Pages: 3

This overview chapter summarises the aims and intentions of the book: namely, a one-stop shop informing applied researchers in psychology and related social science and business and management fields about 21 key topics to be considered when conducting research projects primarily for their theses, including information about new topics such as using artificial intelligence (AI) in research. The four sections of this book are summarised: Getting started, data collection, data analysis, and research dissemination. This chapter also briefly describes each of the 21 chapters in this book. Finally, I warmly thank the contributors from all over the world, and from multiple disciplines both within and external to applied psychology, who so generously submitted their pertinent expertise about conducting research.

Pages: 63

No chapter abstract available.

Pages: 10

This chapter discusses the necessity of designing our research projects to have an impact for end users and describes the five key research design principles central to the applied scientific method which high-quality research is recommended to adopt. These five principles are (a) the inclusion of reliable and valid measures; (b) the inclusion of sufficient and generalisable research samples; (c) the inclusion of the evidence of theoretical sophistication; (d) the inclusion of research designs that promote causal generalisations; and (e) the inclusion of research implications for end users. The chapter argues that the inclusion of these five principles maximises the opportunities of research to achieve an external impact and that this should be one of the key aims of conducting research at all levels. This chapter also discusses the process of research evaluation and the importance of planning this evaluation process within the research design stage.

Pages: 21

This chapter reviews the core concepts of sampling, including different types of samples, considerations about response rate, margin of error, sample weighting, and adjustment. The chapter also presents a series of hypothetical case studies for how one could procure a sample in a variety of complex organisational and research contexts. These case studies cover a range of challenging sample designs that we have experienced in the last decade working in industry, running political polls, and managing a large-scale national-probability longitudinal panel study. Alongside these worked examples, we present the New Zealand Attitudes and Values Study as a real-world case study of how one can conduct a national-probability postal questionnaire study. The chapter includes detailed information on postal questionnaire response rates for people based on their occupation, age, gender, and socioeconomic status drawn from the study. Finally, we conclude by offering a decision guide for sample design.

Pages: 11

Ethics is generally defined as the branch of philosophy that focuses on the establishment of right and wrong. The terms ‘research ethics’ and ‘research integrity’ are often used interchangeably. This chapter discusses human research ethics matters and the ethical practice responsibilities for researchers at all stages of a research project – from the rationale for the research through the design and data stages and then ongoing, such as how the outputs are disseminated. The important elements of ethical risks, consent, and privacy are considered. It is proposed that the feedback and recommendations from research ethics review panels should be viewed as a positive constructive approach to improve research project designs – not as a compliance and enforcement process.

Pages: 19

With technological advancements offering new research opportunities, this chapter explores how artificial intelligence (AI) platforms such as https://www.w3.org/1999/xlink" xlink:href="https://s3-euw1-ap-pe-df-pch-content-public-p.s3.eu-west-1.amazonaws.com/9781003362715/05cbc624-915a-47c8-b94e-9bac4b5bbe8b/content/www.Elicit.com">Elicit.com, https://www.w3.org/1999/xlink" xlink:href="https://s3-euw1-ap-pe-df-pch-content-public-p.s3.eu-west-1.amazonaws.com/9781003362715/05cbc624-915a-47c8-b94e-9bac4b5bbe8b/content/www.ResearchRabbit.ai">ResearchRabbit.ai, ChatPDF, and ChatGPT can be used for facilitating research. We investigate their potential for exploring and synthesising literature and data analysis (specifically with the use of R statistical software). Using examples, we discuss these platforms’ key features that may allow researchers to efficiently collect and organise literature and complement software like R for data analysis. We also discuss some of these platforms’ key limitations, to provide a holistic picture of the extent to which AI can facilitate the research process.

Pages: 139

No chapter abstract available.

