J

NIH Power Calculations 1

1

Reprinted with permission from the June 28, 1993 WHI Protocol, pages 77-83.



The National Academies | 500 Fifth St. N.W. | Washington, D.C. 20001
Copyright © National Academy of Sciences. All rights reserved.
Terms of Use and Privacy Statement



Below are the first 10 and last 10 pages of uncorrected machine-read text (when available) of this chapter, followed by the top 30 algorithmically extracted key phrases from the chapter as a whole.
Intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text on the opening pages of each chapter. Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages.

Do not use for reproduction, copying, pasting, or reading; exclusively for search engines.

OCR for page 127
An Assessment of the NIH Women's Health Initiative J NIH Power Calculations 1 1 Reprinted with permission from the June 28, 1993 WHI Protocol, pages 77-83.

OCR for page 127
An Assessment of the NIH Women's Health Initiative (i) ERT versus Control: Coronary Heart Disease.   Power (%)   Percentage cases Total sample size Average follow-up (y) Intervention effect (%) Control ERT (or PERT) 20,000 25,000 30,000 6 25 3.26 2.71 50 59 67 30 3.26 2.62 66 76 83 35 3.25 2.49 80 88 93 9 25 5.03 4.16 69 79 86 30 5.02 3.97 85 92 96 35 5.01 3.79 94 98 99 (ia) PERT versus Control: Coronary Heart Disease.   Power (%)   Percentage cases Total sample size Average follow-up (y) Intervention effect (%) Control PERT 20,000 25,000 30,000 6 25 3.26 2.71 48 57 65 30 3.26 2.60 64 74 82 35 3.25 2.49 79 87 92 9 25 5.03 4.16 67 77 84 30 5.02 3.97 84 91 95 35 5.01 3.79 94 97 99 (ii) ERT versus Control: Combined Fractures. (The percentage of cases and the powers in this table are based upon our original age distribution assumptions, i.e., 50-59, 60-69, 70-79 year olds enter in the ratio 2:2:1, and hence are conservative estimates.)   Power (%)   Percentage cases Total sample size Average follow-up (y) Intervention effect (%) Control ERT 20,000 25,000 30,000 6 25 5.84 4.86 79 87 92 30 5.84 4.66 92 96 98 35 5.83 4.46 98 99 >99 9 25 8.85 7.31 94 97 99 30 8.84 6.99 99 >99 >99 35 8.82 6.66 >99 >99 >99

OCR for page 127
An Assessment of the NIH Women's Health Initiative (iia) ERT versus Control: Combined Fractures. (The percentage of cases and the powers in this table are based upon our original age distribution assumptions, i.e., 50-59, 60-69, 70-79 year olds enter in the ratio 2:2:1, and hence are conservative estimates.)   Power (%)   Percentage cases Total sample size Average follow-up (y) Intervention effect (%) Control PERT 20,000 25,000 30,000 6 25 5.84 4.86 77 85 91 30 5.84 4.66 90 95 98 35 5.83 4.46 98 99 >99 9 25 8.85 7.31 93 97 99 30 8.84 6.99 99 >99 >99 35 8.82 6.66 >99 >99 >99 (iii) ERT versus Control: Hip Fractures.   Power (%)   Percentage cases Total sample size Average follow-up (y) Intervention effect (%) Control ERT 20,000 25,000 30,000 6 25 2.34 1.94 41 49 56 30 2.34 1.86 55 65 73 35 2.33 1.77 70 79 86 9 25 3.91 3.22 62 71 79 30 3.90 3.07 78 87 92 35 3.89 2.92 90 95 98 (iiia) PERT versus Control: Hip Fractures.   Power (%)   Percentage cases Total sample size Average follow-up (y) Intervention effect (%) Control PERT 20,000 25,000 30,000 6 25 2.34 1.94 39 47 54 30 2.34 1.86 54 63 71 35 2.33 1.77 68 77 84 9 25 3.91 3.22 60 69 77 30 3.90 3.07 76 85 91 35 3.89 2.92 88 94 97

