bbssr: Nonparametric Block Bootstrapped Spearman's Rank Correlation...

Description Usage Arguments Details Value References Examples

Description

Significant serial correlation present in time series data can be accounted for using the nonparametric block bootstrap technique, which incorporates Spearman’s Rank Correlation trend test (Lehmann, 1975; Sneyers, 1990;Kundzewicz and Robson, 2000). Predetermined block lengths are used in resampling the original time series, thus retaining the memory structure of the data. If the value of the test statistic falls in the tails of the empirical bootstrapped distribution, there is likely a trend in the data. The block bootstrap technique is powerful in the presence of autocorrelation (Khaliq et al. 2009; Önöz and Bayazit, 2012).

Usage

1
bbssr(x, ci=0.95, nsim=2000, eta=1, bl.len=NULL)

Arguments

x

- Time series data vector

ci

- Confidence interval

nsim

- Number of bootstrapped simulations

eta

- Added to the block length

bl.len

- Block length

Details

Block lengths are the number of contiguous significant serial correlations, to which the (η) term is added. A value of η = 1 is used as the default as per Khaliq et al. (2009). Alternatively, the user may define the block length. 2000 bootstrap replicates are recommended as per Svensson et al. (2005) and Önöz, B. and Bayazit (2012).

Value

Spearman's Correlation Coefficient - Spearman's correlation coefficient value

Test Statistic - Z-transformed value to test significance ρ(√{n-1})

Test Statistic Empirical Bootstrapped CI - Test statistic empirical bootstrapped confidence interval

References

Box, G. E. P. and Jenkins, G. M. (1970). Time Series Analysis Forecasting and Control. Holden-Day, San Fransisco, California, 712 pp.

Khaliq, M. N., Ouarda, T. B. M. J., Gachon, P., Sushama, L., and St-Hilaire, A. (2009). Identification of hydrological trends in the presence of serial and cross correlations: A review of selected methods and their application to annual flow regimes of Canadian rivers. Journal of Hydrology, 368: 117-130.

Kundzewicz, Z. W. and Robson, A. J. (2000). Detecting Trend and Other Changes in Hydrological Data. World Climate Program-Water, Data and Monitoring. World Meteorological Organization, Geneva (WMO/TD-No. 1013).

Kundzewicz, Z. W. and Robson, A. J. (2004). Change detection in hydrological records-A review of the methodology. Hydrological Sciences Journal, 49(1): 7-19.

Lehmann, E. L. (1975). Nonparametrics: statistical methods based on ranks. Holden-Day, Inc., California, 457 pp.

Önöz, B. and Bayazit M. (2012). Block bootstrap for Mann-Kendall trend test of serially dependent data. Hydrological Processes, 26: 3552-3560.

Sneyers, R. (1990). On the statistical analysis of series of observations. World Meteorological Organization, Technical Note no. 143, WMO no. 415, 192 pp.

Svensson, C., Kundzewicz, Z. W., and Maurer, T. (2005). Trend detection in river flow series: 2. Floods and low-flow index series. Hydrological Sciences Journal, 50(5): 811-823.

Examples

1
2
x<-c(Nile[1:10])
bbssr(x)

modifiedmk documentation built on June 10, 2021, 9:09 a.m.