Pages: 16

This chapter examines the logic and nature of using rigorous and explicit methods to systematically review existing literature pertaining to a research question. This can include the mapping of research studies that have been undertaken on a topic, as well as the synthesis of findings of such studies to answer a specific research question. Reviews tell us what research has been undertaken and what we do know from that research (and how we know it), and this informs what further research we might want to undertake (and how we might know it). Reviews are thus a core initial component in any research strategy. They can also be a means to engage non-researchers in policy, professional, and democratic debates involving research evidence. The chapter discusses the diversity in approaches to reviewing, which reflect the variation in types of research questions and research methods in the social, behavioural, and medical sciences. The standard steps in undertaking systematic reviews are introduced, leading to a consideration of the justifiable evidence claims that can be made from their findings.

Pages: 12

This chapter discusses the use of archival data in psychological research. Archival data are existing data that were collected for a purpose other than their current use. First, we review several sources and types of archival data that may be of particular interest to applied psychology researchers, including social science data archives, public documents, datasets, official records, private documents or records, and mass media. Next, we discuss advantages and disadvantages that are unique to archival data use in psychological research, such as the opportunity to access datasets with a specific methodology, design, or specific population, along with the inherent challenges associated with navigating large, complex datasets with limited control over whether and how variables of interest are measured. Finally, we conclude with a series of recommendations to anyone who may be considering the use of archival data for a research project. We hope this chapter serves as a useful introduction to archival data and helpful resource to those seeking to use archival data in psychological research.

Pages: 12

Qualitative research methods have rapidly gained acceptance in mainstream academic psychology over the past four decades. As qualitative methods become more valued in psychology, particularly for their ability to illuminate social phenomena that quantitative approaches cannot address alone, scholars and practitioners alike are seeking out different qualitative methods to include in their investigations. This chapter provides a brief overview of eight of the most popular types of qualitative research methods: ethnography, phenomenology, discourse analysis, narrative research, grounded theory, action research, historical research, and case study research. As in quantitative or mixed methods approaches, each qualitative method needs to be examined for goodness of fit on a project-by-project basis, and the appropriate methodological choice depends on the research design and questions. Though there is an increasingly large range of qualitative methods or variations, this chapter is a useful starting point for psychologists, scholars, or practitioners who are interested in engaging with qualitative methods

Pages: 11

Case study research is an increasingly used research strategy in several academic disciplines, undertaken with the purpose of researching the phenomenon within a real-life context. A case study aims to analyse a spatially and temporally bounded case, to enable an in-depth understanding. Despite the growth of methodological literature, the concept of case study has been criticised for being fuzzy, and questions about the credibility of case study research have been raised. This chapter addresses issues of ontology, epistemology, and methodology that are central to the principles of case study design, with references to ongoing debates in the literature.

Pages: 18

How do investigators identify the best research design to address their research question? Many researchers gravitate to designs for those that data are most easily available – a strategy that limits the rich menu of possible designs. The primary aim of this chapter is to provide decision heuristics to enable a wider range of design choice, to enhance causal inference. These choices include promising design options such as instrumental variables and synthetic controls. The annotated bibliography provides relevant design references and high-quality exemplars. Rule-out conditions are given for each design, along with important advantages and disadvantages. The chapter addresses little used (regression point displacement), recently created (SMART: sequential multiple allocation research trials), and new (common cause) designs, along with natural experiments. It concludes with explicit design directives aimed to maximise inferential quality, including the following: embed multiple designs to address each research question; first use single-case and then between-group designs to evaluate interventions; ‘think in templates’ to discover novel ways to address questions asked and answered in other disciplines; consider research opportunities in university settings to counter restricted design choice; and use design logic to mend research problems.

Pages: 13

The use of online surveys has grown rapidly in social and behavioural science research, surpassing more established methods. We argue that a better understanding is needed, especially of the strengths and weaknesses of non-probability online surveys that can be conducted relatively quickly and cheaply. We describe two common approaches to non-probability online surveys – river and panel sampling – and theorise their inherent selection biases: topical self-selection and economic self-selection. We conclude that non-probability online surveys do not replace probability surveys but augment the researcher’s toolkit with new digital practices, such as rapid and exploratory studies of small and emerging non-demographic subpopulations.

