 hours?
But, is there a better way to compare time points?
Thank you
Is there a way to estimate the length of each period or seasonality in a time series in real-time? This is useful for adaptive and online time-series processing (streaming) where the entire data is not available a-priori.
Each observation may arrive sequentially or in a batch of observations. We want to be able to analyse observations as they come without having to store the entire historical data; though we may be able to store the most recent observations.
My dependent variable consists of cross-sectional data with 8 observations, while the independent variables consist of time series data with 45 observations.
My Dear
I have a series as y (40 values from sales) and need to use neural networks in a matlab symlink to forecast the future values of y as in times(41,42,43,......50)
When we do GARCH, we make time series stationary.
Stationary means constant mean and variance.
Then how are we modelling variance with GARCH when its stationary?
What am I missing here.
Also, can I find daily standard deviation for a stationary time series, using the rolling window method? Same logic, why am I getting different daily S.D. for a stationary time series using rolling window method?
hello, I have several parameters (chlorophyll, primary production) that I measures at two different marine stations during 2 years (it 's a time series). I need to do a statistical test to look at are there differences between these two locations, despite the fact that the planktonic communities are also changing over time. My data ara not normal so I need a non parametric test . Thanks for your help!
Hello,
Is this true in all cases: "Before applying the Augmented Dickey-Fuller (ADF) test, it is generally recommended to remove or account for the trend and seasonality components of the time series."
Thanks
F CHELLAI
It is a usual practice of calculating CV for rainfall/precipitation data after detrending the time series as suggested by many authors like (Giorgi et al. 2004; Blazquez et al. 2013). "Say, I have total winter rainfall data in a single time series. I calculated the detrended time series by subtracting the linear trend (or the fitted values of the linear regression) from the actual data. I got both positive and negative values in the detrended time series (Residual). If I calculate the CV (SD/mean) of this time series, the values are infinite as the mean of the time series is nearly zero".
Please kindly guide me. I want to know, where am I doing wrong?
I am using a Durbin-Watson test as a method through which to test for autocorrelation in a time series. Said data forms the basis of an interrupted time series analysis. My question is whether the absence of detected autocorrelation in the DW test on a simple model (OLS) is sufficient to inform modelling thereafter (ie. should I undertake the DW test on other plausible model types or does the DW test on an OLS suffice)?
Hello, I am doing my MSc Thesis and using Mann-Kendall trend analysis for discharge flows.
To implement the Mann-Kendall test, is it obligatory to use uncorrelated time series? I checked for autocorrelation in my time series (1 lag autocorrelation and significance level 5%) and found that my time series is autocorrelated.
After implementing the original Mann-Kendall and Mann-Kendall Test with Trend-Free Prewhitening, I realised that the autocorrelation of the original Mann-Kendall had overestimated the trends.
However, should I include in the results for both the original Mann-Kendall and commend the difference with the Mann-Kendall Test with Trend-Free Prewhitening? Or is it wrong to use the results of the Original Mann Kendall because the time series is autocorrelated?
Thank you in advance for any help!
What is the best method for smoothing data if there are both negative and non-negative time series?
I want to apply an ARDL model to a data set of 5 yearly time series (one response and 4 explanatory), spanning from 1971 to 2014. After some research, I found that an ARDL model requires each series to be either I(0) or I(1), therefore a unit root test is necessary. However, when I run the Augmented Dickey-Fuller test in R, I obtain some conflicting results. For example, I have the following series (EI.png). When I run the following test, I obtain results suggesting the presence of a unit root both at the levels and at the differences (TEST1.png):
But when I run the same test on the difference series, the results suggest the absence of a unit root (TEST2.png).
Again, when I put type = "trend", the test shows there is no unit root (TEST3.png).
Can someone please help me understand which of these tests I should report when writing my paper? Can I report a series as stationary if it is trend-stationary? Thank you in advance.
PS: These are all the remaining four series (All.png):
Hi all,
In time series analysis, when we check the normality assumption, did we should make stationary the time series or not? and if was not necessary, such a thing can violate the iid assumption of the observations?
Regards
Salam,
I'm asking If my data is not time series data, then the stationarity is (or is not )a relevant concern for fitting a multiple linear regression model? and if so, what makes differences with time series data?
Thank you
The dependent variable I chose for the study is stationary at level I(0), and other variables are a mixture of I(0) and I(1) time series data.
Can I use the ARDL model for this study? Which model is appropriate?
In the study of G. De Vita et.al. it says "….. it is necessary to ensure that the dependent variable is I(1) in levels .......". https://doi.org/10.1016/j.enpol.2005.07.016
Formula for converting the velocity into acceleration of a time series
Does it make sense to build a regression model for time series data with breaks? Like the time series I posted below with one major break that mark the shift of time series feature?
