Dunnett s test

Data Analysis. (Arlett et al., 1989). A weighted analysis of variance is performed on the mutation frequencies, as the variation in the number of mutations per plate usually increases as the mean increases. Each dose of test compound is compared with the corresponding vehicle control by means of a one-sided Dunnett s test and, in addition, the mutation frequencies are examined to see whether there is a linear relationship with dose. 

Fig. 2. Antinociceptive effects of intraplantar BEO in the capsaicin test. BEO was injected into the plantar surface of the hindpaw 10 min prior to injection of capsaicin (50 ng/paw). Jojoba oil was used as a control, which was without affecting the capsaicin-induced nociceptive response. Data are means + S.E.M. in — 10 mice per group). p < 0.001, p < 0.01 when compared with Jojoba oil-treated controls by Dunnett s test.

Fig. 2. Transient retinal ischemia increases intravitreal glutamate in rat. Neurochemical data from microdialysis experiments carried out in anesthetized rats to demonstrate that ischemia/reperfusion insult increases intravitreal glutamate. The extracellular level of glutamate shows a moderate increase during the first 10 min of ischemia, more evident toward the end of the ischemic period, to reach statistical significance at 10 and 150 min of reperfusion. Baseline glutamate concentrations (basal values) are the mean concentrations obtained by averaging six samples collected consecutively at 10 min intervals immediately before the onset of ischemia (n — 6 rats). Glutamate values (pM) are expressed as mean S.E.M. Statistical significance was assessed by ANOVA followed by Dunnett s test for multiple comparisons. P < 0.05 and P < 0.001 versus basal values.

Dunnett s test With Dunnett s test, we select one of the treatments as a control or reference group. All other groups are then compared against the control. In our case we might declare platinum to be the control and then compare all other treatments against it - a total of four comparisons. 

Performing Dunnett s test In the real world, it would be naughty to start doing a Dunnett s test at this stage, since we have already seen the data and had previously committed ourselves to Tukey s test. However, just so you can see the procedure, we will perform Dunnett s test with platinum as control. 

If you select the option for Dunnett s test in your statistical package, you will additionally have to indicate that platinum is to act as the control. The generic output (Table 13.5) shows the difference of each metal in turn from platinum. Platinum is demonstrated to be inferior to palladium and the alloy, but there is no statistically significant evidence of a difference from rhodium or iridium. 

Dunnett s test Control platinum Confidence Intervals 98.47% Lower limit for difference Upper limit for difference Significant ... 

When Tukey s or Dunnett s test make multiple comparisons, each of these is performed to a higher than normal standard of proof, so that the accumulative risk of generating any false positives remains at the usual 5 per cent. 

The data from our catalyst experiment are balanced , i.e. there are exactly equal numbers of replicates for each catalyst. This is not a requirement for the one-way ANOVA and, if a small amount of data loss occurs, the analysis can still go ahead. For any given number of observations, the power of the ANOVA will be greatest with a balanced data set and this is also true for Tukey s test. The only circumstance where power will be greater with an imbalanced data set is where a Dunnett s test is planned. Here, the control group is of special importance because it is used in all the comparisons. For this test, it is worthwhile trying to generate some extra data for the control group. 

Follow-up tests will rectify both of these short-comings. Tukey s test will look at the difference for every possible pair of levels of the factor. Dunnett s test will treat one level as a reference and then compare all other levels against that. A confidence interval is calculated for the difference between each pair of treatments. If the interval excludes zero, that comparison is statistically significant The intervals are calculated to give each comparison less than a 5 per cent risk of producing a false positive. In this way, the entire series of comparisons will accumulate a total 5 per cent risk. 

Data are expressed as the means SE. Statistical significance is assessed by two-tailed unpaired Student s t-test or one way analysis of variance (ANOVA) followed by either Dunnett s test for multiple comparisons vs. control or the Newman-Keuls test for all pair-wise comparisons. Tests indicating a value of P < 0.05 indicate a statistically significant difference between groups. 

The values are expressed or plotted as the means SE and pA2 values are calculated according to Arunlakshana and Schild (1959). Data are analyzed using the t-test, analysis of variance, Dunnett s test and... 

Figure 4.1 Effect of s.c. (A) and p.o. (B) administration of 6-(N,N-di- -propylamino)tetrahydro-benzo[/>]thiophene (34) on striatal dopamine release in freely moving rats. Data are presented as mean S.E.M. (n = 4). P<0.05 (Dunnett s test).

Fig. 17 Effects of TRK-820 on the scratching behavior in mice induced by histamine (a) or substance P (b). Mice (ICR strain) were given a p.o. administration of vehicle (open bars) or TRK-820 (filled bars). Then, 30 min later, phosphate-buffered saline, pH 7.4 (PBS), histamine (a), or substance P (b) was i.d.-injected. Immediately after the injection of PBS, histamine, or substance P, the number of scratching events was recorded and counted over a 30-min period. The numbers of scratching events observed with histamine or substance P injections in the absence of TRK-820 were considered 100% on the vertical axes. Each value represents the mean standard error of the mean (S.E.M.) (n = 8). P < 0.01 compared between the PBS and histamine- or substance P-injected groups (Dunnett s test). Reprinted from [51] with permission from Elsevier. Copyright (2002)...

It should be noted that these are not the only acceptable methods applicable to multiple comparisons from an ANOVA. In each individual case, the choice among possible approaches is largely dependent on the study design. For example, Dunnett s test can be used when the only comparisons of interest are each test treatment versus a control (for example, in a placebo-controlled, dose-ranging study). Like Tukey s test, Dunnett s method is more powerful than Bonferroni s. In general, other methods gain power compared with Bonferroni s method by... 

Grain densities were calculated from light microscope autoradiographs using an image ana- E < 0.01 compared to control (Dunnett s test). 

Duncan s multiple test range Dunnett s test... 

The statistical analyses of the data concerning the four caterpillar bioassays involves an analysis of variance (ANOVA) for a completely randomized design (CRD) followed by Dunnett s test for each experiment. The ANOVA are done to get a preliminary feel if the treatments had any effect on the test organism. Dunnett s method is chosen because we are interested in determining whether the mean of the control group is significantly different than each of the means of the treatments. Experimental treatments can consist of crude extracts or pure compounds. 

When the effects of multiple doses of a cannabinoid on the response to the single dose A of the contractile agent are investigated, the size of each contraction produced in the presence of the cannabinoid can be compared to the size of the initial contraction evoked in the absence of the cannabinoid. This may be achieved by normalizing the data such that, for example, each contractile response elicited in the presence of the cannabinoid is expressed as a percentage of the initial contractile response, normalized to 100%. The effects of different cannabinoid doses can be compared with the initial contraction by performing a one-way analysis of variance (ANOVA) followed by a post hoc test such as Dunnett s test. 

Data were analysed by using ANOVA, Duncan s New Multiple Range test and Dunnett s test (Zar, 1984). 

FIGURE 22 Quantitative assays for neurite outgrowth activities of acetal derivatives PC12 cells were cultured in two 24-well plates in DMEM+10% HS and 5% FBS for 24 h at a density of 2 X 10 cells/cm. Tlie medium was then changed to DMEM+2% HS and 1% FBS supplemented with NGF (10 ng/mL) in die absence or presence of test compound. After 4 days the length of the longest neurites were quantified. Data are expressed as the meaniSE (n=149). P<0.01 versus control Dunnett s/test... 

---