Millet Bread Acceptance
May
May 23, 2023
- Package
- Data
- Function
- FB + MB: Summary statistics
- Flatbread - phytic acid
- Flatbread - reliability
- Flatbread - drivers of liking
- Flatbread - difference: qualities X f.condition (medium + time) X rate time
- Flatbread - difference: liking X f.condition (medium + time)
- Flatbread - differences, no clip: qualities X f.medium X f.time X rate time
- Flatbread - differences, no clip, liking: f.medium X f.time X rate time
- Flatbread - differences, clip: qualities X f.medium X rate time
- Flatbread - differences, clip, liking: by f.medium
- Flatbread - differences graphs
- Bread - demographics
- Bread - reliability
- Bread - drivers of liking
- Bread - difference: All qualities
- Bread - difference: Overall liking
- Bread - difference: Appearance
- Bread - difference: Color
- Bread - difference: Aroma
- Bread - difference: Texture
- Bread - difference: Flavor
- Bread - difference, graphs: Overall Liking, Unfermented
- Bread - difference, graphs: Overall Liking, Fermented
- Bread - dose response curve: Unfermented vs fermented
- Purchase intent: Chi-square
- Purchase intent: Bar graph
- Purchase intent: Chi-square
- Purchase intent: p(Buy) difference
Package
Data
## `summarise()` has grouped output by 'Participant', 'Ferment.type',
## 'Ferment.days', 'Attribute', 'After'. You can override using the `.groups`
## argument.Function
## Corr function
corrfunc <- function(data, Cor1, Cor2, title) {
ggplot(data = data, aes(x = {{Cor1}}, y = {{Cor2}})) +
geom_jitter()+
geom_smooth(method = lm)+
ggtitle(title) +
stat_cor(method = "pearson") +
theme_light()
}FB + MB: Summary statistics
## Flatbread summary stats
FB.Sum <- FB.Long %>%
select(Attribute, Condition, Rating) %>%
group_by(Condition, Attribute) %>%
get_summary_stats()
FB.Sum## # A tibble: 154 × 15
## Attribute Condit…¹ varia…² n min max median q1 q3 iqr mad
## <chr> <chr> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Astringency 0 None … Rating 24 0 77 9 2.75 25.2 22.5 11.9
## 2 Bitter 0 None … Rating 24 0 55 8.5 0.75 17.2 16.5 12.6
## 3 Liking 0 None … Rating 24 0 64 37 23.8 50 26.2 19.3
## 4 Salty 0 None … Rating 24 0 54 4 1 10.2 9.25 5.93
## 5 Sour 0 None … Rating 24 0 38 4 0.75 7 6.25 4.45
## 6 Sweet 0 None … Rating 24 0 54 5.5 1 9.5 8.5 6.67
## 7 Umami 0 None … Rating 24 0 76 16 4.75 25.8 21 17.0
## 8 Astringency 0 None … Rating 24 0 85 8.5 1 21 20 12.6
## 9 Bitter 0 None … Rating 24 0 59 5.5 0.75 13.2 12.5 8.15
## 10 Liking 0 None … Rating 24 0 64 37 23.8 50 26.2 19.3
## # … with 144 more rows, 4 more variables: mean <dbl>, sd <dbl>, se <dbl>,
## # ci <dbl>, and abbreviated variable names ¹Condition, ²variableFB.Sum.wide <- FB.Sum %>%
select(Attribute, Condition, mean, sd)%>%
pivot_wider(names_from = Attribute, values_from = c(mean, sd))
## Millet bread summary stats
MB.Sum <- MB.Long %>%
select(Attribute, Condition, Rating) %>%
group_by(Condition, Attribute) %>%
get_summary_stats()
MB.Sum## # A tibble: 72 × 15
## Attribute Condition varia…¹ n min max median q1 q3 iqr mad
## <chr> <chr> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Appearance "0% mill… Rating 120 4 9 7 6 8 2 1.48
## 2 Aroma "0% mill… Rating 120 4 9 7 6 8 2 1.48
## 3 Color "0% mill… Rating 120 4 9 7 6 8 2 1.48
## 4 Flavor "0% mill… Rating 120 3 9 7 6 8 2 1.48
## 5 Overall "0% mill… Rating 120 3 9 7 6 8 2 1.48
## 6 Texture "0% mill… Rating 120 4 9 8 7 8 1 1.48
## 7 Appearance "0% mill… Rating 120 2 9 7 6 8 2 1.48
## 8 Aroma "0% mill… Rating 120 4 9 7 6 8 2 1.48
## 9 Color "0% mill… Rating 120 3 9 7 6 8 2 1.48
## 10 Flavor "0% mill… Rating 120 3 9 7 6 8 2 1.48
## # … with 62 more rows, 4 more variables: mean <dbl>, sd <dbl>, se <dbl>,
## # ci <dbl>, and abbreviated variable name ¹variableMB.Sum.wide <- MB.Sum %>%
select(Attribute, Condition, mean, sd) %>%
pivot_wider(names_from = Attribute, values_from = c(mean, sd))Flatbread - phytic acid
## Df Sum Sq Mean Sq F value Pr(>F)
## Condition 4 854623 213656 11.08 0.00107 **
## Residuals 10 192862 19286
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = Phytate ~ Condition, data = PA)
##
## $Condition
## diff lwr upr
## 5% salt water 4 day-5% salt water 2 day -229.70333 -602.88176 143.47509
## None 0 day-5% salt water 2 day 45.91333 -327.26509 419.09176
## Water 2 day-5% salt water 2 day -105.78333 -478.96176 267.39509
## Water 4 day-5% salt water 2 day -619.86000 -993.03842 -246.68158
## None 0 day-5% salt water 4 day 275.61667 -97.56176 648.79509
## Water 2 day-5% salt water 4 day 123.92000 -249.25842 497.09842
## Water 4 day-5% salt water 4 day -390.15667 -763.33509 -16.97824
## Water 2 day-None 0 day -151.69667 -524.87509 221.48176
## Water 4 day-None 0 day -665.77333 -1038.95176 -292.59491
## Water 4 day-Water 2 day -514.07667 -887.25509 -140.89824
## p adj
## 5% salt water 4 day-5% salt water 2 day 0.3208235
## None 0 day-5% salt water 2 day 0.9934223
## Water 2 day-5% salt water 2 day 0.8777774
## Water 4 day-5% salt water 2 day 0.0019754
## None 0 day-5% salt water 4 day 0.1840199
## Water 2 day-5% salt water 4 day 0.8064655
## Water 4 day-5% salt water 4 day 0.0396261
## Water 2 day-None 0 day 0.6761816
## Water 4 day-None 0 day 0.0011451
## Water 4 day-Water 2 day 0.0074802
## `summarise()` has grouped output by 'Condition'. You can override using the
## `.groups` argument.
Flatbread - reliability
FB.re <- FB.raw %>%
pivot_wider(names_from = Rep,
values_from = c(6:18)) %>%
select(5:30)
## Sweet reliability
cor.test(FB.re$Sweet_1, FB.re$Sweet_2)##
## Pearson's product-moment correlation
##
## data: FB.re$Sweet_1 and FB.re$Sweet_2
## t = 7.1893, df = 130, p-value = 4.566e-11
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.3988459 0.6454187
## sample estimates:
## cor
## 0.5333684## Salty reliability
cor.test(FB.re$Salty_1, FB.re$Salty_2)##
## Pearson's product-moment correlation
##
## data: FB.re$Salty_1 and FB.re$Salty_2
## t = 11.424, df = 130, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.6107848 0.7838594
## sample estimates:
## cor
## 0.7077881## Umami reliability
cor.test(FB.re$Umami_1, FB.re$Umami_2)##
## Pearson's product-moment correlation
##
## data: FB.re$Umami_1 and FB.re$Umami_2
## t = 10.277, df = 130, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.5630657 0.7541207
## sample estimates:
## cor
## 0.6695218## Bitter reliability
cor.test(FB.re$Bitter_1, FB.re$Bitter_2)##
## Pearson's product-moment correlation
##
## data: FB.re$Bitter_1 and FB.re$Bitter_2
## t = 6.0308, df = 130, p-value = 1.583e-08
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.3224488 0.5911995
## sample estimates:
## cor
## 0.4675598## Sour reliability
cor.test(FB.re$Sour_1, FB.re$Sour_2)##
## Pearson's product-moment correlation
##
## data: FB.re$Sour_1 and FB.re$Sour_2
## t = 5.8983, df = 130, p-value = 2.993e-08
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.3131931 0.5844615
## sample estimates:
## cor
## 0.4594762## Astringency reliability
cor.test(FB.re$Astringency_1, FB.re$Astringency_2)##
## Pearson's product-moment correlation
##
## data: FB.re$Astringency_1 and FB.re$Astringency_2
## t = 9.521, df = 130, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.5279054 0.7316957
## sample estimates:
## cor
## 0.6409604## After sweet reliability
cor.test(FB.re$After_sweet_1, FB.re$After_sweet_2)##
## Pearson's product-moment correlation
##
## data: FB.re$After_sweet_1 and FB.re$After_sweet_2
## t = 10.419, df = 130, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.5693261 0.7580674
## sample estimates:
## cor
## 0.6745745## After salty reliability
cor.test(FB.re$After_salty_1, FB.re$After_salty_2)##
## Pearson's product-moment correlation
##
## data: FB.re$After_salty_1 and FB.re$After_salty_2
## t = 10.673, df = 130, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.5802766 0.7649377
## sample estimates:
## cor
## 0.6833888## After umami reliability
cor.test(FB.re$After_umami_1, FB.re$After_umami_2)##
## Pearson's product-moment correlation
##
## data: FB.re$After_umami_1 and FB.re$After_umami_2
## t = 9.4876, df = 130, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.526278 0.730647
## sample estimates:
## cor
## 0.6396308## After bitter reliability
cor.test(FB.re$After_bitter_1, FB.re$After_bitter_2)##
## Pearson's product-moment correlation
##
## data: FB.re$After_bitter_1 and FB.re$After_bitter_2
## t = 8.2154, df = 130, p-value = 1.848e-13
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.4596331 0.6868545
## sample estimates:
## cor
## 0.5845925## After sour reliability
cor.test(FB.re$After_sour_1, FB.re$After_sour_2)##
## Pearson's product-moment correlation
##
## data: FB.re$After_sour_1 and FB.re$After_sour_2
## t = 7.0279, df = 130, p-value = 1.06e-10
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.3886917 0.6383526
## sample estimates:
## cor
## 0.5247144## After astringency reliability
cor.test(FB.re$After_astringency_1, FB.re$After_astringency_2)##
## Pearson's product-moment correlation
##
## data: FB.re$After_astringency_1 and FB.re$After_astringency_2
## t = 10.563, df = 130, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.5755905 0.7620028
## sample estimates:
## cor
## 0.6796206## Liking reliability
cor.test(FB.re$Liking_1, FB.re$Liking_2)##
## Pearson's product-moment correlation
##
## data: FB.re$Liking_1 and FB.re$Liking_2
## t = 12.427, df = 130, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.6475050 0.8062154
## sample estimates:
## cor
## 0.7368516Flatbread - drivers of liking
## Corr matrix
FB.cor <- FB.Wide %>%
group_by(Condition) %>%
summarize(Sweet = mean(Sweet), Salty = mean(Salty), Umami = mean(Umami), Bitter = mean(Bitter), Sour = mean(Sour), Astringency = mean(Astringency), Liking = mean(Liking)) %>%
select(!Condition) %>%
cor(.)
corrplot(FB.cor, method = "color", order = "original", tl.col="black") 
## Drivers of liking
FB.driver <- FB.Wide %>%
filter(Ferment.type != "SaltAdded") %>%
group_by(Ferment.type) %>%
summarize(Sweet = mean(Sweet), Salty = mean(Salty), Umami = mean(Umami), Bitter = mean(Bitter), Sour = mean(Sour), Astringency = mean(Astringency), Liking = mean(Liking))Flatbread - difference: qualities X f.condition (medium + time) X rate time
In this section, After = “Yes” means it is an after taste, After = “No” means it is not an after taste.
