Walking
Raynae Dumpfrey
2022-07-23
loading packages
loading data file
descriptive
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 278 25.32 7.74 24 23.72 2.97 16 63 47 3.03 9.6 0.46## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 65 1 0 1 1 0 1 1 0 NaN NaN 0## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 207 2 0 2 2 0 2 2 0 NaN NaN 0Removing incomplete data
Removing Outliers
## [1] 4915.078## vars n mean sd median trimmed mad min max range skew
## X1 1 1180 6079.34 4915.08 5006 5430.54 4341.79 0 36154 36154 1.32
## kurtosis se
## X1 2.36 143.08## [1] 20824.58
## vars n mean sd median trimmed mad min max range skew
## X1 1 1166 5863.18 4506.14 4953.5 5329.42 4278.04 0 20534 20534 0.97
## kurtosis se
## X1 0.52 131.96
## [1] 4618.688## vars n mean sd median trimmed mad min max range skew
## X1 1 1200 5478.76 4618.69 4454.5 4839.76 4129.04 0 30725 30725 1.5
## kurtosis se
## X1 3.2 133.33## [1] 19334.83
## vars n mean sd median trimmed mad min max range skew
## X1 1 1181 5197.45 4056.05 4352 4715.97 4038.6 0 18930 18930 0.98
## kurtosis se
## X1 0.54 118.03
ANOVA Difference in condition for mean number of steps
H1: Do participants in each condition perform a different number of steps?
## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05 ges
## 1 C 1 213 24828962 1368304023 3.865054 0.0506008 0.01782239
##
## $`Levene's Test for Homogeneity of Variance`
## DFn DFd SSn SSd F p p<.05
## 1 1 213 6013628 565899094 2.263482 0.1339373
## C N Mean SD FLSD lo hi
## 1 1 109 5626.438 2807.680 681.4516 5285.712 5967.164
## 2 2 106 4946.714 2218.822 681.4516 4605.988 5287.440*where X-axis C = condition (2=experimental condition); and Y-axis “Mean” = steps
H1 Result: ANOVA not significant. M_steps_C1 =5626 , M_steps_C2 =4946
-
-
Steps is not normally distributed, taking the square root
## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05 ges
## 1 C 1 213 981.5901 72812.11 2.871482 0.09162331 0.01330181
##
## $`Levene's Test for Homogeneity of Variance`
## DFn DFd SSn SSd F p p<.05
## 1 1 213 75.04314 28922.57 0.5526546 0.4580543
## C N Mean SD FLSD lo hi
## 1 1 109 68.56402 19.67653 4.97102 66.07851 71.04953
## 2 2 106 64.29018 17.18199 4.97102 61.80467 66.77569*where X-axis C = condition (2=experimental condition); and Y-axis “Mean” = steps
H1 Result: ANOVA not significant. M_steps_C1 = 68.56 , M_steps_C2 =64.29
-
-
ANOVA steps-7000
## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05 ges
## 1 C 1 213 24828962 1368304023 3.865054 0.0506008 0.01782239
##
## $`Levene's Test for Homogeneity of Variance`
## DFn DFd SSn SSd F p p<.05
## 1 1 213 6013628 565899094 2.263482 0.1339373
## C N Mean SD FLSD lo hi
## 1 1 109 -1373.562 2807.680 681.4516 -1714.288 -1032.836
## 2 2 106 -2053.286 2218.822 681.4516 -2394.012 -1712.560*where X-axis C = condition (2=experimental condition); and Y-axis “Mean” = steps
Result: ANOVA not significant. M_steps_C1 = -1373.56 , M_steps_C2 =-2053.28
meaning that participants on average did not achieve the goal
-
-
Deviation from the MEAN ANOVA for steps
## vars n mean sd median trimmed mad min max range skew
## X1 1 1090 5626.44 4344.22 4770.5 5112.56 4089.01 0 19914 19914 0.99
## kurtosis se
## X1 0.61 131.58## vars n mean sd median trimmed mad min max range skew
## X1 1 1060 4946.71 3841.51 4250 4501.86 3982.26 0 18743 18743 0.99
## kurtosis se
## X1 0.7 117.99## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 C 1 213 0.002217293 1368304023 3.451597e-10 0.9999852
## ges
## 1 1.620468e-12
##
## $`Levene's Test for Homogeneity of Variance`
## DFn DFd SSn SSd F p p<.05
## 1 1 213 6013628 565899094 2.263482 0.1339373
## C N Mean SD FLSD lo hi
## 1 1 109 -0.002272477 2807.680 681.4516 -340.7281 340.7235
## 2 2 106 0.004150943 2218.822 681.4516 -340.7216 340.7299*where X-axis C = condition (2=experimental condition); and Y-axis “Mean” = steps
Result: ANOVA not significant. M_sd_C1 = -0.0022 , M_ssd_C2 = 0.0042
-
-
MSSD measure of variation
## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05 ges
## 1 C 1 213 5.002583 16252.66 0.0655616 0.7981593 0.0003077062
##
## $`Levene's Test for Homogeneity of Variance`
## DFn DFd SSn SSd F p p<.05
## 1 1 213 4.339782 5548.658 0.1665941 0.6835667
## C N Mean SD FLSD lo hi
## 1 1 109 1117.818 810.1485 227.9577 1003.839 1231.796
## 2 2 106 1146.620 884.9613 227.9577 1032.641 1260.599*where X-axis C = condition (2=experimental condition); and Y-axis “Mean” = steps
Result: ANOVA not significant. M_steps_C1 = 1117.82 , M_steps_C2 = 1146.62
-
-
EMGB Constructs, Mixed ANOVA
Doing
H2: Is there a difference between Q1 and Q12 and/or between conditions for pre volition constructs?
## Call:corr.test(x = .)
## Correlation matrix
## INT1_D INT2_D
## INT1_D 1.00 0.65
## INT2_D 0.65 1.00
## Sample Size
## [1] 473
## Probability values (Entries above the diagonal are adjusted for multiple tests.)
## INT1_D INT2_D
## INT1_D 0 0
## INT2_D 0 0
##
## To see confidence intervals of the correlations, print with the short=FALSE option## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 233 1.124064e+04 647.1062 4.047357e+03 2.879961e-149 *
## 2 C 1 233 6.875750e+00 647.1062 2.475714e+00 1.169738e-01
## 3 Q 1 233 3.489894e+00 164.6013 4.940088e+00 2.720133e-02 *
## 4 C:Q 1 233 3.375895e-02 164.6013 4.778718e-02 8.271508e-01
## ges
## 1 9.326515e-01
## 2 8.399573e-03
## 3 4.281041e-03
## 4 4.158831e-05
## C Q N Mean SD FLSD lo hi
## 1 1 1 116 5.090517 1.260778 0.2160452 4.982495 5.198540
## 2 1 12 116 4.935345 1.316336 0.2160452 4.827322 5.043367
## 3 2 1 119 4.865546 1.328784 0.2160452 4.757524 4.973569
## 4 2 12 119 4.676471 1.369443 0.2160452 4.568448 4.784493*where X-axis Q = days; and Y-axis “Mean” = responses to the construct; C1 = control, C2 = goal salience
Result: significant effect of time (Q); intention to walk 7000 steps decreased for both conditions
