Muutke küpsiste eelistusi

Biomeasurement: A Student's Guide to Biological Statistics 4th Revised edition [Pehme köide]

4.25/5 (4 hinnangut Goodreads-ist)
(Reader, Department of Life Sciences, Anglia Ruskin University)
  • Formaat: Paperback / softback, 384 pages, kõrgus x laius x paksus: 245x190x19 mm, kaal: 650 g
  • Ilmumisaeg: 02-May-2019
  • Kirjastus: Oxford University Press
  • ISBN-10: 0198807481
  • ISBN-13: 9780198807483
Teised raamatud teemal:
Biomeasurement: A Student's Guide to Biological Statistics 4th Revised editionSuurem pilt
  • Formaat: Paperback / softback, 384 pages, kõrgus x laius x paksus: 245x190x19 mm, kaal: 650 g
  • Ilmumisaeg: 02-May-2019
  • Kirjastus: Oxford University Press
  • ISBN-10: 0198807481
  • ISBN-13: 9780198807483
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780198807483.html
Märksõnad:
Statistical analysis allows us to attach meaning to data that we have collected; it helps us to understand what experimental results really mean, and to assess whether we can trust what experiments seem to be telling us. Yet, despite being a collection of the most valuable and important tools available to bioscientists, statistics is often the aspect of study most feared by students.

Biomeasurement offers a refreshing, student-focused introduction to the use of statistics in the study of the biosciences. With an emphasis on why statistical techniques are essential tools for bioscientists, the book develops students' confidence to use and further explore the key techniques for themselves.

Beginning by placing the role of data analysis in the context of the wider scientific method and introducing the student to the key terms and concepts common to all statistical tools, the book then guides the student through descriptive statistics, and on to inferential statistics, explaining how and why each type of technique is used, and what each can tell us in order to better understand our data. It goes on to present the key statistical tests, walking the student step-wise through the use of each, with carefully-integrated examples and plentiful opportunities for hands-on practice. The book closes with an overview of choosing the right test to suit your data, and tools for presenting data and their statistical analyses.

Written by a talented educator, whose teaching has won praise from the UK's Quality Assurance Agency for Higher Education, Biomeasurement is sure to engage even the most wary of students, demonstrating the power and importance of statistics throughout the study of bioscience.

Online resources:

The online resources to accompany Biomeasurement include:

For students:

· Screencast walkthroughs for SPSS and R. · Online glossary and flashcard glossary. · Data sets, for use in statistical analysis software packages. · Help sheets offering concise guidance on key techniques and the use of statistical analysis software packages. · Interactive calculation sheets to help students carry out key statistical tests quickly and easily in Excel, without the need for other software. · Full-text versions of Literature Link articles from OUP Journals.

For registered adopters of the book:

· Additional exercises, to supplement those in the book, and suggested tutorial assignments. · Figures from the book, available for download. · PowerPoint presentation outlines for each chapter.

Arvustused

Review from previous edition Biomeasurement does a wonderful job of keeping the biology the focus of analysis, and highlighting the fact that statistics is simply another useful tool to help biological understanding. * Dr Shane Richards, Biological and Biomedical Sciences, University of Durham, UK * This book represents the best I have seen for teaching undergraduate biologists statistics. * Dr Chris Venditti, Department of Biological Sciences, University of Hull, UK * It demystifies and clarifies topics that students can normally find confusing and challenging. It is a must for biologists! * Dr Maria G. Tuohy, School of Natural Sciences, National University of Ireland, Galway * This book was a blessing when I got it for my first year, and I'm still finding it helpful in my second year! It is so easy to navigate; you can read it cover to cover if you are very confused, or just dip into the topics you need. I would definitely recommend it to any students doing a bioscience degree which involves statistical elements. * Bethany Richmond, student at the University of Warwick * As a student with limited mathematical ability, new to statistics who believed I would not be able to pass this module, I read this book chapter by chapter prior to my weekly lectures and everything fell into place without a struggle. A 100% necessary purchase. A 100% necessary read. The book is appealing and very easy to navigate. I have tried to read other statistics books aimed at beginners but this was the only book which I clearly understood. * Julie Carter, student at Anglia Ruskin University *

