Scribd
Upload
310 views5 pages

Get PDF

Uploaded by

Pragya Bajpai
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
310 views5 pages

Get PDF

Uploaded by

Pragya Bajpai
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

Description of Scoring Algorithms

Description of Scoring Algorithms

Purpose
This document describes the algorithms for the generation of
• Conners N Subscale T score
• SDQ Hyperactivity subscale T score
used in the IMAGE project.

Conners
Here we describe the generation of the Conners N subscale T scores for the revised long
version of the Conners rating (copyrighted 1997). The algorithm used is that specified in
the manual accompanying the rating.

Conners Rating
The Conners rating comes in two variants depending on who conducts the rating:
• parent rated CPRS-R:L
• teacher rated CTRS-R:L
These variants differ from each other in the number of questions they contain and how
their answers are used.

Item Scores
The conners rating consists of a number of multiple-choice questions (59 questions for
the Teacher rated conners, 80 the Parent rated conners), these are known as items. For
each item there are four multiple choice answers scored 0 to 3. So each item can have a
score of 0 – 3.

Conners Subscales
For each conners rating there are a number of subscales:
• Parent subscales – subscales A to N
• Teachers subscales A to F, and H to N ( i.e. there is no subscale G)
For each subscale the following scores are calculated:
• raw score
• prorated score (calculated form the raw score)
• T score (calculated form the prorated score)
Here we describe the generation of scores for one particular subscale, subscale N. High
scores in subscale N indicate an above average correspondence to DSM-IV criteria for
combined Inattention and Hyperactive-Impulsive type ADHD. Other subscales scores are
generated in the same way, the only difference being which items relate to each subscale.

Desmond Campbell Page 1 of 5 15/11/2006


Description of Scoring Algorithms

Subscale Raw Score


The subscale’s raw score is found by adding up the item scores of all the items relating to
the subscale. 18 items contribute to subscale N’s raw score. These items are
Rating Type Teacher Conners Parent Conners
3 3
Item Number of 9 9
Items relating to 11 10
Conners 12 20
Subscale N 18 23
20 29
27 30
28 39
29 41
36 42
39 49
42 50
44 55
46 59
49 71
55 76
57 79
58 80

Subscale Prorated Score


If some of the items relating to the subscale are unanswered, the subscale raw score will
probably be lower than if all the items had been answered. The raw score can be adjusted
for unanswered items, such an adjustment results in a prorated score for the subscale. To
find the prorated score the average item score is added to the raw score for each
unanswered item. The formula used for this is

Prorated Score = Raw Score * Number of Items Relating to the Subscale


Number of Answered items Relating to the Subscale

If many items are unanswered then the prorated score becomes inaccurate. Therefore the
prorated score is only valid if 75% or more of the subscale’s items have been answered.

Subscale T Score
The subscale’s prorated score, if valid (see previous section), can be normalised for age
and sex and rescaled so that a population sample would be expected to have a distribution
with a mean of 50 and standard deviation of 10. This is the subscale’s T score. T scores
are obtained from the prorated scores by looking up in a table the t score appropriate for:
• The subject’s prorated score,
• The Subject’s sex
• The rating type of the conners (teacher or parent)

Desmond Campbell Page 2 of 5 15/11/2006


Description of Scoring Algorithms

The tables used to convert N subscale prorated scores into T scores are supplied in file
ConvertConnersNSubscaleProratedScoreToTScore.xls.

Strengths and Difficulties Questionnaire (SDQ)


Here we are describe the generation of the SDQ hyperactivity subscale T scores. The
algorithm used is that specified in the manual accompanying the rating.

SDQ Rating
The SDQ rating come in two variants depending on who conducted the rating, ie
• parent rated
• teacher rated.
These variants are scored in the same way.

Item Scores
The SDQ rating consists of 25 multiple-choice questions, these are known as items. For
each item there are three multiple choice answers scored 0 to 2. So each item can have a
score of 0 – 2.

SDQ Subscales
For the SDQ there are 5 subscales, these are:
• emotional symptoms
• conduct problems
• hyperactivity
• peer problems
• prosocial behaviour

Hyperactivity Subscale Raw Score


The Hyperactivity subscale’s raw score is found by adding up the item scores of all the
items relating to the subscale. The items contributing to the subscale’s raw score are
items 2, 10, 15, 21 and 25.

Hyperactivity Subscale Prorated Score


If some of the items relating to the subscale are unanswered, the subscale raw score will
probably be lower than if all the items had been answered. The raw score can be adjusted
for unanswered items, such an adjustment results in a prorated score for the subscale. To
find the prorated score the average item score is added to the raw score for each
unanswered item. The formula used for this is

Prorated Score = Raw Score * Number of Items Relating to the Subscale


Number of Answered items Relating to the Subscale

Desmond Campbell Page 3 of 5 15/11/2006


Description of Scoring Algorithms

If many items are unanswered then the prorated score becomes inaccurate. Therefore the
prorated score is only valid if 3 or more of the subscale’s items have been answered.

Subscale T Score
The subscale’s prorated score, if valid (see previous section), can be normalised for age
and sex and rescaled so that a population sample would be expected to have a distribution
with a mean of 50 and standard deviation of 10. This is the subscale’s T score. T scores
are obtained from the prorated scores by looking up in a table the t score appropriate for:
• The subject’s prorated score,
• The Subject’s sex
• The rating type of the SDQ (teacher or parent)
The following tables can be used to convert a subject’s SDQ Hyperactivity prorated score
into the appropriate T score.

Parent SDQ Hyperactivity Subscale


Male Female
Pro- Age 9-11 12-14 15-17 6-8 9-11 12-14 15-17
rated band
Score: 6-8
0 37 37 36 39 39 41 42 42
1 41 42 42 44 45 46 47 48
2 45 46 46 48 49 50 49 50
3 49 50 48 50 51 52 51 52
4 50 51 50 52 53 54 55 56
5 52 53 53 56 56 57 58 60
6 55 56 56 57 59 61 61 63
7 58 59 60 59 62 63 64 65
8 60 61 62 62 65 67 67 68
9 63 64 65 66 68 69 71 74
10 67 68 69 70 71 74 77 75

Teacher SDQ Hyperactivity Subscale


Male Female
Pro- Age 9-11 12-14 15-17 6-8 9-11 12-14 15-17
rated band

Desmond Campbell Page 4 of 5 15/11/2006


Description of Scoring Algorithms

Score 6-8
0 40 40 41 44 45 46 46 47
1 44 45 45 46 50 49 49 49
2 47 48 49 48 52 51 51 51
3 49 50 51 50 53 55 55 55
4 50 51 52 53 57 58 59 59
5 52 53 55 56 60 61 62 61
6 56 56 57 58 63 64 64 63
7 58 59 60 61 65 66 66 66
8 60 61 62 63 67 68 68 68
9 62 63 64 66 69 71 71 70
10 65 66 67 68 71 76 73 74

Desmond Campbell Page 5 of 5 15/11/2006

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy