x Turn on thread page Beta
 You are Here: Home

Announcements
1. ok I have a question in this thread http://www.uk-learning.net/t46911.html that also needs to be answered please as I have no clue.

My second question is if neither x or y variables are controlled, yet you are given both yon x and x on y regression lines. Which one do you use? The answer claims use x on y, if under these circumstances is that always the case?

x=1.11 + 1.06y

y=1.78 + 0.586x

Use appropriate line to calculate y=3.4 Why is it x on y line??

muwhaahha after typing all that out i think ive got it, if you need to find x given u know y use x-on-y as x = in terms of y hah! please say im right, or is it not that obvious.
2. I don't really understand what you're saying
I have my own query though
i know you use median and IQR when there are extremes of data
but when is the mean and s.d (i think) better?
but when is the mean and s.d (i think) better?
With large amounts of quantative data that is unlikely to contain extreme values. In reality they will probably give you an idication of which to use.
4. I do believe yes, I think of it this way, if the data has an abnormal result the mean will be accounting for the abnormality. => not as accurate as if one were to use the median. => opposite is the reverse of that.

Talking Binomial,

P(2<= x <=4) using tables it be (value)3 - (value)1 correct?

i understand it when its just P(x>5) or something on its own, but when inbetween its different whats the rule behind this? And is it the same for geometric?
5. thanks guys
another thing
how do you draw regression lines? I mean you have a y intercept but the gradient is usually some weird decimal number?
thanks guys
another thing
how do you draw regression lines? I mean you have a y intercept but the gradient is usually some weird decimal number?
Either they will give you a grid or u just do a rough sketch!
7. even with a grid... it's stupid to ask you to draw lines with decimal gradients... some things in stats are so tedious!
even with a grid... it's stupid to ask you to draw lines with decimal gradients... some things in stats are so tedious!
Won't you have to plot points and then draw the line of regression?
using the a +bx formula?
9. yeah you plot a scatter graph right?
or do you have to manipulate the values using the equation for regression?

alsoi has anyone done the exam paper at the back of Heinemann S1?
yeah you plot a scatter graph right?
or do you have to manipulate the values using the equation for regression?

alsoi has anyone done the exam paper at the back of Heinemann S1?
If you mean the AQa book, i did in the olden days
manipulation
11. ARGH so you have to put every x value through the regression equation and then plot that? the textbook just confuses me on this aspect (edexcel)
ARGH so you have to put every x value through the regression equation and then plot that? the textbook just confuses me on this aspect (edexcel)
I believe so...that's what i did in my stats paper last year....
ARGH so you have to put every x value through the regression equation and then plot that? the textbook just confuses me on this aspect (edexcel)

not EVERY x value.
Pick a couple.

It's a good idea to plot & label the point that's the mean of x and the mean of y - the regression line should go through this.

So if you plot that point, the y-intercept (whcih you know) and one or two more points just to check - sorted.
14. damn you princess uve hijacked my thread and everyones answered ur questions and not my binomial one!

Edit: Sorted Now.

TSR Support Team

We have a brilliant team of more than 60 Support Team members looking after discussions on The Student Room, helping to make it a fun, safe and useful place to hang out.

This forum is supported by:
Updated: June 10, 2004
Today on TSR

### University rankings 2019

Cambridge at number one

### I have imposter syndrome at Cambridge

Poll

The Student Room, Get Revising and Marked by Teachers are trading names of The Student Room Group Ltd.

Register Number: 04666380 (England and Wales), VAT No. 806 8067 22 Registered Office: International House, Queens Road, Brighton, BN1 3XE