RAND-IAQL-12 Scoring Procedure and Translation Table

Scoring Procedure

Each of the 12 items on the RAND-IAQL-12 use five-category response options ranging in value from zero to four. Higher scores indicate greater negative impact of asthma on quality of life. In cases where the items have been administered on a range 1 to 5, first re-score response options for each item to 0 to 4 (e.g., 1=0, 2=1, 3=2, 4=3, 5=4). To find the total raw score, sum across the values of the responses to all 12 questions. The lowest possible score will be 0 and the highest possible score will be 48.

If any of the 12 items are missing (i.e., respondents did not answer the item), create a pro-rated raw score using the following method. If less than six of the 12 questions have been answered by the respondent, then assign the respondent a missing value for the total score. If at least six of the 12 questions have been answered, then sum across the items that have been answered and divide the result by the number of items that were answered to create an average item score. If the result is a fraction, round up. For example, if the respondent answered five items with the highest response option (4), answered two items with the next highest response option (3), and left five items missing, you would sum across the seven items that were answered (result=26) and divide by 7 (result=3.7, rounded to 4). This value is then imputed in place of the missing responses and the total score may be calculated as though there is a complete pattern of responses.

Next, based on a given total score, find the associated IRT-score in the “T-Score” column. The “T-Score” column provides the IRT-based asthma quality of life score estimate given each particular total score. Note that the “T-Score” and “SE” columns transform the IRT metric (N(mean=0, standard deviation =1)) to a T-score metric (mean = 50, standard deviation = 10). A higher T-score means worse asthma quality of life.

RAND-IAQL Main Page

References

Thissen, D., Pommerich, M., Billeaud, K., & Williams, V.S.L. (1995). Item response theory for scores on tests including polytomous items with ordered responses. Applied Psychological Measurement, 19, 39-49.

Thissen, D., Nelson, L., Rosa, K., & McLeod, L.D. (2001). Item response theory for items scored in more than two categories. In D. Thissen & H. Wainer (Eds), Test Scoring (pp. 141-186). Mahwah, NJ: Lawrence Erlbaum Associates.

Scoring Table

Sum Score T-Score SE
0 32.7 5.1
1 37.4 3.7
2 39.9 3.1
3 41.6 2.8
4 43.0 2.6
5 44.2 2.4
6 45.3 2.2
7 46.2 2.1
8 47.1 2.0
9 47.9 2.0
10 48.6 1.9
11 49.3 1.9
12 49.9 1.9
13 50.6 1.8
14 51.2 1.8
15 51.8 1.8
16 52.4 1.8
17 52.9 1.8
18 53.5 1.8
19 54.0 1.8
20 54.5 1.7
21 55.1 1.7
22 55.6 1.7
23 56.1 1.7
24 56.6 1.7
25 57.1 1.7
26 57.6 1.7
27 58.1 1.7
28 58.6 1.7
29 59.1 1.7
30 59.6 1.7
31 60.1 1.7
32 60.6 1.7
33 61.1 1.7
34 61.7 1.7
35 62.2 1.7
36 62.7 1.7
37 63.3 1.8
38 63.9 1.8
39 64.5 1.8
40 65.1 1.9
41 65.8 1.9
42 66.6 2.0
43 67.4 2.1
44 68.3 2.2
45 69.3 2.4
46 70.6 2.6
47 72.2 2.9
48 75.6 4.1
Note: T-score metric is a linear transformation from the IRT theta scale: T-score = 10 * theta + 50.
SE in the table is the standard error on T-score metric.