This preview shows page 1. Sign up to view the full content.
Unformatted text preview: 318 Conﬁdence Interval: Test Statistic: estimator (table value)(standard error) £
¡
DIFFERENCES Method of Analysis : do a onesample “t” ON THE Assumptions: Differences appr. Normally dist. Last Time : PairedDifference Experiments Chpts 7, 8, 9 Wednesday : Systematic approach to material in problems on syllabus! 9.60, 9.97, 9.100, 9.107 and rest of Chpt 9 For Tuesday : Exer. 9.46, 9.52–54, 9.56, 9.59, Today : p. 402 – 406 Wins Lottery”? Thought: Why don’t you ever see the headline ”Psychic STA 2023 c D.Wackerly  Lecture 23 ¡ ¢ £
¨© ¤
¦
§¥
©
¨©
© Basic Statistics Paired SE Mean
8.98
6.79
3.43
95% CI for mean difference : (1.39, 19.01)
TTest of mean difference = 0 (vs > 0): TValue = 2.98 Paired T for Before  After
N
Mean
StDev
Before
6
166.27
22.00
After
6
156.07
16.64
Difference 6
10.20
8.39 Click OK, OK. value 319 PValue=0.015 Choose alternative (Greater than in this case), null Click Options, type in conﬁdence level (for CI) Variable 2. (After in this case) Click in box labelled ”Second”, double click on Variable 1 (Before in this case). Click in box labelled ”First”, double click on Stat Punch in data values Minitab? STA 2023 c D.Wackerly  Lecture 23
¡ male managers, ¢ ¡ of females managers married. of the male female managers 320 ¢ ¢ ©
©
¢ (Male = “1”, Female = “2”). female managers who are married. Find a 95% CI for difference in proportions of male and managers married, § from Fortune 500 corporations. women. £ Ex. # 9.54, p. 407 Managerial careers of men and ¨ ¢ £¤
¥¦
¢ attribute
attribute from pop 2, from pop 1, Independent samples: Pop 2 Pop 1 Have: Two populations Independent Samples (p.402) Comparing Two Population Proportions STA 2023 c D.Wackerly  Lecture 23
§ ¢ # # with attribute estimates estimates estimates # with attribute (p. 402)
(p. 402)
is approx. normally dist’d when both
are large. (p. 402) ©
! ©
! © ©
¤
© ©
" ©
" © ¢
¢
©
¢
¢ ¢
¤ ©
% ¤ ¢ ¢
$
¢
$
¢
¤ STA 2023 c D.Wackerly  Lecture 23 ’s 321 estimator formula sheet (P. 403) ¢ table CI for standard errors
formula sheet male managers, £ ¢ ¡ of the male female managers 322 of females managers married. ¥¦ (Male = “1”, Female = “2”). ©
©
¢ ¢ ¢
¢
¥¦
¨
¢ female managers who are married. Find a 95% CI for difference in proportions of male and managers married, § from Fortune 500 corporations. women. ¨ ¢ § £¤ Ex. # 9.54, p. 407 Managerial careers of men and ©
¡¦ Large Sample ¤ STA 2023 c D.Wackerly  Lecture 23 ©
¨ ¡ £ ¢
©
¨
¤ ©
¥ $ ©
¦
%
¡ ¢
£ Conﬁdence interval: STA 2023 c D.Wackerly  Lecture 23 conﬁdence level , the proportion of male and female managers who are married by between managers who are married exceeds the proportion of At the £ § © ¢ ¡ ¢
¢ ¢
§ ¢
©
¤
¡ ¢
§ $© ¢
©
£
¢
¢
£¤ #$ ¢
©
% !
" $ ©
¢
©
¢
$ ©
¢
% 323 versus OR OR RR or larger score (tail area) smaller score pvalue a ﬁxed particular value of difference Consider testing (p. 404) 324 hypothesized value on formula sheet. standard error total sample size total # “S” in experiment with , estimate this , use the individual ’s
, then 325 NULL HYPOTHESIS standard error COMMON value of If If Formula Sheet estimator TEST STATISTIC STA 2023 c D.Wackerly  Lecture 23 STA 2023 c D.Wackerly  Lecture 23 ¦ ¡ ¤ ¥ ¢¦ ¤ ¤ # ¤ ¤ ¢£ ¡ ¢ ¥ ¥ ¥ ¥ # # # ¥ ¤
¤ ¤
¥
¤
¤
¨§£ ¤
¢
# ¥
¢ ¢
¥
¢¦
# ©
¤
¢
¢
%
% §
¢
$ ¢ $
§
¤
¢ ©©
% ©
§
% ¢
¥
# $
¤
©©
©© 326 Use of true prop. of premi’s given inositol with eye on standard diet had eye injuries. compensate for poorly developed lungs Is ? tail test, eye injuries RR : true prop. of premi’s not given inositol with injuries (2) (1) premature infants given inositol had an eye injury to to high oxygen levels used to of . reduce the risk of eye damage in premature infants? Test Statistic STA 2023 c D.Wackerly  Lecture 23 level, there Pvalue : Lower tail test – oxygen levels for infants given inositol. of premature infants with eye injury due to high pvalue 327 evidence to claim a lower proportion Decision : at the Ex. : # 9.107, p. 431 Does inositol (found in breast milk) £¡ ¨ ¥ ¢ ¢ ¦ ¢ ¢£ ¡
