Index

  • a
  • Air freshener project
    • screening experiment plan  24–37
    • statistical analyses plan  37–55
  • Akaike Information Criteria (AIC)  283
  • Alternative hypothesis  18
  • Analysis Of VAriance (ANOVA)  45–46
    • model assumptions for  46
  • “Appropriateness”  94–97
  • b
  • Bar Charts  266–267
  • Binary logistic model  291, 292
  • Binary logistic regression model  277–284, 288–289
  • Blocking  26, 28–29
  • Box‐Behnken design  139, 147–150
  • Boxplots  12–13
  • c
  • Central composite designs (CCDs)  137, 142–144
    • face‐centered  145–147
  • Central tendency  41
    • fragrances  96
    • measures  7–8
  • Chi‐square test  269–270
  • Coded coefficients  160–161
  • Coded units  51
  • Coefficient of determination  239
  • Coefficient of variation  11
  • Condom project
    • formulations  73
    • means between two groups compare  81–85
    • two proportions test  85–92
    • two‐sample hypothesis test  73
    • variability between two groups compare  74–81
    • variable settings  73
  • Confidence interval (CI)  15–17, 231–232
  • Confidence level  17
  • Consumer voice  257
    • design of experiments‐top score project  284–291
    • “Top‐Two Box” project  259–284
  • Contingency table. See Cross tabulations
  • Contour plots  165–166, 209–210, 212, 232, 234
  • Correlation analysis  218–219
  • Correlation coefficients  215–224
  • Cross tabulations  264–265
  • d
  • Dependent variables  234
  • Descriptive analysis  4–5
  • Design of experiments(DOE)‐top score project
    • binary logistic regression model  288–289
    • binary response variable stratifying by formulations  286–288
    • factorial design  284–285
    • reduce the model  290–291
    • statistical analyses  285–291
    • variables setting  285
  • Deviations  10
  • “Difference:A_B”  98–100
  • Dyspepsia
    • contour plots  234
    • p‐value  231
  • e
  • Experiments  24–25
  • Explanatory variables  234
  • Extreme vertices design
    • with lower and upper limits for components  187–195
    • with linear constraints for components  195–198
  • f
  • Face‐centered design  139
  • Factorial designs  26–27
    • basic principles of  28–30
  • Factors  24–25
  • Fixed batch factor
    • data collection worksheet  244–245
    • predict response values  249–250
    • shelf life estimate  245–249
  • Fragrance Project  58
    • aims  93
    • “Appropriateness”  94–97
    • “Difference:A_B”  98–100
    • paired t‐test  100–103
    • variables setting  93
  • Frequency distributions  5
  • g
  • Gastroesophageal reflux disease (GERD)  213
    • correlation coefficients  215–224
    • dyspepsia  215
    • heartburn  215
    • multicenter randomized pilot study  215
    • multiple linear regression  224–226, 232–243
    • predict response values  231–232
    • quantitative variables evaluation  215–243
    • reduce the model  226–231
    • regurgitation  215
    • scatterplot  215–224
    • scores  215
  • General factorial design  110
  • GERD. See Gastroesophageal reflux disease (GERD)
  • Goodness of fit  239–240
  • Graphic techniques  165, 209
  • h
  • Heartburn
    • contour plots  234
    • prediction for  232
  • Histograms  13
  • Hypothesis tests  18–19
  • i
  • Independent  28
  • Independent predictors  234
  • Inferential analysis  4–5, 13
  • Inferential problems  14–15
  • Intercept  51
  • Interquartile range (IQR)  9
  • m
  • Mean  7
  • Median  7
  • Mixture designs
    • components  167
    • designed factor level combinations  199
    • experimental design  167–199
    • linear constraints  195–198
    • lower and upper limits for components  187–195
    • lower limits for components  175–178
    • mixture‐amount experiment  181–183
    • mixture‐process variable experiment  178–181
    • response optimization  207–209
    • response surface and locate the optimum  209–212
    • response variables  200–202
    • second‐order model  202–207
    • simple mixture experiment  167–175, 183–187
    • statistical analyses  199–200
    • variables setting  200
  • Mixture experiment  167, 170–173
  • Mixture models  199
  • Mix‐Up Project
    • components  167
    • designed factor level combinations  199
    • experimental design  167–199
    • linear constraints  195–198
    • lower and upper limits for components  187–195
    • lower limits for components  175–178
    • mixture‐amount experiment  181–183
    • mixture‐process variable experiment  178–181
    • response optimization  207–209
    • response surface and locate the optimum  209–212
    • response variables  200–202
    • second‐order model  202–207
    • simple mixture experiment  167–175, 183–187
