Interpreting quantitative data / David Byrne.

• Author: ProQuest (Firm); Byrne, D. S. 1947-
• TeilnehmendeR: ProQuest (Firm)
• Year of Publication: 2002
• Language: English
• Physical Description: x, 176 p. :; ill.

Table of Contents

• Machine generated contents note: Introduction 1
• 1 Interpreting the Real and Describing the Complex:
• Why We Have to Measure 12
• Positivism, realism and complexity 14
• Naturalism - a soft foundationalist argument 17
• There are no universals but, nevertheless, we can know 19
• Models and measures: a first pass 21
• Contingency and method - retroduction and retrodiction 25
• Conclusion 27
• 2 The Nature of Measurement: What We Measure and
• How We Measure 29
• Death to the variable 29
• State space 32
• Classification 34
• Sensible and useful measuring 37
• Conclusion 41
• 3 The State's Measurements: The Construction and
• Use of Official Statistics 44
• The history of statistics as measures 45
• Official and semi-official statistics 49
• Social indicators 52
• Tracing individuals 56
• Secondary data analysis 57
• Sources 57
• Conclusion 58
• 4 Measuring the Complex World: The Character of Social Surveys 61
• Knowledge production - the survey as process 63
• Models from surveys - beyond the flowgraph? 66
• Representative before random - sampling in the real world 72
• Conclusion 77
• 5 Probability and Quantitative Reasoning 79
• Objective probability versus the science of clues 80
• Single case probabilities - back to the specific 84
• Gold standard - or dross? 84
• Understanding Head Start 88
• Probabilistic reasoning in relation to non-experimental data 90
• Randomness, probability, significance and investigation 92
• Conclusion 93
• 6 Interpreting Measurements: Exploring, Describing and Classifying 95
• Basic exploration and description 96
• Making sets of categories - taxonomy as social exploration 99
• Can classifying help us to sort out causal processes? 105
• Conclusion 110
• 7 Linear Modelling: Clues as to Causes 112
• Statistical models 113
• Flowgraphs: partial correlation and path analysis 116
• Working with latent variables - making things out of things
• that don't exist anyhow 117
• Multi-level models 120
• Statistical black boxes - Markov chains as an example 122
• Loglinear techniques - exploring for interaction 123
• Conclusion 128
• 8 Coping with Non-linearity and Emergence: Simulation and
• Neural Nets 130
• Simulation - interpreting through virtual worlds 131
• Micro-simulation - projecting on the basis of aggregation 133
• Multi-agent models - interacting entities 135
• Neural nets are not models but inductive empiricists 139
• Models as icons, which are also tools 141
• Using the tools 142
• Conclusion 143
• 9 Qualitative Modelling: Issues of Meaning and Cause 145
• From analytic induction through grounded theory to computer
• modelling - qualitative exploration of cause 147
• Coding qualitative materials 150
• Qualitative Comparative Analysis (QCA) - a Boolean approach 154
• Iconic modelling 157
• Integrative method 159
• Conclusion 160
• Conclusion 162
• Down with: 162
• Up with: 163
• Action theories imply action164.