Hi,
i'd like to ask for advice with my paper "Comparison of correlations of stock prices before and during the pandemic".
I already have the correlation coefficients calculated and shown in a correlation matrix (attached) for both time periods.
The hypothesis is that the correlation coefficients have changed. As we can see from the above picture, it is pretty clear that they have but i'd like to include some mathematical proof. What statistical test should i use for this? T-test? Two-sample or paired? Is such test even applicable to this use case (e.g. comparing changes in correlation coefficients which were calculated from two different time series datasets)? If not, can you advice a different method?
Thank you
I am measuring the expression of a fluorescent protein over a period of 4 hours (15 min intervals), testing 4 different conditions with 2 control groups (one positive for expression of the protein, one negative), all in triplicate. The purpose of this experiment is to ascertain what effect each condition has on expression of the fluorescent protein over the period of 4 hours. I've considered running a Two Factor Anova with Replication to ascertain whether the test conditions have a statistically significant effect on the expression of the fluorescent protein over the 4 hour time period, however I've read that this test may not be appropriate to apply to time series data. I am wondering if this is the case and if so what statistical analysis might be appropriate to perform on this data?
For a particular pixel across multiple co-registered InSAR images, the amplitude value of the received echo may fluctuate from a mean value based on how sustained/changing is the scattering mechanism by the targets within such pixel over time. The selection of pixels as persistent scatterers candidates used for creating a deformation map through time series analysis of several acquisitions is primarily based upon the amplitude dispersion index thresholding at low values in order to properly estimate the phase stability/dispersion only when the Signal-to-Noise ratio is high enough for such pixels, according to the work of (Ferretti et al., 2001).
Source of the figure:
(PDF) Permanent scatterers in SAR interferometry. IEEE Trans Geosci Remot Sen (researchgate.net)
1) What is meant by phase stability in this case?
2) How is the phase's standard deviation across a time series affected by the amplitude dispersion?
3) How does the contribution of uncompensated propagation disturbances such as the atmospheric phase contribution and the satellite's orbital position inaccuracies besides other sources of noise affect the phase stability ?
I have recorded time series of stream temperature over a period of about 6 months with a frequency of 15 minutes. I am trying to attribute the temperature changes to different sources of influence. Therefore, I would like to remove the diurnal signal from my time series so that I am left with whatever else is going on besides the daily warming and cooling.
Are there any methods or papers you can recommend to solve this problem?
For background, the loggers were installed directly over the riverbed, some in shaded areas, some in the open. Most likely there is a tidal influence, which complicates things a bit since the tidal signal has a frequency of about 24 and 12 hours. There may be some groundwater input (probably not) and no tributaries.
Hello Everyone,
I am doing a time series data analysis (ARDL) and there I am using my independent variables as different types of taxes and its impact on income inequality. When I am using these taxes without variables that may affect income inequality I got majority of my tax has a significant and expected sign. So, in that case, do I have to add other variables that may affect income inequality? or is it okay to proceed with my model only with the taxes.
The data must be present as time series.
I need a Stata code for estimating non-ARDL in time-series. I will prefer the code that will show both the short run and long run results of the main variable and control variables.
I have two raster images. First is time series NDVI derived from Landsat 8 of a year. Other is a cropland data layer having different crops. I need to the the NDVI value for each crop present in my study area in Google earth engine. Please suggest me how I get the required NDVI values.
Dear colleagues,
Would you be so kind to advise me where the simultaneous raw data of the brain temperature and EEG time series can be available for public access? I suppose these data are possible mainly to mice or rats.
I have time series data regarding "air temperature" collected from experimental field and in parallel i have also collected the air temperature from local meteorological department for 12 months.
So, right now i am eager to know about relationship between them. Is their any statistical significant difference between them (even in any particular month)?
Please suggest the appropriate statistical test we can perform.
Thanks in advance.
i download time series data from
ERA5 monthly averaged data on single levels from 1959 to present
for every month I have a NC file
"units = 'm of water equivalent'
who I can calculate the total precipitation in a year?
If one has a time series dataset, that contain columns of item number, Date, qty_item_sold. If the frequency of the dataset is 'MS'(Month start) and there are missing value('0.0') in some months due to the lack of purchase orders for those Items how does one handle this type of data set and prepare it for forecasting. Do we drop the rows containing the null values, or do we apply time series missingness mechanisms to fill them in?
I tried dropping the rows and applying statsforecast using models such as AutoArima, AutoETS, Naive. But I don't think the models would are forecasting the dataset properly.
