Research methods in academic inquiry

¶ … science if conducting an experiment that can allow the experimenter to make reasonable inferences about the material described. This paper describes different aspects of the experimental process. It discusses descriptive and inferential statistics; single case and small N. research designs; true experiments and experimental designs; and qausi-experiments. It discusses the relative strengths and weaknesses of each experimental approach.

What are the similarities between descriptive and inferential statistics? What are the differences? When should you use descriptive and inferential statistics?

Descriptive statistics refers to data that describes, shows, or summarizes data in a meaningful way (Lund Research Ltd., 2012). Descriptive statistics present the data, but they do not allow one to make conclusions about data. In other words, descriptive statistics can be described as a way to organize raw data. There are two main types of descriptive visits that are most relevant: measures of central tendency and measures of spread (Lund Research Ltd., 2012). Descriptive statistics are frequently summarized in tables, charts, and graphs, which make it easy to see the general results of a study. "Descriptive statistics are applied to populations and the properties of populations, like the mean or standard deviation, are called parameters as they represent the whole population (i.e. everybody you are interested in)" (Lund Research Ltd., 2012).

Inferential statistics is a means of translating descriptive statistics and trying to apply it to a large group, when one does not have access to an entire population. "Inferential statistics are techniques that allow us to use these samples to make generalizations about the populations from which the samples were drawn. It is, therefore, important the sample accurately represents the population. The process of achieving this is called sampling. Inferential statistics arise out of the fact that sampling naturally incurs sampling error and thus a sample is not expected to perfectly represent the population. The methods of inferential statistics are (1) the estimation of parameter(s) and (2) testing of statistical hypotheses" (Lund Research Ltd., 2012).

One would use descriptive statistics to present the information received from a specific population. Descriptive statistics are clear, but they only allow one to present information about those things that were actually measured. Inferential statistics have a margin of error, but allow the researcher to make conclusions about a broader group than was actually measured.

2. What are the similarities between single-case and small-N research designs? What are the differences? When should you use single-case and small-N research designs?

Single case research design is a design that is frequently used in applied psychology, and is when a subject serves as his own control group. The goal of the single-case research design is to examine the impact of a variable on the subject. "Single-case research is idiographic rather than nomothetic" (Brogan, Unk.). There are several features of a single-subject design including: baseline assessment to determine the status quo before an intervention is applied, and continuous assessment to determine the impact of the intervention.

Many people use the term small-N research design interchangeably with single-case research designs. Small N. studies carefully manipulate a single variable to determine the impact of that variable on the subjects of the study. Clinical trials are a good example of small-N studies.

Both single case and small-N research designs involve the observation of a subject after some type of intervention. Both research designs are idiographic. However, the two research designs have some differences and are useful in different scenarios. Single case research designs are often conducted as case studies and involve the intense observation of a single subject. They have limited utility in the application of research because they only reveal how an intervention interacts with a single subject. However, in cases where something might be extremely rare, a single case design may be the only practical way to study something. In contrast, small-N research designs allow for the study of a larger group, which might be more representative of the actual population of people experiencing a particular problem.

3. What are true experiments? How are threats to internal validity controlled by true experiments? How are they different from experimental designs?

True experiments are those experiments that are conducted "where an effort is made to impose control over all other variables except the one under study. It is often easier to impose this sort of control in a laboratory setting. Thus, true experiments have often been erroneously identified as laboratory studies" (Woolf, 2012). True experiments rigidly control for validity by attempting to isolate variables so that only a single independent variable is studies. The independent variable "is the variable that the experimenter manipulates in a study. It can be any aspect of the environment that is empirically investigated for the purpose of examining its influence on the dependent variable" (Woolf, 2012). Furthermore in true experiments, the subjects are randomly assigned to the experimental and control groups. Finally, true experiments are double blind, which means that neither the experimenter nor the subjects know whether the subjects are in the experimental or control groups (Woolf, 2012).

True experiments differ from experimental designs in the level of control that exists in each different type of research. An experimental design, like a true experiment, attempts to determine cause and effect relationships. They include randomization, the use of a control group, and manipulation of the independent variable. Therefore, true experiments could properly be classified as a subgroup of experimental designs. However, not all experimental designs are true experiments; the hallmark of the true experiment is the manipulation of the independent characteristic of a true experiment.

4. What are quasi-experimental designs? Why are they important? How are they different from experimental designs?

Quasi-experiments are similar to true experiments, but lack the randomization characteristic that describes the true experiment. In other words, quasi-experiments "use naturally formed or pre-existing groups. For example, if we wanted to compare young and old subjects on lung capacity, it is impossible to randomly assign subjects to either the young or old group (naturally formed groups). Therefore, this cannot be a true experiment. When one has naturally formed groups, the variable under study is a subject variable (in this case - age) as opposed to an independent variable. As such, it also limits the conclusions we can draw from such a research study" (Woolf, 2012). While quasi-experiments may be the only way to investigate some variables, including most immutable characteristics like race or age, they can be suggestive of causation but cannot determine causation. When groups are not randomly selected, there are a number of between-group differences that might account for differences.