Resarch and Statistics Paper Psy 315

Research and Statistics Paper Psy 315 Define and explain research and define and explain the scientific method (include an explanation of all five steps). Proper Research is primarily an investigation. Researchers and scientists gather data, facts, and knowledge to help better understand phenomenon, events and people. Through research, analysis, investigations, and experimentation, we gain a better understanding of our world. As I skimmed the text to find a definition, I found the word research several times on several of the pages in the first chapter.

Research is fundamental to any scientific enterprise and statistics is no exception. The scientific method is the set of procedures that enable scientists and researchers to conduct investigations and experiments. Scientists observe an event and then form a hypothesis. A hypothesis is an educated guess about how something works. These researchers then perform experiments that support the hypothesis or these experiments prove it wrong. A conclusions can be made from the investigations and experiments with the data collected and analyzed. The conclusion helps to prove or disprove validity of the hypothesis.

There are several steps that are followed in the scientific method. The steps to this method can be followed by answering questions before and along the way of the investigation. The scientific method can have five steps. The researcher asks themselves these questions and tries o find the answers: 1. What event or phenomenon are we investigating? 2. How does this event occur? A guess as to how the event happens is formed. This is our hypothesis. 3. How can we test this hypothesis? The experimenter then tests the hypothesis through experiments. 4. Are the results looking valid?

Order custom essay Resarch and Statistics Paper Psy 315 with free plagiarism report

450+ experts on 30 subjects Starting from 3 hours delivery

Get Essay Help

The researcher records the observations. Does the experiment need to be changed? Possibly, the researcher adjusts the experiment as the data helps to fine tune the investigation. 5. Does the data support the hypothesis? The researcher analyzes the data. The analysis will have statistical information that is crucial to the investigator. Without statistics, there can be no real scientific analysis of the investigation or experiment. The analysis will tell the researcher if the hypothesis is supported or if they are in essence incorrect. Authors: Cowens, John Source: Teaching Pre K-8, Aug/Sep2006, Vol. 7 Issue 1, p42-46, 3p, 6 Color Photographs, 1 Graph Informastion from: Cowens, J. (2006, August/September). The scientific method. Teaching PreK-8, 37(1), 42. Define and substantively compare and contrast the characteristics of primary and secondary data (not sources). There are two ways that researchers obtain data, primary and secondary. Primary data is collected by the person conducting the investigation. Secondary data is collected from other sources. Primary data is information collected that is specifically geared toward the investigation. This specificity is a plus for primary data.

Primary data can be expensive to collect due to the expense of experimentation and surveys. The man hours can be high and the cost can be high. The time it takes to collect original data can be long and grueling. Secondary data can be a good resource due to the ease of availability. Secondary data can be less expensive and less time consuming. However, secondary data may be information that is not as specific to the investigation or collected for a different specific purpose. Rabianski J. Primary and Secondary Data: Concepts, Concerns, Errors, and Issues. Appraisal Journal [serial online].

January 2003;71(1):43. Available from: Business Source Complete, Ipswich, MA. Accessed March 11, 2013 Explain the role of statistics in research. (Keep the focus within the field of psychology). ------------------------------------------------- Statistics plays a very large role in the field of psychology. Statistics is vital to research in any field of science. Before statistics and even now, people want to know if there is a real cause and effect when they experience an event. Early man (let’s call him Grog) would step out of his drab cave in the early morning.

Grog would perhaps spot an eagle soaring across a beautiful clear blue sky. Our early man, Grog may then have a great day of hunting. Later, Grog would reflect and think about his good day and remember the early morning eagle. Grog would tell and possibly re-tell the tale to his fellow cave people. The appearance of the early morning eagle would become a “clear” and significant sign or omen that the day’s hunt would be good. This would be especially true if the omen appeared and the hunt was good more than once. Is this statistically significant?

