Toggle navigation
Toggle navigation
Home
DCUM Forums
Nanny Forums
Events
About DCUM
Advertising
Search
Recent Topics
Hottest Topics
FAQs and Guidelines
Privacy Policy
Your current identity is: Anonymous
Login
Preview
Subject:
Forum Index
»
Advanced Academic Programs (AAP)
Reply to "NGAT results are available "
Subject:
Emoticons
More smilies
Text Color:
Default
Dark Red
Red
Orange
Brown
Yellow
Green
Olive
Cyan
Blue
Dark Blue
Violet
White
Black
Font:
Very Small
Small
Normal
Big
Giant
Close Marks
[quote=Anonymous][quote=Anonymous][quote=Anonymous] Totally fair. Someone did post a url that had a PowerPoint that made it seem like the distribution was 100 with a std dev of 15 or 16, but it was not a bastion of clarity. Immaterial now, but in case anyone is keeping track for future years, 139 on NGAT was not a universal screener score for my kid.[/quote] I'm the PP who posted the link. Assuming the sample report in the slide describes the same set of 3 tests that FCPS 2nd graders took, it seems clear to me that total standard score as well as the 3 individual standard scores are based on the same normal distribution with mean 100 and sd 15. Note that the percentile is given for total score in that sample report. Disclaimer is that I have no way of being certain that it is indeed the same scoring and sample that generated FCPS results. So total score 130+ likely still means the student's total of 3 tests is better than 2sd above national average. A plausible guess is that the individual total score just sums the 3 raw scores (none of which are known to us) and then was mapped to the national sample distribution of such raw score totals. Regardless, it is surprising that 139 total score wasn't enough to be in top 10% within that school. In statistical sense, a small (=high sampling error) AND very selective (=high sampling bias) sample can still make that happen. [/quote] My understanding is that that slide was for a version where the total score is also maxed at 160. Apparently there are two ways to combine, one maxed at 160 and the other at 175. Regardless, 139 not making the cut seems statistically unlikely, but likely better explained by a model with a higher standard deviation?[/quote]
Options
Disable HTML in this message
Disable BB Code in this message
Disable smilies in this message
Review message
Search
Recent Topics
Hottest Topics