Jones and Nachtsheim · 2011

A Class of Three-Level Designs for Definitive Screening in the Presence of Second-Order Effects

Matches
Very close
Differs

Factorial gives most of the paper's answers. Where they differ, this page says why: some are misprints in the paper.

Show the numbers

Examples

Each example, and how closely Factorial gives its answers.

A definitive screening design in six factors with a simulated response: its main-effect variances, efficiency and the AICc of three modelsExample · pp. 3-4, 12-13Matches
The definitive screening design in 4 factors and 9 runs, the best of 10,000 random starts of the authors' algorithmDesign · pp. 5-12Matches
The definitive screening design in 5 factors and 11 runs, the best of 10,000 random starts of the authors' algorithmDesign · pp. 5-12Differs
The definitive screening design in 6 factors and 13 runs, the best of 10,000 random starts of the authors' algorithmDesign · pp. 5-12Very close
The definitive screening design in 7 factors and 15 runs, the best of 10,000 random starts of the authors' algorithmDesign · pp. 5-12Differs
The definitive screening design in 8 factors and 17 runs, the best of 10,000 random starts of the authors' algorithmDesign · pp. 5-12Very close
The definitive screening design in 9 factors and 19 runs, the best of 10,000 random starts of the authors' algorithmDesign · pp. 5-12Differs
The definitive screening design in 10 factors and 21 runs, the best of 10,000 random starts of the authors' algorithmDesign · pp. 5-12Matches
The definitive screening design in 11 factors and 23 runs, the best of 10,000 random starts of the authors' algorithmDesign · pp. 5-12Differs
The definitive screening design in 12 factors and 25 runs, the best of 10,000 random starts of the authors' algorithmDesign · pp. 5-12Differs

Misprints

Misprints found in the paper, by page. Each shows what the paper prints and what its own data give.

Estimate correlation: mean |r| of a square and an interaction in its factorp. 8
Book 0.065Data 0.109
The projection onto x1, x2 and x3 gives other correlations. The printed row is that of another of the 84 projections onto three factors: 32 of them give its six numbers, the first x1, x2 and x8.
Estimate correlation: max |r| of a square and an interaction in its factorp. 8
Book 0.152Data 0.216
The projection onto x1, x2 and x3 gives other correlations. The printed row is that of another of the 84 projections onto three factors: 32 of them give its six numbers, the first x1, x2 and x8.
Estimate correlation: mean |r| of a square and an interaction without itp. 8
Book 0.334Data 0.375
The projection onto x1, x2 and x3 gives other correlations. The printed row is that of another of the 84 projections onto three factors: 32 of them give its six numbers, the first x1, x2 and x8.
Estimate correlation: max |r| of a square and an interaction without itp. 8
Book 0.396Data 0.393
The projection onto x1, x2 and x3 gives other correlations. The printed row is that of another of the 84 projections onto three factors: 32 of them give its six numbers, the first x1, x2 and x8.
Estimate correlation: mean |r| of two interactionsp. 8
Book 0.144Data 0.140
The projection onto x1, x2 and x3 gives other correlations. The printed row is that of another of the 84 projections onto three factors: 32 of them give its six numbers, the first x1, x2 and x8.

Show the rest

Estimate correlation: max |r| of two interactionsp. 8
Book 0.298Data 0.351
The projection onto x1, x2 and x3 gives other correlations. The printed row is that of another of the 84 projections onto three factors: 32 of them give its six numbers, the first x1, x2 and x8.
Estimate correlation: mean |r| of a square and an interaction in its factorp. 8
Book 0.087Data 0.111
The projection onto x1, x2 and x3 gives other correlations. The printed row is that of another of the 165 projections onto three factors: 54 of them give its six numbers, the first x1, x3 and x5.
Estimate correlation: max |r| of a square and an interaction in its factorp. 8
Book 0.087Data 0.180
The projection onto x1, x2 and x3 gives other correlations. The printed row is that of another of the 165 projections onto three factors: 54 of them give its six numbers, the first x1, x3 and x5.
Estimate correlation: mean |r| of a square and an interaction without itp. 8
Book 0.284Data 0.352
The projection onto x1, x2 and x3 gives other correlations. The printed row is that of another of the 165 projections onto three factors: 54 of them give its six numbers, the first x1, x3 and x5.
Estimate correlation: max |r| of a square and an interaction without itp. 8
Book 0.284Data 0.365
The projection onto x1, x2 and x3 gives other correlations. The printed row is that of another of the 165 projections onto three factors: 54 of them give its six numbers, the first x1, x3 and x5.
Estimate correlation: mean |r| of two interactionsp. 8
Book 0.022Data 0.232
The projection onto x1, x2 and x3 gives other correlations. The printed row is that of another of the 165 projections onto three factors: 54 of them give its six numbers, the first x1, x3 and x5.
Estimate correlation: max |r| of two interactionsp. 8
Book 0.022Data 0.298
The projection onto x1, x2 and x3 gives other correlations. The printed row is that of another of the 165 projections onto three factors: 54 of them give its six numbers, the first x1, x3 and x5.