1.What are the similarities between descriptive and inferential statistics? What are the differences? When should descriptive and inferential statistics be used? Descriptive statistics describes data by organizing factors of a sample such as culture, gender, age, or location and is shown with charts or graphs. Descriptive statistics can interpret larger portions of data and reduce larger portions of data. The measure of central tendency describes the average score being the mean, the median being the midpoint of a spread of scores, and the mode the most frequent. There are certain levels of measurement and descriptive statistics may not be the best technique based on the measurement, these scales include nominal, ordinal, interval, and ratio. With descriptive statistics, based on the data can only give a summary and not predict about a population. Inferential statistics makes conclusions based on the population of the sample of data.
When you start with a population and receive a sample, we get descriptive statistics and from this, inferential statistics. To research differences and relationships of variables, inferential statistics compares more than one sample, allowing correlations between variables that are relevant to a particular research. In inferential statistics there could be error in sampling or measurement, as the same with descriptive statistics. Like descriptive statistics, inferential statistics uses a spread of scores of population with scores retrieved from the sample is the sample distribution, standard error is the standard deviation of the spread of scores, and the likely range the confidence interval. Inferential statistics and descriptive statistics work together in determining whether an interaction effect has occurred in an experiment. The test for an interaction effect involves determining whether the effect of one independent variable differs across the levels of the other independent variable.
The Research paper on Descriptive & Inferential Statistics
The concept of statistics is divided into two major branches of statistical methods known as descriptive and inferential statistics. To comprehend the study as a whole statisticians recommend individuals began focusing on descriptive statistics because it provides a better understanding and smooth transition into inferential. According to descriptive statistics are commonly used to summarize or ...
2.What are the similarities between case studies and small-N research designs? What are the differences? When should case studies and small-N research designs be used?
The analysis of a single individual, event, or group is a case study. There are different types of cases, which are intrinsic, instrumental, and collective. When doing this type of research one must go out into the field to observe or interview in a natural setting. In the field, those collecting data develop a research role, which establishes the position of the investigator and his or her relationships with others in the situation. At one extreme, the researcher is a complete outsider, totally detached from the naturally occurring behavior and activities of the participants. He or she essentially has no involvement in what occurs in the setting. The researcher is detached coming in, collecting data, and then leaving. A complete insider, on the other hand, is a researcher who has an established role in the setting in which data are collected, engaging in genuine and natural participation.
Most fieldworkers’ roles are between these extremes, using what could be labeled insider/outsider or partial participation. These individuals participate to some extent in the setting, rather than just sit on the sidelines, but they are not full participants. Case studies provide in-depth information about people and the possible insight into behavior, in which these can be more controlled at a later time. These types of cases provide opportunities for new techniques. Case studies also make it possible to research rare phenomena. Case studies provide counterinstance, but, case studies challenge theoretical assumptions and use the nomothetic approach and not the idiographic approach.
Roots were developed by B.F. Skinner, small-N research designs study is demonstrated by arranging experimental conditions such that the individual’s behavior changes systematically with the manipulation of an independent variable. Interpreting the effect of a treatment can be difficult if the baseline stage shows excessive variability or increasing or decreasing trends in behavior. The problem of low external validity with single-subject experiments can be reduced by testing small groups of individuals. A frequent criticism of single-subject research designs is that the findings have limited external validity. 3.What are true experiments? How are threats to internal validity controlled by true experiments? How are they different from experimental designs?
The Research paper on Case Study Research
Case One: Barsz v. Max Shapiro, Inc. Ind. Ct. App. 600 N.E.2d 151 (1992) Fact: Marjorie Barsz brought negligence action against Shapiro’s Delicatessen Cafeteria to recover for personal injuries sustained when she slipped and fell, breaking her right ankle and left knee cap. Her husband, Carl Barsz brought action against the restaurant for loss of consortium with his wife due to Mrs. Barsz’s ...
In an experiment, there is only one interpretation of the outcome based on what caused the event. There are three specific characteristics in true experiments. A type of treatment or intervention is implemented, there is a high degree of control that an experimenter has. The experimenter has control over the manipulations of variables, assignment of participants, and choice of dependent variables, and last, characterized by appropriate comparison. Threats to internal validity controlled by true experience start with low statistical power, which shows there may not be enough power to detect a difference or not enough subjects. The threat of violated assumptions of tests is with normal distribution and equal variances leading to incorrect support or non-support. Other threats are fishing, unreliability of measures, restriction of range, unreliability of invention implementation, and extraneous variance in the experimental setting. 4.What are quasi-experimental designs? Why are they important? How are they different from experimental designs?
References
Shaughnessy, J., Zechmeister, E., & Zechmeister, J. (2009).
Research methods in psychology (8th edition).
New York, NY: McGraw-Hill, 68,85.