-
GOAL Desire
## Call:corr.test(x = .)
## Correlation matrix
## GOAL1_D GD2_D
## GOAL1_D 1.00 0.78
## GD2_D 0.78 1.00
## Sample Size
## GOAL1_D GD2_D
## GOAL1_D 403 403
## GD2_D 403 475
## Probability values (Entries above the diagonal are adjusted for multiple tests.)
## GOAL1_D GD2_D
## GOAL1_D 0 0
## GD2_D 0 0
##
## To see confidence intervals of the correlations, print with the short=FALSE option## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 235 1.520934e+04 464.1351 7700.7609366 1.322001e-181 *
## 2 C 1 235 2.029407e+00 464.1351 1.0275256 3.117831e-01
## 3 Q 1 235 9.303797e-01 168.4582 1.2978840 2.557600e-01
## 4 C:Q 1 235 1.113938e-01 168.4582 0.1553948 6.937898e-01
## ges
## 1 0.9600684119
## 2 0.0031978168
## 3 0.0014685791
## 4 0.0001760596## C Q N Mean SD FLSD lo hi
## 1 1 1 117 5.538462 1.185679 0.2166998 5.430112 5.646811
## 2 1 12 117 5.658120 1.138377 0.2166998 5.549770 5.766470
## 3 2 1 120 5.700000 1.213371 0.2166998 5.591650 5.808350
## 4 2 12 120 5.758333 1.100006 0.2166998 5.649983 5.866683Result: no significant effects of goal desire
-
Behavior Desire
## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 233 1.360817e+04 632.0833 5.016275e+03 1.358184e-159 *
## 2 C 1 233 2.443142e-01 632.0833 9.005964e-02 7.643689e-01
## 3 Q 1 233 7.680851e-01 155.1343 1.153605e+00 2.839067e-01
## 4 C:Q 1 233 5.975698e-01 155.1343 8.975044e-01 3.444332e-01
## ges
## 1 0.9453145980
## 2 0.0003102552
## 3 0.0009747449
## 4 0.0007585151## C Q N Mean SD FLSD lo hi
## 1 1 1 116 5.353448 1.340047 0.2097403 5.248578 5.458318
## 2 1 12 116 5.362069 1.294783 0.2097403 5.257199 5.466939
## 3 2 1 119 5.327731 1.353647 0.2097403 5.222861 5.432601
## 4 2 12 119 5.478992 1.206260 0.2097403 5.374121 5.583862Result: no significant effects
-
Attitude
## Call:corr.test(x = .)
## Correlation matrix
## ATT1_D ATT2_D ATT3_D ATT4_D ATT5_D ATT6_D
## ATT1_D 1.00 0.43 0.37 0.32 0.20 0.29
## ATT2_D 0.43 1.00 0.37 0.34 0.23 0.35
## ATT3_D 0.37 0.37 1.00 0.77 0.41 0.39
## ATT4_D 0.32 0.34 0.77 1.00 0.55 0.41
## ATT5_D 0.20 0.23 0.41 0.55 1.00 0.70
## ATT6_D 0.29 0.35 0.39 0.41 0.70 1.00
## Sample Size
## [1] 475
## Probability values (Entries above the diagonal are adjusted for multiple tests.)
## ATT1_D ATT2_D ATT3_D ATT4_D ATT5_D ATT6_D
## ATT1_D 0 0 0 0 0 0
## ATT2_D 0 0 0 0 0 0
## ATT3_D 0 0 0 0 0 0
## ATT4_D 0 0 0 0 0 0
## ATT5_D 0 0 0 0 0 0
## ATT6_D 0 0 0 0 0 0
##
## To see confidence intervals of the correlations, print with the short=FALSE option##
## Reliability analysis
## Call: psych::alpha(x = .)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.81 0.81 0.83 0.41 4.1 0.013 5.8 1 0.37
##
## 95% confidence boundaries
## lower alpha upper
## Feldt 0.78 0.81 0.83
## Duhachek 0.78 0.81 0.83
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## ATT1_D 0.81 0.80 0.83 0.45 4.1 0.014 0.029 0.40
## ATT2_D 0.80 0.80 0.82 0.44 3.9 0.013 0.032 0.40
## ATT3_D 0.76 0.76 0.76 0.38 3.1 0.017 0.023 0.35
## ATT4_D 0.75 0.75 0.75 0.37 3.0 0.018 0.019 0.37
## ATT5_D 0.77 0.77 0.77 0.40 3.4 0.016 0.018 0.37
## ATT6_D 0.77 0.77 0.77 0.40 3.3 0.016 0.027 0.37
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## ATT1_D 475 0.54 0.61 0.48 0.42 6.4 0.96
## ATT2_D 475 0.61 0.64 0.51 0.44 5.6 1.34
## ATT3_D 475 0.78 0.77 0.75 0.65 5.4 1.53
## ATT4_D 475 0.82 0.79 0.79 0.70 5.3 1.60
## ATT5_D 475 0.76 0.72 0.69 0.60 6.1 1.68
## ATT6_D 475 0.74 0.73 0.69 0.61 6.1 1.43
##
## Non missing response frequency for each item
## 1 2 3 4 5 6 7 miss
## ATT1_D 0.00 0.00 0.00 0.05 0.09 0.22 0.63 0
## ATT2_D 0.01 0.02 0.04 0.12 0.22 0.27 0.33 0
## ATT3_D 0.03 0.03 0.05 0.13 0.23 0.25 0.28 0
## ATT4_D 0.04 0.04 0.05 0.12 0.23 0.23 0.29 0
## ATT5_D 0.07 0.02 0.01 0.02 0.06 0.19 0.63 0
## ATT6_D 0.04 0.01 0.02 0.05 0.10 0.25 0.53 0## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 235 1.600690e+04 362.1654 1.038647e+04 1.755979e-196 *
## 2 C 1 235 1.393708e+00 362.1654 9.043420e-01 3.425971e-01
## 3 Q 1 235 4.037154e-01 135.6621 6.993342e-01 4.038570e-01
## 4 C:Q 1 235 2.114776e+00 135.6621 3.663312e+00 5.683771e-02
## ges
## 1 0.9698372813
## 2 0.0027917646
## 3 0.0008102974
## 4 0.0042300417## C Q N Mean SD FLSD lo hi
## 1 1 1 117 5.827635 1.0499798 0.1944651 5.730403 5.924868
## 2 1 12 117 5.904558 1.0376800 0.1944651 5.807326 6.001791
## 3 2 1 120 5.852778 0.9291381 0.1944651 5.755545 5.950010
## 4 2 12 120 5.662500 1.0935390 0.1944651 5.565267 5.759733Result: no significant effects
-
Emotions
PAE
## Call:corr.test(x = .)
## Correlation matrix
## EM1_D EM2_D EM3_D
## EM1_D 1.00 0.78 0.73
## EM2_D 0.78 1.00 0.83
## EM3_D 0.73 0.83 1.00
## Sample Size
## [1] 474
## Probability values (Entries above the diagonal are adjusted for multiple tests.)
## EM1_D EM2_D EM3_D
## EM1_D 0 0 0
## EM2_D 0 0 0
## EM3_D 0 0 0
##
## To see confidence intervals of the correlations, print with the short=FALSE option## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 234 1.663391e+04 395.3079 9846.3342548 3.262967e-193 *
