Looking for Patten Makers Photography? Just click the name and you will be transported accross!

Thursday, November 14, 2013

I am someone - Raising awareness of harrassment and abuse in NZ

"I am someone" officially starts tomorrow.
It is a reaction against perceived rape culture in New Zealand.
Reactions of prominent people in the media, such as Michael Laws, Willie an JT etc. have been key in spurring this movement on.

The links below can be used to view shared experiences of harassment and abuse including, but not limited to, rape.

The content is likely to be disturbing but is worth a read if you have the stomach for it. It is certainly worth a read if your experience of life in NZ is as sheltered as mine (as a bloke who prefers staying at home to partying or going to town the partying/going to town stories were out of step with what I was expecting)

http://iamsomeonenz.wordpress.com/
https://www.facebook.com/events/1422866911263436
http://www.scoop.co.nz/stories/PO1311/S00171/stories-of-harassment-and-sexual-violence-go-live-on-web.htm

Wednesday, November 13, 2013

Roast Busters - Willie, JT, and Amy

Radiolive have pulled Willie Jackson and John Tamihere's interview with 'Amy', a friend of an alleged roast busters victim, from their website.

A snippet of the interview can be heard in Radio NZ national's Mediawatch program from Novermber 10th



Colin Peacock also gives an overview of other related events of Radiolive as well as some background on how the story developed.

Selected alleged quotes can also be found here:
http://wonderfulnow.blogspot.co.nz/2013/11/shame-on-willie-jt-and-radiolive.html

However as the interview has been taken down most of these cannot be verified.

Matthew Hooton's walkout, or kick out, can be heard here:

Friday, November 8, 2013

Significant Model Improvement - F change method

Previously I have written about the AICc, a means of testing which model is the best tradeoff between complexity and explanatory power. While the AICc can rank models from most efficient to least efficient it cannot give any indication on whether the improvement between models is statistically significant. If you want to make a claim about the statistical significance of changes to your model you need an alternative approach. One of the most straight forward is the F change statistic.

The F change statistic operates in much the same way as a standard F statistic. In this case rather than providing a ratio of the unexplained variance to the explained variance you are providing a ratio between the change in explanatory power relative to the unexplained variance.

In order to calculate the F change statistic you will need to know the residual sum of squares (RSS) for each model, the number of parameters (K) in each model (1 and 2 here), and the number of observations (n) you have.

F=((RSS1-RSS2)/(K2-K1))/(RSS2/(n-K2))

The degrees of Freedom for your resulting F statistic are K2-K1 and n-K2.

BONUS: By inspecting the formula given here you should be able to see how a more complicated model with a higher RSS would produce a negative F statistic. Because the F distribution is a squared distribution F statistics can only be positive. In such a case you would consider the absolute value of the F statistic (i.e. -3 become 3). If such a result were found to be significant this would tell you that the more complicated model was significantly worse than the less complicated model rather than the other way around. This also helps to show that F distribution can be used for two tailed and one tailed tests despite its asymmetry.

Thursday, November 7, 2013

Akaike Information Criterion - Sum of Squares Method

The Akaike Information Criterion (AIC) is a tool that can be used to gauge whether the increased predictive power associated with adding additional parameters to a model is worth the associated increase in complexity. It is primarily based on comparing values from maximum likelihood estimation (MLE) methods. Odds are you aren't using an MLE model. Instead you are probably determining your model using a least squares method such as linear regression. Assuming that the assumptions associated with a parametric model are met (equal variance, normally distributed errors) you can use an equivalent method that uses the residual sum of squares.

AIC= nxLn(RSS/n)+2xK

Where Ln is the natural log, RSS is the residual sum of squares, n is the number of observations that make up the sample, and K is the number of parameters in your model. Most of that should be pretty familiar. The only tricky thing is the number of parameters.

A common mistake when calculating the number of parameters is failure to include error. This is because it is not normally thought of as a parameter as, strictly speaking, you're not really predicting it. As a results the number of parameters in a standard linear equation (y=mx+c) is 3 (mx, c, and error) rather than 2.

It is also recommended to add an additional correction factor if n<40xK. As it's not much trouble to calculate it's best to use the corrected version of AIC (AICc).

