Nayland College - Mathematics Home . Year 9 . Year 10 . Level 1 . Level 2 . L3 Statistics . L3 Maths . L3 Calculus . About . Links

# iNZight & Inference

Remember: You Have to run iNZight TWO times!

The iNZight tips page has information on ordering, removing, grouping, re-categorising, & exporting data, and creating variables, adding variables to create box plots and show summary statistics. (Adding another variable can also provide more information)

***Manipulating data in Excel first can be a good idea, especially to combine groups together

 1) To Analyse the Sample 2) To make a Bootstrap Confidence Interval

Run iNZight

##### 1) To Analyse the Sample

Run iNZight normally, import data

Decide on your variable, and what your two groups are (see iNZight tips page for ordering, removing, grouping, re-categorising, & exporting data, and creating variables)

Add variables to create box plots and show summary statistics. (Adding another variable can also provide more information (iNZight tips page)

Input Data

Not sure how to Import Data? Find out here...

REMEMBER: If you upload your own data it MUST be in a .csv file, with variable notation, no commas, no variable definitions etc

Make a dot plot & Box plot

Drag ONE VARIABLE

and

ONE Group to the 'variables'

Note: You may want to manipulate the data in excel first, eg If therre are multiple groups thencombining some together so there is only two groups would be a good idea.

Get SAMPLE SUMMARY statistics

Now DISCUSS the SAMPLE STATISTICS & DOT plot & BOX plot
Remember this by the starship USSCSI or 'DISCUSS' (see the sample page if you are not sure)

##### 2) Bootstrapping using iNZight

Difference between two Population Groups

iNZight Bootstrap confidence intervals

How to compare two groups and answer "Is the median on Blah different from the median of Blah in the population of Blah?

Import data which has two categories

The two columns of data - one is measured data and the other is the group

(variable 1 is primary variable, Variable 2 is group)

Analyse

Discuss the dot plots for the sample groups.

The Arrow represents the difference between the medians of the two sample groups

Remembering that the samples vary each time.

Does the population medians also differ?

Analyse, record my choices

The differences between the pairs of data values is the 'sample'

Bootstrap resamples are taken from this 'sample' of differences.

Resample

You can watch one animation to get the idea..

or resample 1000 times to see the variation in the resampled medians.

The top dot plot is the original sample differences

The bottom dot plot is of a single resample of size 'n' with replacement.

The differences in the resample medians is recorded

Bootstrap Distribution

You can watch one animation to get the idea..

then Re-sample 1000 times to see the bootstrap distribution of the differences between repeated re-samples from each group

Show the CI to see the Bootstrap confidence interval.

Interpret what you see

Multiple re-samples build up a distribution of differences between the means

How do we interpret these results?

What does this tell us?

You MUST discuss the relative position of 0 and what this means with respect to the two population medians (or means)