    • statistical analyses  199–200
    • variables setting  200
  • Multi‐factor ANOVA  45
  • Multiple linear regression model  224–226, 243
  • n
  • Non‐central tendency  41
    • fragrances  96
    • measures  8
  • Normal distribution  54, 241
  • Normal probability plots  242
  • Null hypothesis  18
  • Numeric variable  2
  • o
  • Observations  28
  • Odds ratios  279–283
  • One‐way ANOVA  45
  • Optimal design  192, 193
  • Overlaid plots  165–166, 209–210, 232
  • p
  • Paired t‐test  100–103
  • Pareto chart  43
  • Pearson correlation. See Correlation coefficients
  • Pie Charts  266–267
  • Point estimate  15–16
  • Polymer Project
    • Box‐Behnken Design  147–150
    • central composite designs  139–144
    • experimental design  139–150
    • face‐centered CCD  145–147
    • product's elasticity  138
    • reduce the model  157–161
    • response optimization  162–164
    • response surface and locate the optimum  165–166
    • response variables  150, 151–153
    • second‐order model  138, 153–157
    • statistical analysis  150
    • variables setting  151
  • Population parameters estimation  15–17
  • Prediction interval (PI)  232
  • Product validation  213
  • p‐value  19–20, 44, 159
  • q
  • Quantiles  8
  • Quantitative variable  2, 80, 83
  • Quartiles  8
  • r
  • Random  3
  • Random batch factor
    • data collection worksheet  250–251
    • shelf life estimate  252–256
    • stability studies  250
  • Randomization  28, 54
  • Randomized complete block design (RCBD)  28–29
  • Random samples  54
  • Range  9
  • Regression analysis  218–219
  • Regression equation  229–230
  • Regression model  51, 234–235
  • Regurgitation
    • contour plots  234
    • p‐value  231
  • Replication  29–30
  • Residuals  239
    • analysis  54–55, 240–242
    • vs. fitted values plots  242
    • vs. order plots  241
  • Response surface designs
    • Box‐Behnken Design  147–150
    • central composite designs  139–144
    • experimental design  139–150
    • face‐centered CCD  145–147
    • product's elasticity  138
    • reduce the model  157–161
    • response optimization  162–164
    • response surface and locate the optimum  165–166
    • response variables  150, 151–153
    • second‐order model  138, 153–157
    • statistical analysis  150
    • variables setting  151
  • Response surface model  110, 114–118
  • Response variables  24–25, 111–114, 234
  • R‐squared  49–50
  • R‐squared (R‐sq, R2)  49–50, 121, 160, 205, 228
  • s
  • Sample  3
  • Scatterplot  215–224
  • Scatterplot of thickness
    • vs. CEW  236–238
  • Screening experiment  24–37
    • alternately, choose the desired fractional design  32–33
    • assign the designed factor level combinations to the experimental units  33–37
    • collect data for the response variable  33–37
    • create a full factorial design  30–32
  • Shapes of data distributions  5–6
    • for quantitative variables  6–7
  • Simple linear regression models  236–239
  • Simplex centroid design  174
    • create  167–175
    • mixture‐amount experiment  181–183
    • mixture‐process variable experiment  178–181
    • simple mixture experiment with lower limits for components  175–178
  • Simplex lattice design  167
    • simple mixture experiment  183–187
  • Spearman rank correlation  274–276
  • Stain Removal Project  58
    • aims  104
    • general factorial experiment  104–109
    • reduce the model  118–125
    • response optimization  125–130
    • response surface and locate the optimum  130–136
    • response surface model  114–118
    • response variables  111–114
    • statistical analysis  110–111
  • Standard deviation  10–11
  • Statistical analyses  37–55
  • Statistical unit  3
  • Statistical variables  2–3
  • Surface plots  165–166, 209–210, 232, 234
  • t
  • Throat Care project
    • aims  59
    • mean to a specified value compare  60–66
    • one‐sample hypothesis test  59–60
    • proportion to a specified value compare  67–72
    • variable settings  60
  • “Top‐Two Box” project
    • binary logistic regression model  277–284
    • χ2 test  267–270
    • satisfaction scores by product  260–267
    • variable “Satisfaction”  271–277
    • variables setting  259
  • Two‐level factorial designs  25, 27
  • Two proportions test  91–92
  • Two‐sample inferential problems  79–80
  • Two‐sample t‐test  83–84
  • Two variances test  80–81
  • Two‐way table. See Cross tabulations
  • u
  • Uncoded units  51
  • v
  • Variability  9, 41
    • fragrances  97
  • Variance  10–11
..................Content has been hidden....................

You can't read the all page of ebook, please click here login for view all page.
Reset