TERMIUM Plus^®

Record 1,  Textual support,  English

Record number: 1, Textual support number: 1 CONT

The reliability statistics included the root mean square error(RMSE), relative RMSE(RMSEr), bias(Bias) and relative bias...  2, record 1, English, - reliability%20statistics

Record number: 1, Textual support number: 1 OBS

reliability statistics: term used at Natural Resources Canada - Earth Sciences Sector.  3, record 1, English, - reliability%20statistics

Record 1,  Textual support,  French

Record number: 1, Textual support number: 1 OBS

statistiques de fiabilité : terme en usage à Ressources naturelles Canada - Secteur des sciences de la Terre.  2, record 1, French, - statistiques%20de%20fiabilit%C3%A9

Record 1,  Textual support,  Spanish

Record 2,  Textual support,  English

Record number: 2, Textual support number: 1 DEF

A resampling technique which selects the nearest pixel value in the input image to write to each output location.  2, record 2, English, - nearest%20neighbour%20resampling

Record number: 2, Textual support number: 1 CONT

The raw images were transformed to geographic co-ordinates using ground control points, identifiable both on imagery and in the field. Nearest neighbour resampling was used with an RMS [Root Mean Square] transformation error of approximately one pixel. This enabled accurate identification and location of sites within the SAR image.  3, record 2, English, - nearest%20neighbour%20resampling

Record number: 2, Textual support number: 1 OBS

nearest neighbour resampling: term officially approved by the RADARSAT-2 Terminology Approval Group (RTAG).  4, record 2, English, - nearest%20neighbour%20resampling

Record 2,  Textual support,  French

Record number: 2, Textual support number: 1 DEF

Technique de rééchantillonnage qui consiste à calculer l'indice de luminance d'un pixel dans l'image corrigée en se référant à l'indice de luminance du pixel le plus près, dans l'image d'entrée.  2, record 2, French, - r%C3%A9%C3%A9chantillonnage%20du%20plus%20proche%20voisin

Record number: 2, Textual support number: 1 CONT

Méthode de rééchantillonnage du plus proche voisin. C'est l'unique solution si l'image contient : des valeurs nominales (catégories) [et] des valeurs ordinales (classes).  3, record 2, French, - r%C3%A9%C3%A9chantillonnage%20du%20plus%20proche%20voisin

Record number: 2, Textual support number: 1 OBS

rééchantillonnage du plus proche voisin : terme uniformisé par le Groupe de travail de la terminologie de RADARSAT-2 (GTTR).  2, record 2, French, - r%C3%A9%C3%A9chantillonnage%20du%20plus%20proche%20voisin

Record 2,  Textual support,  Spanish

Record 3,  Textual support,  English

Record number: 3, Textual support number: 1 DEF

A measure of the variability of measurements about their true values.  1, record 3, English, - root%2Dmean%2Dsquare%20error

Record number: 3, Textual support number: 1 OBS

The RMS error is estimated by taking sample measurements and comparing them to their true values. These differences are then squared and summed. The sum is then divided by the number of measurements to achieve a mean square deviation. The square root of the mean square deviation is then taken to produce a characteristic error measure in the same units as the original measurements. The RMS error is directly comparable to the concept of a standard deviation.  1, record 3, English, - root%2Dmean%2Dsquare%20error

Record number: 3, Textual support number: 2 OBS

root-mean-square error; RMS error : terms and definition provided by the Canadian Hydrographic Service.  1, record 3, English, - root%2Dmean%2Dsquare%20error

Record 3,  Textual support,  French

Record number: 3, Textual support number: 1 DEF

Mesure de la variabilité de mesures par rapport à la valeur vraie.  1, record 3, French, - erreur%2Dtype

Record number: 3, Textual support number: 1 OBS

L'erreur-type est estimée en effectuant des mesures et en les comparant à la valeur vraie. Les différences sont mises au carré et additionnées. Cette somme est ensuite divisée par le nombre de mesures effectuées pour obtenir le carré de la moyenne quadratique. En extrayant la racine carrée du carré de la moyenne quadratique, l'on obtient une mesure caractéristique de l'erreur dans les mêmes unités que les mesures d'origine. Le concept d'erreur quadratique moyenne (erreur-type) est directement comparable à celui de l'écart-type.  1, record 3, French, - erreur%2Dtype

Record 3,  Textual support,  Spanish

Record 4,  Textual support,  English

Record number: 4, Textual support number: 1 DEF

The square root of the mean square error [derived from variate values]  1, record 4, English, - root%2Dmean%2Dsquare%20error

Record number: 4, Textual support number: 1 OBS

mean square error: ... the average of the squared distance between the estimate and the parameter.  3, record 4, English, - root%2Dmean%2Dsquare%20error

Record number: 4, Textual support number: 2 OBS

A measure of the error to which one is exposed by the use of an estimator, which is given by the expected value of the squared difference between the estimator and a (theoretically) correct value. For unbiased estimators, the mean square error equals the variance.  1, record 4, English, - root%2Dmean%2Dsquare%20error

Record 4,  Textual support,  French

Record number: 4, Textual support number: 1 CONT

L'erreur type est l'écart type d'une distribution d'échantillonnage d'une mesure obtenue à partir de calculs effectués sur un échantillon.  2, record 4, French, - erreur%2Dtype

Record 4,  Textual support,  Spanish

Record 5,  Textual support,  English

Record number: 5, Textual support number: 1 OBS

Network densities, where sampling locations are representative, and the elements randomly distributed, may be determined using sampling-error theory. The standard error of the mean is, under these circumstances, inversely proportional to the square root of the sample size(...). Over a period of time, the mean error in inversely proportional to the square root of the length of record(...)  1, record 5, English, - sampling%2Derror%20theory

Record 5,  Textual support,  French

Record number: 5, Textual support number: 1 OBS

Là où les sites de prélèvement sont représentatifs, et où les éléments sont distribués au hasard, on peut déterminer les densités de réseau par la théorie de l'erreur d'échantillonnage. L'erreur "standard" de la moyenne est, par rapport à ces facteurs, inversement proportionnelle à la racine carrée de la dimension de l'échantillon (...). Sur une certaine période de temps, l'erreur moyenne est inversement proportionnelle à la racine carrée de la période de compilation (...)  1, record 5, French, - th%C3%A9orie%20de%20l%27erreur%20d%27%C3%A9chantillonnage

Record 5,  Textual support,  Spanish