## 2 C 1 234 2.297171e-01 395.3079 0.1359796 7.126445e-01
## 3 Q 1 234 9.048964e-01 123.8086 1.7102671 1.922341e-01
## 4 C:Q 1 234 6.429125e-02 123.8086 0.1215114 7.277144e-01
## ges
## 1 0.9697361492
## 2 0.0004423197
## 3 0.0017401137
## 4 0.0001238321## C Q N Mean SD FLSD lo hi
## 1 1 1 117 6.014245 1.0875410 0.1865699 5.920960 6.107530
## 2 1 12 117 5.903134 1.1193695 0.1865699 5.809849 5.996419
## 3 2 1 119 5.946779 0.9990421 0.1865699 5.853494 6.040064
## 4 2 12 119 5.882353 1.0033731 0.1865699 5.789068 5.975638Results: no significant effects
-
NAE
## Call:corr.test(x = .)
## Correlation matrix
## EM4_D EM5_D EM6_D
## EM4_D 1.00 0.74 0.53
## EM5_D 0.74 1.00 0.52
## EM6_D 0.53 0.52 1.00
## Sample Size
## [1] 473
## Probability values (Entries above the diagonal are adjusted for multiple tests.)
## EM4_D EM5_D EM6_D
## EM4_D 0 0 0
## EM5_D 0 0 0
## EM6_D 0 0 0
##
## To see confidence intervals of the correlations, print with the short=FALSE option## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 233 5581.5321513 627.4676 2.072612e+03 5.930475e-118 *
## 2 C 1 233 4.0557902 627.4676 1.506052e+00 2.209809e-01
## 3 Q 1 233 0.0286052 211.5166 3.151058e-02 8.592603e-01
## 4 C:Q 1 233 1.0658561 211.5166 1.174113e+00 2.796777e-01
## ges
## 1 8.693276e-01
## 2 4.810910e-03
## 3 3.409388e-05
## 4 1.268801e-03## C Q N Mean SD FLSD lo hi
## 1 1 1 116 3.295977 1.387154 0.2449064 3.173524 3.418430
## 2 1 12 116 3.408046 1.234047 0.2449064 3.285593 3.530499
## 3 2 1 119 3.577031 1.445623 0.2449064 3.454578 3.699484
## 4 2 12 119 3.498599 1.288712 0.2449064 3.376146 3.621053Results: no significant effects
-
NORMS_D_In
dat_NORMS<- select(sub, NORMS_D_In, NORM_D_Des, Q, C, RecipientEmail)
select(dat_NORMS, NORMS_D_In, NORM_D_Des) %>% corr.test()## Call:corr.test(x = .)
## Correlation matrix
## NORMS_D_In NORM_D_Des
## NORMS_D_In 1.00 0.16
## NORM_D_Des 0.16 1.00
## Sample Size
## [1] 475
## Probability values (Entries above the diagonal are adjusted for multiple tests.)
## NORMS_D_In NORM_D_Des
## NORMS_D_In 0 0
## NORM_D_Des 0 0
##
## To see confidence intervals of the correlations, print with the short=FALSE option#only 0.16 correlated, kept seperate
#NORMS_D_In
dat_NORMS_D_In<- select(sub, NORMS_D_In, Q, C, RecipientEmail)
#ggqqplot(sub, "NORMS_D_In", facet.by= "Q")
#ggboxplot(sub, x = "Q", y="NORMS_D_In", add = "point")
dat_NORMS_D_In$RecipientEmail<- as.factor(dat_NORMS_D_In$RecipientEmail)
dat_NORMS_D_In$Q<- as.factor(dat_NORMS_D_In$Q)
dat_NORMS_D_In$NORMS_D_In<- as.numeric(dat_NORMS_D_In$NORMS_D_In)
dat_NORMS_D_In<- na.omit(dat_NORMS_D_In)
pps<- aggregate(dat_NORMS_D_In$'NORMS_D_In', by=list(dat_NORMS_D_In$RecipientEmail), length)
names(pps)[1] <- 'RecipientEmail'
names(pps)[2] <- 'complete'
dat_NORMS_D_In <- merge(pps, dat_NORMS_D_In, by="RecipientEmail")
dat_NORMS_D_In<- dplyr::filter(dat_NORMS_D_In, complete == 2)
fit<- ezANOVA(data = dat_NORMS_D_In,
dv = NORMS_D_In,
wid = RecipientEmail,
within = Q,
between = C,
detailed = TRUE,
within_full = c(Q, NORMS_D_In)
)## Warning: You have removed one or more Ss from the analysis. Refactoring
## "RecipientEmail" for ANOVA.## Warning: Converting "C" to factor for ANOVA.## Warning: Data is unbalanced (unequal N per group). Make sure you specified a
## well-considered value for the type argument to ezANOVA().## Warning: Collapsing data to cell means first using variables supplied to
## "within_full", then collapsing the resulting means to means for the cells
## supplied to "within".fit## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 235 1.788976e+04 474.4531 8.860923e+03 1.437328e-188 *
## 2 C 1 235 1.791627e+00 474.4531 8.874058e-01 3.471487e-01
## 3 Q 1 235 0.000000e+00 111.9916 0.000000e+00 1.000000e+00
## 4 C:Q 1 235 8.440171e-03 111.9916 1.771062e-02 8.942430e-01
## ges
## 1 9.682595e-01
## 2 3.045762e-03
## 3 0.000000e+00
## 4 1.439189e-05#no sig effects
means<- ezPlot(data = dat_NORMS_D_In,
dv = NORMS_D_In,
wid = RecipientEmail,
within = Q,
between = C,
x= Q,
split = C
)## Warning: You have removed one or more Ss from the analysis. Refactoring
## "RecipientEmail" for ANOVA.## Warning: Converting "C" to factor for ANOVA.## Warning: Data is unbalanced (unequal N per group). Make sure you specified a
## well-considered value for the type argument to ezANOVA().## Warning in ezStats(data = data, dv = dv, wid = wid, within = within, within_full
## = within_full, : Unbalanced groups. Mean N will be used in computation of FLSD means$data## C Q N Mean SD FLSD lo hi
## 1 1 1 117 6.076923 1.197367 0.1766872 5.988579 6.165267
## 2 1 12 117 6.085470 1.110861 0.1766872 5.997126 6.173814
## 3 2 1 120 6.208333 1.129407 0.1766872 6.119990 6.296677
## 4 2 12 120 6.200000 1.025720 0.1766872 6.111656 6.288344Results: no significant effects
-
NORM_D_Des
## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 235 1.209122e+04 647.9240 4385.4455167 5.337060e-154 *
