As expected, based on the mean right-to-left/left-to-right trajectories in any one of three subtasks, the classifier outputs could predict the corresponding individual journeys within the other remaining two subtasks at a high level of accuracy at the ensemble level (see 'Materials and methods'; Figure 9, p<0.001, binomial test, chance = 0.5, n = 128 cells).
Extensive treatment forced him to miss the first half of the 2011 season while he recovered and, although he returned impressively by scoring an unbeaten 300 against Yorkshire, it was thought his England Test chance had gone.
"Surely his (limited) Test chances so far suggest he's too green for this match.
Other observers have pointed out that teachers who feel insecure about their ratings may focus on improving the test chances of their most able students at the expense of nurturing the capacities of the least able members of their classroom.
If you're in Atlanta, Houston, Seattle, Tampa, Orlando, Pittsburgh, Charlotte, Greensboro, Winston-Salem, Oklahoma City, Tulsa, New Orleans, or Charleston, fire up your device and give it a speed test — chances are, you're surrounded in 4G ish) radiowaves right this second.
Water maze data were analysed by repeated measures ANOVA and spontaneous exploration task discrimination indices were analysed by one sample t-test (chance = 0) with Bonferroni correction.
The index in preC is significantly smaller than preA (t-test, t8 = 3.911, p<0.0045) and the chance level (one sample t-test, chance = 0, t3 = 3.558, p<0.038), whereas the index in preA is not different from chance (one sample t-test, chance = 0, t5 = 0.6153, p>0.56).
Moreover, the reactivation index is not significantly different from chance in preA mice but is significantly below chance in preC mice (one sample t-test, chance = 0: preA, t11 = 1.582, p>0.14; preC, t10 = 6.316, p<0.0001).
Binomial tests (chance 50%) revealed that the Sham2 group swam to the correct zone significantly more often than predicted by chance (p =.0015; one-tailed), whereas the ATNx2 group did not.
Finally, focusing on individual data we assessed whether individual subjects searched the containers randomly or whether they preferred to use either a feature or a spatial strategy using binomial tests (chance level 0.33).
If your hypothesis survives your tests, chances are, it's valid.