Pages: 11

The processes involved in thought and action, the cognitive processes, are of obvious interest to researchers and practitioners in a number of areas of applied psychology. The more prominent of the methods typically used to assess cognitive processes are briefly reviewed in the present chapter. Among the earliest methods was the study of differences among individuals in their problem-solving ability. Experimental methods sought to identify the component processes of thinking, commonly using reaction time as a dependent measure. Neuropsychological methods drew on both the individual difference approach and experimental methods but used them to identify processing difficulties in patients with brain injury. Newer methods have recruited modern technology to the study of cognitive processes using, for example, the computer as a model for human problem-solving or using brain imaging techniques to examine activities in specific brain regions. Combinations of these methods are likely to bring further advances in understanding.

Pages: 14

Longitudinal research has recently substantially increased in the applied psychology area, because longitudinal data facilitate describing and understanding growth and developmental processes, as well as (Granger) causal relationships between focal variables over a specific period of time. Several well-informed decisions need to be made before collecting longitudinal data. These decisions should be based on theoretical considerations: for example, when and why are causal change processes expected; on methodological considerations: for example, when and how frequently should the causal process be measured; and on analytical considerations: for example, what kind of measures (trait vs state measures) should be used and which statistical method is best suited for analysing them (e.g., hierarchical linear modelling, cross-lagged panel analysis, growth curve modelling). This chapter provides theoretical, methodological, and analytical advice for making these important decisions before collecting longitudinal data. It is divided into three sections. First, we provide a general overview of several popular longitudinal research designs in applied psychology (experimental studies, diary studies, and panel studies). Second, we introduce some guidelines for longitudinal data collection, including theoretical, methodological, and analytical aspects. Third, we summarise the essential considerations one should take into account before collecting longitudinal data.

Pages: 12

Intensive longitudinal methods allow researchers to gather data in close to real time from people, as they go about daily life in the real world. Thus, these methods are tools for understanding variability in perceptions and experiences within people and how that relates to context. This chapter provides a taxonomy to organise the various types of these methods, along dimensions of content focus (experience, context, behaviour, or physiological functioning), perspective (self or observer), form of data (quantitative or qualitative), timing of data recordings (variable, fixed, event contingent, or continuous), and the role of the participant (active or passive). The experience sampling method, and its implementation with smartphones and other technological tools, is described as a prototype for all these methods. The characteristics, advantages, and disadvantages of other methodological variations are also summarised; these methods include daily diaries, the day reconstruction method, event contingent recording, photo voice, activity monitoring, acoustic sampling, ambulatory assessment of physiological functioning, and ecological momentary assessment.

Pages: 18

Organisations intentionally seek to initiate change through intervention programmes, targeting various outcomes, including improved employee wellbeing, attitudes, and productivity. Organisational interventions often involve a substantial investment of time and resources but do not always produce expected sustainable and positive changes in targeted outcomes. A renewed interest in organisational interventions has emerged in recent years, in response to calls to more rigorously examine factors that contribute to organisational intervention effectiveness. This chapter will discuss the topic of designing, implementing, and evaluating organisational interventions. Furthermore, it will specifically discuss emerging approaches to evaluating organisational interventions, including improved research methodology, to assess intervention impact, application of multi- or mixed methods to assess the influence of context and process factors on intervention effectiveness, and the value of closely examining derailed interventions to garner important lessons learned from intervention failures.

Pages: 94

No chapter abstract available.

Pages: 13

Missing data occur almost universally in research, especially applied research. This can give rise to problems of both statistical estimation and interpretation. The work of Donald Rubin in the 1970s was highly influential on researchers’ theoretical and practical understanding of ‘missingness’ – the state of being missing. Previously, approaches to missingness tended to exclude all participants with missing responses (e.g., complete case analysis) or to fill missing data with arbitrary values, such as sample means (e.g., mean imputation). These seemed to solve issues of estimation but merely deferred problems of interpretation. Contemporary approaches to missingness begin by classifying the missingness as either ignorable (missing at random or completely at random) or non-ignorable (missing not at random). Consequently, imputation and maximum likelihood approaches can be employed that minimise problems of estimation and maximise the validity of interpretation. However, when missingness is not at random, problems remain. The chapter concludes with recommendations for researchers.