## 2 C 1 235 1.860772e+00 647.9240 0.6748960 4.121825e-01
## 3 Q 1 235 6.835443e-01 219.6163 0.7314251 3.932927e-01
## 4 C:Q 1 235 2.700110e+00 219.6163 2.8892464 9.049576e-02
## ges
## 1 0.9330537273
## 2 0.0021402912
## 3 0.0007872903
## 4 0.0031027165## C Q N Mean SD FLSD lo hi
## 1 1 1 117 5.025641 1.476608 0.2474256 4.901928 5.149354
## 2 1 12 117 4.948718 1.244617 0.2474256 4.825005 5.072431
## 3 2 1 120 5.000000 1.365850 0.2474256 4.876287 5.123713
## 4 2 12 120 5.225000 1.337642 0.2474256 5.101287 5.348713Result: no significant effects
-
Past Behavior
## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05 ges
## 1 C 1 229 6.036498 581.2968 2.378059 0.1244311 0.01027781
##
## $`Levene's Test for Homogeneity of Variance`
## DFn DFd SSn SSd F p p<.05
## 1 1 229 0.09050976 231.0523 0.0897058 0.7648232## C N Mean SD FLSD lo hi
## 1 1 113 4.831858 1.580589 0.4130995 4.625309 5.038408
## 2 2 118 4.508475 1.605257 0.4130995 4.301925 4.715024Results: no significant effect of condition
-
Perceived behavioral control
## Call:corr.test(x = .)
## Correlation matrix
## PBS_D_Aut PBC_D_Cap
## PBS_D_Aut 1.00 0.64
## PBC_D_Cap 0.64 1.00
## Sample Size
## [1] 474
## Probability values (Entries above the diagonal are adjusted for multiple tests.)
## PBS_D_Aut PBC_D_Cap
## PBS_D_Aut 0 0
## PBC_D_Cap 0 0
##
## To see confidence intervals of the correlations, print with the short=FALSE option## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 234 1.067802e+04 647.7875 3857.2160693 2.193150e-147 *
## 2 C 1 234 1.794340e+01 647.7875 6.4816880 1.154182e-02 *
## 3 Q 1 234 4.101695e+00 204.3321 4.6972386 3.122036e-02 *
## 4 C:Q 1 234 8.162107e-01 204.3321 0.9347201 3.346376e-01
## ges
## 1 0.9260963250
## 2 0.0206231087
## 3 0.0047904611
## 4 0.0009569427
## C Q N Mean SD FLSD lo hi
## 1 1 1 117 5.004274 1.302345 0.2396815 4.884433 5.124114
## 2 1 12 117 4.901709 1.364954 0.2396815 4.781869 5.021550
## 3 2 1 119 4.697479 1.347028 0.2396815 4.577638 4.817320
## 4 2 12 119 4.428571 1.381300 0.2396815 4.308731 4.548412*where X-axis Q = days; and Y-axis “Mean” = responses to the construct; C1 = control, C2 = goal salience
Result: significant effect of time (Q), PBC to walk 7000 steps decreased for both conditions; and significant effect of condition (C), overall C1 had higher PBC than C2
-
Goal Desire Not Doing
## Call:corr.test(x = .)
## Correlation matrix
## GD1_ND GD2_ND
## GD1_ND 1.00 0.83
## GD2_ND 0.83 1.00
## Sample Size
## [1] 473
## Probability values (Entries above the diagonal are adjusted for multiple tests.)
## GD1_ND GD2_ND
## GD1_ND 0 0
## GD2_ND 0 0
##
## To see confidence intervals of the correlations, print with the short=FALSE option## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 233 7226.9127660 1080.6246 1.558238e+03 3.567604e-105 *
## 2 C 1 233 12.4626325 1080.6246 2.687143e+00 1.025105e-01
## 3 Q 1 233 0.4787234 537.3562 2.075766e-01 6.490978e-01
## 4 C:Q 1 233 0.1651117 537.3562 7.159317e-02 7.892678e-01
## ges
## 1 0.8170717646
## 2 0.0076437075
## 3 0.0002957896
## 4 0.0001020376## C Q N Mean SD FLSD lo hi
## 1 1 1 116 4.073276 1.931720 0.3903543 3.878099 4.268453
## 2 1 12 116 4.099138 1.840628 0.3903543 3.903961 4.294315
## 3 2 1 119 3.710084 1.747269 0.3903543 3.514907 3.905261
## 4 2 12 119 3.810924 1.928809 0.3903543 3.615747 4.006102Results: no significant effects
-
Attitude Not Doing
## Call:corr.test(x = .)
## Correlation matrix
## ATT1_ND ATT2_ND ATT3_ND ATT4_ND ATT5_ND ATT6_ND
## ATT1_ND 1.00 0.19 0.45 0.45 0.40 0.42
## ATT2_ND 0.19 1.00 0.19 0.23 0.11 0.21
## ATT3_ND 0.45 0.19 1.00 0.71 0.44 0.40
## ATT4_ND 0.45 0.23 0.71 1.00 0.45 0.49
## ATT5_ND 0.40 0.11 0.44 0.45 1.00 0.52
## ATT6_ND 0.42 0.21 0.40 0.49 0.52 1.00
## Sample Size
## [1] 473
## Probability values (Entries above the diagonal are adjusted for multiple tests.)
## ATT1_ND ATT2_ND ATT3_ND ATT4_ND ATT5_ND ATT6_ND
## ATT1_ND 0 0.00 0 0 0.00 0
## ATT2_ND 0 0.00 0 0 0.01 0
## ATT3_ND 0 0.00 0 0 0.00 0
## ATT4_ND 0 0.00 0 0 0.00 0
## ATT5_ND 0 0.01 0 0 0.00 0
## ATT6_ND 0 0.00 0 0 0.00 0
##
## To see confidence intervals of the correlations, print with the short=FALSE option##
## Reliability analysis
## Call: psych::alpha(x = .)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.78 0.78 0.78 0.38 3.6 0.016 2.8 0.94 0.42
##
## 95% confidence boundaries
## lower alpha upper
## Feldt 0.74 0.78 0.81
## Duhachek 0.74 0.78 0.81
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## ATT1_ND 0.74 0.75 0.75 0.37 3.0 0.019 0.0341 0.42
## ATT2_ND 0.82 0.82 0.80 0.47 4.5 0.013 0.0082 0.45
## ATT3_ND 0.72 0.73 0.70 0.35 2.7 0.021 0.0210 0.41
## ATT4_ND 0.70 0.71 0.69 0.33 2.5 0.022 0.0199 0.40
## ATT5_ND 0.74 0.75 0.74 0.37 3.0 0.019 0.0285 0.41
## ATT6_ND 0.73 0.74 0.73 0.36 2.8 0.020 0.0319 0.42
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## ATT1_ND 473 0.69 0.70 0.60 0.54 2.4 1.2
## ATT2_ND 473 0.49 0.46 0.27 0.24 3.3 1.5
## ATT3_ND 473 0.76 0.77 0.74 0.63 2.8 1.3
## ATT4_ND 473 0.79 0.80 0.79 0.68 2.9 1.3
## ATT5_ND 473 0.70 0.70 0.61 0.53 2.7 1.4
## ATT6_ND 473 0.73 0.73 0.66 0.58 2.9 1.4
##
## Non missing response frequency for each item
## 1 2 3 4 5 6 7 miss
## ATT1_ND 0.28 0.29 0.25 0.15 0.02 0.01 0.01 0.01
## ATT2_ND 0.16 0.16 0.22 0.29 0.10 0.03 0.04 0.01
## ATT3_ND 0.18 0.27 0.27 0.19 0.04 0.03 0.01 0.01
## ATT4_ND 0.16 0.22 0.29 0.25 0.05 0.02 0.02 0.01
## ATT5_ND 0.22 0.28 0.23 0.19 0.03 0.02 0.02 0.01
## ATT6_ND 0.18 0.24 0.24 0.27 0.03 0.03 0.02 0.01## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 233 3.766447e+03 308.64087 2.843377e+03 1.496617e-132 *