Grog did not have the proper tools ( not paper or stone or computer) nor the brain power to do the statistical procedures on his observations. This appearance and the resulting good hunt could be a real significant event with true cause and effect or it could be pure chance and be nothing more than flimsy anecdotal evidence. Unfortunately for Grog, he did not have statistics or the expertise to perform the required investigations of proper research. Often, psychologists want to know what a person will do when confronted with a certain situation or stimulus or event.

With inferential statistics researchers/psychologists use the information/data to infer or to make a conclusion based on the data from the research. “Probability” is derived from inferential statistics. How probable is it that a person will act a certain way can be answered through inferential/probability studies. ------------------------------------------------- The Cult of Statistical Significance By Stephen T. Ziliak and Deirdre N. McCloskey1 ------------------------------------------------- Roosevelt University and University of Illinois-Chicago ------------------------------------------------- “The Cult of Statistical Significance” was presented at the Joint Statistical Meetings, Washington, DC, August 3rd, 2009, in a contributed session of the Section on Statistical Education. For comments Ziliak thanks many individuals, but especially Sharon Begley, Ronald Gauch, Rebecca Goldin, Danny Kaplan, Jacques Kibambe Ngoie, Sid Schwartz, Tom Siegfried, Arnold Zellner and above all Milo Schield for organizing an eyebrow-raising and standing-room only session. ------------------------------------------------- ------------------------------------------------- Psychological Research Methods and Statistics

Edited by Andrew M. Colman 1995, London and New York: Longman. Pp. xvi + 123. ISBN 0-582-27801-5 Research in psychology or in any other scientific field invariably begins with a question in search of an answer. The question may be purely factual -- for example, is sleep-walking more likely to occur during the stage of sleep in which dreams occur, namely rapid eye movement (REM) sleep, than in dreamless (slow-wave) sleep? Alternatively, it may be a practical question -- for example, can the use of hypnosis to recover long-forgottenexperiences increase the likelihood of false memories? According to current research findings, incidentally, the answers to these questions are no and yes respectively. ) A research question may arise from mere curiosity, from a theory that yields a prediction, or from previous research findings that raise a new question. Whatever its origin, provided that it concerns behaviour or mental experience and that it can be expressed in a suitable form for investigation by empirical methods -- that is, by the collection of objective evidence -- it is a legitimate question for psychological research. Psychological research relies on a wide range of methods.

This is partly because it is such a diverse discipline, ranging from biological aspects of behaviour to social psychology and from basic research questions to problems that arise in such applied fields as clinical, educational, and industrial or occupational psychology. Most psychological research methods have the ultimate goal of answering empirical questions about behaviour or mental experience through controlled observation. But different questions call for different research methods, because the nature of a question often constrains the methods that can be used to answer it.

This volume discusses a wide range of commonly used methods of research and statistical analysis. The most powerful research method is undoubtedly controlled experimentation. The reason for the unique importance of controlled experiments in psychology is not that they are necessarily any more objective or precise than other methods, but that they are capable of providing firm evidence regarding cause-and-effect relationships, which no other research method can provide. The defining features of the experimental method are manipulation and control.

The experimenter manipulates the conjectured causal factor (called the independent variable because it is manipulated independently of other variables) and examines its effects on a suitable measure of the behaviour of interest, called the dependent variable. In multivariate research designs, the interactive effects of several independent variables on two or more dependent variables may be studied simultaneously. In addition to manipulating the independent variable(s) and observing the effects on the dependent variable(s), the experimenter controls all other extraneous variables that might influence the results.

Controlled experimentation thus combines the twin features of manipulation (of independent variables) and control (of independent and extraneous variables). In psychological experiments, extraneous variables can seldom be controlled directly. One reason for this is that people differ from one another in ways that affect their behaviour. Even if these individual differences were all known and understood, they could not be suppressed or held constant while the effects of the independent variable was being examined.

