scholarly journals Statistical Uncertainty in Hydrometeorological Trend Analyses

2016 ◽  
Vol 2016 ◽  
pp. 1-26 ◽  
Author(s):  
Charles Onyutha
Keyword(s):  
Linear Trend ◽  
Theoretical Understanding ◽  
Significance Level ◽  
Trend Analyses ◽  
Comprehensive Information ◽  
Cyclical Component ◽  
Resampling Procedure ◽  
Rank Difference ◽  
Short And Long Term

This study demonstrates the existence of uncertainty in hydrometeorological trend analyses using historical rainfall from Kenya in East Africa. With respect to the influence of short- and long-term persistence on trend analyses, a total of 13 approaches of rank-based techniques including Mann-Kendall, Spearman’s Rho, and Cumulative Rank Difference (CRD) tests were employed. Graphically, CRD-based diagnoses of trends and subtrends were performed. To assess data-related uncertainty, a resampling procedure was applied. It was shown that at a selected significance level, the null hypothesisH0(no trend) can be rejected for trend direction while the evidence to rejectH0(zero trend magnitude) is statistically insufficient. Graphical and statistical approaches when combined yield more influential and comprehensive information for inference than relying purely on statistical results. Alongside an apparent linear trend, variations in the nonlinear (e.g., cyclical) component of the series may also not be due to natural randomness. Method-related uncertainty is not negligible especially for series with persistent fluctuations. These findings shed light on the need to assess uncertainty on trend results. Furthermore, it is recommended that the conclusiveness of trends be cautiously premised not only on statistical grounds but also on more considered physical and/or theoretical understanding of the hydrometeorological processes.

scholarly journals How to determine the statistical significance of trends in seasonal records: application to Antarctic temperatures

2021 ◽  
Author(s):  
Armin Bunde ◽  
Josef Ludescher ◽  
Hans Joachim Schellnhuber
Keyword(s):  
Multiple Testing ◽  
Statistical Significance ◽  
Climate Science ◽  
Seasonal Temperature ◽  
Multiple Testing Correction ◽  
Significance Level ◽  
Persistent Data ◽  
Short And Long Term ◽  
False Discoveries

AbstractWe consider trends in the m seasonal subrecords of a record. To determine the statistical significance of the m trends, one usually determines the p value of each season either numerically or analytically and compares it with a significance level $${{\tilde{\alpha }}}$$ α ~ . We show in great detail for short- and long-term persistent records that this procedure, which is standard in climate science, is inadequate since it produces too many false positives (false discoveries). We specify, on the basis of the family wise error rate and by adapting ideas from multiple testing correction approaches, how the procedure must be changed to obtain more suitable significance criteria for the m trends. Our analysis is valid for data with all kinds of persistence. Specifically for long-term persistent data, we derive simple analytical expressions for the quantities of interest, which allow to determine easily the statistical significance of a trend in a seasonal record. As an application, we focus on 17 Antarctic station data. We show that only four trends in the seasonal temperature data are outside the bounds of natural variability, in marked contrast to earlier conclusions.

Health economics using feature selection algorithm and regression method for prediction of ending cash

2019 ◽  
Vol 14 ◽  
Author(s):  
Zinat Ansari
Keyword(s):  
Feature Selection ◽  
Health Economics ◽  
Feature Selection Method ◽  
Selection Algorithm ◽  
Feature Selection Algorithm ◽  
Significance Level ◽  
Short And Long Term ◽  
Attribute Evaluation ◽  
Interest Payments