Preface vii
Acknowledgements ix
Using this book xxii
1 Why am I reading this book?
1(11)
Book and
Chapter Aims
1(1)
1.1 My lecturer is a sadist!
1(2)
1.2 Doing science: the big picture
3(3)
1.2.1 Descriptive questions
3(1)
1.2.2 Questions answered using a research hypothesis
4(1)
Stage 1 Developing research hypotheses
4(1)
Stage 2 Generating predictions
5(1)
Stage 3 Testing predictions
6(1)
1.3 The process in practice
6(1)
1.4 Essential skills for doing science
7(2)
Analysing data
7(1)
Developing hypotheses and predictions
7(1)
Experimental design
8(1)
Taking measurements
8(1)
Critical evaluation
8(1)
Health, safety, and ethical assessment
9(1)
1.5 Types of data analysis
9(1)
Checklist of key points
10(1)
Self-help questions
11(1)
2 Getting to grips with the basics
12(18)
Chapter Aims
12(1)
2.1 Populations and samples
12(5)
2.1.1 The sampling process
13(1)
Sample size
14(1)
Replication and pseudoreplication
14(1)
Random sampling and bias
15(1)
2.1.2 Sample error
15(2)
2.2 Variation and variables
17(4)
2.2.1 Identifying variables
18(1)
2.2.2 Dependent and independent variables
18(1)
2.2.3 Relationships and differences
19(1)
2.2.4 Manipulated versus natural variation in independent variables
20(1)
2.2.5 Lack of independence between variables
21(1)
2.3 Understanding data
21(5)
2.3.1 Differences: related and unrelated data
22(2)
2.3.2 Levels of measurement
24(1)
Nominal (categories)
24(1)
Ordinal (ranks)
24(1)
Scale (counts and measures)
25(1)
2.4 Demystifying formulae
26(2)
2.4.1 Squiggles, lines, and letters
26(1)
2.4.2 Doing things in order
27(1)
Checklist of key points
28(1)
Self-help questions
29(1)
3 Describing a single sample
30(29)
Chapter Aims
30(1)
3.1 The single sample
30(1)
3.2 Descriptive statistics
31(6)
3.2.1 Central tendency
31(1)
Mean (y)
31(1)
Median
32(1)
Mode
33(1)
3.2.2 Variability
33(1)
Range
33(1)
Interquartile range
34(1)
Variance (s2)
34(3)
Standard deviation (s)
37(1)
3.3 Frequency distributions
37(4)
3.3.1 For nominal, ordinal, and discrete scale data
38(1)
3.3.2 For continuous scale data
39(2)
3.4 The normal, and other, theoretical distributions
41(2)
3.4.1 Characteristics of the normal distribution
42(1)
3.4.2 Other distributions: binomial and Poisson
43(1)
3.5 Pies, boxes, and errors
43(1)
35.1 Pie charts as alternatives to frequency-distribution charts
43(3)
3.5.2 Understanding boxplots
44(1)
3.5.3 Introducing error bars
44(2)
3.6 Example data: ranger patrol tusk records
46(1)
3.7 Worked example: using SPSS
47(10)
3.7.1 Descriptive statistics and frequency distributions
47(1)
For nominal, ordinal, and discrete scale data
48(1)
For continuous scale data
49(4)
3.7.2 Pie charts
53(2)
3.7.3 Boxplots
55(2)
Checklist of key points
57(1)
Self-help questions
58(1)
4 Inferring and estimating
59(14)
Chapter Aims
59(1)
4.1 Overview of inferential statistics
59(2)
4.1.1 Why we need inferential statistics---a reminder
59(1)
4.1.2 Uncertainty and probability
60(1)
4.2 Inferring through estimation
61(5)
4.2.1 Standard error (of the mean, S-y)
62(1)
4.2.2 Confidence intervals {of the mean)
63(1)
4.2.3 Error bars revisited
64(1)
4.2.4 Comparing samples
65(1)
4.3 Example data: ground squirrels
66(1)
4.4 Worked example: using SPSS
67(4)
4.4.2 Errorplots
68(3)
Checklist of key points
71(1)
Self-help questions
72(1)
5 Choosing the right test and graph
73(22)
Chapter Aims
73(1)
5.1 Using graphs
74(2)
5.2 NHST and other options