## 2 C 1 233 7.034532e-01 308.64087 5.310528e-01 4.668964e-01
## 3 Q 1 233 2.345745e-01 96.96097 5.636892e-01 4.535352e-01
## 4 C:Q 1 233 4.056317e-02 96.96097 9.747447e-02 7.551609e-01
## ges
## 1 9.027811e-01
## 2 1.731341e-03
## 3 5.780025e-04
## 4 9.999737e-05## C Q N Mean SD FLSD lo hi
## 1 1 1 116 2.804598 0.8634488 0.165816 2.721690 2.887506
## 2 1 12 116 2.778736 0.9782109 0.165816 2.695828 2.861644
## 3 2 1 119 2.900560 0.9325964 0.165816 2.817652 2.983468
## 4 2 12 119 2.837535 0.9531053 0.165816 2.754627 2.920443Results: no significant effects
-
Perceived Beh Control Not Doing
## Call:corr.test(x = .)
## Correlation matrix
## PBC_ND_Aut PBC_ND_Cap
## PBC_ND_Aut 1.00 0.26
## PBC_ND_Cap 0.26 1.00
## Sample Size
## [1] 473
## Probability values (Entries above the diagonal are adjusted for multiple tests.)
## PBC_ND_Aut PBC_ND_Cap
## PBC_ND_Aut 0 0
## PBC_ND_Cap 0 0
##
## To see confidence intervals of the correlations, print with the short=FALSE option## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 233 7258.3170213 678.0608 2494.1538943 1.878486e-126 *
## 2 C 1 233 0.1222264 678.0608 0.0420003 8.377981e-01
## 3 Q 1 233 1.6680851 220.5644 1.7621327 1.856579e-01
## 4 C:Q 1 233 2.2674680 220.5644 2.3953092 1.230568e-01
## ges
## 1 0.8898330802
## 2 0.0001359964
## 3 0.0018528241
## 4 0.0025169125## C Q N Mean SD FLSD lo hi
## 1 1 1 116 3.956897 1.464907 0.2500896 3.831852 4.081941
## 2 1 12 116 3.935345 1.377664 0.2500896 3.810300 4.060390
## 3 2 1 119 3.785714 1.344435 0.2500896 3.660669 3.910759
## 4 2 12 119 4.042017 1.366332 0.2500896 3.916972 4.167062Results: no significant effects
-
Behavior Desire Not Doing
## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 233 2.261619e+03 570.844 923.11956819 5.288682e-83 *
## 2 C 1 233 3.685657e-02 570.844 0.01504366 9.024879e-01
## 3 Q 1 233 1.551064e+00 256.041 1.41148417 2.360198e-01
## 4 C:Q 1 233 9.078973e-01 256.041 0.82619599 3.643140e-01
## ges
## 1 0.7322700620
## 2 0.0000445708
## 3 0.0018722794
## 4 0.0010967687## C Q N Mean SD FLSD lo hi
## 1 1 1 116 2.189655 1.382586 0.2694528 2.054929 2.324382
## 2 1 12 116 2.215517 1.317481 0.2694528 2.080791 2.350244
## 3 2 1 119 2.084034 1.337718 0.2694528 1.949307 2.218760
## 4 2 12 119 2.285714 1.289743 0.2694528 2.150988 2.420441Results: no significant effects
-
Intentions Not doing
## Call:corr.test(x = .)
## Correlation matrix
## INT1_ND INT2_ND
## INT1_ND 1.00 0.39
## INT2_ND 0.39 1.00
## Sample Size
## [1] 473
## Probability values (Entries above the diagonal are adjusted for multiple tests.)
## INT1_ND INT2_ND
## INT1_ND 0 0
## INT2_ND 0 0
##
## To see confidence intervals of the correlations, print with the short=FALSE option## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 233 2140.4446809 599.3508 832.1064014 7.526068e-79 *
## 2 C 1 233 0.7045513 599.3508 0.2738971 6.012268e-01
## 3 Q 1 233 2.3170213 237.5981 2.2721814 1.330690e-01
## 4 C:Q 1 233 0.5848912 237.5981 0.5735722 4.496081e-01
## ges
## 1 0.7188988136
## 2 0.0008411012
## 3 0.0027607715
## 4 0.0006983494## C Q N Mean SD FLSD lo hi
## 1 1 1 116 2.870690 1.330447 0.2501876 2.745596 2.995783
## 2 1 12 116 2.879310 1.250427 0.2501876 2.754217 3.004404
## 3 2 1 119 2.857143 1.275823 0.2501876 2.732049 2.982237
## 4 2 12 119 3.264706 1.308097 0.2501876 3.139612 3.389800Results: no significant effects
-
Habit
## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 (Intercept) 1 233 976752.07660 136239.63 1670.4627937 2.991821e-108 *
## 2 C 1 233 647.29286 136239.63 1.1070144 2.938218e-01
## 3 Q 1 233 46.60426 20782.13 0.5225063 4.704995e-01
## 4 C:Q 1 233 14.27013 20782.13 0.1599904 6.895318e-01
## ges
## 1 8.615052e-01
## 2 4.105390e-03
## 3 2.967132e-04
## 4 9.087169e-05## C Q N Mean SD FLSD lo hi
## 1 1 1 116 46.28448 19.09464 2.427576 45.07069 47.49827
## 2 1 12 116 47.26724 18.40102 2.427576 46.05345 48.48103
## 3 2 1 119 44.28571 18.49147 2.427576 43.07193 45.49950
## 4 2 12 119 44.57143 17.41934 2.427576 43.35764 45.78522Results: no significant effects
-
Moderation Analysis
Not doing intention
## Formula:
## steps ~ C + av + C.XX.av
## <environment: 0x7f9ad849bd88>
##
## Models
## R R^2 Adj. R^2 F df1 df2 p.value
## Model 0.379 0.144 0.132 11.664 3.000 208 4.3e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -47.1469 -11.0859 0.5154 0.0000 9.1322 52.0657
##
## Coefficients
## Estimate StdErr t.value beta p.value
## (Intercept) 98.3635 9.0296 10.8935 < 2e-16 ***
## C -11.8882 5.8408 -2.0354 -0.3195 0.04308 *
## av -8.6655 2.8350 -3.0566 -0.6067 0.00253 **
## C.XX.av 2.5353 1.8388 1.3788 0.3382 0.16943
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Collinearity
## VIF Tolerance
## C 5.9888 0.1670
## av 9.5728 0.1045
## C.XX.av 14.6230 0.0684
## Formula:
## steps ~ C + av + C.XX.av
## <environment: 0x7f9acdd88c28>
##
## Models
## R R^2 Adj. R^2 F df1 df2 p.value
## Model 0.548 0.300 0.290 29.693 3.000 208 5.1e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -53.283 -9.679 1.292 0.000 9.186 46.576
