Extension of Multiple Range Tests to Group Means with Unequal Numbers of Replications

Kramer, Clyde Young

doi:10.2307/3001469

Cited by 2,951 publications

(1,088 citation statements)

References 1 publication

Supporting

Mentioning

1,069

Contrasting

Unclassified

Order By: Relevance

“…Pairwise significance tests within each of the five main effect terms in this model were tested using the TukeyYKramer multiple comparison procedure. 6,7,10 Linear, quadratic, and cubic relationships of day and order in day with sensitivity estimates were also tested. Specificity was analyzed similarly to sensitivity.…”

Section: Discussionmentioning

confidence: 99%

ROC Study of Four LCD Displays Under Typical Medical Center Lighting Conditions

et al. 2006

View full text Add to dashboard Cite

Nine observers reviewed a previously assembled library of 320 chest computed radiography (CR) images. Observers participated in four sessions, reading a different 1/4 of the sample on each of four liquid crystal displays: a 2-megapixel (MP) consumer color display, a 2-MP business color display, a 2-MP medical-grade gray display, and a 3-MP gray display. Each display was calibrated according to the DICOM Part 14 standard. The viewing application required observer login, then randomized the order of the subsample seen on the display, and timed the responses of the observer to render a 1Y Y5 judgment on the absence or presence of ILD on chest CRs. Selections of 1Y Y2 were considered negative, 3 was indeterminate, and 4Y Y5 were positive. The order of viewing sessions was also randomized for each observer. The experiment was conducted under controlled lighting, temperature, and sound conditions to mimic conditions typically found in a patient examination room. Lighting was indirect, and illuminance at the display face was 195 T 8% lux and was monitored over the course of the experiment. The average observer sensitivity for the 2 MP color consumer, 2 MP business color, 2 MP gray, and 3 MP gray displays were 83.7%, 84.1%, 85.5%, and 86.7%, respectively. The only pairwise significant difference was between the 2-MP consumer color and the 2-MP gray (P = 0.05). Effect of order within a session was not significant (P = 0.21): period 1 (84.3%), period 2 (86.2%), period 3 (85.4%), period 4 (84.1%). Observer specificity for the various displays was not statistically significant (P = 0.21). Finally, a timing analysis showed no significant difference between the displays for the user group (P = 0.13), ranging from 5.3 s (2 MP color business) to 5.9 s (3 MP Gray). There was, however, a reduction in time over the study that was significant (P G G G 0.001) for all users; the group average decreased from 6.5 to 4.7 s per image. Physical measurements of the resolution, contrast, and noise properties of the displays were acquired. Most notably, the noise of the displays varied by 3.5Â Â Â Â between the lowest and highest noise displays. Differences in display noise were indicative of observer performance. However, the large difference in the magnitude of the noise was not predictive of the small difference (3%) in the observer sensitivity for various displays. This is likely because detection of interstitial lung disease is limited by B B B B Banatomical noise^rather than display or x-ray image noise.

show abstract

Section: Discussionmentioning

confidence: 99%

ROC Study of Four LCD Displays Under Typical Medical Center Lighting Conditions

et al. 2006

View full text Add to dashboard Cite

show abstract

“…Thus, pairwise differences between groups were tested by the Tukey-Kramer HSD test on the least-squares means (Kramer, 1956), which is more conservative than Student's ttests for individual pairwise comparisons.…”

Section: Statistical Analysesmentioning

confidence: 99%

Endocranial volumes of primate species: scaling analyses using a comprehensive and reliable data set

Isler

Kirk

Miller

et al. 2008

Journal of Human Evolution

277

289

View full text Add to dashboard Cite

We present a compilation of endocranial volumes (ECV) for 176 non-human primate species, based on individual data collected from 3813 museum specimens, at least 88% being wild-caught. In combination with body mass data from wild individuals, strong correlations between endocranial volume and body mass within taxonomic groups were found. Errors attributable to different techniques for measuring cranial capacity were negligible and unbiased. The overall slopes for regressions of log ECV on log body mass in primates are 0.773 for least-squares regression and 0.793 for reduced major axis regression. The leastsquares slope is reduced to 0.565 when independent contrasts are substituted for species means (branch lengths from molecular studies). A common slope of 0.646 is obtained with logged species means when grade shifts between major groups are taken into account using ANCOVA. In addition to providing a comprehensive and reliable database for comparative analyses of primate brain size, we show that the scaling relationship between brain mass and ECV does not differ significantly from isometry in primates. We also demonstrate that ECV does not differ substantially between captive and wild samples of the same species. ECV may be a more reliable indicator of brain size than brain mass, because considerably larger samples can be collected to better represent the full range of intraspecific variation. We also provide support for the maternal energy hypothesis by showing that BMR and gestation period are both positively correlated with brain size in primates, after controlling for the influence of body mass and potential effects of phylogenetic relatedness.

show abstract

“…For comparison of the lipid values between the three countries (overall values and values for the different age strata), a oneway analysis of variance was performed. If a significant F value (p < 0.05) was obtained, the multiple comparison method of Tukey-Kramer 6 was used for a pairwise comparison of the sample means.…”

Section: Methodsmentioning

confidence: 99%

Serum lipids in the People's Republic of China. Comparison of Western and Eastern populations.

Kesteloot¹,

Huang²,

Xs³

et al. 1985

Arteriosclerosis

View full text Add to dashboard Cite

Serum cholesterol and HDL cholesterol levels were measured in an urban and a rural population of the People's Republic of China and compared with cholesterol values obtained in Belgium and in the Republic of Korea, with use of the same methodology. Total cholesterol levels were markedly lower In the People's Republic of China than in Belgium and generally lower than in Korea, both in male and female subjects. However, the differences In HDL cholesterol levels among the three populations were small in males and only significantly higher in Belgium in the age classes below 34 years. In women of all age groups, HDL cholesterol values were significantly higher In Belgium than in China and Korea. Total cholesterol levels below 100 mg/dl were found In the People's Republic of China in about 2% of the participants. Apolipoprotein B was significantly lower, and the apolipoprotein A,/B ratio was significantly higher, In China and Korea compared to Belgium. I schemic heart disease remains a major problem in Western countries, whereas Oriental populations are relatively immune to this disease. Since serum lipid values are an indicator of the relative risk for ischemic heart disease in Western countries, it is important to study the distribution of serum lipid values in populations where this disease is rare.The purpose of this article is to present data on the serum lipid distribution obtained in a population sample from the People's Republic of China (PRC) and to compare this distribution with data obtained in another Oriental population (the Republic of Korea) and in a typically Western population (Belgium). Methods Study PopulationsThe Chinese population studied consisted of 495 male and 561 female subjects. All were living in the region of Beijing. Of the participants, 256 male and Laboratory MethodsBlood samples for the measurement of serum lipids were taken from nonfasting subjects, and blood sera were separated by centrifugation after coagulation. All serum samples were stored at -2 0° C for a period of 4 to 8 weeks. They were airmailed to Belgium and arrived frozen. To assure standardization, 427 by guest on May 11, 2018 http://atvb.ahajournals.org/ Downloaded from

show abstract

Extension of Multiple Range Tests to Group Means with Unequal Numbers of Replications

Cited by 2,951 publications

References 1 publication

ROC Study of Four LCD Displays Under Typical Medical Center Lighting Conditions

ROC Study of Four LCD Displays Under Typical Medical Center Lighting Conditions

Endocranial volumes of primate species: scaling analyses using a comprehensive and reliable data set

Serum lipids in the People's Republic of China. Comparison of Western and Eastern populations.

Contact Info

Product

Resources

About