AICc=AIC+(2xK(K+1))/(n-K-1)

The model with the lowest AICc is the model that provides the best trade-off between the complexity of the model and its ability to explain the data. The numbers themselves are meaningless on their own and offer no insight into whether the difference between models is significant. However if you have 2 AICc values you can use them to find out the likelihood that the models are equally good.

exp(AICc(low)-AICc(high))/2)

A key advantage of the AICc is that it allows you to test as many models as you like without taking a penalty for the number of models tested. The key downside (as already noted) is that it does not tell you about whether there is a significant difference in the variance explained between models. If that is what you are interested in an F change statistic is more appropriate.

A general overview of the AIC can be found here
http://en.wikipedia.org/wiki/Akaike_information_criterion

More specific coverage can be found here:
http://www.mun.ca/biology/quant/ModelSelectionMultimodelInference.pdf
(Burnham and Anderson (2002). Model Selection and Multimodel Inference. Springer. Colorado:USA)

One tailed F-test - Possible?

The F distribution is asymmetrical.
Some people believe that this means you cannot have a one tailed F test.
This is incorrect and is the result of what an F statistic represents and how a one tailed test works.
Here I will explain why you can have a one tailed F test despite the F distribution being asymmetrical.

1) The F distribution

The F distribution is asymmetrical because it is the distirbution of squared values. In the case of a distribution where F(1,X) it is simply the square of a t distribution. Those who are familiar with a t distribution now have all the informatoin they need to know that one tailed tests should be possible with an F statistic.


2) Calculating an F statistic

One area of misunderstanding comes from the fact that F statistic calculation involves squaring values. This means all values become positive leading some people to believe that the F statistic no longer conveys information about the direction of an effect. As one tailed tests rely on information about the direction of an effect these same people conclude that F statistics cannot be used for one tailed tests.

This is not correct.

While the Statistic itself contains no information about the direction of the difference the original data does.

This post is a stub and will be updated in the future.
If it appears to be useful to people the update will occur sooner.
Feel free to add questions and comments below to encourage attention and updates.

Monday, November 4, 2013

Roast Busters - What Does it mean?

So, as it turns out, a group of young Auckland men referring to themselves as Roast Busters have been engaging in behavior than many lay people would describe as rape. This is then followed up with public naming of their victims on facebook. While Police say it's not a crime yet, with the 3 news interview suggesting that crimes haven't happened unless they have been reported, they do admit that the behaviour is immoral.

Links to articles can be found here:

http://www.nzherald.co.nz/nz/news/article.cfm?c_id=1&objectid=11151135
http://www.3news.co.nz/Facebook-teen-sex-shaming-exposed/tabid/309/articleID/319919/Default.aspx#.UnbAQ_lmiSo
http://www.3news.co.nz/Roast-Busters-part-of-a-growing-trend---NetSafe/tabid/309/articleID/319966/Default.aspx#.UnbAQflmiSo

If anyone knows what the name Roast Busters means please feel free to share this information in the comments below.

Urban Dictionary (through looking for definitions of Roasting and Busting) would seem to suggest that the name refers to participation in group and/or sequential sex to the point of ejaculation.

http://www.urbandictionary.com/define.php?term=roasting definitions 2 and 3
http://www.urbandictionary.com/define.php?term=busting defintion 2

You may also be interested in:
http://testingtestingnz.blogspot.co.nz/2013/11/roast-busters-willie-jt-and-amy.html

Friday, November 1, 2013

ANZ Scam



ANZ Online
 <noreply@sabanciuniv.edu>
6:06 AM (2 hours ago)
to Recipients
Dear Customer, 

Your access will expire soon

For security reasons, please use our website below to restore your account.

www.anz.co.nz (actually links to http://4095l.3owl.com/anz.html, changed to google for safety purposes)

ANZ Bank New Zealand Limited

How to know this is a scam
- I am not an ANZ customer
- Banks don't send e-mails like this
- The link does not actually take you to the ANZ website despite superficial appearances
- It appears to have been addressed to multiple recipients (my name is not listed, instead I am addressed as 'Customer')
- The e-mail address that sent this is not from ANZ
- No ANZ branding in the e-mail
- No additional contact details

Thursday, October 24, 2013

Restore your access - SCAM

Below is a scam targetting BNZ customers.
I have changed the link so that it will take you to google if it is clicked.
The original link address was:
http://inwestycje.kielce.pl/eng/.js/index.html

Whenever you get an e-mail with a link in it it is a good idea to check the address of the link before proceeding.

