Set up workspace
# Normal plot
formals(normalPlot)## $mean
## [1] 0
##
## $sd
## [1] 1
##
## $bounds
## c(-1, 1)
##
## $tails
## [1] FALSE
normalPlot(bounds = c(-1.13, Inf))87%
normalPlot(bounds = c(-Inf, 0.18)) 57%
normalPlot(bounds = c(8, Inf)) ~0%
normalPlot(bounds = c(-0.5, 0.5)) 38%
Leo: 4948 seconds
Mary: 5513 seconds
Men:
mean: 4313 seconds
std: 583 seconds.
Women:
mean: 5261 seconds
std: 807 seconds
Men: N(4313, 583)
Women: N(5261, 807)
They tell you how each did with respect to their group.
Leo
(4948 - 4313)/583## [1] 1.089194
Mary
(5513 - 5261)/807## [1] 0.3122677
Leo did better in his group because his score is about 1 standard deviation above the mean; whereas, Mary’s is only 0.3 standard deviations above the mean.
pnorm(1.089)## [1] 0.8619231
He finished faster than about 86% of his group.
pnorm(0.3122)## [1] 0.6225557
She finishined faster than about 62% of her group.
This would change the answers to the above parts. For instance, if one of the plots were bimodal, this would be a completely different context for comparing their results.
scores <- c(54, 55, 56, 56, 57, 58, 58, 59, 60, 60, 60, 61, 61, 62, 62, 63, 63, 63, 64, 65, 65, 67, 67, 69, 73) length(scores[scores > (61.52 - 1*4.58) & scores < (61.52 + 1*4.58)])/length(scores)## [1] 0.68
length(scores[scores > (61.52 - 2*4.58) & scores < (61.52 + 2*4.58)])/length(scores)## [1] 0.96
length(scores[scores > (61.52 - 3*4.58) & scores < (61.52 + 3*4.58)])/length(scores)## [1] 1
Expect: 68% between 56.94 and 66.1
95% between 52.36 and 70.68
99.7% between 47.78 and 75.26
As we can see, this is the case for our data.
qqnormsim(scores)Given the above qq plot simulations, it doesl look like this data is approximately normally distributed.
((1-0.02)^9)*0.2## [1] 0.1667496
About a 17% chance.
(1-0.02)^100## [1] 0.1326196
About a 13% chance of no failures in batch of 100.
1/0.02## [1] 50
sqrt((1 - 0.02)/(0.02^2))## [1] 49.49747
This is a geometric distribution. Expect about 50 transistors before having had the first defect (standard deviation of: 49.497)
1/0.05## [1] 20
sqrt((1 - 0.05)/(0.05^2))## [1] 19.49359
Expect first defect with 20th (std of 19.49).
Increasing the probability decreases the expected number before first defect and the standard deviation of the expected number before the first defect.
P(boy) = 0.51
3 kids
((3*2)/(2))*((0.51)^2)*(0.49)## [1] 0.382347
About 38% chance of two boys
3/8## [1] 0.375
There would be many more combinations to write out.
P(success) = 0.15
(9*8/2) * ((0.15)^3) * ((0.85)^(7))## [1] 0.03895012
About a 4% chance
Still 15%
As probability of any single event is assumed to be independent, the expected chance of what will occur for a single event is different than what may occur over ten