## Construct a 5 conditions df
FB.5cond.df <- FB.aov.df %>%
filter(Condition != "Brine 0") %>%
convert_as_factor()
## Summary statistics
FB.5cond.df %>%
group_by(Condition, Attribute, After) %>%
filter(Attribute != "Liking") %>%
get_summary_stats()## # A tibble: 60 × 16
## Attribute After Condi…¹ varia…² n min max median q1 q3 iqr
## <fct> <fct> <fct> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Astringency No Brine 2 Rating 12 1 70.5 7.75 2.62 31 28.4
## 2 Astringency Yes Brine 2 Rating 12 0 69 8.5 3.5 29.1 25.6
## 3 Bitter No Brine 2 Rating 12 0 59.5 6.25 1.5 17.6 16.1
## 4 Bitter Yes Brine 2 Rating 12 0 52.5 6.5 0.375 13.6 13.2
## 5 Salty No Brine 2 Rating 12 3.5 65.5 25.5 11.4 37.9 26.5
## 6 Salty Yes Brine 2 Rating 12 0.5 56.5 21.5 9.75 43.5 33.8
## 7 Sour No Brine 2 Rating 12 0 27 3 1.38 10.1 8.75
## 8 Sour Yes Brine 2 Rating 12 0 33 2.75 0.875 10.1 9.25
## 9 Sweet No Brine 2 Rating 12 0 52.5 13.2 4.25 26.5 22.2
## 10 Sweet Yes Brine 2 Rating 12 0 59 12.5 4.12 26.8 22.6
## # … with 50 more rows, 5 more variables: mad <dbl>, mean <dbl>, sd <dbl>,
## # se <dbl>, ci <dbl>, and abbreviated variable names ¹Condition, ²variable## Differences in attributes
## Visualization
FB.5cond.df %>%
filter(Attribute != "Liking") %>%
ggplot(aes(Condition, Rating, color = Attribute)) +
geom_boxplot() +
facet_grid(vars(After), vars(Clip)) +
scale_color_jco() +
theme_bw()
## Repeated measure ANOVA
FB.5cond.df %>%
filter(Attribute != "Liking",
Clip == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Attribute, Condition, After)) ## significant findings: Attribute, Condition, Attribute X Condition, Condition X After ## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Attribute 5 55 6.442 8.88e-05 * 1.00e-01
## 2 Condition 4 44 7.708 8.49e-05 * 5.30e-02
## 3 After 1 11 0.121 7.35e-01 5.02e-05
## 4 Attribute:Condition 20 220 3.843 3.16e-07 * 7.30e-02
## 5 Attribute:After 5 55 2.119 7.70e-02 1.00e-03
## 6 Condition:After 4 44 3.702 1.10e-02 * 3.00e-03
## 7 Attribute:Condition:After 20 220 1.037 4.20e-01 3.00e-03
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Attribute 0.168 0.323
## 2 Condition 0.393 0.469
## 3 Attribute:After 0.128 0.196
## 4 Condition:After 0.236 0.147
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Attribute 0.630 3.15, 34.64 0.001000 * 0.912 4.56, 50.15
## 2 Condition 0.661 2.64, 29.09 0.000917 * 0.890 3.56, 39.15
## 3 Attribute:After 0.625 3.12, 34.37 0.114000 0.901 4.51, 49.57
## 4 Condition:After 0.693 2.77, 30.48 0.025000 * 0.949 3.8, 41.78
## p[HF] p[HF]<.05
## 1 0.000164 *
## 2 0.000183 *
## 3 0.085000
## 4 0.013000 * ## Posthoc - effect of Condition (medium + time) for each Attribute
PH.CxAtt.aov <- FB.5cond.df %>%
filter(Attribute != "Liking", Clip == "No") %>%
select(! After) %>%
group_by(Participant, Attribute, Condition) %>%
summarize(Rating = mean(Rating)) %>%
group_by(Attribute) %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Condition))## `summarise()` has grouped output by 'Participant', 'Attribute'. You can
## override using the `.groups` argument. get_anova_table(PH.CxAtt.aov)## # A tibble: 6 × 8
## Attribute Effect DFn DFd F p `p<.05` ges
## <fct> <chr> <dbl> <dbl> <dbl> <dbl> <chr> <dbl>
## 1 Astringency Condition 1.76 19.4 4.30 0.032 "*" 0.083
## 2 Bitter Condition 4 44 8.97 0.0000218 "*" 0.169
## 3 Salty Condition 2.09 23.0 8.45 0.002 "*" 0.257
## 4 Sour Condition 4 44 5.81 0.000761 "*" 0.175
## 5 Sweet Condition 4 44 2.92 0.031 "*" 0.068
## 6 Umami Condition 4 44 2.02 0.109 "" 0.067 ## Posthoc - effect of Condition (medium + time) on after taste
PH.CxAta.aov <- FB.5cond.df %>%
filter(Attribute != "Liking", Clip == "No") %>%
select(! Attribute) %>%
group_by(Participant, After, Condition) %>%
summarize(Rating = mean(Rating)) %>%
group_by(After) %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Condition))## `summarise()` has grouped output by 'Participant', 'After'. You can override
## using the `.groups` argument. get_anova_table(PH.CxAta.aov)## # A tibble: 2 × 8
## After Effect DFn DFd F p `p<.05` ges
## <fct> <chr> <dbl> <dbl> <dbl> <dbl> <chr> <dbl>
## 1 No Condition 4 44 7.26 0.000141 * 0.095
## 2 Yes Condition 4 44 7.32 0.000131 * 0.102 ## Posthoc - across Attribute
FB.5cond.df %>%
filter(Attribute != "Liking") %>%
filter(Clip == "No") %>%
dunn_test(Rating ~ Attribute)## # A tibble: 15 × 9
## .y. group1 group2 n1 n2 statistic p p.adj p.adj.sig…¹
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <chr>
## 1 Rating Astringency Bitter 120 120 -1.16 2.45e- 1 9.67e- 1 ns
## 2 Rating Astringency Salty 120 120 -1.80 7.23e- 2 4.60e- 1 ns
## 3 Rating Astringency Sour 120 120 -3.64 2.75e- 4 3.02e- 3 **
## 4 Rating Astringency Sweet 120 120 -2.47 1.36e- 2 1.20e- 1 ns
## 5 Rating Astringency Umami 120 120 3.07 2.14e- 3 2.14e- 2 *
## 6 Rating Bitter Salty 120 120 -0.635 5.26e- 1 1 e+ 0 ns
## 7 Rating Bitter Sour 120 120 -2.48 1.33e- 2 1.20e- 1 ns
## 8 Rating Bitter Sweet 120 120 -1.30 1.92e- 1 9.60e- 1 ns
## 9 Rating Bitter Umami 120 120 4.23 2.30e- 5 2.76e- 4 ***
## 10 Rating Salty Sour 120 120 -1.84 6.57e- 2 4.60e- 1 ns
## 11 Rating Salty Sweet 120 120 -0.670 5.03e- 1 1 e+ 0 ns
## 12 Rating Salty Umami 120 120 4.87 1.13e- 6 1.47e- 5 ****
## 13 Rating Sour Sweet 120 120 1.17 2.42e- 1 9.67e- 1 ns
## 14 Rating Sour Umami 120 120 6.71 1.96e-11 2.95e-10 ****
## 15 Rating Sweet Umami 120 120 5.54 3.06e- 8 4.28e- 7 ****
## # … with abbreviated variable name ¹p.adj.signif ## Posthoc - across Condition
FB.5cond.df %>%
filter(Attribute != "Liking") %>%
filter (Clip == "No") %>%
dunn_test(Rating ~ Condition)## # A tibble: 10 × 9
## .y. group1 group2 n1 n2 statistic p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <chr>
## 1 Rating Brine 2 Brine 4 144 144 1.19 0.233 0.930 ns
## 2 Rating Brine 2 Water 0 144 144 -2.76 0.00584 0.0467 *
## 3 Rating Brine 2 Water 2 144 144 -1.00 0.316 0.930 ns
## 4 Rating Brine 2 Water 4 144 144 1.14 0.254 0.930 ns
## 5 Rating Brine 4 Water 0 144 144 -3.95 0.0000780 0.000780 ***
## 6 Rating Brine 4 Water 2 144 144 -2.20 0.0281 0.197 ns
## 7 Rating Brine 4 Water 4 144 144 -0.0539 0.957 0.957 ns
## 8 Rating Water 0 Water 2 144 144 1.75 0.0793 0.397 ns
## 9 Rating Water 0 Water 4 144 144 3.90 0.0000976 0.000878 ***
## 10 Rating Water 2 Water 4 144 144 2.14 0.0322 0.197 nsFlatbread - difference: liking X f.condition (medium + time)
## Construct a 5 conditions df
FB.5cond.df <- FB.aov.df %>%
filter(Condition != "Brine 0")
## Summary statistics
FB.5cond.df %>%
filter(Attribute == "Liking") %>%
group_by(Condition, Attribute) %>%
get_summary_stats()## # A tibble: 5 × 15
## Attri…¹ Condi…² varia…³ n min max median q1 q3 iqr mad mean
## <fct> <fct> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Liking Brine 2 Rating 24 16 73.5 46.5 32.9 63.4 30.5 23.7 46.7
## 2 Liking Brine 4 Rating 48 3.5 83.5 42.2 27.4 51 23.6 18.5 40.1
## 3 Liking Water 0 Rating 24 4.5 57 36.2 26.8 45.5 18.8 15.2 34.8
## 4 Liking Water 2 Rating 24 2.5 53.5 28 25 40.9 15.9 8.15 31.2
## 5 Liking Water 4 Rating 48 1 95.5 18 6.38 28.9 22.5 18.2 21.6
## # … with 3 more variables: sd <dbl>, se <dbl>, ci <dbl>, and abbreviated
## # variable names ¹Attribute, ²Condition, ³variable## Differences in Liking
## Visualization
FB.5cond.df %>%
filter(Attribute == "Liking") %>%
ggplot(aes(Condition, Rating, color = Condition)) +
geom_boxplot() +
scale_color_jco() +
theme_bw()
## Repeated measure ANOVA
FB.5cond.df %>%
filter(Attribute == "Liking",
Clip == "No",
After == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Condition)) ## Significant## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Condition 4 44 7.737 8.22e-05 * 0.236
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Condition 0.059 0.002 *
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF] p[HF] p[HF]<.05
## 1 Condition 0.473 1.89, 20.83 0.003 * 0.569 2.28, 25.03 0.002 * ## Posthoc - across Condition
FB.5cond.df %>%
filter(Attribute == "Liking") %>%
dunn_test(Rating ~ Condition)## # A tibble: 10 × 9
## .y. group1 group2 n1 n2 statistic p p.adj p.adj…¹
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <chr>
## 1 Rating Brine 2 Brine 4 24 48 -1.28 0.202 0.607 ns
## 2 Rating Brine 2 Water 0 24 24 -1.95 0.0515 0.257 ns
## 3 Rating Brine 2 Water 2 24 24 -2.65 0.00795 0.0556 ns
## 4 Rating Brine 2 Water 4 24 48 -5.33 0.0000000977 0.000000977 ****
## 5 Rating Brine 4 Water 0 48 24 -0.974 0.330 0.660 ns
## 6 Rating Brine 4 Water 2 48 24 -1.79 0.0735 0.294 ns
## 7 Rating Brine 4 Water 4 48 48 -4.97 0.000000680 0.00000612 ****
## 8 Rating Water 0 Water 2 24 24 -0.707 0.480 0.660 ns
## 9 Rating Water 0 Water 4 24 48 -3.08 0.00206 0.0164 *
## 10 Rating Water 2 Water 4 24 48 -2.27 0.0234 0.141 ns
## # … with abbreviated variable name ¹p.adj.signifFlatbread - differences, no clip: qualities X f.medium X f.time X rate time
## Summary statistics
FB.5cond.df %>%
filter(Attribute == "Liking") %>%
group_by(Condition, Attribute) %>%
get_summary_stats()## # A tibble: 5 × 15
## Attri…¹ Condi…² varia…³ n min max median q1 q3 iqr mad mean
## <fct> <fct> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Liking Brine 2 Rating 24 16 73.5 46.5 32.9 63.4 30.5 23.7 46.7
## 2 Liking Brine 4 Rating 48 3.5 83.5 42.2 27.4 51 23.6 18.5 40.1
## 3 Liking Water 0 Rating 24 4.5 57 36.2 26.8 45.5 18.8 15.2 34.8
## 4 Liking Water 2 Rating 24 2.5 53.5 28 25 40.9 15.9 8.15 31.2
## 5 Liking Water 4 Rating 48 1 95.5 18 6.38 28.9 22.5 18.2 21.6
## # … with 3 more variables: sd <dbl>, se <dbl>, ci <dbl>, and abbreviated
## # variable names ¹Attribute, ²Condition, ³variable## Differences in attributes
FB.aov.df %>%
filter(Attribute != "Liking",
Clip == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Attribute, Ferment.type, Ferment.days, After)) # rate time (aka. after taste is NOT significant)## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05
## 1 Attribute 5 55 6.650 6.58e-05 *
## 2 Ferment.type 1 11 0.141 7.15e-01
## 3 Ferment.days 2 22 11.364 4.08e-04 *
## 4 After 1 11 0.130 7.25e-01
## 5 Attribute:Ferment.type 5 55 4.955 8.14e-04 *
## 6 Attribute:Ferment.days 10 110 2.315 1.60e-02 *
## 7 Ferment.type:Ferment.days 2 22 1.491 2.47e-01
## 8 Attribute:After 5 55 3.498 8.00e-03 *
## 9 Ferment.type:After 1 11 7.255 2.10e-02 *
## 10 Ferment.days:After 2 22 0.930 4.10e-01
## 11 Attribute:Ferment.type:Ferment.days 10 110 3.945 1.30e-04 *
## 12 Attribute:Ferment.type:After 5 55 1.735 1.42e-01
## 13 Attribute:Ferment.days:After 10 110 0.778 6.50e-01
## 14 Ferment.type:Ferment.days:After 2 22 4.057 3.20e-02 *
## 15 Attribute:Ferment.type:Ferment.days:After 10 110 1.098 3.70e-01
## ges
## 1 1.01e-01
## 2 9.60e-05
## 3 6.70e-02
## 4 5.23e-05
## 5 3.30e-02
## 6 1.70e-02
## 7 2.00e-03
## 8 2.00e-03
## 9 1.00e-03
## 10 2.69e-04
## 11 2.30e-02
## 12 9.97e-04
## 13 1.00e-03
## 14 2.00e-03
## 15 1.00e-03
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Attribute 1.09e-01 1.41e-01
## 2 Ferment.days 6.37e-01 1.04e-01
## 3 Attribute:Ferment.type 2.10e-02 2.00e-03 *
## 4 Attribute:Ferment.days 6.96e-06 8.00e-03 *
## 5 Ferment.type:Ferment.days 7.06e-01 1.76e-01
## 6 Attribute:After 1.44e-01 2.47e-01
## 7 Ferment.days:After 8.56e-01 4.59e-01
## 8 Attribute:Ferment.type:Ferment.days 3.50e-07 4.89e-05 *
## 9 Attribute:Ferment.type:After 1.01e-01 1.22e-01
## 10 Attribute:Ferment.days:After 2.09e-05 3.50e-02 *
## 11 Ferment.type:Ferment.days:After 5.98e-01 7.60e-02
## 12 Attribute:Ferment.type:Ferment.days:After 3.26e-04 4.75e-01
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05
## 1 Attribute 0.572 2.86, 31.48 0.002 *
## 2 Ferment.days 0.733 1.47, 16.14 0.002 *
## 3 Attribute:Ferment.type 0.504 2.52, 27.7 0.010 *
## 4 Attribute:Ferment.days 0.340 3.4, 37.36 0.085
## 5 Ferment.type:Ferment.days 0.773 1.55, 17 0.250
## 6 Attribute:After 0.636 3.18, 34.97 0.024 *
## 7 Ferment.days:After 0.874 1.75, 19.23 0.400
## 8 Attribute:Ferment.type:Ferment.days 0.430 4.3, 47.25 0.007 *
## 9 Attribute:Ferment.type:After 0.517 2.58, 28.42 0.188
## 10 Attribute:Ferment.days:After 0.427 4.27, 46.98 0.553
## 11 Ferment.type:Ferment.days:After 0.713 1.43, 15.69 0.050 *
## 12 Attribute:Ferment.type:Ferment.days:After 0.502 5.02, 55.19 0.372
## HFe DF[HF] p[HF] p[HF]<.05
## 1 0.795 3.97, 43.72 0.000293 *
## 2 0.818 1.64, 18 0.001000 *
## 3 0.665 3.33, 36.59 0.004000 *
## 4 0.510 5.1, 56.07 0.054000
## 5 0.875 1.75, 19.25 0.249000
## 6 0.924 4.62, 50.85 0.010000 *
## 7 1.026 2.05, 22.56 0.410000
## 8 0.739 7.39, 81.3 0.000760 *
## 9 0.689 3.45, 37.91 0.170000
## 10 0.732 7.32, 80.52 0.613000
## 11 0.790 1.58, 17.37 0.044000 *
## 12 0.973 9.73, 107.03 0.370000 ## Posthoc - astringency: f.medium X f.time
FB.aov.df %>%
filter(Attribute == "Astringency",
After == "No", Clip == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Ferment.type, Ferment.days))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferment.type 1 11 4.710 0.053 0.020
## 2 Ferment.days 2 22 2.613 0.096 0.030
## 3 Ferment.type:Ferment.days 2 22 3.723 0.041 * 0.028
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Ferment.days 0.670 0.135
## 2 Ferment.type:Ferment.days 0.768 0.266
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Ferment.days 0.752 1.5, 16.55 0.114 0.845 1.69, 18.59
