Attention ! Ne pas confondre la moyenne et la médiane.
et la médiane ( Me ) et le mode ( Mo ) sont des mesures qui indiquent la position où semble se rassembler les valeurs de l'échantillon. a) La moyenne ( ? ).
Moyenne arithmétique simple et pondérée mode
https://ses.editions-bordas.fr/9782047326817/assets/fiche-methode-8-moyenne-arithmetique-simple-et-ponderee-mode-mediane-1/preview
A worldwide comparison of regional flood estimation methods and
crue moyenne annuelle et des distributions de fréquence des crues pour régionales satisfaisantes basées uniquement sur la médiane de la pluie moyenne.
Daytime Sleepiness
was to compare the value of the mean versus the median sleep latency in the en faveur de la mediane moyenne et mCdiane sont toutes deux acceptables en ...
Some Further Problems in the Classification of Human Chromosomes
the average over cells of the difference between the length of the median entre la longueur du chromosome median et la longueur moyenne des trois ...
Moyenne ou médiane?
Comment expliquer cette différence? Equilibre des masses ?? Partage des masses. Revenus de 2012. Po urce nta.
Les statistiques
Positions relatives du mode de la médiane et de la moyenne: La compréhension des différences entre ces valeurs est importante car leur position respectives
The migrant pay gap: Understanding wage differences between
wage differences between migrants and nationals – analyses wage data of 49 countries of the migrant pay gap (based on mean and median hourly wages).
Introduction à lapproche bootstrap - Irène Buvat
25-Sept-2000 La différence entre deux valeurs moyenne est-elle ... moyenne médiane
A Comprehensive Evaluation of Measures of Core Inflation in
09-Sept-2019 moyenne tronquée l'IPC-médiane pondérée et l'IPC-composante commune ... Table 1 presents the average difference in year-over-year growth of ...
Sleep, 18(S}:342-345
© 1995 American Sleep Disorders Association and Sleep Research SocietyDaytime Sleepiness
Mean Versus Median for the Multiple Sleep Latency
Test Selim R. Benbadis, Michael Perry, Barbara R. Wolgamuth, John Turnbull and WallaceB. Mendelson
Cleveland Clinic Foundation Sleep Disorders Center, Department of Neurology,Cleveland,
Ohio, U.S.A.
Summary: Since its introduction in the mid-1970s, the mUltiple sleep latency test (MSLT) has become the standard
method for evaluating hypersomnolence. The mean sleep latency is usually calculated and constitutes the traditional basis for interpretation. Mean and median are both measures of the central tendency of a distribution, but becausethe trials of the MSLT are limited to 20 minutes, the median may be more appropriate. The objective of this study
was to compare the value of the mean versus the median sleep latency in the interpretation of the MSLT. We retrospectively analyzed100 MSL Ts performed for evaluation of excessive daytime sleepiness. Patients' ages ranged
from 6 to 84 years (mean 43). Mean and median sleep latencies were calculated according to standard formulas.We classified each record into one
of three categories, using both the mean and the median sleep latencies: normal(> 10 minutes), moderate (205 and 10 minutes), and severe sleepiness "5 minutes). Of the 100 MSLTs, 89
remained in the same category (normal, moderate, severe) whether mean or median was used. In II cases, the category changed. All shifts were by one category, that is, no shift occurred between normal and severe. This study suggests that, despite valid theoretical arguments for the use of the median, both measures are equally acceptable for clinical purposes. Key Words:MSLT -Daytime sleepiness-Central tendency-Mean.
Resume: Depuis son introduction par l'ecole califomienne, Ie test de latence multiple de sommeil (TLMS) est
devenu la methode de reterence dans Ie bilan des etats d'hypersomnolence. En general, la moyenne des latences d'endormissement est calculee, et constitue la base de l'interpretation. La moyenne et la mCdiane mesurent la tendance centrale d'une distribution, mais du fait que les siestes du TLMS sont limitees a 20 minutes, la mCdianepeut sembler plus adequate. Le but de ce travail etait de com parer la valeur de la moyenne et de la mCdiane dans
l'interpretation du TLMS. Nous avons etudie de fa,calculees selon les formules standards. En utilisant d'une part la moyenne et d'autre part la mCdiane, nous avons
classe chaque enregistrement en 3 categories d'hypersomnolence: normal (> 10 minutes), moderee (20 5 et 10minutes), et severe " 5 minutes). Sur les 100 tests, 89 n'ont pas change de categorie quel que soit Ie parametre
utilise.Dans II cas, la classification a change, et toutes ont change d'une seule categorie (aucun changement ne
s'est produit entre normale et severe). Nous concluons que, en depit des arguments statistico-mathematiquesjustifies en faveur de la mediane, moyenne et mCdiane sont toutes deux acceptables en pratique clinique. Since its introduction at the Stanford University Sleep Research Center in the mid-1970s, the multiple sleep latency test (MSL T) has become the standard method for evaluating hypersomnolence (1). Beginning with early studies, accepted rules for interpretation have been based on the mean sleep latency: values greater than 10 are usually considered normal, whereas values less than 5 are considered indicative of pathological sleepiness. Values between 5 and10 represent a gray
Accepted for publication February 1995.