This seems to rule out the possibility of experimental control in most areas of psychology, but in the 1920s the British statistician Ronald Aylmer Fisher discovered a remarkable solution to this problem, called randomization. To understand the idea behind randomization, imagine that the experimenter wishes to test the hypothesis that the anti-depressive drug Prozac (fluoxetine hydrochloride) causes an increase in aggressiveness. The independent variable is ingestion of Prozac and the dependent variable is a score on some suitable test of aggressiveness.

The experimenter could assign subjects to two treatment conditions strictly at random, by drawing their names out of a hat, for example, and could then treat the two groups identically apart from the manipulation of the independent variable. Before being tested for aggressiveness, the experimental group could be given a pill containing Prozac and the control group a placebo (an inactive dummy pill). The effect of the randomization would be to control, at a single stroke, for allextraneous variables, including ones of that the researcher had not even considered.

For example, if two-thirds of the subjects were women, then each group would end up roughly two-thirds female, and if some of the subjects had criminal records for offences involving violence, then these people would probably be more or less even divided between the experimental and control groups, especially if the groups were large. Randomization would not guarantee that the two groups would be identical but merely that they would tend to be roughly similar on all extraneous variables. More precisely, randomization would ensure that any differences between the groups were distributed strictly according to the laws of chance.

Therefore, if the two groups turned out to differ on the test of aggressiveness, this difference would have to be due either to the independent variable (the effect of Prozac) or to chance. This explains the purpose and function of inferential statistics in psychology. For any specified difference, a statistical test enables a researcher to calculate the probability or odds of a difference as large as that arising by chance alone. In other words, a statistical test tells us the probability of such a large difference arising under the null hypothesisthat the independent variable has no effect.

If a difference is observed in an experiment, and if the probability under the null hypothesis of such a large difference arising by chance alone is sufficiently small (by convention, usually less than 5 per cent, often written p < . 05), then the researcher is entitled to conclude with confidence that the observed difference is due to the independent variable. This conclusion can be drawn with confidence, because if the difference is not due to chance, then it must be due to the independent variable, provided that the experiment was properly controlled.

The logical connection between randomized experimentation and inferential statistics is explained in greater depth in Colman (1988, chap. 4). A grasp of the elements of statistics is necessary for psychologists, because research findings are generally reported in numerical form and analysed statistically. In some areas of psychology, including naturalistic observations and case-studies (see below), qualitative research methods are occasionally used, and research of this kind requires quite different methods of data collection and analysis.

For a survey of the relatively uncommon but none the less important qualitative research methods, including ethnography, personal construct approaches, discourse analysis, and action research, see the book by Banister, Burman, Parker, Taylor, and Tindall (1994). In chapter 1 of this volume, David D. Stretch introduces the fundamental ideas behind experimental design in psychology. He begins by explaining the appropriate form of a psychological research question and how incorrectly formulated questions can sometimes be transformed into questions suitable for experimental investigation.

He then discusses experimental control, problems of sampling and randomization, issues of interpretability, plausibility, generalizability, and communicability, and proper planning of research. Stretch concludes his chapter with a discussion of the subtle and complex problems of measurement in psychology. He uses an extremely instructive example to show how two different though equally plausible measures of a dependent variable can lead to completely different -- in fact, mutually contradictory -- conclusions.

Chapter 2, by Brian S. Everitt, is devoted entirely to analysis of variance designs. These are by far the most common research designs in psychology. Everitt's discussion covers one-way designs, which involve the manipulation of only one independent variable; factorial designs, in which two or more independent variables are manipulated simultaneously; and within-subject repeated-measure designs, in which instead of being randomly assigned to treatment conditions, the same subjects are used in all conditions.

Chapter 2 concludes with a discussion of analysis of covariance, a technique designed to increase the sensitivity of analysis of variance by controlling statistically for one or more extraneous variables called covariates. Analysis of covariance is sometimes used in the hope of compensating for the failure to control extraneous variables by randomization, but Everitt discusses certain problems caused by such use. In chapter 3, A. W. MacRae provides a detailed discussion of the ideas behind statistics, both descriptive and inferential.

