Dynamic factor analysis to estimate common trends in fisheries time series

Zuur, Alain F.; Tuck, I.; Bailey, N.

doi:10.1139/f03-030

Cited by 255 publications

(333 citation statements)

References 18 publications

Supporting

Mentioning

310

Contrasting

Order By: Relevance

“…DFA is a multivariate time-series analysis technique to estimate common trends, to study the interactions between response variables and to determine the effects of explanatory variables in a time series data set (Zuur and Pierce, 2004;Zuur et al, 2003a). The underlying DFA model is given by (Zuur and Pierce, 2004):…”

Section: Dynamic Factor Analysis (Dfa)mentioning

confidence: 99%

Common trends in German Bight benthic macrofaunal communities: Assessing temporal variability and the relative importance of environmental variables

Shojaei

Gutow

Dannheim

et al. 2016

Journal of Sea Research

View full text Add to dashboard Cite

We examined long-term variability in the abundance of German Bight soft bottom macro-zoobenthos together with major environmental factors (sea surface temperature, winter NAO index, salinity, phosphate, nitrate and silicate) using one of the most comprehensive ecological long-term data sets in the North Sea . Two techniques, Min/Max Autocorrelation Factor Analysis (MAFA) and Dynamic Factor Analysis (DFA) were used to identify underlying common trends in the macrofaunal time series and the relationships between this series and environmental variables. These methods are particularly suitable for relatively short (N15-25 years), non-stationary multivariate data series. Both MAFA and DFA identify a common trend in German Bight macrofaunal abundance i.e. a slight decrease (1981-mid-1990s) followed by a sharp trough in the late 1990s. Subsequently, scores increased again towards 2011. Our analysis indicates that winter temperature and North Atlantic Oscillation were the predominant environmental drivers of temporal variation in German Bight macrofaunal abundance. The techniques applied here are suitable tools to describe temporal fluctuations in complex and noisy multiple time series data and can detect distinct shifts and trends within such time series.

show abstract

Section: Dynamic Factor Analysis (Dfa)mentioning

confidence: 99%

Common trends in German Bight benthic macrofaunal communities: Assessing temporal variability and the relative importance of environmental variables

Shojaei

Gutow

Dannheim

et al. 2016

Journal of Sea Research

View full text Add to dashboard Cite

show abstract

“…2). While 0.2 is commonly used as the cut-off point, here this was relaxed to 0.1 (Zuur et al, 2003). Carangids contribute towards trend-1 only with a factor loading of 0.288.…”

Section: Resultsmentioning

confidence: 99%

“…The timeseries vectors are usually standardised before subjecting them to DFA. However in this study, all the time series vectors used were in the same scale (or units) and hence this step does not affect the results (Zuur et al, 2003).…”

Section: Icar-central Marine Fisheries Researchmentioning

confidence: 99%

“…Dynamic factor analysis (DFA) is a statistical tool used to identify and extract common trends existing in multivariate time series data and it can be used to estimate common trends in short and non-stationary time series (Zuur et al, 2003;Zuur and Pierce, 2004). Globally there were several attempts to model trends in marine fishery resources with the help of DFA (Zuur et al, 2003;Zuur and Pierce, 2004;Chen et al, 2006;Huang et al, 2006). In this study recent historic data were analysed to delineate the common trends for major fishery resources landed along the Indian coast.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Trends in abundance of marine fishery resources in India examined through dynamic factor analysis

et al. 2016

View full text Add to dashboard Cite

Dynamic factor analysis (DFA) was used to identify common trends to explain the variability for a historical time series data on all India annual marine fish landings for 16 resource groups. In this study, three common trends were identified for classifying the resource groups. Trend-1 increases gradually and reaches a peak in 1997, decreases sharply until 2001 and then increases further. Landings of carangids were clearly related to trend-1 with positive factor loading magnitude. Trend-1 is important for Bombayduck as well but with negative factor loading. In the case of trend-2, it is declining until 1993 and remains steady with slight fluctuations till 2003 and increases further. Both, silverbellies and pomfrets landings were determined by trend-2 with similar positive factor loadings. All other resources were associated with more than one trend. Trend-3 shows an increasing trend throughout the period with slight fluctuations. Perches, seerfishes, tunnies, flatfishes, crustaceans and molluscs formed a homogenous group associated with both trend-1 and trend-3. These trends were important for elasmobranchs too as they had similar loadings on both trends but with opposite signs. Resource-wise explanations based on the different trends are discussed citing the examples of clupeids, carangids, Bombayduck, pomfrets and silverbellies.

show abstract

“…In many applications, the number of indicators may exceed the number of observations. Also, current techniques for generating components from time-dependent variables assume stationarity of the time series, see for example, (Jollife, 2002), (Zuur et. al., 2003), (Heaton andSolo, 2004), and(Fernandez-Macho, 1997).…”

Section: Introductionmentioning

confidence: 99%

Principal components analysis of nonstationary time series data

Lansangan

Barrios

2008

Stat Comput

View full text Add to dashboard Cite

The effect of nonstationarity in time series columns of input data in principal components analysis is examined. This usually happens when indexing economic indicators for monitoring purposes. The first component averages all the variables without reducing dimensionality. As an alternative, sparse principal components analysis can be used but attainment of sparsity among the loadings is influenced by the choice of a parameter (λ).Varying cross-correlation and autocorrelation structures were simulated with number of observations exceeding the number of variables. Sparse component loadings even for nonstationary time series columns of the input data can be achieved provided that appropriate value of λ is used. We provide the possible range of values of λ that will ensure convergence of the sparse principal components algorithm and sparsity of component loadings.

show abstract

Dynamic factor analysis to estimate common trends in fisheries time series

Cited by 255 publications

References 18 publications

Common trends in German Bight benthic macrofaunal communities: Assessing temporal variability and the relative importance of environmental variables

Common trends in German Bight benthic macrofaunal communities: Assessing temporal variability and the relative importance of environmental variables

Trends in abundance of marine fishery resources in India examined through dynamic factor analysis

Principal components analysis of nonstationary time series data

Contact Info

Product

Resources

About