You have reached the maximum number of permitted attempts to login. Your online banking service has been temporarily restricted.


To restore your online access click: Log On to BNZ and proceed with the verification process.

Please don't reply directly to this automatically-generated e-mail message.

Sincerely,
Online Banking Team 

Wednesday, October 23, 2013

Lumley Insurance: Customer experience

When my car was stolen and recovered by the police things got off to a good start insurance wise. An assessor visited the car in the impound and quickly declared the car a write off. As the car was an old run about - once the excess was taken from the cover outlined in my policy - I was told I could expect to have $700 paid into my account within a week or so. While this was far less than it would take to replace my car that was on me, in terms of not getting adequate insurance in the first place, so all good.

Later that week I received a call from an independent investigator. Apparently this was standard policy under Lumley. While this seemed a little odd I had nothing to hide and met the investigator later that afternoon. The investigator seemed happy with my statements and promptly filed a report.

A week later we had heard nothing back from Lumley and had to file an unrelated claim when someone backed into our other vehicle. I checked on the progress of the claim for the stolen vehicle and was told it should be resolved by the middle of the week.

Another week later and we had heard nothing back about either vehicle. I called again. The ball with the damaged vehicle got rolling while I was told that the stolen vehicle should be resolved by the middle of the following week.

1 month after making the initial claim and being told to expect a fast resolution Lumley had not paid out on the claim nor had anyone from Lumley attempted to contact us to explain the delay. I called again and was told that the claim was currently unresolved. The person on the phone said they would need to contact the person in charge of the claim and could call me back in 20 minutes.

After 1 month of apparent inaction 20 minutes was enough time to decide to decline the $700 claim. In addition to this I was also informed that I would now owe Lumley $300 to cover an excess related to damage that the thieves caused to another person's property.

While complaining to a supervisor did eventually see this decision reversed the damage to my trust in the company had already been done.

Important disclaimer:
The stolen vehicle was covered for 3rd party, fire and theft. The reason for the delay seemed to be a lack of conclusive evidence over whether the vehicle had been stolen or simply rolled through a neighbour's property in neutral. While this is understandable this lack of conclusive evidence should have been available to Lumley from the time that the investigator's report was submitted.

Key areas for improvement:
- Communication and accountability
Delays in processing claims are understandable, particularly when a non-standard element is involved. Ideally someone from Lumley should have contacted me with a revised deadline for the claim settlement/decision date and a reason for any changes. In addition to this when I was given timeframes by Lumley staff someone should have been accountable for meeting those deadlines.
- Claims as opportunities
Insurance companies sell trust. Claims provide an opportunity for an insurer to demonstrate their trustworthiness to individual clients. They potentially offer an opporunity to secure (or lose) a lifelong customer. In this case Lumley demonstrated a lack of trustworthiness. This then decreased confidence in the other policies we held with them (home, contents, another car). This lead to us (a young professional couple) changing insurance providers over a $700 claim.


Migelli 250r 2013 vs Kawasaki Ninja 250 and 300

This is currently under construction. You may like to check back in the near future.

For those on a learner or restricted motorcycle licence in New Zealand, or those looking for a bike with a smaller engine, 250cc sports bikes can be quite appealing. Before the change in the LAMS regulations Kawasaki's 250cc Ninja was a strong player in this market carrying strong name recognition with proven reliability and performance. While the Ninja looks set to stay in stock for a while many dealers are now offering competitors with a lower retail price as well as the new 300cc Ninja. Which should you buy?

What's the difference?

Unlike a previous comparison between the GN125 and the GN250 the Migelli 250r and Ninja 250 the differences aren't based on engine displacement, nor are they superficial differences. Before considering the

Styling

While both bikes are sports bikes

Engine

While they share a displacement of 250cc the engine set-up differs. The Migelli is a single cylinder while the ninja is a V-twin.

Cooling

Liquid cooling is used on both bikes.

Weight

The Migelli is lighter than the Ninja

Power

in terms of output the

Motorway Speed Capability

Both bikes are capable of motorway speed in NZ

Top Speed

Ninja ~150kmph
Migelli ~140kmph

Price

The current price from Colemans is

Resale Value

While the Ninja has a demonstrable resale value it is too early to comment conclusively on the resale value of the Migelli.

Fuel Efficiency

From Fuelly the current Ninja model can travel about 24km/L. This is comparable to the reported efficiency of the Migelli (4L/100km or 25km/L).