Getting the most from your curves: Exploring and reporting data using informative graphical techniques (original) (raw)
Related papers
Using confidence intervals for graphically based data interpretation
Canadian Journal of Experimental Psychology/Revue canadienne de psychologie expérimentale, 2003
As a potential alternative to standard null hypothesis significance testing, we describe methods for graphical presentation of data--particularly condition means and their corresponding confidence intervals--for a wide range of factorial designs used in experimental psychology. We describe and illustrate confidence intervals specifically appropriate for betweensubject versus within-subject factors. For designs involving more than two levels of a factor, we describe the use of contrasts for graphical illustration of theoretically meaningful components of main effects and interactions. These graphical techniques lend themselves to a natural and straightforward assessment of statistical power.
Applications of multivariate visualization to behavioral sciences
Behavior Research Methods, Instruments, & Computers, 1995
The complexity of psychological science often requires the collection and analysis of multidimensional data. Such data bring about a corresponding cognitive load that has led scientists to develop techniques of scientific visualization to ease the burden. This paper provides an introduction to scientific visualization techniques, a framework for understanding those techniques, and an assessment of the suitability of this approach for psychology. The framework employed builds on the notion of balancing noise and smooth in statistical analysis. Widespread availability ofdesk-top computing allows psychologists to develop and manipulate complex multivariate data sets. While researchers in the physical and engineering sciences have dealt with increasing data complexity by using scientific visualization, researchers in the behavioral sciences have been slower to adopt these tools (Butler, 1993). To address this discrepancy, this paper defines scientific visualization, presents a theoretical framework for understanding visualization, and reviews a number of multivariate visualization techniques in light of this framework. Because all graphics and animations available to illustrate the concepts discussed here cannot be incorporated in this print version, a hypertext version of this paper containing these illustrations is available through WorldWide Web browsers. The primary document and supporting software can be found in the ASU resources section of the server at http: //seamonkey. ed.asu.edu/-Behrens/. WHAT IS SCIENTIFIC VISUALIZATION? We define scientific visualization as the process ofexploring and displaying data in a manner that builds a visual analogy to the physical world in the service ofuser insight and learning. This entails finding a balance between the detail of the raw data and the parsimony ofstatistical summary. Each component of this definition will now be addressed. VISualization as Data Exploration Although most statistical training in psychology focuses on confirmatory data analysis (see Aiken, West, Sechrest, & Reno, 1990), there is in statistics a well-established tradition called exploratory data analysis (EDA). Pioneered by the work of John Tukey (1977), this tradition emphasizes the seeking of unexpected structure and the
Journal of Physics Conference Series
Numerous studies have examined students' difficulties in understanding some notions related to statistical problems. Some authors observed that the presentation of distinct visual representations could increase statistical reasoning, supporting the principle of graphical facilitation. But other researchers disagree with this viewpoint, emphasising the impediments related to the use of illustrations that could overcharge the cognitive system with insignificant data. In this work we aim at comparing the probabilistic statistical reasoning regarding two different formats of problem presentations: graphical and verbal-numerical. We have conceived and presented five pairs of homologous simple problems in the verbal numerical and graphical format to 311 undergraduate Psychology students (n=156 in Italy and n=155 in Spain) without statistical expertise. The purpose of our work was to evaluate the effect of graphical facilitation in probabilistic statistical reasoning. Every undergradua...