76(2)
5.3 Which NHST?
78(3)
5.3.1 Tests of frequencies
79(1)
5.3.2 Tests of relationship
80(1)
5.3.3 Tests of difference
80(1)
5.4 Worked examples: graphs with two variables using SPSS
81(12)
5.4.1 Frequency distributions
82(1)
5.4.2 Pie charts
83(2)
5.4.3 Scatterplots
85(1)
5.4.4 Boxplots
86(1)
Related samples
87(1)
Unrelated samples
88(2)
5.4.5 Errorplots
90(1)
Related samples
90(1)
Unrelated samples
91(2)
Checklist of key points
93(1)
Self-help questions
93(2)
6 Overview of null hypothesis significance testing
95(16)
Chapter Aims
95(1)
6.1 Four steps of null hypothesis significance testing
95(5)
6.1.1 Step 1: construct a (statistical) null hypothesis (H0)
96(1)
6.1.2 Step 2: decide on a critical significance level (α)
97(1)
6.1.3 Step 3: calculate your statistic
97(1)
6.1.4 Step 4: reject or accept the null hypothesis
98(1)
Step 4 Using critical value tables
98(1)
Step 4 Using P values on computer output
98(2)
6.2 Parametric and nonparametric
100(2)
6.2.1 Comparison of parametric and nonparametric
100(1)
6.2.2 Checking criteria for parametric tests using the normal distribution
101(1)
6.2.3 Choosing between parametric and nonparametric
101(1)
6.2.4 Transformation
102(1)
6.3 One-and two-tailed tests
102(1)
6.4 Effect sizes and their confidence intervals
103(2)
6.4.1 Uses of effect size
103(1)
6.4.2 Ways of measuring effect size
104(1)
6.5 Error and power
105(3)
6.5.1 Type I and type II error
105(1)
6.5.2 Statistical power
106(1)
6.5.3 Power analyses: a priori and post hoc
106(1)
6.5.4 Implications for interpreting your results
107(1)
6.6 Criticism of NHST
108(1)
Checklist of key points
109(1)
Self-help questions
110(1)
7 Tests on frequencies
111(32)
Chapter Aims
111(1)
Notes on symbols
111(1)
7.1 Introduction to chi-square tests
111(5)
7.1.1 Only use frequency data
112(1)
7.1.2 Types of chi-square test
112(2)
7.1.3 Sample size considerations
114(1)
7.1.4 When to use chi-square with caution
114(1)
7.1.5 Alternatives to chi-square tests
115(1)
7.2 Example data
116(3)
7.2.1 One-way: Mendel's peas
116(1)
7.2.2 Two way: Mikumi's elephants
117(2)
7.3 One-way chi-square test
119(11)
7.3.1 When to use
119(1)
7.3.2 Four steps
120(1)
Using critical value tables
120(1)
Using P values on computer output
120(1)
7.3.3 Worked example: by hand
121(1)
With expected according to a 1:1:1:1 Mendelian ratio (test of homogeneity)
121(1)
With expected according to a 9:3:3:1 Mendelian ratio
122(1)
7.3.4 Worked example: using SPSS
123(2)
With expected according to a 1:1:1:1 Mendelian ratio (test of homogeneity)
125(2)
With expected according to a 9:3:3:1 Mendelian ratio
127(2)
7.3.5 Literature link: weary lettuces
129(1)
7.4 Two-way chi-square test
130(10)
7.4.1 When to use
130(1)
7.4.2 Tour steps
131(1)
Using critical value tables
132(1)
Using P values on computer output
132(1)
7.4.3 Worked example: by hand
132(2)
7.4.4 Worked example: using SPSS
134(3)
7.4.3 Literature link: treatment alliance
137(3)
Checklist of key points
140(1)
Self-help questions
141(2)
8 Tests of difference: two unrelated samples
143(23)
Chapter Aims
143(1)
8.1 Introduction to the t- and Mann-Whitney U tests
143(3)
8.1.1 Variables and levels of measurement needed
143(1)
8.1.2 Comparison of t- and Mann-Whitney U tests
144(1)
8.1.3 The t-test and the parametric criteria
144(1)
8.1.4 Sample size considerations
145(1)
8.1.5 Alternatives to t-and Mann-Whitney U tests