Descriptive statistics include a variety of methods of summarizing numerical data in ways that make them more easily interpretable, including diagrams, graphs, and numerical summaries such as means (averages), standard deviations (measures of variability), correlations (measures of the degree to which two variables are related to each other), and so forth. Inferential statistical methods are devoted to interpreting data and enabling researchers to decide whether the results of their experiments are statistically significant or may be explained by mere chance.

MacRae includes a brief discussion of Bayesian methods, which in contrast to classical statistical methods are designed to answer the more natural question: "How likely is it that such-and-such a conclusion is correct? " For more information on Bayesian methods, the book by Lee (1989) is strongly recommended: it explains the main ideas lucidly without sidestepping difficulties Inferential Statistics For descriptive statistics such as correlation, the “mean,” or average, and some others that will be considered in context later in the book, the purpose is to describe or summarize aspects of behavior to understand them better.

Inferential statistics start with descriptive ones and go further in allowing researchers to draw meaningful conclusions — especially in experiments. These procedures are beyond the scope of this book, but the basic logic is helpful in understanding how psychologists know what they know. Again recalling Bandura's experiment of observational learning of aggression, consider just the model-punished and model-rewarded groups. It was stated that the former children imitated few behaviors and the latter significantly more.

What this really means is that, based on statistical analysis, the difference between the two groups was large enough and consistent enough to be unlikely to have occurred simply by “chance. ” That is, it would have been a long shot to obtain the observed difference if what happened to the model wasn't a factor. Thus, Bandura and colleagues discounted the possibility of chance alone and concluded that what the children saw happen to the model was the cause of the difference in their behavior.

Psychologists study what people tend to do in a given situation, recognizing that not all people will behave as predicted — just as the children in the model-rewarded group did not all imitate all the behaviors. In a nutshell, the question is simply whether a tendency is strong enough — as assessed by statistics — to warrant a conclusion about cause and effect. This logic may seem puzzling to you, and it isn't important that you grasp it to understand the many experiments that are noted throughout this book. Indeed, it isn't mentioned again.

The point of mentioning it at all is to underscore that people are far less predictable than chemical reactions and the like, and therefore have to be studied somewhat differently — usually without formulas. 1. 1 Determine appropriate measures based on an operational definition for research tools. Researchers utilize the method of operational definition to better tailor their research. They must know what all of the variables are, how to measure these variables and how they fit into the study. They must make sure that they are actually studying what they say they are studying.

The definitions/parameters of the variables must be strictly defined. 1. 2 Select appropriate data collection methods to investigate psychological research problems. The research methods and the way all experimentations are collected must be done in a scientific, logical and ethical manner. Most research methods are either non-experimental, experimental, or quasi-experimental. These are separated by the number and extent of the of controls used. The controls help to account for the effect of variable use on the non-control or experiment group. 1. Examine the differences between descriptive and inferential statistics and their use in the social sciences. When a chart or graph (the shape of a distribution) is described in words, then one is using “descriptive statistics”. These descriptions can help to summarize and analyze a large amount of data. With inferential statistics researchers/psychologists use the information/data to infer or to make a conclusion based on the data from the research. “Probability” is derived from inferential statistics. How probable is it that a person will act a certain way can be answered through inferential/probability studies.

REFERENCES: Aron, A. , Aron, E. , ; Coups, E. (2006). Statistics for psychology (4th ed. ). Upper Saddle River, NJ: Pearson/Allyn Bacon. Cowens, J. (2006). The scientific method. Teaching PreK-8, 37(1), 42. Hawthorne, G. (2003). The effect of different methods of collecting data: Mail, telephone and filter data collection issues in utility measurement. Quality of Life Research, 12(8), 1081. McPherson, G. R. (2001). Teaching ; learning the scientific method. The American Biology Teacher, 63(4), 242. .

Don't let plagiarism ruin your grade

Run a free check or have your essay done for you

Check my essay Hire Writer