#rc is reading comprehension
p$rc1[p$X2C==3]<-1
p$rc1[p$X2C!=3]<-0
p$rc2[p$X2E==5]<-1
p$rc2[p$X2E!=5]<-0
p$rc3[p$X2E.1==5]<-1
p$rc3[p$X2E.1!=5]<-0
p$rc4[p$X2C.1==3]<-1
p$rc4[p$X2C.1!=3]<-0
p$rc<-p$rc1+p$rc2+p$rc3+p$rc4
summary(p$rc)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 2.000 2.000 2.216 3.000 4.000#intensity of phone use (composite measure: alpha=.9)
p$freq<-(p$freq_1+p$freq_2+p$freq_3+p$freq_6+p$freq_5+p$freq_7+p$freq_8)
fr<-p[,284:290]
library(psych)## Warning: package 'psych' was built under R version 3.2.5alpha(fr)##
## Reliability analysis
## Call: alpha(x = fr)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd
## 0.9 0.9 0.9 0.56 8.8 0.022 3 1
##
## lower alpha upper 95% confidence boundaries
## 0.85 0.9 0.94
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se
## freq_1 0.86 0.87 0.86 0.52 6.5 0.029
## freq_2 0.89 0.89 0.90 0.59 8.5 0.023
## freq_3 0.88 0.88 0.88 0.54 7.1 0.027
## freq_5 0.88 0.88 0.89 0.56 7.7 0.025
## freq_6 0.88 0.88 0.88 0.54 7.0 0.027
## freq_7 0.89 0.89 0.89 0.58 8.1 0.024
## freq_8 0.89 0.89 0.89 0.57 8.0 0.024
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## freq_1 51 0.89 0.89 0.89 0.84 3.4 1.3
## freq_2 51 0.70 0.71 0.64 0.60 2.7 1.2
## freq_3 51 0.83 0.82 0.79 0.75 3.0 1.3
## freq_5 51 0.76 0.77 0.73 0.68 2.7 1.2
## freq_6 51 0.83 0.83 0.81 0.75 3.1 1.3
## freq_7 51 0.74 0.74 0.69 0.64 2.9 1.3
## freq_8 51 0.76 0.75 0.69 0.65 3.4 1.4
##
## Non missing response frequency for each item
## 1 2 3 4 5 miss
## freq_1 0.12 0.18 0.12 0.41 0.18 0
## freq_2 0.20 0.18 0.43 0.10 0.10 0
## freq_3 0.20 0.16 0.18 0.35 0.12 0
## freq_5 0.16 0.31 0.25 0.20 0.08 0
## freq_6 0.16 0.14 0.24 0.35 0.12 0
## freq_7 0.20 0.18 0.29 0.22 0.12 0
## freq_8 0.18 0.10 0.20 0.25 0.27 0p$mindful<-((8-p$m1r)+(8-p$m2)+(8-p$m3)+(8-p$m4)+(8-p$m5r))/5
p$stress<-(p$s1+p$s2+(6-p$s3R)+(6-p$s4R)+p$s5)/5
#attention / digit cancellation task
p[is.na(p)]<-0
p$x71[p$X7_448==1]<-1
p$x72[p$X7_456==1]<-1
p$x73[p$X7_472==1&p$X7_471==1]<-1
p$x74[p$X7_478==1]<-1
p$x75[p$X7_485==1]<-1
p$x76[p$X7_486==1&p$X7_487==1]<-1
p$x77[p$X7_490==1&p$X7_491==1]<-1
p$x7<-p$x71+p$x72+p$x73+p$x74+p$x75+p$x76+p$x77
p[is.na(p)]<-0
p$x31[p$X3_60==1]<-1
p$x32[p$X3_76==1]<-1
p$x33[p$X3_81==1]<-1
p$x34[p$X3_84==1]<-1
p$x35[p$X3_350==1]<-1
p$x36[p$X3_355==1]<-1
p$x37[p$X3_371==1]<-1
p$x3<-p$x31+p$x32+p$x33+p$x34+p$x35+p$x36+p$x37
p[is.na(p)]<-0
p$x61[p$X6_68==1]<-1
p$x62[p$X6_91==1&p$X6_102]<-1
p$x63[p$X6_347==1]<-1
p$x64[p$X6_352==1]<-1
p$x65[p$X6_347==1]<-1
p$x65[p$X6_352==1]<-1
p$x62[p$X6_362==1&p$X6_363]<-1
p$x65[p$X6_365==1]<-1
p$x6<-p$x61+p$x62+p$x63+p$x64+p$x65
p[is.na(p)]<-0
p$x3.21[p$X3_57==1&p$X3_58==1]<-1
p$x3.22[p$X3_63==1]<-1
p$x3.23[p$X3_76==1]<-1
p$x3.24[p$X3_81==1]<-1
p$x3.25[p$X3_84==1]<-1
p$x3.2<-p$x3.25+p$x3.24+p$x3.23+p$x3.22+p$x3.21
p$attn<-p$x3+p$x6+p$x7+p$x3.2First, reading comprehension and intensity of checking phone
cor.test(p$rc, p$freq)##
## Pearson's product-moment correlation
##
## data: p$rc and p$freq
## t = 1.0456, df = 49, p-value = 0.3009
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.1332753 0.4067577
## sample estimates:
## cor
## 0.1477345Then reading comp and frequency of checking phone (single item)
cor.test(p$rc, p$check)##