## 2 Ferment.type:Ferment.days 0.811 1.62, 17.85 0.052 0.932 1.86, 20.5
## p[HF] p[HF]<.05
## 1 0.107
## 2 0.044 * # Astrigency, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Astringency",
After == "No", Clip == "No") %>%
group_by(Ferment.days) %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 3 × 11
## Fermen…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Rati… Brine Water 12 12 NaN 11 NaN NaN ""
## 2 2 Rati… Brine Water 12 12 -0.378 11 0.712 0.712 "ns"
## 3 4 Rati… Brine Water 12 12 -2.59 11 0.025 0.025 "*"
## # … with abbreviated variable names ¹Ferment.days, ²statistic, ³p.adj.signif # Astrigency, posthoc - pairwise comparisons by f.time
FB.aov.df %>%
filter(Attribute == "Astringency",
After == "No", Clip == "No") %>%
group_by(Ferment.type) %>%
pairwise_t_test(
Rating ~ Ferment.days, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Ferment.type .y. group1 group2 n1 n2 stati…¹ df p p.adj p.adj…²
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Brine Rati… 0 2 12 12 -0.225 11 0.826 1 ns
## 2 Brine Rati… 0 4 12 12 -0.153 11 0.881 1 ns
## 3 Brine Rati… 2 4 12 12 0.0991 11 0.923 1 ns
## 4 Water Rati… 0 2 12 12 -0.546 11 0.596 1 ns
## 5 Water Rati… 0 4 12 12 -2.23 11 0.048 0.143 ns
## 6 Water Rati… 2 4 12 12 -2.27 11 0.044 0.132 ns
## # … with abbreviated variable names ¹statistic, ²p.adj.signif ## Posthoc - astringency after: f.medium X f.time
FB.aov.df %>%
filter(Attribute == "Astringency",
After == "Yes", Clip == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Ferment.type, Ferment.days))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferment.type 1 11 4.115 0.067 0.012
## 2 Ferment.days 2 22 3.293 0.056 0.049
## 3 Ferment.type:Ferment.days 2 22 5.464 0.012 * 0.024
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Ferment.days 0.586 0.069
## 2 Ferment.type:Ferment.days 0.683 0.149
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Ferment.days 0.707 1.41, 15.56 0.077 0.781 1.56, 17.19
## 2 Ferment.type:Ferment.days 0.759 1.52, 16.71 0.021 * 0.856 1.71, 18.83
## p[HF] p[HF]<.05
## 1 0.071
## 2 0.017 * # Astrigency after, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Astringency",
After == "Yes", Clip == "No") %>%
group_by(Ferment.days) %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 3 × 11
## Ferme…¹ .y. group1 group2 n1 n2 statis…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Rati… Brine Water 12 12 NaN 11 NaN NaN ""
## 2 2 Rati… Brine Water 12 12 -0.0376 11 0.971 0.971 "ns"
## 3 4 Rati… Brine Water 12 12 -2.58 11 0.026 0.026 "*"
## # … with abbreviated variable names ¹Ferment.days, ²statistic, ³p.adj.signif # Astrigency after, posthoc - pairwise comparisons by f.time
FB.aov.df %>%
filter(Attribute == "Astringency",
After == "Yes", Clip == "No") %>%
group_by(Ferment.type) %>%
pairwise_t_test(
Rating ~ Ferment.days, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Ferment.type .y. group1 group2 n1 n2 stati…¹ df p p.adj p.adj…²
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Brine Rati… 0 2 12 12 -0.913 11 0.381 1 ns
## 2 Brine Rati… 0 4 12 12 -1.26 11 0.233 0.699 ns
## 3 Brine Rati… 2 4 12 12 -0.596 11 0.563 1 ns
## 4 Water Rati… 0 2 12 12 -0.621 11 0.547 1 ns
## 5 Water Rati… 0 4 12 12 -2.24 11 0.047 0.141 ns
## 6 Water Rati… 2 4 12 12 -2.13 11 0.057 0.17 ns
## # … with abbreviated variable names ¹statistic, ²p.adj.signif ## Posthoc - Bitter: f.medium X f.time
FB.aov.df %>%
filter(Attribute == "Bitter",
After == "No", Clip == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Ferment.type, Ferment.days))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferment.type 1 11 1.323 0.274 0.005
## 2 Ferment.days 2 22 6.532 0.006 * 0.092
## 3 Ferment.type:Ferment.days 2 22 1.564 0.232 0.007
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Ferment.days 0.994 0.969
## 2 Ferment.type:Ferment.days 0.882 0.534
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Ferment.days 0.994 1.99, 21.86 0.006 * 1.212 2.42, 26.67
## 2 Ferment.type:Ferment.days 0.895 1.79, 19.68 0.234 1.057 2.11, 23.25
## p[HF] p[HF]<.05
## 1 0.006 *
## 2 0.232 # Bitter, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Bitter",
After == "No", Clip == "No") %>%
group_by(Ferment.days) %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 3 × 11
## Fermen…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Rati… Brine Water 12 12 NaN 11 NaN NaN ""
## 2 2 Rati… Brine Water 12 12 -0.146 11 0.887 0.887 "ns"
## 3 4 Rati… Brine Water 12 12 -1.97 11 0.075 0.075 "ns"
## # … with abbreviated variable names ¹Ferment.days, ²statistic, ³p.adj.signif # Bitter, posthoc - pairwise comparisons by f.time
FB.aov.df %>%
filter(Attribute == "Bitter",
After == "No", Clip == "No") %>%
group_by(Ferment.type) %>%
pairwise_t_test(
Rating ~ Ferment.days, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Ferment.type .y. group1 group2 n1 n2 stati…¹ df p p.adj p.adj…²
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Brine Rati… 0 2 12 12 -0.362 11 0.724 1 ns
## 2 Brine Rati… 0 4 12 12 -2.58 11 0.026 0.077 ns
## 3 Brine Rati… 2 4 12 12 -1.68 11 0.121 0.363 ns
## 4 Water Rati… 0 2 12 12 -0.988 11 0.344 1 ns
## 5 Water Rati… 0 4 12 12 -3.48 11 0.005 0.016 *
## 6 Water Rati… 2 4 12 12 -3.25 11 0.008 0.023 *
## # … with abbreviated variable names ¹statistic, ²p.adj.signif ## Posthoc - Bitter after: f.medium X f.time
FB.aov.df %>%
filter(Attribute == "Bitter",
After == "Yes", Clip == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Ferment.type, Ferment.days))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferment.type 1 11 11.337 0.006000 * 0.060
## 2 Ferment.days 2 22 12.457 0.000241 * 0.159
## 3 Ferment.type:Ferment.days 2 22 10.034 0.000800 * 0.073
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Ferment.days 0.898 0.585
## 2 Ferment.type:Ferment.days 0.919 0.656
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe
## 1 Ferment.days 0.908 1.82, 19.97 0.000415 * 1.077
## 2 Ferment.type:Ferment.days 0.925 1.85, 20.35 0.001000 * 1.104
## DF[HF] p[HF] p[HF]<.05
## 1 2.15, 23.7 0.000241 *
## 2 2.21, 24.29 0.000800 * # Bitter after, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Bitter",
After == "Yes", Clip == "No") %>%
group_by(Ferment.days) %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 3 × 11
## Ferment.days .y. group1 group2 n1 n2 stati…¹ df p p.adj
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl>
## 1 0 Rati… Brine Water 12 12 NaN 11 NaN NaN
## 2 2 Rati… Brine Water 12 12 -0.795 11 4.43e-1 4.43e-1
## 3 4 Rati… Brine Water 12 12 -4.54 11 8.44e-4 8.44e-4
## # … with 1 more variable: p.adj.signif <chr>, and abbreviated variable name
## # ¹statistic # Bitter after, posthoc - pairwise comparisons by f.time
FB.aov.df %>%
filter(Attribute == "Bitter",
After == "Yes", Clip == "No") %>%
group_by(Ferment.type) %>%
pairwise_t_test(
Rating ~ Ferment.days, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Ferment.…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Brine Rati… 0 2 12 12 -0.177 11 8.63e-1 1 ns
## 2 Brine Rati… 0 4 12 12 -1.56 11 1.46e-1 0.438 ns
## 3 Brine Rati… 2 4 12 12 -1.39 11 1.91e-1 0.573 ns
## 4 Water Rati… 0 2 12 12 -1.74 11 1.1 e-1 0.33 ns
## 5 Water Rati… 0 4 12 12 -4.94 11 4.41e-4 0.001 **
## 6 Water Rati… 2 4 12 12 -4.42 11 1 e-3 0.003 **
## # … with abbreviated variable names ¹Ferment.type, ²statistic, ³p.adj.signif ## Posthoc - Salty: f.medium X f.time
FB.aov.df %>%
filter(Attribute == "Salty",
After == "No", Clip == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Ferment.type, Ferment.days))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferment.type 1 11 9.284 0.011 * 0.153
## 2 Ferment.days 2 22 9.358 0.001 * 0.127
## 3 Ferment.type:Ferment.days 2 22 6.883 0.005 * 0.085
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Ferment.days 0.813 0.355
## 2 Ferment.type:Ferment.days 0.796 0.320
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Ferment.days 0.842 1.68, 18.53 0.002 * 0.978 1.96, 21.51
## 2 Ferment.type:Ferment.days 0.831 1.66, 18.27 0.008 * 0.960 1.92, 21.13
## p[HF] p[HF]<.05
## 1 0.001 *
## 2 0.005 * # Salty, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Salty",
After == "No", Clip == "No") %>%
group_by(Ferment.days) %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 3 × 11
## Fermen…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Rati… Brine Water 12 12 NaN 11 NaN NaN ""
## 2 2 Rati… Brine Water 12 12 2.68 11 0.021 0.021 "*"
## 3 4 Rati… Brine Water 12 12 3.04 11 0.011 0.011 "*"
## # … with abbreviated variable names ¹Ferment.days, ²statistic, ³p.adj.signif # Salty, posthoc - pairwise comparisons by f.time
FB.aov.df %>%
filter(Attribute == "Salty",
After == "No", Clip == "No") %>%
group_by(Ferment.type) %>%
pairwise_t_test(
Rating ~ Ferment.days, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Ferment.type .y. group1 group2 n1 n2 stati…¹ df p p.adj p.adj…²
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Brine Rati… 0 2 12 12 -3.33 11 0.007 0.02 *
## 2 Brine Rati… 0 4 12 12 -3.44 11 0.005 0.016 *
## 3 Brine Rati… 2 4 12 12 -0.474 11 0.645 1 ns
## 4 Water Rati… 0 2 12 12 -1.19 11 0.26 0.78 ns
## 5 Water Rati… 0 4 12 12 -0.744 11 0.472 1 ns
## 6 Water Rati… 2 4 12 12 1.12 11 0.286 0.858 ns
## # … with abbreviated variable names ¹statistic, ²p.adj.signif ## Posthoc - Salty after: f.medium X f.time
FB.aov.df %>%
filter(Attribute == "Salty",
After == "Yes", Clip == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Ferment.type, Ferment.days))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferment.type 1 11 13.609 0.004 * 0.102
## 2 Ferment.days 2 22 7.528 0.003 * 0.110
## 3 Ferment.type:Ferment.days 2 22 3.868 0.036 * 0.055
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Ferment.days 0.965 0.836
## 2 Ferment.type:Ferment.days 0.742 0.224
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Ferment.days 0.966 1.93, 21.25 0.004 * 1.168 2.34, 25.7
## 2 Ferment.type:Ferment.days 0.795 1.59, 17.48 0.049 * 0.907 1.81, 19.95
## p[HF] p[HF]<.05
## 1 0.003 *
## 2 0.042 * # Salty after, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Salty",
After == "Yes", Clip == "No") %>%
group_by(Ferment.days) %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 3 × 11
## Fermen…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Rati… Brine Water 12 12 NaN 11 NaN NaN ""
## 2 2 Rati… Brine Water 12 12 3.47 11 0.005 0.005 "**"
## 3 4 Rati… Brine Water 12 12 2.13 11 0.057 0.057 "ns"
## # … with abbreviated variable names ¹Ferment.days, ²statistic, ³p.adj.signif # Salty after, posthoc - pairwise comparisons by f.time
FB.aov.df %>%
filter(Attribute == "Salty",
After == "Yes", Clip == "No") %>%
group_by(Ferment.type) %>%
pairwise_t_test(
Rating ~ Ferment.days, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Ferment.type .y. group1 group2 n1 n2 stati…¹ df p p.adj p.adj…²
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Brine Rati… 0 2 12 12 -3.79 11 0.003 0.009 **
## 2 Brine Rati… 0 4 12 12 -3.08 11 0.011 0.032 *
## 3 Brine Rati… 2 4 12 12 0.359 11 0.727 1 ns
## 4 Water Rati… 0 2 12 12 -1.63 11 0.132 0.396 ns
## 5 Water Rati… 0 4 12 12 -1.09 11 0.299 0.897 ns
## 6 Water Rati… 2 4 12 12 -0.457 11 0.657 1 ns
## # … with abbreviated variable names ¹statistic, ²p.adj.signif ## Posthoc - Sour: f.medium X f.time
FB.aov.df %>%
filter(Attribute == "Sour",
After == "No", Clip == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Ferment.type, Ferment.days))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferment.type 1 11 1.442 0.255 0.019
## 2 Ferment.days 2 22 6.594 0.006 * 0.125
## 3 Ferment.type:Ferment.days 2 22 0.726 0.495 0.010
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Ferment.days 0.573 0.062
## 2 Ferment.type:Ferment.days 0.964 0.832
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Ferment.days 0.701 1.4, 15.41 0.014 * 0.772 1.54, 16.98
## 2 Ferment.type:Ferment.days 0.965 1.93, 21.23 0.491 1.167 2.33, 25.66
## p[HF] p[HF]<.05
## 1 0.011 *
## 2 0.495 # Sour, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Sour",
After == "No", Clip == "No") %>%
group_by(Ferment.days) %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 3 × 11
## Fermen…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Rati… Brine Water 12 12 NaN 11 NaN NaN ""
## 2 2 Rati… Brine Water 12 12 -1.21 11 0.252 0.252 "ns"
## 3 4 Rati… Brine Water 12 12 -0.900 11 0.387 0.387 "ns"
## # … with abbreviated variable names ¹Ferment.days, ²statistic, ³p.adj.signif # Sour, posthoc - pairwise comparisons by f.time
FB.aov.df %>%
filter(Attribute == "Sour",
After == "No", Clip == "No") %>%
group_by(Ferment.type) %>%
pairwise_t_test(
Rating ~ Ferment.days, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Ferment.type .y. group1 group2 n1 n2 stati…¹ df p p.adj p.adj…²
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Brine Rati… 0 2 12 12 -0.686 11 0.507 1 ns
## 2 Brine Rati… 0 4 12 12 -1.74 11 0.11 0.33 ns
## 3 Brine Rati… 2 4 12 12 -1.77 11 0.104 0.312 ns
## 4 Water Rati… 0 2 12 12 -2.17 11 0.053 0.159 ns
## 5 Water Rati… 0 4 12 12 -3.67 11 0.004 0.011 *
## 6 Water Rati… 2 4 12 12 -1.35 11 0.204 0.612 ns
## # … with abbreviated variable names ¹statistic, ²p.adj.signif ## Posthoc - Sour after: f.medium X f.time
FB.aov.df %>%