¡ ¢ # ¢ ¢ ¢ ¤
¢ ¤
¢
$ STA 2023 c D.Wackerly  Lecture 23
¢ % % ¢ ¡
¢ ¢ ¢
¢
¢
¨
¢
¢¤
§
¢ ¤ ¢ #
% ¥
¤
value larger than – Claim – Claim – ? ? ? signiﬁcantly lower for any
¥ , claim a lower proportion with breathing irregs if given inositol. Not ¢ For any ¢ ¢ ¢ ¢ 328 Stat Basic Statistics 329 Click in box ”Use pooled estimate for p for test”. Choose alternative (Less than in Ex 9.107) Click ”Options” type in # successes (29 in Ex 9.107). trials (110 in Ex 9.107), in box labelled ”Successes” ”Second Sample” in box labelled ”Trial”, type in # of type in # successes (14 in Ex 9.107). trials (110 in Ex 9.107), in box labelled ”Successes” ”First Sample” in box labelled ”Trial”, type in # of Click Radio button “Summarized data” 2Proportions Minitab? STA 2023 c D.Wackerly  Lecture 23 X
14
29 N
110
110 Sample p
0.127273
0.263636
Estimate for p(1)  p(2) : 0.136364
95% CI for p(1)  p(2): (0.239604, 0.0331235)
Test for p(1)  p(2) = 0 (vs < 0) : Z = 2.55
P=0.005 Sample
1
2 Test and Confidence Interval for Two Proportions Click OK, OK
¢ STA 2023 c D.Wackerly  Lecture 23 ¢
samples from? or
or (c) Hypothesis Test (reach a decision) (b) Conﬁdence Interval (a) Find Sample Size(s) 3. What is the OBJECTIVE of the exercise? (b) 2 Populations : (a) 1 Population : 2. What is the PARAMETER if interest? (c) More than 2 (STA3024) (b) (a) . with conﬁdence units standard error
table formula sheet estimator form. sheet table value (b) Conﬁdence Interval with conﬁdence coefﬁcient
Estimate to within ¤ 1. How many POPULATIONS have I taken (will I take) £ (a) Sample Size
§
¤ §
Systematic Approach to Chapters 7, 8, 9 4. How to proceed? acquired by age 18. Albert Einstein small S.S. large S.S. Thought: Common sense is the collection of prejudices
¤ STA 2023 c D.Wackerly  Lecture 24 330 § STA 2023 c D.Wackerly  Lecture 24 331 std. error
form. sheet §
¡
¡ §
¡
¡ ¤
¢
Parameter OR “something” OR “something” “something” “something” – How about sample(s) Test Statistic Param Param Param What am I “trying to prove”? : i. Large ( ) or small ( )? ii. Independent or Paired? 332 Large Sample(s) STA 2023 c D.Wackerly  Lecture 24 estimator hypothesized value standard error Param Param Param “something” OR “something” OR “something” Hypothesized Value from NULL HYPOTH. or Estimator and Stand. Error from Form. Sheet ¢ (c) Hypothesis Testing ¢ ¡ ¤
¦ ¡ ¤ STA 2023 c D.Wackerly  Lecture 24 £¥£¡£¡£¡¤¡£¡£¡£¡¢ ¡
¢ ¨¨ ¨
¢
£ ¥ §
¤ £¥£¡¤¡£¡£¡£¡£¡£¡£¡¤¡£¡¢ ¡
£¦£¡£¡£¡£¡£¡£¡£¡£¡£¡£¡¡ £¦£¡£¡£¡£¡£¡£¡£¡¡
¥ ¢¦ ¥ ¥
¤ ¤ ¢¦ §
¤
¤
¡ §§ 333 RR ££¡¤¡£¡£¡£¡£¡£¡£¡¤¡£¡¡ ©
££¡£¡£¡£¡£¡£¡£¡£¡£¡£¡¡ ¢
£ Param Param Param , not ¡ ¡ OR “something” OR “something” the calculated value of “something” . 2. Independent Samples (assuming 1. ¡ Small Sample(s) ¨ # d.f. calc ) (tail area) calc Calculate DIFFERENCES for all pair 3. Paired Samples £¥£¡¤¡£¡£¡£¡£¡£¡¢ ¡ £¦£¡£¡£¡¤¡£¡£¡£¡¡ ¢ ¤ ¥ ¢¦
Pvalues : calc differences. Use onesamp. proc. to analyse the ¡ ¢
¤
¨
% §£
%
¤
¥
¤ pvalue known. 2. Use if
“large” unknown 1. Use if “small” 5. Use for CI or tests : Large Samples 4. Use for test 3. Use for CI
. Formula Sheet STA 2023 c D.Wackerly  Lecture 24
¤
¦ 8. Use to test 7. Use for CI or test 6. Use for CI or tests : Small Samples ¦ ¡ ¡
¡ ££¡¤¡£¡£¡£¡£¡£¡¡ © #
#
¡ ¡
££¡£¡£¡¤¡£¡£¡£¡¡ ¨ ¢
¦
¤ £
334 ¢ STA 2023 c D.Wackerly  Lecture 24 335 Use “system” for several examples from text. STA 2023 c D.Wackerly  Lecture 24 336 ...
View
Full
Document
This note was uploaded on 07/28/2011 for the course STA 2023 taught by Professor Ripol during the Fall '08 term at University of Florida.
 Fall '08
 Ripol
 Statistics, Standard Error

Click to edit the document details