## Pearson's product-moment correlation
##
## data: p$rc and p$check
## t = 0.14946, df = 49, p-value = 0.8818
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.2557412 0.2951940
## sample estimates:
## cor
## 0.02134694Then both measures of phone use and mindfulness while reading the passages
cor.test(p$check, p$mindful)##
## Pearson's product-moment correlation
##
## data: p$check and p$mindful
## t = -2.2336, df = 49, p-value = 0.03011
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.53477209 -0.03100207
## sample estimates:
## cor
## -0.3039886cor.test(p$freq, p$mindful)##
## Pearson's product-moment correlation
##
## data: p$freq and p$mindful
## t = 0.29973, df = 49, p-value = 0.7657
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.2355815 0.3146536
## sample estimates:
## cor
## 0.04277952Then both measures of phone use and attention task
cor.test(p$freq, p$attn)##
## Pearson's product-moment correlation
##
## data: p$freq and p$attn
## t = -0.96225, df = 1, p-value = 0.5122
## alternative hypothesis: true correlation is not equal to 0
## sample estimates:
## cor
## -0.6933752cor.test(p$check, p$attn)##
## Pearson's product-moment correlation
##
## data: p$check and p$attn
## t = -1.1547, df = 1, p-value = 0.4544
## alternative hypothesis: true correlation is not equal to 0
## sample estimates:
## cor
## -0.7559289And finally measures of phone use and stress
cor.test(p$stress, p$freq)##
## Pearson's product-moment correlation
##
## data: p$stress and p$freq
## t = 1.8346, df = 49, p-value = 0.07264
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.02372122 0.49455116
## sample estimates:
## cor
## 0.2535198cor.test(p$stress, p$check)##
## Pearson's product-moment correlation
##
## data: p$stress and p$check
## t = 1.5648, df = 49, p-value = 0.1241
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.06110247 0.46573822
## sample estimates:
## cor
## 0.2181547We also asked “was your phone out of sight during the survey” so we can look at that as a non manipulated variable… people whose phone was out of sight reported lower stress and lower mindfulness but not better reading comprehension or attention
p[is.na(p)]<-0
out<-subset(p, manipcheck==1)
not<-subset(p, manipcheck==2)
t.test(out$stress, not$stress)##
## Welch Two Sample t-test
##
## data: out$stress and not$stress
## t = -2.3455, df = 42.933, p-value = 0.02369
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -1.04450926 -0.07871655
## sample estimates:
## mean of x mean of y
## 2.548387 3.110000t.test(out$mindful, not$mindful)##
## Welch Two Sample t-test
##
## data: out$mindful and not$mindful
## t = 1.5324, df = 46.503, p-value = 0.1322
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.153055 1.130474
## sample estimates:
## mean of x mean of y
## 5.23871 4.75000t.test(out$rc, not$rc)##
## Welch Two Sample t-test
##
## data: out$rc and not$rc
## t = -0.16308, df = 32.105, p-value = 0.8715
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.7614614 0.6485582
## sample estimates:
## mean of x mean of y
## 2.193548 2.250000t.test(out$attn, not$attn)##
## Welch Two Sample t-test
##
## data: out$attn and not$attn
## t = -0.67296, df = 32.053, p-value = 0.5058
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -4.130568 2.078955
## sample estimates:
## mean of x mean of y
## 0.7741935 1.8000000