Background: Health economics are amongst academic fields which can aid in ameliorating conditions so as to perform better decisions in regards to the economy such as determining cash prices. The prediction of ending cash is fundamental for internal and external users and can come quite handy in terms of health economics. The most important purpose of financial reporting is the presentation of information to predict ending cash. Ergo, the aim of the research is to predict ending cash value using feature selection and MLR method from 2010-2012. Methods: A feature selection algorithm (Best-First, Greedy-Stepwise and Ranker) was employed in this research to nominate relevant data that affect ending cash. Results: Based on the results of the deployed feature selection method, the following features were indicated as the most relevant in terms of determine ending cash: interest payments for loans, dividends received from short and long term deposits, total net flow of investment activities, net increase (decrease) in cash and beginning cash based on best-first (CFS-Subset-Evaluation) and Greedy-Stepwise (CFS-Subset-Evaluation). Net out flow, dividends, dividends paid, interest payments for loans and dividends received deposits for short and long term were the most important data as indicated by the Ranker (Info-Gain-Attribute-Evaluation, Gain-Ratio-Attribute-Evaluation and Symmetricer-Attribute-Evaluation). According to Ranker (Principal-Components and Relifef-FAttribute-Evaluation) the best data for determining ending cash include beginning cash, interest payments for loans, dividends, net increase (decrease) in cash and dividends received from short and long term deposits. The findings were also indicative of a positive and highly significant correlation between dividends received from short and long term deposits and beginning cash (1.00**), with a significance level of 0.01, whereas the observed correlation between interest payments for loans and ending cash (0.999**), at a significance level of 0.01 was negatively significant. Conclusions: The present research attempted to reduce the volume of data required for predicting end cash by means of employing a feature selection so as to save both precious money and time.

Short- and Long-Term Results of Total vs Subtotal Thyroid- ectomies in the Surgical Treatment of Graves' Disease

Swiss Surgery ◽  
2001 ◽  
Vol 7 (1) ◽  
pp. 20-24 ◽  
Author(s):  
Robert ◽  
Mariéthoz ◽  
Pache ◽  
Bertin ◽  
Caulfield ◽  
...  
Keyword(s):  
Recurrent Laryngeal Nerve ◽  
Nerve Palsy ◽  
Recurrent Laryngeal Nerve Palsy ◽  
Laryngeal Nerve ◽  
Long Term Results ◽  
Graves Disease ◽  
Laryngeal Nerve Palsy ◽  
Short And Long Term

Objective: Approximately one out of five patients with Graves' disease (GD) undergoes a thyroidectomy after a mean period of 18 months of medical treatment. This retrospective and non-randomized study from a teaching hospital compares short- and long-term results of total (TT) and subtotal thyroidectomies (ST) for this disease. Methods: From 1987 to 1997, 94 patients were operated for GD. Thirty-three patients underwent a TT (mostly since 1993) and 61 a ST (keeping 4 to 8 grams of thyroid tissue - mean 6 g). All patients had received propylthiouracil and/or neo-mercazole and were in a euthyroid state at the time of surgery; they also took potassium iodide (lugol) for ten days before surgery. Results: There were no deaths. Transient hypocalcemia (< 3 months) occurred in 32 patients (15 TT and 17 ST) and persistent hypocalcemia in 8 having had TT. Two patients developed transient recurrent laryngeal nerve palsy after ST (< 3 months). After a median follow-up period of seven years (1-15) with five patients lost to follow-up, 41 patients having had a ST are in a hypothyroid state (73%), thirteen are euthyroid (23%), and two suffered recurrent hyperthyroidism, requiring completion of thyroidectomy. All 33 patients having had TT - with follow-ups averaging two years (0.5-8) - are receiving thyroxin substitution. Conclusions: There were no instances of persistent recurrent laryngeal nerve palsy in either group, but persistent hypoparathyroidism occurred more frequently after TT. Long after ST, hypothyroidism developed in nearly three of four cases, whereas euthyroidy was maintained in only one-fourth; recurrent hyperthyroidy was rare.

Short- and long-term memory tasks predict working memory performance, and vice versa.

2019 ◽  
Vol 73 (2) ◽  
pp. 79-93 ◽  
Author(s):  
Ian Neath ◽  
Jean Saint-Aubin ◽  
Tamra J. Bireta ◽  
Andrew J. Gabel ◽  
Chelsea G. Hudson ◽  
...  
Keyword(s):  
Working Memory ◽  
Memory Performance ◽  
Long Term Memory ◽  
Term Memory ◽  
Short And Long Term
Sign in / Sign up

Export Citation Format

Share Document