Pages: 14

Researchers will routinely be faced with the challenge of ensuring that the data to be analysed are in the best form to provide evidence to assess the research questions. Contrary to expectations, this is not merely a time to transform skewed distributions and delete possible outliers. Data preparation involves checking that the data reflect the expected processes in the populations of interest. It is important that the research keeps careful audit trails of all such procedures and actions. The initial phase involves descriptive statistics and figures such as scatter plots and may lead to a re-evaluation of the original analysis plan. Next, after models have been fit, a diagnostics phase involves widely used procedures to assess the appropriateness of the model for the actual data. These procedures, in slightly modified forms, can also be applied to research that uses existing data. Suggestions for further reading are provided for those who seek more advanced material.

Pages: 11

This chapter introduces the thematic analysis (TA) family of methods, highlighting characteristics shared by the various branches of the TA family, as well as important philosophical, conceptual, and procedural differences. We discuss various ways of distinguishing between the different branches of the TA family – small q and Big Q TA; scientifically descriptive and artfully interpretative TA; and coding reliability, codebook, and reflexive TA. We note that small q, scientifically descriptive, and coding reliability approaches cluster together, as do Big Q, artfully interpretative, and reflexive, with codebook approaches somewhere in between. To dig deeper into the differences within the TA family, we explore competing and conflicting conceptualisations of themes (topic summaries or shared meaning? diamonds or interpretative stories?) and researcher subjectivity (bias or resource?) and different strategies for determining when sufficient data have been generated (statistical models, saturation, or information power?). A common problem in the practice of TA is that the diversity within the TA family is often poorly understood, with researchers ‘mashing together’, seemingly unknowingly, elements of different and often incompatible approaches. The aim of this chapter, therefore, is to support researchers in becoming knowing practitioners of TA, who make deliberative choices about which TA approach and procedures best fit their research values, and enacting these coherently to produce TA research with methodological integrity.

Pages: 14

Structural equation modelling (SEM) consists of a family of statistical techniques for examining relationships among variables and has become increasingly popular in psychological research. In this chapter, the basic process of constructing a structural equation model is introduced. Then three issues receiving much attention in the SEM literature are discussed: estimation methods for nonnormal and categorical variables, model-data fit evaluation, and use of parcels in SEM. The chapter concludes with a brief introduction of SEM with mean structures and Bayesian SEM.

Pages: 14

This chapter introduces the best practice approaches to testing moderated mediation with structural equation modelling (SEM) in applied psychological studies. Different analytical methods are suggested for examining three types of moderators. First, two different approaches for comparing the mediating effects across groups using multiple-group SEM are introduced, when the moderator is a categorical variable. Second, the four-step latent moderated structural equation modelling (LMS) approach for testing moderated mediation is explained, when the moderator is a latent continuous variable. The LMS approach provides more accurate estimates and confidence intervals for testing moderated mediating effects than the regression approach and PROCESS. Finally, the multilevel regression approach and multilevel SEM are introduced for testing cross-level moderated mediation. It is hoped that future researchers can use the most appropriate procedures to test their moderated mediation hypotheses to advance the knowledge of applied psychology.

Pages: 15

Multilevel research methods, which take similarities shared by the members of a group into account, have been increasingly popular in social sciences. Multilevel modelling allows researchers to more accurately reflect the complex nature of their data, to identify where and how effects occur. However, some simplifying assumptions made by researchers (i.e., the independence of observations) that allowed the use of well-known statistical techniques may have resulted in inappropriate conclusions. This chapter provides a brief background on how to design multilevel studies and conduct preliminary analysis. It also details common multilevel analysis types, including the traditional multilevel analysis, multilevel structural equation modelling, and longitudinal multilevel modelling, using examples from published studies.

Pages: 11

There is an overwhelming amount of literature available on how to write a thesis, and it is often difficult for students to decide where to begin to read and, furthermore, to decide which of this information is relevant. This chapter attempts to summarise the most relevant information and present some common problems and challenges often faced by students in the write-up phase of their thesis. It is not a how-to guide; rather, it presents helpful information and advice surrounding writing a thesis. Additionally, this chapter provides advice on how to present the research as a report to organisations which have participated in the research.