OCR for page 127
An Assessment of the NIH Women's Health Initiative (iv) ERT versus Control: Breast Cancer.   Power (%)   Percentage Cases Total Sample Size Average follow-up (y) Increase due to ERT (%) Control ERT 20,000 25,000 30,000 6 20 2.07 2.25 13 15 17 30 2.08 2.35 23 28 32 9 20 3.04 3.40 27 33 38 30 3.05 3.60 52 61 69 14 20 4.5 5.17 52 62 70 30 4.53 5.54 85 92 96 (iva) PERT versus Control: Breast Cancer.   Power (%)   Percentage Cases Total Sample Size Average follow-up (y) Increase due to PERT (%) Control 20,000 ERT 25,000 30,000 6 20 2.07 2.25 12 14 16 30 2.08 2.35 22 27 31 9 20 3.04 3.40 26 32 37 30 3.05 3.60 50 60 67 14 20 4.50 5.17 51 60 68 30 4.53 5.54 83 91 95

OCR for page 127
An Assessment of the NIH Women's Health Initiative (i) Dietary Modification: Breast Cancer.   Power (%)   Percentage of cases Sample size Average follow-up (y) Intervention effect (%) Control Intervention 42,000 48,000 54,000 6 11 2.05 1.89 25 28 31 12 2.05 1.87 32 35 39 14 2.05 1.85 39 44 48 9 11 2.92 2.61 58 63 69 12 2.92 2.57 70 75 80 14 2.92 2.52 81 86 89 (ii) Dietary Modification: Colorectal Cancer.   Power (%)   Percentage of cases Sample size Average follow-up (y) Intervention effect (%) Control Intervention 42,000 48,000 54,000 6 18 1.07 0.93 33 37 41 20 1.07 0.92 40 45 49 22 1.07 0.91 47 52 57 9 18 1.61 1.32 77 83 87 20 1.61 1.29 86 90 93 22 1.60 1.25 92 95 97 (iii) Dietary Modification: Coronary Heart Disease.   Power (%)   Percentage of cases Sample size Average follow-up (y) Intervention effect Control Intervention 42,000 48,000 54,000 6 11 3.04 2.72 48 53 58 12 3.03 2.67 58 64 69 14 3.02 2.63 68 74 79 9 11 4.62 4.15 62 67 72 12 4.60 4.08 72 78 83 14 4.58 4.00 82 86 90

OCR for page 127
An Assessment of the NIH Women's Health Initiative (i) Calcium/Vitamin D versus Control: Hip Fractures   Power (%)   Percentage cases Total sample size Average Follow-up (y) Intervention effect (%) Control ERT (or PERT) 20,000 25,000 30,000 5 25 1.88 1.58 53 67 78   30 1.88 1.51 69 83 91   35 1.88 1.45 83 93 97 8 25 3.35 2.76 81 92 97   30 3.34 2.64 93 98 >99   35 3.34 2.51 98 >99 >99 (ii) Calcium/Vitamin D versus Control: Combined Fractures (The percentages of cases and powers in this table are based upon our original age distribution assumptions i.e., 50-59, 60-69, 70-79 year olds enter in the ratio 2.2.1 and hence are conservative estimates.)   Power (%)   Percentage cases Total sample size Average Follow-up (y) Intervention effect (%) Control Calcium/ Vitamin D 25,000 35,000 45,000 5 25 4.84 4.07 90 97 99   30 4.84 3.91 98 >99 >99   35 4.83 3.75 >99 >99 >99 8 25 7.85 6.49 99 >99 >99   30 7.83 6.20 >99 >99 >99   35 7.82 5.91 >99 >99 >99 (iii) Calcium/Vitamin D versus Control: Colorectal Cancer   Power (%)   Percentage cases Total sample size Average Follow-up (y) Intervention effect (%) Control Calcium/ Vitamin D 25,000 35,000 45,000 5 18 0.86 0.76 17 23 28   20 0.86 0.75 20 27 33   22 0.86 0.74 24 31 38 8 25 1.42 1.17 52 66 77   30 1.42 1.15 60 75 85   35 1.42 1.12 69 83 91