filter(Attribute == "Sour",
After == "Yes", Clip == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Ferment.type, Ferment.days))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferment.type 1 11 10.317 0.008000 * 0.079
## 2 Ferment.days 2 22 9.623 0.000994 * 0.150
## 3 Ferment.type:Ferment.days 2 22 8.246 0.002000 * 0.055
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Ferment.days 0.500 0.031 *
## 2 Ferment.type:Ferment.days 0.913 0.636
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Ferment.days 0.667 1.33, 14.67 0.005 * 0.724 1.45, 15.93
## 2 Ferment.type:Ferment.days 0.920 1.84, 20.25 0.003 * 1.096 2.19, 24.12
## p[HF] p[HF]<.05
## 1 0.004 *
## 2 0.002 * # Sour after, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Sour",
After == "Yes", Clip == "No") %>%
group_by(Ferment.days) %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 3 × 11
## Fermen…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Rati… Brine Water 12 12 NaN 11 NaN NaN ""
## 2 2 Rati… Brine Water 12 12 -2.09 11 0.061 0.061 "ns"
## 3 4 Rati… Brine Water 12 12 -3.57 11 0.004 0.004 "**"
## # … with abbreviated variable names ¹Ferment.days, ²statistic, ³p.adj.signif # Sour after, posthoc - pairwise comparisons by f.time
FB.aov.df %>%
filter(Attribute == "Sour",
After == "Yes", Clip == "No") %>%
group_by(Ferment.type) %>%
pairwise_t_test(
Rating ~ Ferment.days, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Ferment.type .y. group1 group2 n1 n2 stati…¹ df p p.adj p.adj…²
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Brine Rati… 0 2 12 12 -0.985 11 0.346 1 ns
## 2 Brine Rati… 0 4 12 12 -1.50 11 0.162 0.486 ns
## 3 Brine Rati… 2 4 12 12 -1.48 11 0.168 0.504 ns
## 4 Water Rati… 0 2 12 12 -2.39 11 0.036 0.107 ns
## 5 Water Rati… 0 4 12 12 -4.04 11 0.002 0.006 **
## 6 Water Rati… 2 4 12 12 -3.48 11 0.005 0.015 *
## # … with abbreviated variable names ¹statistic, ²p.adj.signif ## Posthoc - Sweet: f.medium X f.time
FB.aov.df %>%
filter(Attribute == "Sweet",
After == "No", Clip == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Ferment.type, Ferment.days))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferment.type 1 11 6.541 0.027 * 0.042
## 2 Ferment.days 2 22 3.043 0.068 0.058
## 3 Ferment.type:Ferment.days 2 22 4.750 0.019 * 0.025
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Ferment.days 0.717 0.189
## 2 Ferment.type:Ferment.days 0.907 0.613
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Ferment.days 0.779 1.56, 17.14 0.084 0.884 1.77, 19.46
## 2 Ferment.type:Ferment.days 0.915 1.83, 20.13 0.023 * 1.088 2.18, 23.94
## p[HF] p[HF]<.05
## 1 0.076
## 2 0.019 * # Sweet, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Sweet",
After == "No", Clip == "No") %>%
group_by(Ferment.days) %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 3 × 11
## Fermen…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Rati… Brine Water 12 12 NaN 11 NaN NaN ""
## 2 2 Rati… Brine Water 12 12 1.94 11 0.079 0.079 "ns"
## 3 4 Rati… Brine Water 12 12 2.71 11 0.02 0.02 "*"
## # … with abbreviated variable names ¹Ferment.days, ²statistic, ³p.adj.signif # Sweet, posthoc - pairwise comparisons by f.time
FB.aov.df %>%
filter(Attribute == "Sweet",
After == "No", Clip == "No") %>%
group_by(Ferment.type) %>%
pairwise_t_test(
Rating ~ Ferment.days, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Ferment.type .y. group1 group2 n1 n2 stati…¹ df p p.adj p.adj…²
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Brine Rati… 0 2 12 12 -3.08 11 0.011 0.032 *
## 2 Brine Rati… 0 4 12 12 -2.60 11 0.025 0.074 ns
## 3 Brine Rati… 2 4 12 12 -0.752 11 0.468 1 ns
## 4 Water Rati… 0 2 12 12 -1.10 11 0.294 0.882 ns
## 5 Water Rati… 0 4 12 12 -0.618 11 0.549 1 ns
## 6 Water Rati… 2 4 12 12 0.217 11 0.832 1 ns
## # … with abbreviated variable names ¹statistic, ²p.adj.signif ## Posthoc - Sweet after: f.medium X f.time
FB.aov.df %>%
filter(Attribute == "Sweet",
After == "Yes", Clip == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Ferment.type, Ferment.days))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferment.type 1 11 3.677 0.081 0.022
## 2 Ferment.days 2 22 0.364 0.699 0.006
## 3 Ferment.type:Ferment.days 2 22 2.700 0.089 0.012
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Ferment.days 0.945 0.755
## 2 Ferment.type:Ferment.days 0.853 0.452
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Ferment.days 0.948 1.9, 20.86 0.688 1.140 2.28, 25.08
## 2 Ferment.type:Ferment.days 0.872 1.74, 19.18 0.098 1.022 2.04, 22.49
## p[HF] p[HF]<.05
## 1 0.699
## 2 0.089 # Sweet after, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Sweet",
After == "Yes", Clip == "No") %>%
group_by(Ferment.days) %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 3 × 11
## Fermen…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Rati… Brine Water 12 12 NaN 11 NaN NaN ""
## 2 2 Rati… Brine Water 12 12 1.51 11 0.16 0.16 "ns"
## 3 4 Rati… Brine Water 12 12 2.08 11 0.062 0.062 "ns"
## # … with abbreviated variable names ¹Ferment.days, ²statistic, ³p.adj.signif # Sweet after, posthoc - pairwise comparisons by f.time
FB.aov.df %>%
filter(Attribute == "Sweet",
After == "Yes", Clip == "No") %>%
group_by(Ferment.type) %>%
pairwise_t_test(
Rating ~ Ferment.days, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Ferment.type .y. group1 group2 n1 n2 stati…¹ df p p.adj p.adj…²
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Brine Rati… 0 2 12 12 -0.947 11 0.364 1 ns
## 2 Brine Rati… 0 4 12 12 -1.75 11 0.109 0.327 ns
## 3 Brine Rati… 2 4 12 12 -0.665 11 0.52 1 ns
## 4 Water Rati… 0 2 12 12 0.504 11 0.624 1 ns
## 5 Water Rati… 0 4 12 12 0.249 11 0.808 1 ns
## 6 Water Rati… 2 4 12 12 -0.215 11 0.833 1 ns
## # … with abbreviated variable names ¹statistic, ²p.adj.signif ## Posthoc - Umami: f.medium X f.time
FB.aov.df %>%
filter(Attribute == "Umami",
After == "No", Clip == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Ferment.type, Ferment.days))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferment.type 1 11 0.225 0.644 0.003
## 2 Ferment.days 2 22 5.138 0.015 * 0.077
## 3 Ferment.type:Ferment.days 2 22 0.325 0.726 0.003
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Ferment.days 0.705 0.175
## 2 Ferment.type:Ferment.days 0.868 0.493
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Ferment.days 0.772 1.54, 16.99 0.024 * 0.875 1.75, 19.24
## 2 Ferment.type:Ferment.days 0.884 1.77, 19.44 0.700 1.040 2.08, 22.88
## p[HF] p[HF]<.05
## 1 0.019 *
## 2 0.726 # Umami, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Umami",
After == "No", Clip == "No") %>%
group_by(Ferment.days) %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 3 × 11
## Fermen…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Rati… Brine Water 12 12 NaN 11 NaN NaN ""
## 2 2 Rati… Brine Water 12 12 0.174 11 0.865 0.865 "ns"
## 3 4 Rati… Brine Water 12 12 0.701 11 0.498 0.498 "ns"
## # … with abbreviated variable names ¹Ferment.days, ²statistic, ³p.adj.signif # Umami, posthoc - pairwise comparisons by f.time
FB.aov.df %>%
filter(Attribute == "Umami",
After == "No", Clip == "No") %>%
group_by(Ferment.type) %>%
pairwise_t_test(
Rating ~ Ferment.days, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Ferment.type .y. group1 group2 n1 n2 stati…¹ df p p.adj p.adj…²
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Brine Rati… 0 2 12 12 -2.02 11 0.069 0.206 ns
## 2 Brine Rati… 0 4 12 12 -2.31 11 0.041 0.124 ns
## 3 Brine Rati… 2 4 12 12 -0.608 11 0.556 1 ns
## 4 Water Rati… 0 2 12 12 -1.99 11 0.072 0.215 ns
## 5 Water Rati… 0 4 12 12 -1.47 11 0.171 0.513 ns
## 6 Water Rati… 2 4 12 12 0.440 11 0.669 1 ns
## # … with abbreviated variable names ¹statistic, ²p.adj.signif ## Posthoc - Umami after: f.medium X f.time
FB.aov.df %>%
filter(Attribute == "Umami",
After == "Yes", Clip == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Ferment.type, Ferment.days))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferment.type 1 11 0.062 0.807 0.000601
## 2 Ferment.days 2 22 7.789 0.003 * 0.099000
## 3 Ferment.type:Ferment.days 2 22 0.027 0.973 0.000309
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Ferment.days 0.468 0.022 *
## 2 Ferment.type:Ferment.days 0.957 0.803
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Ferment.days 0.653 1.31, 14.36 0.01 * 0.705 1.41, 15.5
## 2 Ferment.type:Ferment.days 0.959 1.92, 21.09 0.97 1.157 2.31, 25.45
## p[HF] p[HF]<.05
## 1 0.008 *
## 2 0.973 # Umami after, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Umami",
After == "Yes", Clip == "No") %>%
group_by(Ferment.days) %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 3 × 11
## Fermen…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Rati… Brine Water 12 12 NaN 11 NaN NaN ""
## 2 2 Rati… Brine Water 12 12 0.176 11 0.863 0.863 "ns"
## 3 4 Rati… Brine Water 12 12 0.243 11 0.812 0.812 "ns"
## # … with abbreviated variable names ¹Ferment.days, ²statistic, ³p.adj.signif # Umami after, posthoc - pairwise comparisons by f.time
FB.aov.df %>%
filter(Attribute == "Umami",
After == "Yes", Clip == "No") %>%
group_by(Ferment.type) %>%
pairwise_t_test(
Rating ~ Ferment.days, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Ferment.type .y. group1 group2 n1 n2 stati…¹ df p p.adj p.adj…²
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Brine Rati… 0 2 12 12 -2.04 11 0.067 0.2 ns
## 2 Brine Rati… 0 4 12 12 -3.41 11 0.006 0.018 *
## 3 Brine Rati… 2 4 12 12 -0.705 11 0.495 1 ns
## 4 Water Rati… 0 2 12 12 -2.23 11 0.047 0.141 ns
## 5 Water Rati… 0 4 12 12 -2.02 11 0.068 0.204 ns
## 6 Water Rati… 2 4 12 12 -0.583 11 0.572 1 ns
## # … with abbreviated variable names ¹statistic, ²p.adj.signifFlatbread - differences, no clip, liking: f.medium X f.time X rate time
## Differences in attributes
FB.aov.df %>%
filter(Attribute == "Liking",
After =="No", Clip == "No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Ferment.type, Ferment.days))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferment.type 1 11 16.252 0.002 * 0.125
## 2 Ferment.days 2 22 2.809 0.082 0.045
## 3 Ferment.type:Ferment.days 2 22 6.452 0.006 * 0.080
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Ferment.days 0.765 0.262
## 2 Ferment.type:Ferment.days 0.267 0.001 *
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Ferment.days 0.810 1.62, 17.81 0.096 0.929 1.86, 20.44
## 2 Ferment.type:Ferment.days 0.577 1.15, 12.7 0.022 * 0.602 1.2, 13.24
## p[HF] p[HF]<.05
## 1 0.087
## 2 0.020 * # Liking, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Liking",
After == "No", Clip == "No") %>%
group_by(Ferment.days) %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 3 × 11
## Ferment.days .y. group1 group2 n1 n2 stati…¹ df p p.adj
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl>
## 1 0 Rati… Brine Water 12 12 NaN 11 NaN NaN
## 2 2 Rati… Brine Water 12 12 5.33 11 2.41e-4 2.41e-4
## 3 4 Rati… Brine Water 12 12 2.92 11 1.4 e-2 1.4 e-2
## # … with 1 more variable: p.adj.signif <chr>, and abbreviated variable name
## # ¹statistic # Liking, posthoc - pairwise comparisons by f.time
FB.aov.df %>%
filter(Attribute == "Liking",
After == "No", Clip == "No") %>%
group_by(Ferment.type) %>%
pairwise_t_test(
Rating ~ Ferment.days, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Ferment.type .y. group1 group2 n1 n2 stati…¹ df p p.adj p.adj…²
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Brine Rati… 0 2 12 12 -3.14 11 0.009 0.028 *
## 2 Brine Rati… 0 4 12 12 -1.28 11 0.225 0.675 ns
## 3 Brine Rati… 2 4 12 12 1.28 11 0.227 0.681 ns
## 4 Water Rati… 0 2 12 12 1.13 11 0.282 0.846 ns
## 5 Water Rati… 0 4 12 12 2.57 11 0.026 0.078 ns
## 6 Water Rati… 2 4 12 12 1.96 11 0.076 0.227 ns
## # … with abbreviated variable names ¹statistic, ²p.adj.signifFlatbread - differences, clip: qualities X f.medium X rate time
## Differences in attributes: Attribute X f.type X After taste
FB.aov.df %>%
filter(Attribute != "Liking",
Ferment.days == "4", Clip == "Yes") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Attribute, Ferment.type, After)) # rate time (aka. after taste is NOT significant)## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Attribute 5 55 2.454 0.045 * 0.041000
## 2 Ferment.type 1 11 0.367 0.557 0.000718
## 3 After 1 11 0.080 0.783 0.000091
## 4 Attribute:Ferment.type 5 55 4.160 0.003 * 0.049000
## 5 Attribute:After 5 55 1.895 0.110 0.004000
## 6 Ferment.type:After 1 11 9.938 0.009 * 0.002000
## 7 Attribute:Ferment.type:After 5 55 2.893 0.022 * 0.005000
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Attribute 0.273 0.636
## 2 Attribute:Ferment.type 0.084 0.079
## 3 Attribute:After 0.211 0.457
## 4 Attribute:Ferment.type:After 0.235 0.531
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe
## 1 Attribute 0.669 3.34, 36.79 0.073 0.996
## 2 Attribute:Ferment.type 0.550 2.75, 30.23 0.016 * 0.751
## 3 Attribute:After 0.675 3.38, 37.15 0.141 1.011
## 4 Attribute:Ferment.type:After 0.658 3.29, 36.17 0.044 * 0.971
## DF[HF] p[HF] p[HF]<.05
## 1 4.98, 54.79 0.045 *
## 2 3.75, 41.3 0.007 *
## 3 5.05, 55.59 0.110
## 4 4.86, 53.43 0.023 *## Differences in attributes: Attribute X f.type
FB.aov.df %>%
