lecture 15, 16, 17

Question 1

Large sample about population proportion

Answer 1

case 1: Ho: p=p0 vs Ha: p<p0 (reject H0 if z<-za)
case 2: H0: p=p0 vs Ha: p>p0 (reject H0 if z>za)
case 3: H0: p=p0 vs Ha: p (not=) p0 (reject H0 if z>za/2)

Question 2

test stat for proportion

Answer 2

z= p(hat)-p/sqrt (pq/n)

Question 3

conditions for large sample test for p

Answer 3

1: a random sample is selected form a binomial population
2: the sample size n is large. this condition will be satisfied if both np0>15 + nq0>15

Question 4

goal of difference of means tests

Answer 4

mean1-mean2=0

Question 5

standard error of statistic

Answer 5

sigma(x1-x2)= sqrt(sigma21/n1 + sigma22/n2)

Question 6

one sided and two sided tests and rejection regions

Answer 6

u1-u2=0 vs u1-u2>0
z>za
u1-u2=0 vs u1-u2<0
z<-za
u1-u2=0 vs u1-u2 (not equal) 0
z>za/2

Question 7

test stat

Answer 7

z=(x1-x2)-Do/ sqrt(s21/n1 + s22/n2)

Question 8

conditions

Answer 8

2 samples are randomly selected in an independent manner from 2 target populations
n1>30 n2>30

Question 9

on calculator

Answer 9

2-SampZtest or Ttest

Question 10

conditions for the pooled sample thing

Answer 10

both populations are normal and sigma1 and sigma2 are equal (creates pooled sample estimator of variance)

Question 11

what is s2p

Answer 11

minimum variance unbiased estimator of variance when variance1 and variance2= standard variation

Question 12

what is pooled sample estimator of variance

Answer 12

simply a weighted average of 2 sample variances with height given each variance proportional to its degrees of freedom (n1+n2-2)

(n1-1)s21 + (n2-1)s22/ n1+n2-2

Question 13

one sided tests and two sided tests for small samples

Answer 13

u1-u2=0 vs u1-u2>0
t>ta
u1-u2=0 vs u1-u2<0
t<-ta
u1-u2=0 vs u1-u2 not equal to 0
t>ta/2

Question 14

calc functions for small sample

Answer 14

2-SampTint for confidence interval
2-SampTtest for p value

Question 15

blocking

Answer 15

making comparisons within groups of similar experimental units

Question 16

conditions for paired difference test?

Answer 16

target population and nd>30

Question 17

is the pair of differences test better than the independent?

Answer 17

most of the time but there is a loss of info but it is offset by the reduction in variability