Hello , I have 6 variables in my model , time series data 34 year. i am Using EViews10 , i tried to added lag length( maximum lag 3 ), but the model still suffering from serial correlation problem . I have idea that is applied first difference for dependent variable , I applied the idea, after that the serial correlation removed from the model, but I am not sure this idea right or not .
My questions are :
1- How to remove serial correlation for ARDL model?
2- My idea that I applied it right or wrong?
thanks in advance .
If it is assumed that the time series X affects the time series Y, is it possible to quantify the effect of X attractor, reconstructed in the phase space through Takens's theorem, on the reconstructed Y attractor?
There is Granger causality, for example, to model this causal behavior in time series. Is there any similar technique to model the causality between two attractors in the phase space ( X -> Y)?
Intervention analysis in time series refers to the analysis of how the mean level of a series changes after an intervention, when it is assumed that the same ARIMA structure for the series holds both before and after the intervention. With this, is it possible and trust the result of using a univariate data without other predictor variables?
Hello Everyone,
In my study, I'm utilizing Eviews 10 software to analyze secondary time-series data. According to the manual, it includes inferential statistics and a reliability test. Could someone kindly clarify what tests go under inferential tests and what sort of tests I need to do to confirm the reliability of the collected data?
Thanks
Hello ,
I am doing drought propagation using two catchments with SPI and SSI . My question , I would to do like the graph in the picture attached. Do have any useful tutorial or maybe some suggestion R packages that is suitable to produce the same graph.
Thanks in advance
Hi all,
Does anybody know how or where I can download a multi-model mean time series of the CMIP6 climate projection scenarios a certain location? It seems I can only find output from separate models, which is a lot work to put them together.
Thanks
My undergraduate thesis is based on time-series data and I am using ARDL model. I got some sample thesis from online websites, but some may have missed some parts while some may have added additional parts. As a result, I couldn't figure out the correct structure from this. Therefore, if anyone has an ARDL model-based thesis study, please share it. It would be helpful for my final year thesis.
Thanks in advance
Hello,
I want to decompose oil price shocks into three elements (oil supply shocks, aggregate demand shock and oil-specific demand shock) according to Kilian (see attachment). In order to execute this in a programming software like R it needs to have a matrix of the data. I do not find information on which data shall be contained in this matrix? I think there is a time series of oil prices or is there any pre-work to be executed to seperate the three elements in advance?
The theoretical code is given as: c(...) includes all the data
m <- matrix(c(....),2,2)
cm <- chol(m)
cm
t(cm) %*% cm #-- = 'm'
crossprod(cm) #-- = 'm'
Thank you.
I wan to understand the difference between structural shifts in the time series and regime shift in the time series. Both are time varying models.
e.g., traffic volume versus crashes per year (other than using simple correlation)
I want to provide a prediction model for the concentration of pollutant particles with the help of meteorological data and the concentration of pollutant particles. My output is particle concentration (regression) and my input is meteorological data. My data is time series. Which models consider the sequence of time series?Thank you for my answer.
I am working on univariate time series prediction problem. Found many tools available for time series forecasting. But wanted to know if....
Any machine learning models that can predict time series like ARIMA without converting into supervised data?
Please suggest.
Dear Sir/Madam,
I am using time-series secondary data in my research. But I am not sure as to how to test validity and reliability of the data.
I have a predefined correlation matrix for N variable and want to generate time series for these variables satisfying their correlation. The time could be of any number of data points (i.e., 300).
I tried as follows but couldn't preserve the correlation of all N variable.
- generated a time series (randomly) for one of the variables and stored.
- manipulated the time series of first variable by adding some noise to get desired correlation value between 1st and second.
- once second time series reflects the predefined correlation between 1st and 2nd, then stored and generated time series for all N variables in same way satisfying the predefined correlation of all with first variable.
- now, moving to test the correlation of 2nd and 3rd and try to modify the times series of 3rd to maintain its predefined correlation with 2nd but its correlation with 1st is disturbed.
- beyond this my method doesn't work.
Any suggestion(s) or already written script(s) in MATLAB, R or Python will be much appreciated.
If I have a dataset with different periods how I can deal with it as time-series
For example, we have a multivariate time series comprising 8 univariate time series. I am aware some deep learning libraries can help to predict each of the time series in the multivariate series. I want to control what to forecast (for instance, forecast the first 4 series). Is it possible to use such deep learning libraries to accomplish that or there is a better way to do it?
Thanks
I'd appreciate your help for:
what are the implications of finding evidence for structure breaks in the multivariate time series ?