filter(Attribute != "Liking",
Ferment.days == "4", Clip == "Yes", After =="No") %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Attribute, Ferment.type)) # rate time (aka. after taste is NOT significant)## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Attribute 5 55 2.979 0.019 * 0.061
## 2 Ferment.type 1 11 2.105 0.175 0.005
## 3 Attribute:Ferment.type 5 55 3.104 0.015 * 0.045
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Attribute 0.162 0.296
## 2 Attribute:Ferment.type 0.082 0.072
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Attribute 0.562 2.81, 30.91 0.050 * 0.775 3.87, 42.6
## 2 Attribute:Ferment.type 0.543 2.72, 29.89 0.046 * 0.739 3.69, 40.64
## p[HF] p[HF]<.05
## 1 0.031 *
## 2 0.028 * # Astringency, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Astringency",
After == "No", Clip == "Yes") %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 1 × 10
## .y. group1 group2 n1 n2 statistic df p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Rating Brine Water 12 12 -1.60 11 0.137 0.137 ns # Astrigency after, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Astringency",
After == "Yes", Clip == "Yes") %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 1 × 10
## .y. group1 group2 n1 n2 statistic df p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Rating Brine Water 12 12 -1.29 11 0.224 0.224 ns # Bitter, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Bitter",
After == "No", Clip == "Yes") %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 1 × 10
## .y. group1 group2 n1 n2 statistic df p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Rating Brine Water 12 12 -1.02 11 0.331 0.331 ns # Bitter after, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Bitter",
After == "Yes", Clip == "Yes") %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 1 × 10
## .y. group1 group2 n1 n2 statistic df p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Rating Brine Water 12 12 -3.37 11 0.006 0.006 ** # Salty, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Salty",
After == "No", Clip == "Yes") %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 1 × 10
## .y. group1 group2 n1 n2 statistic df p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Rating Brine Water 12 12 2.49 11 0.03 0.03 * # Salty after, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Salty",
After == "Yes", Clip == "Yes") %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 1 × 10
## .y. group1 group2 n1 n2 statistic df p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Rating Brine Water 12 12 2.51 11 0.029 0.029 * # Sour, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Sour",
After == "No", Clip == "Yes") %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 1 × 10
## .y. group1 group2 n1 n2 statistic df p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Rating Brine Water 12 12 -0.0308 11 0.976 0.976 ns # Sour after, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Sour",
After == "Yes", Clip == "Yes") %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 1 × 10
## .y. group1 group2 n1 n2 statistic df p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Rating Brine Water 12 12 -0.969 11 0.353 0.353 ns # Sweet, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Sweet",
After == "No", Clip == "Yes") %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 1 × 10
## .y. group1 group2 n1 n2 statistic df p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Rating Brine Water 12 12 0.241 11 0.814 0.814 ns # Sweet after, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Sweet",
After == "Yes", Clip == "Yes") %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 1 × 10
## .y. group1 group2 n1 n2 statistic df p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Rating Brine Water 12 12 1.02 11 0.328 0.328 ns # Umami, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Umami",
After == "No", Clip == "Yes") %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 1 × 10
## .y. group1 group2 n1 n2 statistic df p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Rating Brine Water 12 12 1.61 11 0.135 0.135 ns # Umami after, posthoc - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Umami",
After == "Yes", Clip == "Yes") %>%
pairwise_t_test(
Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 1 × 10
## .y. group1 group2 n1 n2 statistic df p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Rating Brine Water 12 12 0.767 11 0.459 0.459 nsFlatbread - differences, clip, liking: by f.medium
# Liking - pairwise comparisons by f.medium
FB.aov.df %>%
filter(Attribute == "Liking",
After == "No", Clip == "Yes") %>%
pairwise_t_test(Rating ~ Ferment.type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 1 × 10
## .y. group1 group2 n1 n2 statistic df p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Rating Brine Water 12 12 3.77 11 0.003 0.003 **Flatbread - differences graphs
## Posthoc graphs for after bitter, saltiness and after sour
FB.driver.taste <- FB.Wide %>%
filter(Ferment.type != "SaltAdded", After == "No") %>%
group_by(Condition) %>%
summarize(mSweet = mean(Sweet), sdSweet = sd(Sweet), mSalty = mean(Salty), sdSalty = sd(Salty), mUmami = mean(Umami), sdUmami = sd(Umami), mBitter = mean(Bitter), sdBitter = sd(Bitter), mSour = mean(Sour), sdSour = sd(Sour), mLiking = mean(Liking), sdLiking = sd(Liking))
FB.driver.taste$Condition <- factor(FB.driver.taste$Condition,
levels = c("0 None No No", "2 Brine No No", "4 Brine No No", "4 Brine Yes No", "2 Water No No", "4 Water No No", "4 Water Yes No"))
FB.driver.ataste <- FB.Wide %>%
filter(Ferment.type != "SaltAdded", After == "Yes") %>%
group_by(Condition) %>%
summarize(mSweet = mean(Sweet), sdSweet = sd(Sweet), mSalty = mean(Salty), sdSalty = sd(Salty), mUmami = mean(Umami), sdUmami = sd(Umami), mBitter = mean(Bitter), sdBitter = sd(Bitter), mSour = mean(Sour), sdSour = sd(Sour), mLiking = mean(Liking), sdLiking = sd(Liking))
FB.driver.ataste$Condition <- factor(FB.driver.ataste$Condition,
levels = c("0 None No Yes", "2 Brine No Yes", "4 Brine No Yes", "4 Brine Yes Yes", "2 Water No Yes", "4 Water No Yes", "4 Water Yes Yes"))
## Overall liking
FB.driver.taste %>%
select(Condition, mLiking, sdLiking) %>%
ggplot(aes(x = Condition, y = mLiking, fill = Condition)) +
geom_bar(stat = "identity", color = "black", position = position_dodge()) +
geom_errorbar(aes(ymin = mLiking - sdLiking/sqrt(12), ymax = mLiking + sdLiking/sqrt(12), width = 0.3)) +
scale_fill_manual(values = c("#2E7D32", "#80CBC4", "#009688", "#B2DFDB", "#AFB42B", "#827717", "#E6EE9C"))+
ylim(0, 100)+
theme_bw()
## Bitter aftertaste
FB.driver.ataste %>%
select(Condition, mBitter, sdBitter) %>%
ggplot(aes(x = Condition, y = mBitter, fill = Condition)) +
geom_bar(stat = "identity", color = "black", position = position_dodge()) +
geom_errorbar(aes(ymin = mBitter - sdBitter/sqrt(12), ymax = mBitter + sdBitter/sqrt(12), width = 0.3)) +
scale_fill_manual(values = c("#2E7D32", "#80CBC4", "#009688", "#B2DFDB", "#AFB42B", "#827717", "#E6EE9C"))+
ylim(0, 50)+
theme_bw()
## Saltiness
FB.driver.taste %>%
select(Condition, mSalty, sdSalty) %>%
ggplot(aes(x = Condition, y = mSalty, fill = Condition)) +
geom_bar(stat = "identity", color = "black", position = position_dodge()) +
geom_errorbar(aes(ymin = mSalty - sdSalty/sqrt(12), ymax = mSalty + sdSalty/sqrt(12), width = 0.3)) +
scale_fill_manual(values = c("#2E7D32", "#80CBC4", "#009688", "#B2DFDB", "#AFB42B", "#827717", "#E6EE9C"))+
ylim(0, 50)+
theme_bw()
## Salty aftertaste
FB.driver.ataste %>%
select(Condition, mSalty, sdSalty) %>%
ggplot(aes(x = Condition, y = mSalty, fill = Condition)) +
geom_bar(stat = "identity", color = "black", position = position_dodge()) +
geom_errorbar(aes(ymin = mSalty - sdSalty/sqrt(12), ymax = mSalty + sdSalty/sqrt(12), width = 0.3)) +
scale_fill_manual(values = c("#2E7D32", "#80CBC4", "#009688", "#B2DFDB", "#AFB42B", "#827717", "#E6EE9C"))+
ylim(0, 50)+
theme_bw()
## Sourness
FB.driver.taste %>%
select(Condition, mSour, sdSour) %>%
ggplot(aes(x = Condition, y = mSour, fill = Condition)) +
geom_bar(stat = "identity", color = "black", position = position_dodge()) +
geom_errorbar(aes(ymin = mSour - sdSour/sqrt(12), ymax = mSour + sdSour/sqrt(12), width = 0.3)) +
scale_fill_manual(values = c("#2E7D32", "#80CBC4", "#009688", "#B2DFDB", "#AFB42B", "#827717", "#E6EE9C"))+
ylim(0, 50)+
theme_bw()
## Sour aftertaste
FB.driver.ataste %>%
select(Condition, mSour, sdSour) %>%
ggplot(aes(x = Condition, y = mSour, fill = Condition)) +
geom_bar(stat = "identity", color = "black", position = position_dodge()) +
geom_errorbar(aes(ymin = mSour - sdSour/sqrt(12), ymax = mSour + sdSour/sqrt(12), width = 0.3)) +
scale_fill_manual(values = c("#2E7D32", "#80CBC4", "#009688", "#B2DFDB", "#AFB42B", "#827717", "#E6EE9C"))+
ylim(0, 50)+
theme_bw()
Bread - demographics
Demo %>%
get_summary_stats() ## # A tibble: 323 × 13
## variable n min max median q1 q3 iqr mad mean sd
## <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 ID 30 1 30 15.5 8.25 22.8 14.5 11.1 15.5 8.80
## 2 Age 30 18 63 27 24 37 13 6.67 31.1 10.0
## 3 Height 30 60 72 67.5 64 69.8 5.75 4.45 66.6 3.80
## 4 Weight 30 100 270 160 150 180 30 25.9 164. 34.1
## 5 BMI 30 19.5 37.7 25.1 22.8 28.0 5.14 3.71 25.9 4.23
## 6 FN1 30 1 4 2 1 3 2 1.48 2 1.02
## 7 FN2 30 1 4 2 1 2 1 1.48 1.87 0.937
## 8 FN3 30 1 7 2 2 4.75 2.75 1.48 2.97 1.67
## 9 FN4 30 1 4 1 1 1 0 0 1.3 0.702
## 10 FN5 30 1 4 1 1 1 0 0 1.3 0.651
## # … with 313 more rows, and 2 more variables: se <dbl>, ci <dbl>Demo %>%
count(Sex) ## # A tibble: 2 × 2
## Sex n
## <chr> <int>
## 1 Female 20
## 2 Male 10Demo %>%
count(Race) ## # A tibble: 5 × 2
## Race n
## <chr> <int>
## 1 Asian 9
## 2 Asian/Caucasian 2
## 3 Black/AA 5
## 4 Black/Caucasian 1
## 5 Caucasian 13## Age & Food Neophobia
Demo %>%
ggplot(aes(x = Age, y = FNSscore)) +
geom_point() +
geom_smooth(method = "lm") +
theme_bw() +
stat_cor()## `geom_smooth()` using formula = 'y ~ x'
## Age & WW Score
Demo %>%
ggplot(aes(x = Age, y = WWscore)) +
geom_point() +
geom_smooth(method = "lm") +
theme_bw() +
stat_cor()## `geom_smooth()` using formula = 'y ~ x'
## BMI & Food Neophobia
Demo %>%
ggplot(aes(x = BMI, y = FNSscore)) +
geom_point() +
geom_smooth(method = "lm") +
theme_bw() +
stat_cor()## `geom_smooth()` using formula = 'y ~ x'
## BMI & WW Score
Demo %>%
ggplot(aes(x = BMI, y = WWscore)) +
geom_point() +
geom_smooth(method = "lm") +
theme_bw() +
stat_cor()## `geom_smooth()` using formula = 'y ~ x'
## FNS & WW Score
Demo %>%
ggplot(aes(x = FNSscore, y = WWscore)) +
geom_point() +
geom_smooth(method = "lm") +
theme_bw() +
stat_cor()## `geom_smooth()` using formula = 'y ~ x'
## FNS & WW Intake
Demo %>%
ggplot(aes(x = FNSscore, y = WWoz)) +
geom_point() +
geom_smooth(method = "lm") +
theme_bw() +
stat_cor()## `geom_smooth()` using formula = 'y ~ x'
## WW Score & WW Intake
Demo %>%
ggplot(aes(x = WWscore, y = WWoz)) +
geom_point() +
geom_smooth(method = "lm") +
theme_bw() +
stat_cor()## `geom_smooth()` using formula = 'y ~ x'
Bread - reliability
## Overall liking
cor.test(MB.Wide$Overall_1, MB.Wide$Overall_2)##
## Pearson's product-moment correlation
##
## data: MB.Wide$Overall_1 and MB.Wide$Overall_2
## t = 22.644, df = 358, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.7212086 0.8067407
## sample estimates:
## cor
## 0.7673667## Overall appearance
cor.test(MB.Wide$Appearance_1, MB.Wide$Appearance_2)##
## Pearson's product-moment correlation
##
## data: MB.Wide$Appearance_1 and MB.Wide$Appearance_2
## t = 20.23, df = 358, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.6781664 0.7751789
## sample estimates:
## cor
## 0.7303343## Overall color
cor.test(MB.Wide$Color_1, MB.Wide$Color_2)##
## Pearson's product-moment correlation
##
## data: MB.Wide$Color_1 and MB.Wide$Color_2
## t = 26.348, df = 358, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.7738718 0.8447049
## sample estimates:
## cor
## 0.8122618## Overall aroma
cor.test(MB.Wide$Aroma_1, MB.Wide$Aroma_2)##
## Pearson's product-moment correlation
##
## data: MB.Wide$Aroma_1 and MB.Wide$Aroma_2
## t = 16.863, df = 358, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.6034870 0.7192445
## sample estimates:
## cor
## 0.6653462## Overall texture
cor.test(MB.Wide$Texture_1, MB.Wide$Texture_2)##
## Pearson's product-moment correlation
##
## data: MB.Wide$Texture_1 and MB.Wide$Texture_2
## t = 26.5, df = 358, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.7757356 0.8460355
## sample estimates:
## cor
## 0.8138424## Overall flavor
cor.test(MB.Wide$Flavor_1, MB.Wide$Flavor_2)##
## Pearson's product-moment correlation
##
## data: MB.Wide$Flavor_1 and MB.Wide$Flavor_2
## t = 15.85, df = 358, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.5771048 0.6991191
## sample estimates:
## cor
## 0.6421613Bread - drivers of liking
Please note that for the purchase intent question, 1 is coded as “Buy”, 2 is coded as “Maybe”, 3 is coded as “Not Buy”. That is why the relationship between liking and purchase intent is negative.
## corrplot
MB.cor <- MB.sum.df %>%
select(!c(Condition, Ferm.Type, Millet.Ratio, Participant)) %>% cor(.)
