Message-ID: <581115250.3351.1638102173162.JavaMail.atlassian@plg-s04> Subject: Exported From Confluence MIME-Version: 1.0 Content-Type: multipart/related; boundary="----=_Part_3350_1406797522.1638102173161" ------=_Part_3350_1406797522.1638102173161 Content-Type: text/html; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Content-Location: file:///C:/exported.html Priestley-Subba Rao (PSR) test user guide

# Priestley-Subba Rao (PSR) test user guide

=20
=20
=20
=20

A test of stationarity to check, i= f statistical properties do not change with time. Stationarity in a strict = sense is the strongest form of stationarity. It means that the joint statis= tical distribution of any collection of the time series variates never depe= nds on time, the mean, variance and any moment of any variate is the same w= hichever variate. The second order stationarity is often consider for norma= l use. In this case a constant mean, a constant variance, and an autocovari= ance that does not depend on time. To check if a time series is stationary = in second order mean a Priestley-Subba Rao (PSR) Test is used. =20
=20
=20
=20

REFERENCES Document Repository

CATEGORY Collective Properties of Seismicity

KEYWORDS Statistical analysis, Statistical propert= ies of seismicity

IS-EPOS. (2017). Priestley-Subba Rao (PSR) test [Web application]. = Retrieved from https://tcs.ah-epos.eu/

=20
=20
=20
=20
=20
=20

# Step by Step In order to use the PSR test = application the user must upload a time series data available in the worksp= ace. This is the mandatory input to the application. The time series data c= an be easily created with other tools available on the EPISODES Platform, a= s described below.The workflow for PSR test = application: Choose a catalog (or extract part of the catalog with Catalog Filte= r) from a selected episode. Add to user workspace the Catalog to Vector conver= ter application. It allows to extract vectors of = time and time=E2=80=93correlated attributes of user's choice from the seism= ic catalog. Select the seismic catalog to be used and= choose the parameter to be analyze (e.g. Mw). Figure 1. Input of GDF to Vector= s converter application.The application generates two files: tim= e_vector.mat and time_correlated_param_vector.mat. These are input files to= the Time Series Builder application that user should use next.2. Add the Time Series Builder to = the workspace. This application allows the user to generate data series bas= ed on time vector and time-correlated parameter vector files created in the= previous step. Please check detail in the Chapter Time Series Builder user guide. = As a result Time_series.mat appers.3. Add PSR test application to the workspace. The mandatory input is the time series = file generated in the previous step.In the following parameters the User nee= ds to specify: Number of tapers (min. 5) N= umber of block (2, 2) S= tatistical significance (0, 1) D= ata normalization using mean value  D= ata normalization using tapered series Press the button to initi= ate the process. 4. Outputs P value T - p value intera= ction between times P value I+R - p value interaction with residuals P value T+I+R  - p val= ue of total interaction Interpretation of results - if the= interaction of I+R is not significant, we conclude that tested time series= is a uniformly modulated process and if T is significant that mean the pro= cess is non-stationarity.I= f the interaction of I+R is significant, we conclude that tested time serie= s is non-stationary and non-uniformly modulated.Back to top

=20
=20
=20
=20
=20
=20

## Related Do= cuments

=20
• =20
=20 Page:= =20
=20
• =20
• =20
=20 Page:= =20
=20
• =20
• =20
=20 Page:= =20
=20
• =20
• =20
=20 Page:= =20
=20
• =20
• =20
=20 Page:= =20
=20
• =20
• =20
=20 Page:= =20
=20
• =20
• =20
=20 Page:= =20
=20
• =20
• =20
=20 Page:= =20
=20
• =20
• =20
=20 Page:= =20
=20
• =20
=20

=20
=20 =20
=20