146(1)
8.2 Example data: dem bones
146(2)
8.3 t-Test
148(7)
8.3.1 When to use
148(1)
8.3.2 Four steps of a t-test
149(1)
Using critical value tables
149(1)
Using P values on computer output
150(1)
8.3.3 Worked example: by hand
150(2)
8.3.4 Worked example: using SPSS
152(2)
8.3.5 Literature link: silicon and sorghum
154(1)
8.4 Mann-Whitney U test
155(8)
8.4.1 When to use
155(1)
8.4.2 Four steps of a Mann-Whitney U test
156(1)
Using critical value tables
156(1)
Using P values on computer output
157(1)
8.4.3 Worked example: by hand
157(1)
8.4.4 Worked example: using SPSS
158(4)
8.4.5 Literature link: Alzheimer's disease
162(1)
Checklist of key points
163(1)
Self-help questions
164(2)
9 Tests of difference: two related samples
166(23)
Chapter Aims
166(1)
9.1 Introduction to paired t- and Wilcoxon signed-rank tests
166(3)
9.1.1 Variables and levels of measurement needed
167(1)
9.1.2 Comparison of paired t- and Wilcoxon signed-rank tests
167(1)
9.1.3 The paired t-test and the parametric criteria
168(1)
9.1.4 Sample size considerations
168(1)
9.1.5 Alternatives to and extensions of the paired t- and Wilcoxon signed-rank tests
169(1)
9.2 Example data; bighorn ewes
169(3)
9.3 Paired t-test
172(7)
9.3.1 When to use
172(1)
9.3.2 Four steps of a paired t-test
172(1)
Using critical value tables
173(1)
Using P values on computer output
173(1)
9.3.3 Worked example: by hand
173(3)
9.3.4 Worked example: using SPSS
176(1)
9.3.5 Literature link: slug slime
177(2)
9.4 Wilcoxon signed-rank test
179(8)
9.4.1 When to use
179(1)
9.4.2 Four steps of a Wilcoxon signed-rank test
180(1)
Using critical value tables
181(1)
Using P values on computer output
181(1)
9.4.3 Worked example: by hand
182(1)
9.4.4 Worked example: using SPSS
183(2)
9.4.5 Literature link: head injuries
185(2)
Checklist of key points
187(1)
Self-help questions
187(2)
10 Tests of difference: more than two samples
189(22)
Chapter Aims
189(1)
10.1 Introduction to one-way and Kruskal--Wallis tests
189(5)
10.1.1 Variables and levels of measurement needed
190(1)
10.1.2 Comparison of one-way and Kruskal--Wallis tests
191(1)
10.1.3 One-way Anova and the parametric criteria
191(1)
10.1.4 Sample size considerations
192(1)
10.1.5 Alternatives to and extensions of one-way and Kruskal--Wallis tests
193(1)
10.1.6 The language of Anova
193(1)
10.1.7 Multiple comparisons
194(1)
10.2 Example data: nitrogen levels in reeds
194(2)
10.3 One-way Anova test
196(1)
10.3.1 When to use
197(1)
10.32 Four steps of a one-way Anova
197(5)
Using critical value tables
199(1)
Using P values on computer output
199(1)
10.3.3 Worked example: using SPSS
199(2)
10.3.4 Literature link: running rats
201(1)
10.4 Kruskal--Wallis test
202(6)
10.4.1 When to use
203(1)
10.4.2 Four steps of a Kruskal--Wallis test
203(1)
Using critical value tables
204(1)
Using P values on computer output
204(1)
10.4.3 Worked example: using, SPSS
205(2)
10.4.4 Literature link: cooperating long tailed tits
207(1)
10.5 Model I and model II Anova
208(1)
Checklist of key points
208(1)
Self-help questions
209(2)
11 Tests of relationship: regression
211(20)
Chapter Aims
211(1)
11.1 Introduction to bivariate linear regression
211(3)
11.1.1 Variables arid levels of measurement needed
212(1)
11.1.2 Linear model: scary-not!
213(1)
11.13 The three regression questions
214(3)
11.1.4 Added extras: how much is explained, and prediction
214(1)