corrplot(MB.cor, method = 'color', order = 'alphabet', tl.col = 'black')
## Appearance
corrfunc(MB.sum.df, Appearance, Overall, "Appearance X Overall")## `geom_smooth()` using formula = 'y ~ x'
MB.sum.df %>%
group_by(Condition) %>%
summarize(mean_Appearance = mean(Appearance), sd = sd(Appearance)) %>%
ggplot(aes(x = Condition, y = mean_Appearance, fill = Condition)) +
geom_bar(stat = "identity", color = "black", position = position_dodge()) +
geom_errorbar(aes(ymin = mean_Appearance - sd/sqrt(12), ymax = mean_Appearance + sd/sqrt(12), width = 0.3)) +
scale_fill_manual(values = c("#2E7D32","#2E7D32", "#2E7D32", "#2E7D32", "#2E7D32", "#2E7D32", "#AFB42B", "#AFB42B", "#AFB42B", "#AFB42B", "#AFB42B", "#AFB42B"))+
ylim(0, 9) +
theme_bw()
## Color
corrfunc(MB.sum.df, Color, Overall, "Color X Overall")## `geom_smooth()` using formula = 'y ~ x'
MB.sum.df %>%
group_by(Condition) %>%
summarize(mean_Color = mean(Color), sd = sd(Color)) %>%
ggplot(aes(x = Condition, y = mean_Color, fill = Condition)) +
geom_bar(stat = "identity", color = "black", position = position_dodge()) +
geom_errorbar(aes(ymin = mean_Color - sd/sqrt(12), ymax = mean_Color + sd/sqrt(12), width = 0.3)) +
scale_fill_manual(values = c("#2E7D32","#2E7D32", "#2E7D32", "#2E7D32", "#2E7D32", "#2E7D32", "#AFB42B", "#AFB42B", "#AFB42B", "#AFB42B", "#AFB42B", "#AFB42B"))+
ylim(0, 9) +
theme_bw()
## Aroma
corrfunc(MB.sum.df, Aroma, Overall, "Aroma X Overall")## `geom_smooth()` using formula = 'y ~ x'
MB.sum.df %>%
group_by(Condition) %>%
summarize(mean_Aroma = mean(Aroma), sd = sd(Aroma)) %>%
ggplot(aes(x = Condition, y = mean_Aroma, fill = Condition)) +
geom_bar(stat = "identity", color = "black", position = position_dodge()) +
geom_errorbar(aes(ymin = mean_Aroma - sd/sqrt(12), ymax = mean_Aroma + sd/sqrt(12), width = 0.3)) +
scale_fill_manual(values = c("#2E7D32","#2E7D32", "#2E7D32", "#2E7D32", "#2E7D32", "#2E7D32", "#AFB42B", "#AFB42B", "#AFB42B", "#AFB42B", "#AFB42B", "#AFB42B"))+
ylim(0, 9) +
theme_bw()
## Texture
corrfunc(MB.sum.df, Texture, Overall, "Texture X Overall")## `geom_smooth()` using formula = 'y ~ x'
MB.sum.df %>%
group_by(Condition) %>%
summarize(mean_Texture = mean(Texture), sd = sd(Texture)) %>%
ggplot(aes(x = Condition, y = mean_Texture, fill = Condition)) +
geom_bar(stat = "identity", color = "black", position = position_dodge()) +
geom_errorbar(aes(ymin = mean_Texture - sd/sqrt(12), ymax = mean_Texture + sd/sqrt(12), width = 0.3)) +
scale_fill_manual(values = c("#2E7D32","#2E7D32", "#2E7D32", "#2E7D32", "#2E7D32", "#2E7D32", "#AFB42B", "#AFB42B", "#AFB42B", "#AFB42B", "#AFB42B", "#AFB42B"))+
ylim(0, 9) +
theme_bw()
## Flavor
corrfunc(MB.sum.df, Flavor, Overall, "Flavor X Overall")## `geom_smooth()` using formula = 'y ~ x'
MB.sum.df %>%
group_by(Condition) %>%
summarize(mean_Flavor = mean(Flavor), sd = sd(Flavor)) %>%
ggplot(aes(x = Condition, y = mean_Flavor, fill = Condition)) +
geom_bar(stat = "identity", color = "black", position = position_dodge()) +
geom_errorbar(aes(ymin = mean_Flavor - sd/sqrt(12), ymax = mean_Flavor + sd/sqrt(12), width = 0.3)) +
scale_fill_manual(values = c("#2E7D32","#2E7D32", "#2E7D32", "#2E7D32", "#2E7D32", "#2E7D32", "#AFB42B", "#AFB42B", "#AFB42B", "#AFB42B", "#AFB42B", "#AFB42B"))+
ylim(0, 9) +
theme_bw()
Bread - difference: All qualities
## F.type X ratio X attributes
MB.sum.long.df %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Ferm.Type, Millet.Ratio, Attribute))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferm.Type 1 29 25.034 2.51e-05 * 0.025
## 2 Millet.Ratio 5 145 87.706 4.51e-42 * 0.282
## 3 Attribute 5 145 13.576 7.28e-11 * 0.041
## 4 Ferm.Type:Millet.Ratio 5 145 19.799 5.21e-15 * 0.037
## 5 Ferm.Type:Attribute 5 145 10.620 1.04e-08 * 0.007
## 6 Millet.Ratio:Attribute 25 725 30.629 3.83e-96 * 0.086
## 7 Ferm.Type:Millet.Ratio:Attribute 25 725 4.487 6.18e-12 * 0.009
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Millet.Ratio 2.60e-02 1.17e-14 *
## 2 Attribute 1.08e-01 1.19e-07 *
## 3 Ferm.Type:Millet.Ratio 2.42e-01 4.71e-04 *
## 4 Ferm.Type:Attribute 7.40e-02 1.80e-09 *
## 5 Millet.Ratio:Attribute 1.09e-13 1.20e-18 *
## 6 Ferm.Type:Millet.Ratio:Attribute 5.56e-14 4.59e-20 *
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe
## 1 Millet.Ratio 0.430 2.15, 62.28 1.94e-19 * 0.465
## 2 Attribute 0.632 3.16, 91.65 1.26e-07 * 0.718
## 3 Ferm.Type:Millet.Ratio 0.617 3.09, 89.49 4.30e-10 * 0.699
## 4 Ferm.Type:Attribute 0.530 2.65, 76.91 1.51e-05 * 0.589
## 5 Millet.Ratio:Attribute 0.309 7.72, 223.98 2.02e-31 * 0.432
## 6 Ferm.Type:Millet.Ratio:Attribute 0.374 9.34, 270.93 1.24e-05 * 0.566
## DF[HF] p[HF] p[HF]<.05
## 1 2.32, 67.42 7.54e-21 *
## 2 3.59, 104.17 2.17e-08 *
## 3 3.5, 101.36 3.79e-11 *
## 4 2.94, 85.37 6.07e-06 *
## 5 10.8, 313.08 5.88e-43 *
## 6 14.16, 410.53 1.37e-07 * ## Posthoc - F.type X ratio
MB.sum.long.df %>%
group_by(Ferm.Type, Millet.Ratio, Participant) %>%
summarize(Rating = mean(Rating)) %>%
ungroup() %>%
anova_test(., dv = Rating, wid = Participant,
within = c(Ferm.Type, Millet.Ratio))## `summarise()` has grouped output by 'Ferm.Type', 'Millet.Ratio'. You can
## override using the `.groups` argument.## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferm.Type 1 29 25.034 2.51e-05 * 0.033
## 2 Millet.Ratio 5 145 87.706 4.51e-42 * 0.346
## 3 Ferm.Type:Millet.Ratio 5 145 19.799 5.21e-15 * 0.049
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Millet.Ratio 0.026 1.07e-14 *
## 2 Ferm.Type:Millet.Ratio 0.242 4.62e-04 *
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Millet.Ratio 0.430 2.15, 62.28 1.94e-19 * 0.465 2.32, 67.42
## 2 Ferm.Type:Millet.Ratio 0.617 3.09, 89.49 4.30e-10 * 0.699 3.5, 101.36
## p[HF] p[HF]<.05
## 1 7.54e-21 *
## 2 3.79e-11 * # Overall liking, posthoc - pairwise comparisons by f.type
MB.sum.long.df %>%
group_by(Ferm.Type, Millet.Ratio, Participant) %>%
summarize(Rating = mean(Rating)) %>%
ungroup() %>%
pairwise_t_test(
Rating ~ Ferm.Type, paired = TRUE,
p.adjust.method = "bonferroni")## `summarise()` has grouped output by 'Ferm.Type', 'Millet.Ratio'. You can
## override using the `.groups` argument.## # A tibble: 1 × 10
## .y. group1 group2 n1 n2 stati…¹ df p p.adj p.adj…²
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Rating Fermented Unfermented 180 180 -6.06 179 7.81e-9 7.81e-9 ****
## # … with abbreviated variable names ¹statistic, ²p.adj.signif # Overall liking, posthoc - pairwise comparisons by ratio
MB.sum.long.df %>%
group_by(Ferm.Type, Millet.Ratio, Participant) %>%
summarize(Rating = mean(Rating)) %>%
ungroup() %>%
pairwise_t_test(
Rating ~ Millet.Ratio, paired = TRUE,
p.adjust.method = "bonferroni")## `summarise()` has grouped output by 'Ferm.Type', 'Millet.Ratio'. You can
## override using the `.groups` argument.## # A tibble: 15 × 10
## .y. group1 group2 n1 n2 statistic df p p.adj p.adj.si…¹
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Rating 0 10 60 60 0.134 59 8.94e- 1 1 e+ 0 ns
## 2 Rating 0 20 60 60 2.64 59 1.1 e- 2 1.6 e- 1 ns
## 3 Rating 0 30 60 60 7.20 59 1.25e- 9 1.88e- 8 ****
## 4 Rating 0 40 60 60 10.2 59 1.46e-14 2.19e-13 ****
## 5 Rating 0 50 60 60 11.3 59 2.05e-16 3.08e-15 ****
## 6 Rating 10 20 60 60 2.40 59 2 e- 2 2.92e- 1 ns
## 7 Rating 10 30 60 60 10.2 59 1.29e-14 1.94e-13 ****
## 8 Rating 10 40 60 60 12.7 59 1.43e-18 2.15e-17 ****
## 9 Rating 10 50 60 60 12.6 59 2.56e-18 3.84e-17 ****
## 10 Rating 20 30 60 60 6.54 59 1.62e- 8 2.43e- 7 ****
## 11 Rating 20 40 60 60 10.8 59 1.33e-15 2 e-14 ****
## 12 Rating 20 50 60 60 12.6 59 2.11e-18 3.16e-17 ****
## 13 Rating 30 40 60 60 7.95 59 6.54e-11 9.81e-10 ****
## 14 Rating 30 50 60 60 8.63 59 4.71e-12 7.06e-11 ****
## 15 Rating 40 50 60 60 5.80 59 2.78e- 7 4.17e- 6 ****
## # … with abbreviated variable name ¹p.adj.signifBread - difference: Overall liking
## F.type X ratio
MB.sum.df %>%
anova_test(., dv = Overall, wid = Participant,
within = c(Ferm.Type, Millet.Ratio))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferm.Type 1 29 34.718 2.14e-06 * 0.060
## 2 Millet.Ratio 5 145 93.117 1.72e-43 * 0.449
## 3 Ferm.Type:Millet.Ratio 5 145 17.590 1.35e-13 * 0.068
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Millet.Ratio 0.078 3.05e-09 *
## 2 Ferm.Type:Millet.Ratio 0.432 6.60e-02
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe
## 1 Millet.Ratio 0.497 2.48, 72.04 8.0e-23 * 0.547
## 2 Ferm.Type:Millet.Ratio 0.718 3.59, 104.06 2.3e-10 * 0.832
## DF[HF] p[HF] p[HF]<.05
## 1 2.74, 79.32 6.88e-25 *
## 2 4.16, 120.57 1.14e-11 * # Overall liking, posthoc - pairwise comparisons by f.type
MB.sum.df %>%
select(c(Participant, Ferm.Type, Millet.Ratio, Overall)) %>%
group_by(Millet.Ratio) %>%
pairwise_t_test(
Overall ~ Ferm.Type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Millet…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Over… Ferme… Unfer… 30 30 0.0790 29 9.38e-1 9.38e-1 ns
## 2 10 Over… Ferme… Unfer… 30 30 -2.19 29 3.7 e-2 3.7 e-2 *
## 3 20 Over… Ferme… Unfer… 30 30 0.452 29 6.54e-1 6.54e-1 ns
## 4 30 Over… Ferme… Unfer… 30 30 -3.49 29 2 e-3 2 e-3 **
## 5 40 Over… Ferme… Unfer… 30 30 -5.29 29 1.12e-5 1.12e-5 ****
## 6 50 Over… Ferme… Unfer… 30 30 -6.19 29 9.51e-7 9.51e-7 ****
## # … with abbreviated variable names ¹Millet.Ratio, ²statistic, ³p.adj.signif # Overall liking, posthoc - pairwise comparisons by ratio
MB.sum.df %>%
select(c(Participant, Ferm.Type, Millet.Ratio, Overall)) %>%
group_by(Ferm.Type) %>%
pairwise_t_test(
Overall ~ Millet.Ratio, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 30 × 11
## Ferm.Type .y. group1 group2 n1 n2 statistic df p p.adj
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl>
## 1 Fermented Overall 0 10 30 30 0.586 29 5.63e- 1 1 e+ 0
## 2 Fermented Overall 0 20 30 30 1.23 29 2.27e- 1 1 e+ 0
## 3 Fermented Overall 0 30 30 30 5.77 29 3.02e- 6 4.53e- 5
## 4 Fermented Overall 0 40 30 30 8.82 29 1.05e- 9 1.58e- 8
## 5 Fermented Overall 0 50 30 30 12.1 29 7.73e-13 1.16e-11
## 6 Fermented Overall 10 20 30 30 0.656 29 5.17e- 1 1 e+ 0
## 7 Fermented Overall 10 30 30 30 9.12 29 5.07e-10 7.61e- 9
## 8 Fermented Overall 10 40 30 30 11.4 29 2.94e-12 4.41e-11
## 9 Fermented Overall 10 50 30 30 13.9 29 2.34e-14 3.51e-13
## 10 Fermented Overall 20 30 30 30 6.04 29 1.42e- 6 2.13e- 5
## # … with 20 more rows, and 1 more variable: p.adj.signif <chr>## Scatter plot
MB.sum.df %>%
ggplot(aes(x = Millet.Ratio, y = Overall, color = Ferm.Type, group = Ferm.Type)) +
geom_jitter() +
geom_smooth(method = "lm")+
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
stat_cor()+
theme_bw()## `geom_smooth()` using formula = 'y ~ x'
## Boxplot
## Overall
MB.sum.df %>%
ggplot(aes(x = Ferm.Type, y = Overall, color = Ferm.Type)) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE, method = "t.test") +
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
theme_bw()
## Faceted by millet ratio
MB.sum.df %>%
ggplot(aes(x = Ferm.Type, y = Overall, color = Ferm.Type)) +
geom_boxplot() +
geom_jitter()+
facet_wrap(~as.factor(Millet.Ratio)) +
stat_compare_means(paired = TRUE, method = "t.test") +
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
theme_bw()
Bread - difference: Appearance
## F.type X ratio
MB.sum.df %>%
anova_test(., dv = Appearance, wid = Participant,
within = c(Ferm.Type, Millet.Ratio))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferm.Type 1 29 2.857 1.02e-01 0.003
## 2 Millet.Ratio 5 145 56.227 2.94e-32 * 0.260
## 3 Ferm.Type:Millet.Ratio 5 145 2.156 6.20e-02 0.011
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Millet.Ratio 0.023 2.47e-15 *
## 2 Ferm.Type:Millet.Ratio 0.154 5.06e-06 *
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Millet.Ratio 0.488 2.44, 70.79 5.93e-17 * 0.536 2.68, 77.78
## 2 Ferm.Type:Millet.Ratio 0.550 2.75, 79.68 1.05e-01 0.613 3.06, 88.84
## p[HF] p[HF]<.05
## 1 2.12e-18 *
## 2 9.80e-02 # Appearance liking, posthoc - pairwise comparisons by f.type
MB.sum.df %>%
select(c(Participant, Ferm.Type, Millet.Ratio, Appearance)) %>%
group_by(Millet.Ratio) %>%
pairwise_t_test(
Appearance ~ Ferm.Type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Millet.Ratio .y. group1 group2 n1 n2 stati…¹ df p p.adj p.adj…²
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Appe… Ferme… Unfer… 30 30 1.99 29 0.056 0.056 ns
## 2 10 Appe… Ferme… Unfer… 30 30 -3.17 29 0.004 0.004 **
## 3 20 Appe… Ferme… Unfer… 30 30 -0.329 29 0.744 0.744 ns
## 4 30 Appe… Ferme… Unfer… 30 30 0.0584 29 0.954 0.954 ns
## 5 40 Appe… Ferme… Unfer… 30 30 -1.17 29 0.252 0.252 ns
## 6 50 Appe… Ferme… Unfer… 30 30 -1.74 29 0.092 0.092 ns
## # … with abbreviated variable names ¹statistic, ²p.adj.signif # Appearance liking, posthoc - pairwise comparisons by ratio
MB.sum.df %>%
select(c(Participant, Ferm.Type, Millet.Ratio, Appearance)) %>%