##
## Coefficients
## Estimate StdErr t.value beta p.value
## (Intercept) 107.5371 8.9479 12.0182 < 2e-16 ***
## C -11.3206 5.8010 -1.9515 -0.3043 0.05234 .
## av -12.4172 2.7525 -4.5113 -0.8418 1e-05 ***
## C.XX.av 3.0554 1.7293 1.7668 0.4430 0.07872 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Collinearity
## VIF Tolerance
## C 7.2226 0.1385
## av 10.3444 0.0967
## C.XX.av 18.6724 0.0536##
## Call:
## lm(formula = steps ~ av, data = MOD2)
##
## Residuals:
## Min 1Q Median 3Q Max
## -56.244 -10.412 1.508 9.286 47.365
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 91.0482 2.8851 31.558 <2e-16 ***
## av -7.9021 0.8595 -9.194 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 15.78 on 210 degrees of freedom
## Multiple R-squared: 0.287, Adjusted R-squared: 0.2836
## F-statistic: 84.53 on 1 and 210 DF, p-value: < 2.2e-16
T0 Results:
Model significant;
significant effect of condition (C), C1 (control) higher overall T0 nd_intention;
significant effect of not_doing_int (av), low nd_intention is predictive of more steps;
interaction effect not significant
T1 Results:
Model significant;
significant effect of T1 nd_intention, low nd_intention is predictive of more steps;
interaction not significant;
T1 nd_intention explains 28% of the variation in steps, independent of condition
-
Doing Intention
## Formula:
## steps ~ C + av + C.XX.av
## <environment: 0x7f9acc6f3648>
##
## Models
## R R^2 Adj. R^2 F df1 df2 p.value
## Model 0.506 0.256 0.245 23.835 3.000 208 2.7e-13 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -35.9069 -10.7886 -0.1856 0.0000 10.4731 55.3522
##
## Coefficients
## Estimate StdErr t.value beta p.value
## (Intercept) 10.26536 14.21357 0.72222 0.47097
## C 14.59833 8.85612 1.64839 0.3924 0.10078
## av 12.11873 2.73558 4.43003 0.8425 2e-05 ***
## C.XX.av -3.49586 1.73055 -2.02009 -0.5726 0.04466 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Collinearity
## VIF Tolerance
## C 15.838 0.0631
## av 10.109 0.0989
## C.XX.av 22.459 0.0445## Simple Slope:
## simple slope standard error t-value p.value
## Low av (-1 SD) 1.815404 3.166969 0.5732305 0.56710781
## High av (+1 SD) -7.247510 3.170408 -2.2859863 0.02326242
## Formula:
## steps ~ C + av + C.XX.av
## <environment: 0x7f9ab9c07290>
##
## Models
## R R^2 Adj. R^2 F df1 df2 p.value
## Model 0.553 0.306 0.296 30.504 3.000 208 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -42.4548 -7.7783 0.4915 0.0000 9.2720 44.8410
##
## Coefficients
## Estimate StdErr t.value beta p.value
## (Intercept) 17.84210 13.33006 1.33849 0.1822
## C 7.53083 8.34703 0.90222 0.2024 0.3680
## av 11.03382 2.67325 4.12749 0.7542 5e-05 ***
## C.XX.av -2.13513 1.69943 -1.25638 -0.3390 0.2104
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Collinearity
## VIF Tolerance
## C 15.076 0.0663
## av 10.001 0.1000
## C.XX.av 21.803 0.0459##
## Call:
## lm(formula = steps ~ av, data = MOD2)
##
## Residuals:
## Min 1Q Median 3Q Max
## -41.061 -7.542 0.188 9.604 46.235
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 28.7142 4.1648 6.894 6.22e-11 ***
## av 7.9517 0.8474 9.384 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 15.69 on 210 degrees of freedom
## Multiple R-squared: 0.2954, Adjusted R-squared: 0.2921
## F-statistic: 88.06 on 1 and 210 DF, p-value: < 2.2e-16
Results:
T0:
Model significant
no sig effect of condition
significant effect of d_intention (av); the higher the d_intention, the more steps performed
significant interaction effect
- simple slope: only (+1 SD) significant; for those high in d_intentions, perform more steps in control (C1) than experimental (C2) condition
T1:
model significant
no sig effect of condition
sig effect of d_intention (av); the higher the d_intention, the more steps performed, d_intention explained 29% of the variation in steps
no sig interaction effect
-
Habit
## Formula:
## steps ~ C + total + C.XX.total
## <environment: 0x7f9abaf4c010>
##
## Models
## R R^2 Adj. R^2 F df1 df2 p.value
## Model 0.406 0.165 0.153 13.724 3.000 208 3.3e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -41.662 -11.924 1.071 0.000 11.484 50.005
##
## Coefficients
## Estimate StdErr t.value beta p.value
## (Intercept) 57.81607 9.78987 5.90571 <2e-16 ***
## C -5.88742 6.18445 -0.95197 -0.1582 0.3422
## total 0.30776 0.19956 1.54224 0.3046 0.1245
## C.XX.total 0.05719 0.12876 0.44413 0.1066 0.6574
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Collinearity
## VIF Tolerance
## C 6.8851 0.1452
## total 9.7214 0.1029
## C.XX.total 14.3519 0.0697
## Formula:
## steps ~ C + total + C.XX.total
## <environment: 0x7f9ace88fe78>
##
## Models
## R R^2 Adj. R^2 F df1 df2 p.value
## Model 0.532 0.283 0.273 27.426 3.000 208 5.5e-15 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -44.595 -9.014 1.484 0.000 11.635 40.369
##
## Coefficients
## Estimate StdErr t.value beta p.value
## (Intercept) 46.47048 9.50519 4.88896 < 2e-16 ***
## C -3.28026 6.05882 -0.54140 -0.0882 0.58881
## total 0.54670 0.19497 2.80410 0.5096 0.00552 **
## C.XX.total 0.00746 0.12695 0.05873 0.0133 0.95322
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Collinearity
## VIF Tolerance
## C 7.6983 0.1299
## total 9.5883 0.1043
## C.XX.total 14.9787 0.0668##
## Call:
## lm(formula = steps ~ total, data = MOD2)
##
## Residuals:
## Min 1Q Median 3Q Max
## -43.208 -10.254 0.775 11.339 42.182
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 41.25026 3.01431 13.685 <2e-16 ***
## total 0.56479 0.06294 8.974 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 15.89 on 210 degrees of freedom
## Multiple R-squared: 0.2772, Adjusted R-squared: 0.2738
## F-statistic: 80.54 on 1 and 210 DF, p-value: < 2.2e-16
Results:
T0:
model significant
no significant effects
T1:
model significant
significant effect of SRHI (total), the higher SRHI the more steps were performed, SRHI explains 27% of the variation in steps at T1
no sig interaction
-
-
Exploratory Law of Recency Analyses
*the following analyses attempted to replicate the law of recency paper
I used days as a clustering variable (similar to trials)
Tested the effect on the number of steps completed by days of a goal achievement (R_Goal), days following a goal achievement (Prev_R), and Condition (1 = control, 2 =experimental)
## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 Prev_R 1 56 286.195436 637.3104 25.1477843 5.681427e-06 *