11.1.5 Regression and the parametric criteria
215(1)
11.1.6 Sample size considerations
216(1)
11.1.7 Alternatives to and extensions of bivariate linear regression and Anova
217(1)
11.2 Example data: species richness
217(1)
11.3 Regression test
218(1)
11.3.1 When to use
219(1)
11.3.2 Four steps of a regression test
219(1)
Using critical value tables
220(1)
Using P values on computer output
220(1)
11.3.3 Worked example: using SPSS for a regression test
221(2)
11.3.4 Worked example: using SPSS to get the added extras
223(2)
11.3.5 Reporting bivariate linear regression results
225(1)
11.3.6 Literature link: nodules
226(1)
11.4 Model I and model II regression
227(1)
Checklist of key points
228(1)
Self-help questions
229(2)
12 Tests of relationship: correlation
231(22)
Chapter Aims
231(1)
12.1 Introduction to the Pearson and Spearman correlation tests
231(6)
12.1.1 Variables and levels of measurement needed
232(2)
12.1.2 Comparison of Pearson's and Spearman's tests
234(1)
12.1.3 Pearson and the parametric criteria
235(1)
12.1.4 Sample size considerations
235(1)
12.1.5 The correlation coefficient
236(1)
12.1.6 Partial, multiple, and multivariate correlation
236(1)
12.2 Example data: eyeballs
237(1)
12.3 Pearson correlation test
238(6)
12.3.1 When to use
238(2)
12.3.2 Four steps of a Pearson correlation test
240(1)
Using critical value tables
241(1)
Using P values on computer output
241(1)
12.3.3 Worked example: using SPSS
241(2)
12.3.4 Literature link: male sacrifice
243(1)
12.4 Spearman correlation test
244(5)
12.4.1 When to use
245(1)
12.4.2 Four steps of a Spearman correlation test
245(1)
Using critical value tables
246(1)
Using P values on computer output
246(1)
12.4.3 Worked example: using SPSS
246(2)
12.4.4 Literature link: defoliating ryegrass
248(1)
12.5 Comparison of correlation and regression
249(1)
Checklist of key points
250(1)
Self-help questions
251(2)
13 Introducing the generalized linear model: general linear model
253(37)
Chapter Aims
253(1)
Notes on terminology
253(1)
13.1 Introduction to the general linear model
254(9)
13.1.1 Variables and levels of measurement
255(1)
13.1.2 The linear model revisited
256(3)
13.1.3 The language of GLMs
259(1)
13.1.4 Questions and extras
259(1)
13.1.5 Types of sums of squares
260(1)
13.1.6 Model assumptions and the parametric criteria
261(1)
Normality of error
261(1)
Homogeneity of variance
261(1)
Linearity
261(2)
13.2 Example data: watered willows
263(2)
13.3 General linear model
265(14)
13.3.1 When to use
265(1)
13.3.2 GLM and the four steps
266(1)
13.3.3 Worked example: using SPSS
267(1)
Looking at the model overall (answering question 2a, Section 13.1.4)
267(2)
Looking at individual explanatory variables (answering question 2b, Section 13.1.4)
269(2)
Looking at R: (answering question 3, Section 13.1.4)
271(1)
Using coefficients (answering question 1, Section 13.1.4)
272(2)
Using coefficients (making predictions)
274(1)
Checking model assumptions
274(1)
13.3.4 Reporting results from GLM
275(3)
13.3.5 Literature link: brains and booze
278(1)
13.4 Interaction
279(3)
13.4.1 Worked example: using SPSS, interaction
281(1)
13.5 Random factors and mixed models
282(1)
13.6 The multiple-model approach
283(2)
13.6.1 Finding the best model
284(1)
13.6.2 Reporting results from multiple models
284(1)
13.7 The general and generalized linear models compared
285(1)
Checklist of key points
285(3)