group_by(Ferm.Type) %>%
pairwise_t_test(
Appearance ~ Millet.Ratio, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 30 × 11
## Ferm.…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Fermen… Appe… 0 10 30 30 2.68 29 1.2 e-2 1.8 e-1 ns
## 2 Fermen… Appe… 0 20 30 30 3.03 29 5 e-3 7.7 e-2 ns
## 3 Fermen… Appe… 0 30 30 30 3.67 29 9.83e-4 1.5 e-2 *
## 4 Fermen… Appe… 0 40 30 30 8.15 29 5.5 e-9 8.25e-8 ****
## 5 Fermen… Appe… 0 50 30 30 7.73 29 1.59e-8 2.39e-7 ****
## 6 Fermen… Appe… 10 20 30 30 1.13 29 2.7 e-1 1 e+0 ns
## 7 Fermen… Appe… 10 30 30 30 2.99 29 6 e-3 8.5 e-2 ns
## 8 Fermen… Appe… 10 40 30 30 7.88 29 1.09e-8 1.64e-7 ****
## 9 Fermen… Appe… 10 50 30 30 6.98 29 1.13e-7 1.7 e-6 ****
## 10 Fermen… Appe… 20 30 30 30 1.38 29 1.79e-1 1 e+0 ns
## # … with 20 more rows, and abbreviated variable names ¹Ferm.Type, ²statistic,
## # ³p.adj.signif## Scatter plot
MB.sum.df %>%
ggplot(aes(x = Millet.Ratio, y = Appearance, color = Ferm.Type, group = Ferm.Type)) +
geom_jitter() +
geom_smooth(method = "lm")+
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
stat_cor()+
theme_bw()## `geom_smooth()` using formula = 'y ~ x'
## Boxplot
## Appearance
MB.sum.df %>%
ggplot(aes(x = Ferm.Type, y = Appearance, color = Ferm.Type)) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE, method = "t.test") +
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
theme_bw()
## Faceted by millet ratio
MB.sum.df %>%
ggplot(aes(x = Ferm.Type, y = Appearance, color = Ferm.Type)) +
geom_boxplot() +
geom_jitter()+
facet_wrap(~as.factor(Millet.Ratio)) +
stat_compare_means(paired = TRUE, method = "t.test") +
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
theme_bw()
Bread - difference: Color
## F.type X ratio
MB.sum.df %>%
anova_test(., dv = Color, wid = Participant,
within = c(Ferm.Type, Millet.Ratio))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferm.Type 1 29 0.839 3.67e-01 0.000447
## 2 Millet.Ratio 5 145 12.628 3.46e-10 * 0.057000
## 3 Ferm.Type:Millet.Ratio 5 145 4.734 4.91e-04 * 0.008000
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Millet.Ratio 0.015 9.66e-18 *
## 2 Ferm.Type:Millet.Ratio 0.335 9.00e-03 *
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe
## 1 Millet.Ratio 0.357 1.78, 51.76 6.38e-05 * 0.379
## 2 Ferm.Type:Millet.Ratio 0.683 3.41, 98.97 3.00e-03 * 0.785
## DF[HF] p[HF] p[HF]<.05
## 1 1.89, 54.93 4.2e-05 *
## 2 3.92, 113.77 2.0e-03 * # Color liking, posthoc - pairwise comparisons by f.type
MB.sum.df %>%
select(c(Participant, Ferm.Type, Millet.Ratio, Color)) %>%
group_by(Millet.Ratio) %>%
pairwise_t_test(
Color ~ Ferm.Type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Millet.Ratio .y. group1 group2 n1 n2 stati…¹ df p p.adj p.adj…²
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Color Ferme… Unfer… 30 30 1.92 29 0.065 0.065 ns
## 2 10 Color Ferme… Unfer… 30 30 -2.48 29 0.019 0.019 *
## 3 20 Color Ferme… Unfer… 30 30 1.90 29 0.067 0.067 ns
## 4 30 Color Ferme… Unfer… 30 30 0.666 29 0.51 0.51 ns
## 5 40 Color Ferme… Unfer… 30 30 -1.16 29 0.255 0.255 ns
## 6 50 Color Ferme… Unfer… 30 30 -2.57 29 0.016 0.016 *
## # … with abbreviated variable names ¹statistic, ²p.adj.signif # Color liking, posthoc - pairwise comparisons by ratio
MB.sum.df %>%
select(c(Participant, Ferm.Type, Millet.Ratio, Color)) %>%
group_by(Ferm.Type) %>%
pairwise_t_test(
Color ~ Millet.Ratio, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 30 × 11
## Ferm.…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Fermen… Color 0 10 30 30 2.38 29 2.4 e-2 3.63e-1 ns
## 2 Fermen… Color 0 20 30 30 1.04 29 3.09e-1 1 e+0 ns
## 3 Fermen… Color 0 30 30 30 2.49 29 1.9 e-2 2.79e-1 ns
## 4 Fermen… Color 0 40 30 30 3.73 29 8.33e-4 1.2 e-2 *
## 5 Fermen… Color 0 50 30 30 4.35 29 1.54e-4 2 e-3 **
## 6 Fermen… Color 10 20 30 30 -2.06 29 4.9 e-2 7.35e-1 ns
## 7 Fermen… Color 10 30 30 30 1.41 29 1.7 e-1 1 e+0 ns
## 8 Fermen… Color 10 40 30 30 3.96 29 4.52e-4 7 e-3 **
## 9 Fermen… Color 10 50 30 30 4.68 29 6.12e-5 9.18e-4 ***
## 10 Fermen… Color 20 30 30 30 2.41 29 2.2 e-2 3.34e-1 ns
## # … with 20 more rows, and abbreviated variable names ¹Ferm.Type, ²statistic,
## # ³p.adj.signif## Scatter plot
MB.sum.df %>%
ggplot(aes(x = Millet.Ratio, y = Color, color = Ferm.Type, group = Ferm.Type)) +
geom_jitter() +
geom_smooth(method = "lm")+
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
stat_cor()+
theme_bw()## `geom_smooth()` using formula = 'y ~ x'
## Boxplot
## Appearance
MB.sum.df %>%
ggplot(aes(x = Ferm.Type, y = Color, color = Ferm.Type)) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE, method = "t.test") +
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
theme_bw()
## Faceted by millet ratio
MB.sum.df %>%
ggplot(aes(x = Ferm.Type, y = Color, color = Ferm.Type)) +
geom_boxplot() +
geom_jitter()+
facet_wrap(~as.factor(Millet.Ratio)) +
stat_compare_means(paired = TRUE, method = "t.test") +
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
theme_bw()
Bread - difference: Aroma
## F.type X ratio
MB.sum.df %>%
anova_test(., dv = Aroma, wid = Participant,
within = c(Ferm.Type, Millet.Ratio))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferm.Type 1 29 13.494 9.63e-04 * 0.047
## 2 Millet.Ratio 5 145 15.711 2.41e-12 * 0.097
## 3 Ferm.Type:Millet.Ratio 5 145 16.375 8.60e-13 * 0.068
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Millet.Ratio 0.051 2.67e-11 *
## 2 Ferm.Type:Millet.Ratio 0.145 2.68e-06 *
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe DF[HF]
## 1 Millet.Ratio 0.446 2.23, 64.67 1.17e-06 * 0.485 2.42, 70.3
## 2 Ferm.Type:Millet.Ratio 0.544 2.72, 78.9 6.39e-08 * 0.606 3.03, 87.86
## p[HF] p[HF]<.05
## 1 4.65e-07 *
## 2 1.38e-08 * # Aroma liking, posthoc - pairwise comparisons by f.type
MB.sum.df %>%
select(c(Participant, Ferm.Type, Millet.Ratio, Aroma)) %>%
group_by(Millet.Ratio) %>%
pairwise_t_test(
Aroma ~ Ferm.Type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Millet…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Aroma Ferme… Unfer… 30 30 0.872 29 3.9 e-1 3.9 e-1 ns
## 2 10 Aroma Ferme… Unfer… 30 30 -1.91 29 6.6 e-2 6.6 e-2 ns
## 3 20 Aroma Ferme… Unfer… 30 30 -0.368 29 7.15e-1 7.15e-1 ns
## 4 30 Aroma Ferme… Unfer… 30 30 -1.88 29 7 e-2 7 e-2 ns
## 5 40 Aroma Ferme… Unfer… 30 30 -3.55 29 1 e-3 1 e-3 **
## 6 50 Aroma Ferme… Unfer… 30 30 -5.51 29 6.21e-6 6.21e-6 ****
## # … with abbreviated variable names ¹Millet.Ratio, ²statistic, ³p.adj.signif # Aroma liking, posthoc - pairwise comparisons by ratio
MB.sum.df %>%
select(c(Participant, Ferm.Type, Millet.Ratio, Aroma)) %>%
group_by(Ferm.Type) %>%
pairwise_t_test(
Aroma ~ Millet.Ratio, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 30 × 11
## Ferm.…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Fermen… Aroma 0 10 30 30 1.18 29 2.49e-1 1 e+0 ns
## 2 Fermen… Aroma 0 20 30 30 0.0671 29 9.47e-1 1 e+0 ns
## 3 Fermen… Aroma 0 30 30 30 2.21 29 3.5 e-2 5.26e-1 ns
## 4 Fermen… Aroma 0 40 30 30 3.43 29 2 e-3 2.8 e-2 *
## 5 Fermen… Aroma 0 50 30 30 5.73 29 3.35e-6 5.02e-5 ****
## 6 Fermen… Aroma 10 20 30 30 -1.50 29 1.45e-1 1 e+0 ns
## 7 Fermen… Aroma 10 30 30 30 1.97 29 5.9 e-2 8.78e-1 ns
## 8 Fermen… Aroma 10 40 30 30 3.76 29 7.67e-4 1.2 e-2 *
## 9 Fermen… Aroma 10 50 30 30 5.84 29 2.48e-6 3.72e-5 ****
## 10 Fermen… Aroma 20 30 30 30 3.38 29 2 e-3 3.2 e-2 *
## # … with 20 more rows, and abbreviated variable names ¹Ferm.Type, ²statistic,
## # ³p.adj.signif## Scatter plot
MB.sum.df %>%
ggplot(aes(x = Millet.Ratio, y = Aroma, color = Ferm.Type, group = Ferm.Type)) +
geom_jitter() +
geom_smooth(method = "lm")+
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
stat_cor()+
theme_bw()## `geom_smooth()` using formula = 'y ~ x'
## Boxplot
## Appearance
MB.sum.df %>%
ggplot(aes(x = Ferm.Type, y = Aroma, color = Ferm.Type)) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE, method = "t.test") +
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
theme_bw()
## Faceted by millet ratio
MB.sum.df %>%
ggplot(aes(x = Ferm.Type, y = Aroma, color = Ferm.Type)) +
geom_boxplot() +
geom_jitter()+
facet_wrap(~as.factor(Millet.Ratio)) +
stat_compare_means(paired = TRUE, method = "t.test") +
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
theme_bw()
Bread - difference: Texture
## F.type X ratio
MB.sum.df %>%
anova_test(., dv = Texture, wid = Participant,
within = c(Ferm.Type, Millet.Ratio))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferm.Type 1 29 23.125 4.31e-05 * 0.029
## 2 Millet.Ratio 5 145 121.044 6.14e-50 * 0.528
## 3 Ferm.Type:Millet.Ratio 5 145 9.078 1.57e-07 * 0.037
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Millet.Ratio 0.066 5.13e-10 *
## 2 Ferm.Type:Millet.Ratio 0.222 2.06e-04 *
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe
## 1 Millet.Ratio 0.505 2.53, 73.23 1.98e-26 * 0.557
## 2 Ferm.Type:Millet.Ratio 0.617 3.09, 89.47 2.18e-05 * 0.699
## DF[HF] p[HF] p[HF]<.05
## 1 2.79, 80.79 6.54e-29 *
## 2 3.49, 101.34 7.54e-06 * # Texture liking, posthoc - pairwise comparisons by f.type
MB.sum.df %>%
select(c(Participant, Ferm.Type, Millet.Ratio, Texture)) %>%
group_by(Millet.Ratio) %>%
pairwise_t_test(
Texture ~ Ferm.Type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Millet…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Text… Ferme… Unfer… 30 30 1.33 29 1.93e-1 1.93e-1 ns
## 2 10 Text… Ferme… Unfer… 30 30 -1.90 29 6.8 e-2 6.8 e-2 ns
## 3 20 Text… Ferme… Unfer… 30 30 0.790 29 4.36e-1 4.36e-1 ns
## 4 30 Text… Ferme… Unfer… 30 30 -3.29 29 3 e-3 3 e-3 **
## 5 40 Text… Ferme… Unfer… 30 30 -4.46 29 1.12e-4 1.12e-4 ***
## 6 50 Text… Ferme… Unfer… 30 30 -4.15 29 2.69e-4 2.69e-4 ***
## # … with abbreviated variable names ¹Millet.Ratio, ²statistic, ³p.adj.signif # Texture liking, posthoc - pairwise comparisons by ratio
MB.sum.df %>%
select(c(Participant, Ferm.Type, Millet.Ratio, Texture)) %>%
group_by(Ferm.Type) %>%
pairwise_t_test(
Texture ~ Millet.Ratio, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 30 × 11
## Ferm.Type .y. group1 group2 n1 n2 statistic df p p.adj
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl>
## 1 Fermented Texture 0 10 30 30 2.30 29 2.9 e- 2 4.32e- 1
## 2 Fermented Texture 0 20 30 30 3.43 29 2 e- 3 2.7 e- 2
## 3 Fermented Texture 0 30 30 30 8.14 29 5.65e- 9 8.48e- 8
## 4 Fermented Texture 0 40 30 30 13.0 29 1.33e-13 2 e-12
## 5 Fermented Texture 0 50 30 30 14.8 29 4.69e-15 7.04e-14
## 6 Fermented Texture 10 20 30 30 0.239 29 8.13e- 1 1 e+ 0
## 7 Fermented Texture 10 30 30 30 9.12 29 5.15e-10 7.72e- 9
## 8 Fermented Texture 10 40 30 30 11.8 29 1.25e-12 1.88e-11
## 9 Fermented Texture 10 50 30 30 11.8 29 1.33e-12 2 e-11
## 10 Fermented Texture 20 30 30 30 6.66 29 2.66e- 7 3.99e- 6
## # … with 20 more rows, and 1 more variable: p.adj.signif <chr>## Scatter plot
MB.sum.df %>%
ggplot(aes(x = Millet.Ratio, y = Texture, color = Ferm.Type, group = Ferm.Type)) +
geom_jitter() +
geom_smooth(method = "lm")+
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
stat_cor()+
theme_bw()## `geom_smooth()` using formula = 'y ~ x'
## Boxplot
## Appearance
MB.sum.df %>%
ggplot(aes(x = Ferm.Type, y = Texture, color = Ferm.Type)) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE, method = "t.test") +
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
theme_bw()
## Faceted by millet ratio
MB.sum.df %>%
ggplot(aes(x = Ferm.Type, y = Texture, color = Ferm.Type)) +
geom_boxplot() +
geom_jitter()+
facet_wrap(~as.factor(Millet.Ratio)) +
stat_compare_means(paired = TRUE, method = "t.test") +
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
theme_bw()
Bread - difference: Flavor
## F.type X ratio
MB.sum.df %>%
anova_test(., dv = Flavor, wid = Participant,
within = c(Ferm.Type, Millet.Ratio))## ANOVA Table (type III tests)
##
## $ANOVA
## Effect DFn DFd F p p<.05 ges
## 1 Ferm.Type 1 29 28.478 9.96e-06 * 0.057
## 2 Millet.Ratio 5 145 42.039 1.36e-26 * 0.290
## 3 Ferm.Type:Millet.Ratio 5 145 23.675 2.37e-17 * 0.088
##
## $`Mauchly's Test for Sphericity`
## Effect W p p<.05
## 1 Millet.Ratio 0.073 1.50e-09 *
## 2 Ferm.Type:Millet.Ratio 0.239 4.19e-04 *
##
## $`Sphericity Corrections`
## Effect GGe DF[GG] p[GG] p[GG]<.05 HFe
## 1 Millet.Ratio 0.458 2.29, 66.36 2.03e-13 * 0.499
## 2 Ferm.Type:Millet.Ratio 0.642 3.21, 93.08 6.24e-12 * 0.731
## DF[HF] p[HF] p[HF]<.05
## 1 2.5, 72.36 1.99e-14 *
## 2 3.66, 106.02 2.76e-13 * # Flavor liking, posthoc - pairwise comparisons by f.type
MB.sum.df %>%
select(c(Participant, Ferm.Type, Millet.Ratio, Flavor)) %>%
group_by(Millet.Ratio) %>%
pairwise_t_test(
Flavor ~ Ferm.Type, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 6 × 11
## Millet…¹ .y. group1 group2 n1 n2 stati…² df p p.adj p.adj…³
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 0 Flav… Ferme… Unfer… 30 30 -0.514 29 6.11e-1 6.11e-1 ns
