Summary:

Part I: Confirmatory Results

w/ Different Exclusion Criteria (5-response min., 2-response min., No min.)

## removed: no response rate exclusion criteria used ##

Proceeding with No minimum response inclusion criteria…

Part II: Exploratory and Confirmatory Model Fits

  • PE is a significant predictor of dense sampling Positive and Negative Affect (PA; NA)
  • Outcome (exam grade) is no longer significant predictor of PA or NA

Dataset Affect predictor Estimate SE p-value
Exploratory Positive outcome -0.2799268 0.2746970 NA
Exploratory Positive PE 3.0213880 0.6386234 NA
Exploratory Negative outcome -0.7100594 0.4486658 NA
Exploratory Negative PE -1.7950201 0.8262051 NA
Confirmatory Positive outcome 0.1972835 0.2705651 0.5338107
Confirmatory Positive PE 2.9954688 0.4683352 0.0000001
Confirmatory Negative outcome -0.6125286 0.3023054 0.0727062
Confirmatory Negative PE -2.3275103 0.5668274 0.0007153

Part III: CIs for Model Parameters, and PE - Outcome contrasts

  • Confirmatory PA model: Outcome term is not significantly different from zero
  • PE - Outcome contrast is significant for PA and NA models
Dataset Affect Parameter Estimate SE X2 P Lower Upper
Exploratory Positive Outcome -0.2799268 0.2746970 1.0384393 0.3081847 -0.8183229 0.2584694
Exploratory Positive PE 3.0213880 0.6386234 22.3832635 0.0000022 1.7697092 4.2730668
Exploratory Positive PE - Outcome 3.3013148 0.7834249 17.7573907 0.0000251 1.7658302 4.8367993
Exploratory Negative Outcome -0.7100594 0.4486658 2.5046292 0.1135122 -1.5894281 0.1693094
Exploratory Negative PE -1.7950201 0.8262051 4.7202275 0.0298098 -3.4143523 -0.1756879
Exploratory Negative PE - Outcome -1.0849608 1.1430269 0.9009800 0.3425191 -3.3252523 1.1553308
Confirmatory Positive Outcome 0.1972835 0.2705651 0.5316651 0.4659077 -0.3330143 0.7275814
Confirmatory Positive PE 2.9954688 0.4683352 40.9087340 0.0000000 2.0775487 3.9133889
Confirmatory Positive PE - Outcome 2.7981853 0.6423043 18.9789082 0.0000132 1.5392919 4.0570786
Confirmatory Negative Outcome -0.6125286 0.3023054 4.1054525 0.0427452 -1.2050362 -0.0200210
Confirmatory Negative PE -2.3275103 0.5668274 16.8609287 0.0000402 -3.4384716 -1.2165489
Confirmatory Negative PE - Outcome -1.7149817 0.7945313 4.6590459 0.0308904 -3.2722343 -0.1577290

Part IV: Comparing ‘Outcome-Only’ and ‘PE + Outcome’ Models

  • inclusion of PE term significantly improves model fit (over outcome-only models)
Dataset Affect Model Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
Exploratory Positive Outcome 12 9428.141 9489.411 -4702.071 9404.141 NA NA NA
Exploratory Positive Outcome + PE 22 9363.921 9476.249 -4659.961 9319.921 84.22011 10 0
Exploratory Negative Outcome 12 9957.264 10018.533 -4966.632 9933.264 NA NA NA
Exploratory Negative Outcome + PE 22 9909.290 10021.617 -4932.645 9865.290 67.97405 10 0
Confirmatory Positive Outcome 12 16598.659 16666.472 -8287.329 16574.659 NA NA NA
Confirmatory Positive Outcome + PE 22 16478.026 16602.351 -8217.013 16434.026 140.63235 10 0
Confirmatory Negative Outcome 12 16968.494 17036.308 -8472.247 16944.494 NA NA NA
Confirmatory Negative Outcome + PE 22 16867.960 16992.285 -8411.980 16823.960 120.53415 10 0

Part V: Interactive Model: modeling PA and NA together

Affect ~ Affect_valence:(outcome + PE) + (1 | cohort / id / exam_num)

## removed: in progress ##

Part VI: Model Fits for Sample Subject

  • The paneled plot below depicts observed PA and NA (green points) for an exploratory subject, plus the following model fits
  • orange Affect ~ PE + Outcome
  • blue Affect ~ Outcome