Self-help questions
288(2)
14 More on the generalized linear model: logistic and loglinear models
290(32)
Chapter Aims
290(1)
14.1 Introduction to the logistic and loglinear models
290(4)
14.1.1 Variables and levels of measurement
291(1)
14.1.2 Link functions revisited
292(1)
14.1.3 Questions and extras
293(1)
14.1.4 Model assumptions and overdispersion
293(1)
14.2 Example data: urban birds
294(1)
14.3 The binary logistic model
295(12)
14.3.1 When to use
295(1)
14.3.2 Binary logistic models and the four steps
296(1)
14.3.3 Worked example: using SPSS
296(6)
Answering question 3 How good is the model?
302(1)
Answering question 2a Is the model significant overall?
302(1)
Answering question 2b Are individual explanatory variables significant?
303(1)
Answering question 1 What is the model?
304(1)
Effect size
305(1)
Checking for overdispersion
306(1)
14.3.4 Literature link: death by AMI
306(1)
14.4 The loglinear model
307(11)
14.4.1 When to use
307(1)
14.4.2 Loglinear models and the four steps
308(1)
14.4.3 Worked example: using SPSS
308(5)
Answering question 3 How good is the model?
313(1)
Answering question 2a Is the model significant overall?
313(1)
Answering question 2b Are individual explanatory variables significant?
314(1)
Answering question 1 What is the model?
315(1)
Effect size
316(1)
Checking for overdispersion
317(1)
14.4.4 Literature link: sea cows
317(1)
14.5 The general, binary logistic, and loglinear models compared
318(1)
14.6 Alternatives and extensions
318(2)
Checklist of key points
320(1)
Self-help questions
321(1)
Answers to self-help questions
322(5)
Chapter 1
322(1)
Chapter 2
322(1)
Chapter 3
322(1)
Chapter 4
323(1)
Chapter 5
323(1)
Chapter 6
324(1)
Chapter 7
324(1)
Chapter 8
324(1)
Chapter 9
325(1)
Chapter 10
325(1)
Chapter 11
325(1)
Chapter 12
325(1)
Chapter 13
325(1)
Chapter 14
326(1)
Appendix I How to enter data into SPSS
327(3)
Name
327(1)
Type, width, and decimals
327(1)
Label
327(1)
Values
327(1)
Missing
328(1)
Columns
328(1)
Align
328(1)
Measure
328(1)
Role
329(1)
Appendix II Statistical tables of critical values
330(10)
Χ2
330(1)
t
331(1)
U
332(2)
T
334(2)
F
336(1)
H
337(1)
r
338(1)
r5
339(1)
Appendix III Summary guidance on reporting statistical results
340(3)
Descriptive statistics
340(1)
Confidence intervals
340(1)
Statistical tests
340(2)
Effect size
342(1)
Appendix IV Statistics and experimental design
343(3)
Designs with control groups
343(1)
Balanced and unbalanced design
343(1)
Completely randomized designs
343(1)
One-way or one-factor designs
343(1)
Multi-way or multi-factor designs
344(1)
Fully crossed designs
344(1)
Incomplete designs
344(1)
Blocking
344(1)
Paired design
344(1)
Covariate
344(1)
Within-subject designs
345(1)
Split-plot designs
345(1)
Selected further reading
346(3)
Next steps ...
346(1)
For when you are feeling stronger ...
347(1)
Online ...
348(1)
References 349(4)
Index 353
Dr Dawn Hawkins is Reader in the School of Life Sciences at Anglia Ruskin University. She has over 20 years' experience in curriculum development and teaching whole organism biology and statistics in higher education. Her textbook is based on the quantitative modules that she teaches to undergraduate and postgraduate bioscientists. As well as the use of statistics in the biosciences, her research interests also include the behaviour, ecology and conservation of animals in East African ecosystems.