## 2 10 Flav… Ferme… Unfer… 30 30 -1.17 29 2.5 e-1 2.5 e-1 ns
## 3 20 Flav… Ferme… Unfer… 30 30 -0.311 29 7.58e-1 7.58e-1 ns
## 4 30 Flav… Ferme… Unfer… 30 30 -1.57 29 1.27e-1 1.27e-1 ns
## 5 40 Flav… Ferme… Unfer… 30 30 -4.01 29 3.89e-4 3.89e-4 ***
## 6 50 Flav… Ferme… Unfer… 30 30 -8.06 29 6.87e-9 6.87e-9 ****
## # … with abbreviated variable names ¹Millet.Ratio, ²statistic, ³p.adj.signif # Flavor liking, posthoc - pairwise comparisons by ratio
MB.sum.df %>%
select(c(Participant, Ferm.Type, Millet.Ratio, Flavor)) %>%
group_by(Ferm.Type) %>%
pairwise_t_test(
Flavor ~ Millet.Ratio, paired = TRUE,
p.adjust.method = "bonferroni")## # A tibble: 30 × 11
## Ferm.Type .y. group1 group2 n1 n2 statistic df p p.adj
## * <fct> <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <dbl>
## 1 Fermented Flavor 0 10 30 30 -0.357 29 7.24e- 1 1 e+ 0
## 2 Fermented Flavor 0 20 30 30 0.711 29 4.83e- 1 1 e+ 0
## 3 Fermented Flavor 0 30 30 30 3.16 29 4 e- 3 5.6 e- 2
## 4 Fermented Flavor 0 40 30 30 4.82 29 4.14e- 5 6.21e- 4
## 5 Fermented Flavor 0 50 30 30 8.38 29 3.11e- 9 4.66e- 8
## 6 Fermented Flavor 10 20 30 30 1.36 29 1.84e- 1 1 e+ 0
## 7 Fermented Flavor 10 30 30 30 5.89 29 2.14e- 6 3.21e- 5
## 8 Fermented Flavor 10 40 30 30 8.44 29 2.69e- 9 4.04e- 8
## 9 Fermented Flavor 10 50 30 30 11.9 29 1.04e-12 1.56e-11
## 10 Fermented Flavor 20 30 30 30 3.74 29 7.99e- 4 1.2 e- 2
## # … with 20 more rows, and 1 more variable: p.adj.signif <chr>## Scatter plot
MB.sum.df %>%
ggplot(aes(x = Millet.Ratio, y = Flavor, color = Ferm.Type, group = Ferm.Type)) +
geom_jitter() +
geom_smooth(method = "lm")+
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
stat_cor()+
theme_bw()## `geom_smooth()` using formula = 'y ~ x'
## Boxplot
## Appearance
MB.sum.df %>%
ggplot(aes(x = Ferm.Type, y = Flavor, color = Ferm.Type)) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE, method = "t.test") +
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
theme_bw()
## Faceted by millet ratio
MB.sum.df %>%
ggplot(aes(x = Ferm.Type, y = Flavor, color = Ferm.Type)) +
geom_boxplot() +
geom_jitter()+
facet_wrap(~as.factor(Millet.Ratio)) +
stat_compare_means(paired = TRUE, method = "t.test") +
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
theme_bw()
Bread - difference, graphs: Overall Liking, Unfermented
Overall.Unferm <- MB.Long %>%
filter(Attribute == "Overall") %>%
filter(Ferm.Type == "Unfermented") %>%
group_by(Millet.Ratio, Participant) %>%
summarize(Rating = mean(Rating)) %>% ungroup()## `summarise()` has grouped output by 'Millet.Ratio'. You can override using the
## `.groups` argument.## Boxplot
Overall.Unferm %>%
ggplot(aes(x = as.factor(Millet.Ratio), y = Rating, color = as.factor(Millet.Ratio))) +
geom_boxplot() +
geom_jitter()+
scale_color_manual(values = c("#2E7D32", "#2E7D32", "#2E7D32", "#2E7D32", "#2E7D32", "#2E7D32"))+
theme_bw() +
scale_y_continuous(breaks = seq(0, 9), limits = c(0, 9))+
ggtitle("Unfermented Millet Subsitution Ratio vs Liking")
## 0 vs 10
Overall.Unferm %>%
filter(Millet.Ratio%in%c("0", "10")) %>%
ggplot(aes(x = as.factor(Millet.Ratio), y = Rating, color = as.factor(Millet.Ratio))) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE) +
scale_color_manual(values = c("#2E7D32", "#2E7D32"))+
theme_bw()
## 0 vs 20
Overall.Unferm %>%
filter(Millet.Ratio%in%c("0", "20")) %>%
ggplot(aes(x = as.factor(Millet.Ratio), y = Rating, color = as.factor(Millet.Ratio))) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE) +
scale_color_manual(values = c("#2E7D32", "#2E7D32"))+
theme_bw()
## 0 vs 30
Overall.Unferm %>%
filter(Millet.Ratio%in%c("0", "30")) %>%
ggplot(aes(x = as.factor(Millet.Ratio), y = Rating, color = as.factor(Millet.Ratio))) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE) +
scale_color_manual(values = c("#2E7D32", "#2E7D32"))+
theme_bw()
## 0 vs 40
Overall.Unferm %>%
filter(Millet.Ratio%in%c("0", "40")) %>%
ggplot(aes(x = as.factor(Millet.Ratio), y = Rating, color = as.factor(Millet.Ratio))) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE) +
scale_color_manual(values = c("#2E7D32", "#2E7D32"))+
theme_bw() 
## 0 vs 50
Overall.Unferm %>%
filter(Millet.Ratio%in%c("0", "50")) %>%
ggplot(aes(x = as.factor(Millet.Ratio), y = Rating, color = as.factor(Millet.Ratio))) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE) +
scale_color_manual(values = c("#2E7D32", "#2E7D32"))+
theme_bw()
Bread - difference, graphs: Overall Liking, Fermented
Overall.Ferm <- MB.Long %>%
filter(Attribute == "Overall") %>%
filter(Ferm.Type == "Fermented") %>%
group_by(Millet.Ratio, Participant) %>%
summarize(Rating = mean(Rating)) %>% ungroup()## `summarise()` has grouped output by 'Millet.Ratio'. You can override using the
## `.groups` argument. ## Boxplot
Overall.Ferm %>%
ggplot(aes(x = as.factor(Millet.Ratio), y = Rating, color = as.factor(Millet.Ratio))) +
geom_boxplot() +
geom_jitter()+
theme_bw() +
scale_color_manual(values = c("#827717", "#827717", "#827717", "#827717", "#827717", "#827717"))+
scale_y_continuous(breaks = seq(0, 9), limits = c(0, 9))+
ggtitle("Fermented Millet Subsitution Ratio vs Liking")
## 0 vs 10
Overall.Ferm %>%
filter(Millet.Ratio%in%c("0", "10")) %>%
ggplot(aes(x = as.factor(Millet.Ratio), y = Rating, color = as.factor(Millet.Ratio))) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE) +
scale_color_manual(values = c("#AFB42B", "#AFB42B"))+
theme_bw()
## 0 vs 20
Overall.Ferm %>%
filter(Millet.Ratio%in%c("0", "20")) %>%
ggplot(aes(x = as.factor(Millet.Ratio), y = Rating, color = as.factor(Millet.Ratio))) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE) +
scale_color_manual(values = c("#AFB42B", "#AFB42B"))+
theme_bw()
## 0 vs 30
Overall.Ferm %>%
filter(Millet.Ratio%in%c("0", "30")) %>%
ggplot(aes(x = as.factor(Millet.Ratio), y = Rating, color = as.factor(Millet.Ratio))) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE) +
scale_color_manual(values = c("#AFB42B", "#AFB42B"))+
theme_bw()
## 0 vs 40
Overall.Ferm %>%
filter(Millet.Ratio %in% c("0", "40")) %>%
ggplot(aes(x = as.factor(Millet.Ratio), y = Rating, color = as.factor(Millet.Ratio))) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE) +
scale_color_manual(values = c("#AFB42B", "#AFB42B"))+
theme_bw() 
## 0 vs 50
Overall.Ferm %>%
filter(Millet.Ratio%in%c("40", "50")) %>%
ggplot(aes(x = as.factor(Millet.Ratio), y = Rating, color = as.factor(Millet.Ratio))) +
geom_boxplot() +
geom_jitter()+
stat_compare_means(paired = TRUE) +
scale_color_manual(values = c("#AFB42B", "#AFB42B"))+
theme_bw()
Bread - dose response curve: Unfermented vs fermented
MilletDose.Overall <- MB.Wide %>%
mutate(Overall = (Overall_1 + Overall_2) /2) %>%
group_by(Millet.Ratio, Ferm.Type) %>%
summarize(Overall = mean(Overall), SD = sd(c(Overall_1 + Overall_2))) %>%
mutate(Ratio = case_when(Ferm.Type == "Fermented" ~ Millet.Ratio + 1,
Ferm.Type == "Unfermented" ~ Millet.Ratio))## `summarise()` has grouped output by 'Millet.Ratio'. You can override using the
## `.groups` argument.MilletDose.Overall %>%
ggplot(aes(x = Ratio, y = Overall, color = Ferm.Type)) +
geom_point() +
geom_line(aes(group = Ferm.Type))+
geom_errorbar(aes(ymin = (Overall - (SD/sqrt(11))), ymax = (Overall + (SD/sqrt(11)))), width = 1) +
theme_bw() +
scale_color_manual(values = c("#AFB42B", "#2E7D32"))+
scale_y_continuous(breaks = seq(0, 9), limits = c(0, 9))
Purchase intent: Chi-square
## Combine two columns
Decision$Condition <- paste(Decision$Ferm.Type, Decision$Millet.Ratio)
Decision.chi <- Decision %>%
dplyr::select(Condition, Buy) %>%
group_by(Condition, Buy) %>%
summarize(n = n()) %>%
pivot_wider(names_from = Buy, values_from = n, values_fill = 0) %>%
column_to_rownames(var = "Condition") %>%
rename("Buy" = "1", "Maybe" = "2", "Not Buy" = "3")## `summarise()` has grouped output by 'Condition'. You can override using the
## `.groups` argument.chisq.test(Decision.chi)##
## Pearson's Chi-squared test
##
## data: Decision.chi
## X-squared = 506.01, df = 22, p-value < 2.2e-16Purchase intent: Bar graph
## Buy or not buy bar chart
Decision$Ferm.Type <- factor(Decision$Ferm.Type, levels = c("Unfermented", "Fermented"))
Decision%>%
mutate(Buy = case_when(Buy == "1" ~ "Buy",
Buy == "2" ~ "Maybe",
Buy == "3" ~ "Not Buy")) %>%
ggplot(aes(x = as.factor(Millet.Ratio), fill = Buy)) +
geom_bar(position="fill") +
facet_grid(vars(Ferm.Type), vars(Day)) +
scale_fill_manual(values = c("#2E7D32", "#FF9800", "#B71C1C"))+
theme_bw() +
theme(strip.background = element_rect(fill="white"))
Purchase intent: Chi-square
## Combine two columns
Decision$Condition <- paste(Decision$Ferm.Type, Decision$Millet.Ratio)
Decision.chi <- Decision %>%
dplyr::select(Condition, Buy) %>%
group_by(Condition, Buy) %>%
summarize(n = n()) %>%
pivot_wider(names_from = Buy, values_from = n, values_fill = 0) %>%
column_to_rownames(var = "Condition") %>%
rename("Buy" = "1", "Maybe" = "2", "Not Buy" = "3")## `summarise()` has grouped output by 'Condition'. You can override using the
## `.groups` argument.chisq.test(Decision.chi)##
## Pearson's Chi-squared test
##
## data: Decision.chi
## X-squared = 506.01, df = 22, p-value < 2.2e-16Purchase intent: p(Buy) difference
## Retest reliability
P.purchase.wide <- P.purchase %>%
pivot_wider(names_from = Rep,
values_from = Prob) %>%
mutate(Rep.1 = rowMeans(select(., "1", "2")),
Rep.2 = rowMeans(select(., "3", "4")))
cor.test(P.purchase.wide$Rep.1, P.purchase.wide$Rep.2, method ="kendall")## Warning in cor.test.default(P.purchase.wide$Rep.1, P.purchase.wide$Rep.2, :
## Cannot compute exact p-value with ties##
## Kendall's rank correlation tau
##
## data: P.purchase.wide$Rep.1 and P.purchase.wide$Rep.2
## z = 6.7924, p-value = 1.103e-11
## alternative hypothesis: true tau is not equal to 0
## sample estimates:
## tau
## 0.799359## Fermented - p(buy) difference
P.purchase %>%
filter(Type =="p(buy)") %>%
filter(Condition %in% c("Ferm.0", "Ferm.10", "Ferm.20", "Ferm.30", "Ferm.40", "Ferm.50")) %>%
friedman_test(Prob ~ Condition|Rep) ## Friedman## # A tibble: 1 × 6
## .y. n statistic df p method
## * <chr> <int> <dbl> <dbl> <dbl> <chr>
## 1 Prob 4 17.7 5 0.00337 Friedman testP.purchase %>%
filter(Type =="p(buy)") %>%
filter(Condition %in% c("Ferm.0", "Ferm.10", "Ferm.20", "Ferm.30", "Ferm.40", "Ferm.50")) %>%
wilcox_test(Prob ~ Condition, p.adjust.method = "fdr") ## Wilcoxon posthoc## # A tibble: 15 × 9
## .y. group1 group2 n1 n2 statistic p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <chr>
## 1 Prob Ferm.0 Ferm.10 4 4 10.5 0.559 0.601 ns
## 2 Prob Ferm.0 Ferm.20 4 4 10.5 0.561 0.601 ns
## 3 Prob Ferm.0 Ferm.30 4 4 16 0.029 0.044 *
## 4 Prob Ferm.0 Ferm.40 4 4 16 0.029 0.044 *
## 5 Prob Ferm.0 Ferm.50 4 4 16 0.026 0.044 *
## 6 Prob Ferm.10 Ferm.20 4 4 9 0.881 0.881 ns
## 7 Prob Ferm.10 Ferm.30 4 4 16 0.028 0.044 *
## 8 Prob Ferm.10 Ferm.40 4 4 16 0.029 0.044 *
## 9 Prob Ferm.10 Ferm.50 4 4 16 0.026 0.044 *
## 10 Prob Ferm.20 Ferm.30 4 4 16 0.029 0.044 *
## 11 Prob Ferm.20 Ferm.40 4 4 16 0.029 0.044 *
## 12 Prob Ferm.20 Ferm.50 4 4 16 0.026 0.044 *
## 13 Prob Ferm.30 Ferm.40 4 4 14 0.104 0.13 ns
## 14 Prob Ferm.30 Ferm.50 4 4 16 0.026 0.044 *
## 15 Prob Ferm.40 Ferm.50 4 4 14.5 0.074 0.101 ns## Unfermented - p(buy) difference
P.purchase %>%
filter(Type =="p(buy)") %>%
filter(Condition %in% c("Unferm.0", "Unferm.10", "Unferm.20", "Unferm.30", "Unferm.40", "Unferm.50")) %>%
friedman_test(Prob ~ Condition|Rep) ## Friedman## # A tibble: 1 × 6
## .y. n statistic df p method
## * <chr> <int> <dbl> <dbl> <dbl> <chr>
## 1 Prob 4 19.9 5 0.00131 Friedman testP.purchase %>%
filter(Type =="p(buy)") %>%
filter(Condition %in% c("Unferm.0", "Unferm.10", "Unferm.20", "Unferm.30", "Unferm.40", "Unferm.50")) %>%
wilcox_test(Prob ~ Condition, p.adjust.method = "fdr") ## Wilcoxon posthoc## # A tibble: 15 × 9
## .y. group1 group2 n1 n2 statistic p p.adj p.adj.signif
## * <chr> <chr> <chr> <int> <int> <dbl> <dbl> <dbl> <chr>
## 1 Prob Unferm.0 Unferm.10 4 4 2.5 0.137 0.147 ns
## 2 Prob Unferm.0 Unferm.20 4 4 16 0.029 0.037 *
## 3 Prob Unferm.0 Unferm.30 4 4 16 0.028 0.037 *
## 4 Prob Unferm.0 Unferm.40 4 4 16 0.028 0.037 *
## 5 Prob Unferm.0 Unferm.50 4 4 16 0.026 0.037 *
## 6 Prob Unferm.10 Unferm.20 4 4 16 0.029 0.037 *
## 7 Prob Unferm.10 Unferm.30 4 4 16 0.029 0.037 *
## 8 Prob Unferm.10 Unferm.40 4 4 16 0.029 0.037 *
## 9 Prob Unferm.10 Unferm.50 4 4 16 0.026 0.037 *
## 10 Prob Unferm.20 Unferm.30 4 4 16 0.029 0.037 *
## 11 Prob Unferm.20 Unferm.40 4 4 16 0.029 0.037 *
## 12 Prob Unferm.20 Unferm.50 4 4 16 0.026 0.037 *
## 13 Prob Unferm.30 Unferm.40 4 4 15.5 0.04 0.046 *
## 14 Prob Unferm.30 Unferm.50 4 4 16 0.026 0.037 *
## 15 Prob Unferm.40 Unferm.50 4 4 13 0.18 0.18 ns