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)
  • NEW: Outcome (exam grade) is a significant predictor of NA, but not PA.

Dataset Affect predictor Estimate SE p-value
Exploratory Positive outcome -0.3019002 0.2754267 NA
Exploratory Positive PE 3.2385371 0.6396089 NA
Exploratory Negative outcome -0.6492627 0.4386921 NA
Exploratory Negative PE -2.1821786 0.8411758 NA
Confirmatory Positive outcome 0.1955046 0.2081566 0.4124225
Confirmatory Positive PE 3.0527652 0.4288276 0.0000258
Confirmatory Negative outcome -0.6743806 0.2746970 0.0399461
Confirmatory Negative PE -2.6588425 0.4787488 0.0000004

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

  • NEW: Outcome term is significantly different from zero in model predicting NA, but not PA.
  • PE - Outcome contrast is significant for PA and NA models
Dataset Affect Parameter Estimate SE X2 P Lower Upper
Exploratory Positive Outcome -0.3019002 0.2754267 1.2014744 0.2730272 -0.8417266 0.2379263
Exploratory Positive PE 3.2385371 0.6396089 25.6370884 0.0000004 1.9849266 4.4921476
Exploratory Positive PE - Outcome 3.5404372 0.7801918 20.5925936 0.0000057 2.0112894 5.0695850
Exploratory Negative Outcome -0.6492627 0.4386921 2.1903889 0.1388743 -1.5090835 0.2105581
Exploratory Negative PE -2.1821786 0.8411758 6.7298764 0.0094811 -3.8308528 -0.5335044
Exploratory Negative PE - Outcome -1.5329159 1.1448568 1.7928103 0.1805841 -3.7767940 0.7109622
Confirmatory Positive Outcome 0.1955046 0.2081566 0.8821319 0.3476184 -0.2124749 0.6034841
Confirmatory Positive PE 3.0527652 0.4288276 50.6782101 0.0000000 2.2122785 3.8932519
Confirmatory Positive PE - Outcome 2.8572606 0.5785290 24.3921105 0.0000008 1.7233645 3.9911567
Confirmatory Negative Outcome -0.6743806 0.2746970 6.0270149 0.0140885 -1.2127769 -0.1359843
Confirmatory Negative PE -2.6588425 0.4787488 30.8439335 0.0000000 -3.5971730 -1.7205120
Confirmatory Negative PE - Outcome -1.9844619 0.6710673 8.7448715 0.0031047 -3.2997296 -0.6691943

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 9352.517 9464.844 -4654.258 9308.517 95.62475 10 0
Exploratory Negative Outcome 12 9957.264 10018.533 -4966.632 9933.264 NA NA NA
Exploratory Negative Outcome + PE 22 9896.852 10009.180 -4926.426 9852.852 80.41169 10 0
Confirmatory Positive Outcome 12 22416.483 22487.922 -11196.241 22392.483 NA NA NA
Confirmatory Positive Outcome + PE 22 22283.660 22414.633 -11119.830 22239.660 152.82275 10 0
Confirmatory Negative Outcome 12 22917.636 22989.076 -11446.818 22893.636 NA NA NA
Confirmatory Negative Outcome + PE 22 22800.103 22931.076 -11378.051 22756.103 137.53292 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