Address correspondence
and reprint requests to Selim R. Ben badis, Department of Neurology, Medical College of Wisconsin,9200 West Wisconsin Avenue, Milwaukee, WI 53226, U.S.A.
zone and can be viewed as indicative of moderate sleepiness (1-3).Mean and median are both measures of the central
tendency of a distribution. The term mean, or average, usually refers to arithmetic mean, and this is most widely used in theMSLT. Because the trials of the
MSLT are limited to 20 minutes, the distribution is truncated, and the median may be a more appropriate measure than the mean.In the published guidelines
for theMSLT (2), both mean and median are cited as
possible measures, but their respective merit has not been assessed.The objective of this study was to com
pare the value of the mean and the median sleep latency in the clinical interpretation of the MSLT.342 Downloaded from https://academic.oup.com/sleep/article/18/5/342/2749676 by guest on 23 October 2023
MEAN VS. MEDIAN FOR THE MSLT 343
PATIENTS AND METHODS
Patients
We retrospectively analyzed the data from 100
MSLTs performed on 100 patients for evaluation of
excessive daytime sleepiness (EDS). Ages ranged from6 to 84 years [mean 43, standard deviation (SD)
16].There were 63 males and 37 females.
MSLT method
MSLTs were recorded on Grass model
78 poly
graphs. Electrodes were attached with collodion, using the following montage: four channels of electroen cephalogram (EEG) using midline placement and in cluding an occipital electrode, four channels of elec trooculogram using left and right outer canthus, left above eye and left under eye, one electromyograph (EMG) channel (mental to submental), and one elec trocardiogram (EKG) channel. MSLTs were per formed during the day following an overnight poly somnogram and included at least four trials. If only one sleep onset rapid eye movement (REM) period (SOREMP) occurred in the first four naps, then a fifth trial was recorded. All trials were separated by90 min
utes, during which patients were instructed to stay awake. All MSLTs were scored using 30-second epochs and according to standard criteria for sleep staging (4). Three epochs of stage 1 or one epoch of any other sleep stage were required to establish sleep onset.Mean and median sleep latencies were calculated
according to standard formulas (5). Although several types of mean may be employed, the arithmetic mean is most commonly used; it is calculated by adding the observations and dividing the sum by the number of observations. The median is defined as the middle ob servation, that is, half the observations are smaller and half are larger. It is calculated by first arranging the observations from smallest to largest. The median is the middle value if there is an odd number of obser vations, and the mean of the two middle values ifthere is an even number of observations.For the purpose
of this study, we then classified each record into one of three categories, using both the mean sleep latency and the median sleep latency. The cate gories of sleepiness, according to either mean or me dian, were: normal (N) if> 10 minutes, moderate (M) if 2: 5 and $10 minutes and severe (S) if < 5 minutes.Each record was therefore assigned two classifica
tions: one using the mean, and one using the median.If there was a discrepancy between the two classi
fications, patients' charts were reviewed to gather rel evant history. # patIents 2 2 d<-3 -3§d<·2 -2"dOf the 100 MSLTs, using the more traditional mean
sleep latency, 26 were classified as normal, whereas 35 showed evidence of moderate sleepiness (2: 5 and $10) and 39 showed evidence of severe sleepiness (mean < 5). Seven patients showed one SOREMP only, and26 patients showed 2 or more
SOREMPs. The mean
was greater than the median in67 patients, the median
was greater than the mean in 28 and mean and median were equal in5. The distribution of the differences,
mean minus median, is shown in Fig. 1. The differences ranged from -4.0 to +4.1 (average +0.35, SD 1.42).In 89 patients, classification remained the same
whether mean or median was used. In 11, the category changed, and these data are shown in Table1. Ages
ranged from 8 to61 years (mean 42.7, SD 16.4). There
were six males and five females. All shifts were by one category, that is, betweenNand M or between M and
S' no shift occurred between normal and severe sleepFour of these "shifting" cases showed at least
oneSOREMP; three had a diagnosis of narcolepsy and
one of severe obstructive sleep apnea. In10 of the 11 "shifting" cases, the mean was greater
than the median. The absolute value of the difference between mean and median ranged from 0.6 to 5 (mean2.3, SD
1.1).DISCUSSION
From a statistical point of view
Mean and the median are equally easy to compute,
particularly with a small number of observations, asSleep, Vol. 18, No.5, 1995 Downloaded from https://academic.oup.com/sleep/article/18/5/342/2749676 by guest on 23 October 2023
344 S. R. BENBADIS ET AL.
TABLE I. Data on patients whose MSLT would be classified differently using the mean or the median sleep latency
Sleep latency (minutes) Mean minus
Patient
median no. Age/sex Nap I Nap 2 Nap 3 Nap 4 Nap 5 Mean Median difference SOREMpa I60/M 1.5 5.5 2 9.5 6 4.9 (S)b 5.5 (M) -0.6 None
2371M 18 4 5.5 3 7.63 (M) 4.75 (S) +2.88 None
quotesdbs_dbs47.pdfusesText_47[PDF] médiane triangle isocèle
[PDF] médiane triangle rectangle
[PDF] médiane triangle rectangle isocèle
[PDF] Médiane, moyenne arithmétique et pondérée
[PDF] Médiane, quartiles et diagramme en boite
[PDF] médiane,moyenne d'une tranche de chiffre
[PDF] médiane,quartile,moyenne
[PDF] medianes concourantes
[PDF] médianes d'un rectangle
[PDF] médias audiovisuels définition
[PDF] médias et démocratie le grand malentendu pdf
[PDF] médias et démocratie pdf
[PDF] médias et opinion politique
[PDF] medias et opinion publique en france depuis l'affaire dreyfus kartable