Skip to main content

Table 3 Actual P(Qj = 1 | Li) for various subsets of Dataset 2 - complete sample, a random half of the sample, online sample (n = 100) and clinic sample (n = 62)

From: A new adaptive testing algorithm for shortening health literacy assessments

Q-ID Class (Li) Complete Sample Random 50% split Online Sample Clinic Sample
  Low 0.5 0.43 0.56 0.47
1 Moderate 0.69 0.68 0.60 0.85
  High 1 1 1 1
  Low 0.31 0.35 0.25 0.34
2 Moderate 0.81 0.79 0.85 0.74
  High 1 1 1 1
  Low 0.69 0.70 0.63 0.72
3 Moderate 0.93 0.95 0.96 0.89
  High 1 1 1 1
  Low 0.60 0.61 0.81 0.5
4 Moderate 0.96 0.95 0.98 0.93
  High 1 1 1 1
  Low 0.56 0.61 0.87 0.41
5 Moderate 0.95 0.97 0.94 0.96
  High 1 1 1 1
  Low 0.5 0.48 0.69 0.41
6 Moderate 0.85 0.84 0.87 0.81
  High 1 1 1 1
  Low 0.4 0.43 0.75 0.22
7 Moderate 0.92 0.95 0.96 0.85
  High 1 1 1 1
  Low 0.13 0.17 0.06 0.16
8 Moderate 0.46 0.5 0.47 0.44
  High 1 1 1 1