## 2 R_Goal 1 56 34276.738682 637.3104 3011.8720342 2.226335e-50 *
## 3 C 1 56 8.133155 637.3104 0.7146544 4.015006e-01
## 4 Prev_R:R_Goal 1 56 175.002484 637.3104 15.3773407 2.425513e-04 *
## 5 Prev_R:C 1 56 59.031894 637.3104 5.1870895 2.659416e-02 *
## 6 R_Goal:C 1 56 23.293945 637.3104 2.0468220 1.580809e-01
## 7 Prev_R:R_Goal:C 1 56 100.522491 637.3104 8.8328380 4.354395e-03 *
## ges
## 1 0.30990106
## 2 0.98174631
## 3 0.01260088
## 4 0.21543729
## 5 0.08477425
## 6 0.03526157
## 7 0.13624019
##
## $`Levene's Test for Homogeneity of Variance`
## DFn DFd SSn SSd F p p<.05
## 1 7 56 60.06051 231.2607 2.077673 0.06107351
##
## $aov
## Call:
## aov(formula = formula(aov_formula), data = data)
##
## Terms:
## Prev_R R_Goal C Prev_R:R_Goal Prev_R:C R_Goal:C
## Sum of Squares 286.20 34276.74 8.13 175.00 59.03 23.29
## Deg. of Freedom 1 1 1 1 1 1
## Prev_R:R_Goal:C Residuals
## Sum of Squares 100.52 637.31
## Deg. of Freedom 1 56
##
## Residual standard error: 3.373506
## Estimated effects may be unbalanced
## 24 observations deleted due to missingness## Prev_R R_Goal C N Mean SD FLSD lo hi
## 1 0 0 1 8 49.73809 3.255372 3.529221 47.97348 51.50270
## 2 0 0 2 8 49.64600 1.955276 3.529221 47.88139 51.41061
## 3 0 1 1 8 98.03032 2.680808 3.529221 96.26571 99.79493
## 4 0 1 2 8 100.53809 2.877008 3.529221 98.77348 102.30270
## 5 1 0 1 8 56.68892 3.025437 3.529221 54.92431 58.45353
## 6 1 0 2 8 57.76826 6.055855 3.529221 56.00365 59.53287
## 7 1 1 1 8 103.37977 2.743185 3.529221 101.61516 105.14438
## 8 1 1 2 8 97.03288 2.794311 3.529221 95.26827 98.79749
## 9 <NA> 0 1 7 55.28922 8.552164 3.529221 53.52461 57.05383
## 10 <NA> 0 2 8 50.40894 17.183259 3.529221 48.64433 52.17355
## 11 <NA> 1 1 5 100.16961 6.240567 3.529221 98.40500 101.93422
## 12 <NA> 1 2 4 93.70140 5.396216 3.529221 91.93679 95.46601## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = formula(aov_formula), data = data)
##
## $Prev_R
## diff lwr upr p adj
## 1-0 4.229328 2.539842 5.918814 5.7e-06
##
## $R_Goal
## diff lwr upr p adj
## 1-0 46.28495 44.59546 47.97443 0
##
## $C
## diff lwr upr p adj
## 2-1 -0.7129672 -2.402453 0.976519 0.4015006
##
## $`Prev_R:R_Goal`
## diff lwr upr p adj
## 1:0-0:0 7.5365405 4.378367 10.694714 0.0000003
## 0:1-0:0 49.5921580 46.433984 52.750332 0.0000000
## 1:1-0:0 50.5142733 47.356100 53.672447 0.0000000
## 0:1-1:0 42.0556174 38.897444 45.213791 0.0000000
## 1:1-1:0 42.9777328 39.819559 46.135906 0.0000000
## 1:1-0:1 0.9221153 -2.236058 4.080289 0.8662492
##
## $`Prev_R:C`
## diff lwr upr p adj
## 1:1-0:1 6.150133 2.9919597 9.308307 0.0000199
## 0:2-0:1 1.207838 -1.9503354 4.366012 0.7427175
## 1:2-0:1 3.516361 0.3581872 6.674534 0.0234086
## 0:2-1:1 -4.942295 -8.1004687 -1.784122 0.0006582
## 1:2-1:1 -2.633773 -5.7919462 0.524401 0.1335245
## 1:2-0:2 2.308523 -0.8496511 5.466696 0.2251686
##
## $`R_Goal:C`
## diff lwr upr p adj
## 1:1-0:1 47.4915404 44.333367 50.649714 0.0000000
## 0:2-0:1 0.4936278 -2.664546 3.651801 0.9758729
## 1:2-0:1 45.5719782 42.413805 48.730152 0.0000000
## 0:2-1:1 -46.9979125 -50.156086 -43.839739 0.0000000
## 1:2-1:1 -1.9195622 -5.077736 1.238611 0.3817296
## 1:2-0:2 45.0783503 41.920177 48.236524 0.0000000
##
## $`Prev_R:R_Goal:C`
## diff lwr upr p adj
## 1:0:1-0:0:1 6.95082331 1.640448 12.261199 0.0029796
## 0:1:1-0:0:1 48.29223037 42.981855 53.602606 0.0000000
## 1:1:1-0:0:1 53.64167373 48.331298 58.952049 0.0000000
## 0:0:2-0:0:1 -0.09208938 -5.402465 5.218286 1.0000000
## 1:0:2-0:0:1 8.03016839 2.719793 13.340544 0.0003554
## 0:1:2-0:0:1 50.79999620 45.489621 56.110372 0.0000000
## 1:1:2-0:0:1 47.29478349 41.984408 52.605159 0.0000000
## 0:1:1-1:0:1 41.34140706 36.031032 46.651782 0.0000000
## 1:1:1-1:0:1 46.69085041 41.380475 52.001226 0.0000000
## 0:0:2-1:0:1 -7.04291269 -12.353288 -1.732537 0.0025023
## 1:0:2-1:0:1 1.07934507 -4.231030 6.389720 0.9981078
## 0:1:2-1:0:1 43.84917289 38.538798 49.159548 0.0000000
## 1:1:2-1:0:1 40.34396017 35.033585 45.654336 0.0000000
## 1:1:1-0:1:1 5.34944335 0.039068 10.659819 0.0471108
## 0:0:2-0:1:1 -48.38431975 -53.694695 -43.073944 0.0000000
## 1:0:2-0:1:1 -40.26206199 -45.572437 -34.951687 0.0000000
## 0:1:2-0:1:1 2.50776583 -2.802610 7.818141 0.8111195
## 1:1:2-0:1:1 -0.99744689 -6.307822 4.312928 0.9988583
## 0:0:2-1:1:1 -53.73376311 -59.044138 -48.423388 0.0000000
## 1:0:2-1:1:1 -45.61150534 -50.921881 -40.301130 0.0000000
## 0:1:2-1:1:1 -2.84167752 -8.152053 2.468698 0.6967865
## 1:1:2-1:1:1 -6.34689024 -11.657266 -1.036515 0.0090143
## 1:0:2-0:0:2 8.12225777 2.811882 13.432633 0.0002943
## 0:1:2-0:0:2 50.89208558 45.581710 56.202461 0.0000000
## 1:1:2-0:0:2 47.38687287 42.076498 52.697248 0.0000000
## 0:1:2-1:0:2 42.76982782 37.459452 48.080203 0.0000000
## 1:1:2-1:0:2 39.26461510 33.954240 44.574990 0.0000000
## 1:1:2-0:1:2 -3.50521271 -8.815588 1.805163 0.4412510Results: *note steps have been transformed
sig main effect of previous response (Prev_R), for days after which participants achieved their goal, they completed more steps; M_0 = 74.4, M_1= 78.91
sig main effect of goal achievement (R_Goal), days where there was a goal achievement predicted more steps M_0 = 54.44, M_1=99.90
sig previous response and goal interaction, days in which there was a goal achievement following a previous achievement predicted more steps M_goal1_prev1 = 101, M_goal0_prev0 = 50.02
sig previous response and condition interaction, days following a goal achievement predicted the most number of steps for Condition 1 (M=109.24) compared to Condition 2 (M=77.39)
perhaps goal salience encourages people to achieve the goal but not continue further, a similar explanation could be used for the recycling study
-
Tested the effect on the total number days > 7000 steps (T_Goal, goal achievement) by days of a goal achievement (R_Goal), days following a goal achievement (Prev_R), and Condition (1 = control, 2 =experimental)
