All About T-Score

[Pen88n]

verysianmom:

Hi can someone tell me if HCL is useful if my daughter's score is below 250?

HCL points are only applicable to top 30% of cohort. As to cut off of this top 30%, I'm not sure of the COP.

But if you intend your DD to go to a SAP school, I believe HCL foundation will help her in sec sch years.

[jtoh]

verysianmom:

Hi can someone tell me if HCL is useful if my daughter's score is below 250?

HCL scores are only useful if you're applying to SAP schools. If you score distinction, you can add 3 bonus points to your PSLE score, +2 for merit etc. So if adding the bonus points to your dd's PSLE score helps to get her into a SAP school, it'll help even if her score is <250. There are some SAP schools whose COP is <250.

[papaya99]

Can someone estimate the mean & standard deviation for all subjects for this year PSLE ? thank you.

[verykiasu2010]

papaya99:

Can someone estimate the mean & standard deviation for all subjects for this year PSLE ? thank you.

every year's questions and raw scores from the candidates are different

you won't be able to estimate till the scripts are marked and scored

normally it ranges between 8 to 16 for the SD of each subject, depends on each year's cohort

easy papers mean smaller SD, harder paper means higher SD

[vlim]

verykiasu2010:

papaya99:

Can someone estimate the mean & standard deviation for all subjects for this year PSLE ? thank you.

every year's questions and raw scores from the candidates are different

you won't be able to estimate till the scripts are marked and scored

normally it ranges between 8 to 16 for the SD of each subject, depends on each year's cohort

easy papers mean smaller SD, harder paper means higher SD

i thought is opposite .. :?

[Pen88n]

vlim:

verykiasu2010:

[quote=\"papaya99\"]Can someone estimate the mean & standard deviation for all subjects for this year PSLE ? thank you.

every year's questions and raw scores from the candidates are different

you won't be able to estimate till the scripts are marked and scored

normally it ranges between 8 to 16 for the SD of each subject, depends on each year's cohort

easy papers mean smaller SD, harder paper means higher SD

i thought is opposite .. :?[/quote]Vlim, agreed. I think it should be:
Easy paper => higher mean, wider spread, SD larger => overall lower T-score for that subject
Difficult paper => lower mean, centred around mean, SD smaller => T-score can be high if excel in paper

[verykiasu2010]

easier papers mean many many of the candidates will score around the same high marks, meaning the variance from the mean (average) is smaller, hence the standard deviation is small. yes the mean is higher but the many people crowing around the mean means that the variance is small


if the paper is tough, only the real high achievers 9not so many) are able to score high high, and the average (mean) will be much lower than the high achievers.....hence the variance from the mean is wider, giving you a higher standard deviation

that is why is a year of easy paper, highest t-score seem to be low, at most a low 28x, where as in a year of tough papers, the highest t-score could be 29x

http://en.wikipedia.org/wiki/Standard_deviation


Interpretation and application

A large standard deviation indicates that the data points are far from the mean and a small standard deviation indicates that they are clustered closely around the mean.

For example, each of the three populations {0, 0, 14, 14}, {0, 6, 8, 14} and {6, 6, 8, 8} has a mean of 7. Their standard deviations are 7, 5, and 1, respectively. The third population has a much smaller standard deviation than the other two because its values are all close to 7. In a loose sense, the standard deviation tells us how far from the mean the data points tend to be. It will have the same units as the data points themselves. If, for instance, the data set {0, 6, 8, 14} represents the ages of a population of four siblings in years, the standard deviation is 5 years.

[coolit]

Thanks verykiasu2010, your explanation is superbly clear. Where do you get this information?


So I can say that if the papers are all relatively easier, the average is higher but the high scores are lower?

[verykiasu2010]

coolit:

Thanks verykiasu2010, your explanation is superbly clear. Where do you get this information?


So I can say that if the papers are all relatively easier, the average is higher but the high scores are lower?

the explanation can be found all over internet. the para I copied has been credited to wiki, referenced above

you are right to say that easy paper -->high average --> low t-score

assume everyone in the cohort gets 100% for all 4 subjects : mean = 100, variance = zero, SD = zero, t-score for each subject = 50, max t-score for the psle = 200 when everyone gets 100% for all subjects

presently NYPS website also has a complete explanation with ppt for the PSLE t-score calculation. download it for your record and use.

http://www.nyps.moe.edu.sg/News/P6%20T%20score%5B1%5D.pps

[coolit]

I see thanks verykiasu2010, I did not know this information was so widely available.

I am much clearer about this after reading the info you have given.