Descriptive Analysis of Psychological Data
Statistics and Research Methods in Psychology with Excel
Psychologists usually gather a large set of data during their investigations for understanding behavioural issues and mental processes for solving some real-life problems. The large set of data is meaningless unless it is reduced in some manageable form. To derive meaningful conclusions, descriptive analysis of the data is required. Descriptive analysis enables an investigator to describe a large set of observations by the use of a single indicator. Consider a situation where a survey is conducted on 130 employees to know their job satisfaction. A questionnaire is administered, and a set of 130 scores on job satisfaction is obtained. Merely by observing these scores, one cannot draw any conclusion. One needs to find some average value of this data set to draw the conclusion concretely. Such an average value is known as measure of central tendency. The measures of central tendency include mean, median and mode. These averages are computed in order to get a representative score of the data set. All three measures of central tendency are useful in different situations. For instance, in the above example, mean is the best measure of central tendency to show the average job satisfaction of the employees. Since the data on job satisfaction is measured on interval scale, mean has been chosen as the indicator of central tendency. A more detailed discussion on measures of central tendency and their application shall be provided later in this chapter. Consider another situation in which the average scores on the job satisfaction of employees in the two organizations are the same. In the first organization, job satisfaction scores do not fluctuate much, whereas in the second organization, it varies a lot and, therefore, simply by comparing the means of the two groups, one cannot draw any conclusion as to which organization is superior in terms of job satisfaction. In order to have the correct picture, one needs to compute some measure of variability also which explains the variation of scores around its mean value. Thus, to explain the nature of the data set correctly, one needs to compute both, the measure of central tendency and the measure of variability.
An Introduction to Psychological Statistics
2018
Prologue: A letter to my students Dear Students: I get it. Please believe me when I say that I completely understand, from firsthand experience, that statistics is rough. I was forced to take an introductory statistics course as part of my education, and I went in to it with dread. To be honest, for that first semester, I hated statistics. I was fortunate enough to have a wonderful professor who was knowledgeable and passionate about the subject. Nevertheless, I didn't understand what was going on, why I was required to take the course, or why any of it mattered to my major or my life. Now, almost ten years later, I am deeply in love with statistics. Once I understood the logic behind statistics (and I promise, it is there, even if you don't see it at first), everything became crystal clear. More importantly, it enabled me to use that same logic not on numerical data but in my everyday life. We are constantly bombarded by information, and finding a way to filter that information in an objective way is crucial to surviving this onslaught with your sanity intact. This is what statistics, and logic we use in it, enables us to do. Through the lens of statistics, we learn to find the signal hidden in the noise when it is there and to know when an apparent trend or pattern is really just randomness. I understand that this is a foreign language to most people, and it was for me as well. I also understand that it can quickly become esoteric, complicated, and overwhelming. I encourage you to persist. Eventually, a lightbulb will turn on, and your life will be illuminated in a way it never has before. I say all this to communicate to you that I am on your side. I have been in your seat, and I have agonized over these same concepts. Everything in this text has been put together in a way to convey not just formulae for manipulating numbers but to make connections across different chapters, topics, and methods, to demonstrate that it is all useful and important. So I say again: I get it. I am on your side, and together, we will learn to do some amazing things.
We provide a comprehensive review of simple and advanced statistical analyses using an intuitive visual approach explicitly modeling Latent Variables (LV). This method can better illuminate what is assumed in each analytical method and what is actually estimated, by translating the causal relationships embedded in the graphical models in equation form. We recommend the graphical display rooted in the century old path analysis, that details all parameters of each statistical model, and suggest labeling that clarifies what is given vs. what is estimated. We link in the process classical and modern analyses under the encompassing broader umbrella of Generalized Latent Variable Modeling, and demonstrate that LVs are omnipresent in all statistical approaches, yet until directly ‘seeing’ them in visual graphical displays, they are unnecessarily overlooked. The advantages of directly modeling LVs are shown with examples of analyses from the Active8 intervention designed to increase physical activity.
Inference by Eye: Confidence Intervals and How to Read Pictures of Data
American Psychologist, 2005
Wider use in psychology of confidence intervals (CIs), especially as error bars in figures, is a desirable development. However, psychologists seldom use CIs and may not understand them well. The authors discuss the interpretation of figures with error bars and analyze the relationship between CIs and statistical significance testing. They propose 7 rules of eye to guide the inferential use of figures with error bars. These include general principles: Seek bars that relate directly to effects of interest, be sensitive to experimental design, and interpret the intervals. They also include guidelines for inferential interpretation of the overlap of CIs on independent group means. Wider use of interval estimation in psychology has the potential to improve research communication substantially.