There are any number of reasons for believing that those assumptions are unreasonable for most scale construction in the social sciences, but the main thing I would emphasize is the need to allow for correlated factors via an oblique rotation such as Oblimin. Back in the early days of developing intelligence tests, it may have made sense to search for uncorrelated orthogonal factors, but that logic seldom applies outside the most extreme cases of psychometric work. In particular, when someone is specifying a model with two or more factors, the conceptual or theoretical names they give these factors almost universally imply that the underlying constructs should be correlated. The problem of assuming that your factors are uncorrelated i. That correlation will almost always be non-zero and often it will be substantial.
|Published (Last):||3 November 2007|
|PDF File Size:||11.42 Mb|
|ePub File Size:||16.90 Mb|
|Price:||Free* [*Free Regsitration Required]|
MM MM Chapter 9 t-tests : I stripped a lot of the methods content to go in Chapter 1, so this chapter is more purely about the t-test now. I added some discussion on median splits, and doing t-tests from only the means and standard deviations. Chapter 11 GLM 2 : Similar to the old Chapter 9, but I added a section on assumptions that now discusses the need for the covariate and treatment effect to be independent. I also added some discussion of eta-squared and partial eta-squared Spss produces partial eta-squared but I ignored it completely in the last edition.
Consequently I restructured much of the material in this example and I had to create a new data set when I realized that the old one violated the assumption that I had just spent several pages telling people not to violate. Chapter 12 GLM 3 : This chapter is ostensibly the same as the old Chapter 10, but with nicer diagrams. I edited it down quite a bit and restructured material so there was less repetition. I added an explanation of the between-participant sum of squares also.
The first example tutors marking essays is now an end of chapter task, and the new example is one about celebrities eating kangaroo testicles on television. It needed to be done. Chapter 15 Non-parametric statistics : This chapter is more or less the same as the old Chapter Chapter 16 MAnova : I rewrote a lot of the material on the interpretation of discriminant function analysis because I thought it pretty awful.
Chapter 17 Factor analysis : This chapter is very similar to the old Chapter I wrote some material on interpretation of the determinant. Chapter 18 Categorical data : This is similar to Chapter 16 in the previous edition. I added some material on interpreting standardized residuals. Chapter 19 Multilevel linear models : This is a new chapter.
Goodbye The first edition of this book was the result of two years give or take a few weeks to write up my Ph. The second edition was another two years of work and I was terrified that all of the changes would be the death of it. I can hear the cries of lecturers around the world refusing to use the book because of cruelty to eels.
This book has been part of my life now for over 10 years; it began and continues to be a labour of love. Andy My contact details are at www. Do the chapters get more difficult as I go through the book? Why have I done this? Many books teach different tests in isolation and never really give you a grip of the similarities between them; this, I think, creates an unnecessary mystery.
Most of the tests in this book are the same thing expressed in slightly different ways. So, I wanted the book to tell this story. These icons are designed to give you an idea of the difficulty of the section.
These are sections that everyone should be able to understand. These are topics that I teach my second years and so anyone with a bit of background in statistics should be able to get to grips with them.
However, some of these sections will be quite challenging even for second years. These are intermediate sections. Why do I keep seeing stupid faces everywhere? As the book progresses he becomes increasingly despondent. Read into that what you will. Of course the educational specialists think he needs a specific role, and so his role is to look cute and make bad cat-related jokes.
Cramming Sam: Samantha hates statistics. So, she appears and gives you a summary of the key points that you need to know. Jane Superbrain: Jane is the cleverest person in the whole universe she makes Smart Alex look like a bit of an imbecile.
The reason she is so clever is that she steals the brains of statisticians and eats them. Apparently they taste of sweaty tank tops, but nevertheless she likes them.
As it happens, she is also able to absorb the contents of brains while she eats them. Having devoured some top statistics brains she knows all the really hard stuff and appears in boxes to tell you really advanced things that are a bit tangential to the main text. That tells you all that you need to know about my statistics ability. He turned up at universities, cornered academics, kidnapped their families and threatened to put them in a bath of crayfish unless he was given real data.
The generous ones relented, but others? So, when you see Leni you know that you will get some real data, from a real research study to analyse. Keep it real. Let us not be the ones to disappoint a young, dirty, slightly smelly boy who dines on gruel, so when Oliver appears you can be certain of one thing: there is additional information to be found on the companion website.
Like many of us, this leaves little time for him to analyse data, and this makes him very sad. Smart Alex: Alex is a very important character because he appears when things get particularly difficult. What is on the companion website?
This has two benefits: 1 The book is slightly lighter than it would have been, and 2 rather than being restricted to the size of a CD-ROM, there is no limit to the amount of fascinating extra material that I can give you although Sage have had to purchase a new server to fit it all on.
To enter my world of delights, go to www. How will you know when there are extra goodies on this website? The website contains resources for students and lecturers alike: MM MM MM Data files: You need data files to work through the examples in the book and they are all on the companion website.
There are data files here for a range of students, including those studying psychology, business and health sciences. Some of these movies are open access, but because the publishers want to sell some books, others are available only to lecturers. The idea is that they can put them on their virtual learning environments. Podcast: My publishers think that watching a film of me explaining what this book is all about is going to get people flocking to the bookshop.
I think it will have people flocking to the medicine cabinet. Either way, if you want to see how truly uncharismatic I am, watch and cringe.
Summary: Discovering statistics using SPSS (third edition)
Introducing Statistical Methods: Discovering Statistics Using SPSS by Andy Field (2009, Paperback)