**I wanted to include a “Distance from last goal” variable but had trouble with the coding, perhaps something to discuss
## $ANOVA
## Effect DFn DFd SSn SSd F p p<.05
## 1 m_Prev_R 9 195 1.545624e+03 38.54187 868.88676335 3.477821e-152 *
## 2 C 1 195 5.329208e-03 38.54187 0.02696277 8.697411e-01
## 3 m_Prev_R:C 9 195 1.311424e+00 38.54187 0.73722923 6.744479e-01
## ges
## 1 0.9756705595
## 2 0.0001382515
## 3 0.0329062960
##
## $`Levene's Test for Homogeneity of Variance`
## DFn DFd SSn SSd F p p<.05
## 1 19 195 5.346504 31.04187 1.767678 0.0288383 *
##
## $aov
## Call:
## aov(formula = formula(aov_formula), data = data)
##
## Terms:
## m_Prev_R C m_Prev_R:C Residuals
## Sum of Squares 1577.4623 0.0053 1.3114 38.5419
## Deg. of Freedom 9 1 9 195
##
## Residual standard error: 0.4445791
## Estimated effects may be unbalanced## m_Prev_R C N Mean SD FLSD lo hi
## 1 0 1 22 0.04545455 0.2132007 0.3781914 -0.14364117 0.2345503
## 2 0 2 25 0.20000000 0.4082483 0.3781914 0.01090428 0.3890957
## 3 0.1 1 13 1.15384615 0.3755338 0.3781914 0.96475044 1.3429419
## 4 0.1 2 22 1.13636364 0.3512501 0.3781914 0.94726792 1.3254594
## 5 0.2 1 16 2.43750000 0.5123475 0.3781914 2.24840428 2.6265957
## 6 0.2 2 20 2.35000000 0.4893605 0.3781914 2.16090428 2.5390957
## 7 0.3 1 18 3.22222222 0.4277926 0.3781914 3.03312651 3.4113179
## 8 0.3 2 13 3.38461538 0.5063697 0.3781914 3.19551967 3.5737111
## 9 0.4 1 12 4.50000000 0.5222330 0.3781914 4.31090428 4.6890957
## 10 0.4 2 10 4.40000000 0.6992059 0.3781914 4.21090428 4.5890957
## 11 0.5 1 7 5.71428571 0.4879500 0.3781914 5.52519000 5.9033814
## 12 0.5 2 3 5.33333333 0.5773503 0.3781914 5.14423762 5.5224290
## 13 0.6 1 5 6.80000000 0.4472136 0.3781914 6.61090428 6.9890957
## 14 0.6 2 4 6.50000000 0.5773503 0.3781914 6.31090428 6.6890957
## 15 0.7 1 9 7.66666667 0.5000000 0.3781914 7.47757095 7.8557624
## 16 0.7 2 3 7.66666667 0.5773503 0.3781914 7.47757095 7.8557624
## 17 0.8 1 2 9.00000000 0.0000000 0.3781914 8.81090428 9.1890957
## 18 0.8 2 3 9.00000000 0.0000000 0.3781914 8.81090428 9.1890957
## 19 0.9 1 5 10.00000000 0.0000000 0.3781914 9.81090428 10.1890957
## 20 0.9 2 3 9.66666667 0.5773503 0.3781914 9.47757095 9.8557624Results:
significant effect of previous goal achievement
no effects of condition or interaction effects
participants who consistently achieved their goal (m_Prev_R =0.9, or 90% of the time) had more days of goal achievement (m_T_Goal = 9.83, which is near perfect) than participants who did not (m_Prev_R=0, m_T_Goal=0.125)
since there are no effects of condition on goal achievement, the previous assertion could explain the effect, that pps in the goal salience condition are simply focused on goal achievement and not “exceeding” number of expected steps
result also adds support for the law of recency effect
-
Habits and Goal Achievement
## Call:corr.test(x = .)
## Correlation matrix
## total m_s_steps m_Prev_R m_R_Goal
## total 1.00 0.53 0.50 0.53
## m_s_steps 0.53 1.00 0.86 0.87
## m_Prev_R 0.50 0.86 1.00 0.99
## m_R_Goal 0.53 0.87 0.99 1.00
## Sample Size
## [1] 212
## Probability values (Entries above the diagonal are adjusted for multiple tests.)
## total m_s_steps m_Prev_R m_R_Goal
## total 0 0 0 0
## m_s_steps 0 0 0 0
## m_Prev_R 0 0 0 0
## m_R_Goal 0 0 0 0
##
## To see confidence intervals of the correlations, print with the short=FALSE option##
## Call:
## lm(formula = m_s_steps ~ total, data = goals)
##
## Residuals:
## Min 1Q Median 3Q Max
## -43.208 -10.254 0.775 11.339 42.182
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 41.25026 3.01431 13.685 <2e-16 ***
## total 0.56479 0.06294 8.974 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 15.89 on 210 degrees of freedom
## Multiple R-squared: 0.2772, Adjusted R-squared: 0.2738
## F-statistic: 80.54 on 1 and 210 DF, p-value: < 2.2e-16##
## Call:
## lm(formula = m_s_steps ~ total * m_Prev_R, data = goals)
##
## Residuals:
## Min 1Q Median 3Q Max
## -29.450 -5.449 1.246 6.912 18.972
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 34.94511 3.10213 11.265 < 2e-16 ***
## total 0.20787 0.06992 2.973 0.0033 **
## m_Prev_R 6.90785 0.82497 8.373 8.22e-15 ***
## total:m_Prev_R -0.01936 0.01485 -1.304 0.1937
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 9.38 on 208 degrees of freedom
## Multiple R-squared: 0.7505, Adjusted R-squared: 0.7469
## F-statistic: 208.6 on 3 and 208 DF, p-value: < 2.2e-16##
## Call:
## lm(formula = total ~ m_Prev_R, data = goals)
##
## Residuals:
## Min 1Q Median 3Q Max
## -50.951 -10.545 -0.058 10.637 42.455
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 31.5717 1.8628 16.948 < 2e-16 ***
## m_Prev_R 3.4865 0.4132 8.438 5.24e-15 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 15.06 on 210 degrees of freedom
## Multiple R-squared: 0.2532, Adjusted R-squared: 0.2496
## F-statistic: 71.2 on 1 and 210 DF, p-value: 5.239e-15##
## Call:
## lm(formula = total ~ m_R_Goal, data = goals)
##
## Residuals:
## Min 1Q Median 3Q Max
## -52.232 -10.336 0.664 11.664 40.020
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 34.336 1.530 22.444 <2e-16 ***
## m_R_Goal 33.218 3.685 9.014 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 14.79 on 210 degrees of freedom
## Multiple R-squared: 0.279, Adjusted R-squared: 0.2756
## F-statistic: 81.26 on 1 and 210 DF, p-value: < 2.2e-16## Formula:
## total ~ m_Prev_R + m_R_Goal + m_Prev_R.XX.m_R_Goal
## <environment: 0x7f9abf691740>
##
## Models
## R R^2 Adj. R^2 F df1 df2 p.value
## Model 0.543 0.295 0.285 29.015 3.000 208 1e-15 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residuals
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -51.0553 -10.6514 0.6609 0.0000 11.0249 35.9975
##
## Coefficients
## Estimate StdErr t.value beta p.value
## (Intercept) 37.73836 3.41371 11.05494 < 2e-16 ***
## m_Prev_R -4.53773 2.63842 -1.71987 -0.6549 0.08694 .
## m_R_Goal 84.03797 23.92261 3.51291 1.3363 0.00054 ***
## m_Prev_R.XX.m_R_Goal -1.17008 1.36414 -0.85774 -0.1694 0.39202
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Collinearity
## VIF Tolerance
## m_Prev_R 42.781 0.0234
## m_R_Goal 42.693 0.0234
## m_Prev_R.XX.m_R_Goal 11.515 0.0868**note total = total T1 habit score
Results:
model f1: T1 habit index sig predicts mean number of steps, explains 27% of the variation in steps
model f2: adding previous_response to the model, reduces effect of T1 habit; habit and previous response do not interact, model explains 75% of the variation in steps
model m1: previous response sig predicts habit, model explains 25% of variation in T1 habit
model m2: goal achievement sig explains 28% of the variation in T1 habit
model m3: adding previous response and goal achievement together, effect of previous response is no longer significant, no interaction effects, model explains 28% of the variation in T1 habit
perhaps could be used to say that recency effects sig predict performance and goal achievement but do not directly habit