Research process and methodology

¶ … Operational Definitions of Each of These

It states clearly the expected relationship between the variables

It states the nature of the relationship

It states the direction of the relationship

It implies that the predicted relationship can be tested empirically

It is grounded in theory.

The article What is a null hypothesis? explains what distinguishes a null hypothesis from a research hypothesis in the following way. A hypothesis is a tentative statement that proposes a possible explanation to some phenomenon or event. To test whether a hypothesis is true or not, a researcher carries out some kinds of test to see if the hypothesis is backed up by its results. An example of a hypothesis is:

Obesity is due to eating too much candy.

To prove this hypothesis, the researcher might examine data on whether candy is correlated with obesity. However, after reviewing the results, it is possible that any relationship that appears in the data was produced by random chance. Therefore, the researcher must compare the results against the opposite situation; candy does not lead to obesity. This is known as the null hypothesis -- the assertion that the things the research was testing are not related and that results are the produce of random chance events.

Null Hypothesis: Obesity is not due to eating too much candy.

Alternate Hypothesis: Obesity is due to eating too much candy.

In statistics, the only way of supporting a hypothesis is to refute the null hypothesis. Rather than trying to prove an idea (the alternate hypothesis) right, the research must show that the null hypothesis is likely to be wrong -- the researcher has to 'refute' or 'nullify' the null hypothesis. The researcher has to assume that the alternate hypothesis is wrong until the researcher finds evidence to the contrary.

A non-directional hypothesis is used to prove (or disprove) that changing one variable has an effect on another variable (Non-directional hypothesis). Thus, according to this source, a non-directional hypothesis will contain words like "influence," "change," "alter," and "affect" rather than asking whether the effect is positive or negative. A non-directional hypothesis would be used when both positive and negative differences are of equal importance in providing evidence with which to test the null hypothesis and in situations where the researcher isn't sure how an experimental group will perform against a control group (Hypothesis testing). Non-directional hypotheses are frequently used in: a) political science to weigh opinions of various issues among the people; b) economics when studying consumer confidence; c) pharmaceutical research to determine if drugs have any affects; and d) information theory to analyze data sources and decentralized dataflow (Non-directional hypothesis).

Directional hypothesis measures the effects of two variables on each other (Hypothesis testing. In other words, it measures the direction of variation of two variables. This effect of one variable on the other variable can be in positive direction or in negative direction. Thus, the use of directional testing is used when either only positive or negative differences are of interest in an experimental study.

Validity and reliability are related, but different concepts. Validity is the extent to which an indicator or set of indicators actually measure the concept it represents (Methods for social researchers in developing countries). For example, does a classroom test really measure the student's knowledge of the subject being tested? Reliability, on the other hand, is the extent to which any measuring procedure gives similar results with repeated use with the same respondents (Methods for social researchers in developing countries). For example, would an average test score be the same or similar when carried out again on a comparable test group? In order for a test to be valid, it must be reliable; but reliability does not guarantee validity. This is because a reliable measure could be measuring something consistently, but not necessarily what it is supposed to be measuring.

In the research process, reliability refers to the consistency, stability, and repeatability of a data collection instrument (Intro to research methods). According to this source, a reliable instrument is important because it does not respond to chance factors or environmental conditions; it will have consistent results if repeated overtime or if used by two different researchers.

To understand the importance of reliability, it is useful to understand why research instruments must be reliable in terms of stability, equivalence and internal consistency (Intro to research methods) as well as agreement among coders or raters, a concept called interrater reliability (Interrater reliability). A stable research instrument is one that can be repeated on the same individual more than once and achieve the same results. Further, with equivalence, the same results can be obtained using different observers at the same time and similar tests given at the same time will yield the same results. Internal consistency refers to the extent to which all parts of the measurement technique are measuring the same concept. For example, when developing a questionnaire, each question should provide a measure consistent with the overall results of the test. Interrater reliability is the extent to which two or more individuals (coders or raters) agree (Interrater reliability). Thus, interrater reliability addresses the consistency of the implementation of a rating system

Unreliable measures can cause researchers to draw unsatisfactory conclusions, formulate faulty theories, or make inaccurate claims about the generalizability of their research. Inherent difficulties related to the use of unreliable measures include (Difficulties of achieving reliability):

Quixotic reliability refers to the situation where a single manner of observation consistently, yet erroneously, yields the same result. For example, the responses of subjects do not always accurately represent their mental or physical state.

Diachronic reliability refers to the lack of stability of observations over time. For instance, when researchers administers tests to the same subjects a year later after the initial test, many confounding variables could have impacted the researchers' ability to reproduce the same circumstances present at the first test.

Synchronic reliability refers to the lack of similarity of observations within the same time frame. Multiple, but different observations, might simultaneously be true.

A case study is a qualitative research method useful at bringing an understanding of a complex issue or object and can extend experience or add strength to what is already known through previous research (the case study as a research method). Case studies emphasize detailed contextual analysis of a limited number of events or conditions and their relationships. Researchers have used the case study research method for many years across a variety of disciplines; but social scientists in particular have widely used case studies to examine contemporary real-life situations and provide the basis for the application of ideas and extension of methods (the case study as a research method). Other areas that have used case study techniques extensively include government and evaluative scenarios (Tellis, 1997). As explained by Tellis, the government has carried out studies to determine whether particular programs were efficient or if the goals of a particular program were being met. Evaluative applications have been conducted to assess the effectiveness of educational initiatives. In the government and evaluative studies, quantitative techniques tended to obscure some of the important information that the researchers needed to uncover. Further, as explained in the case study as a research method, researchers from many disciplines use the case study method to build upon theory, to produce new theory, to dispute or challenge theory, to explain a situation, to provide a basis to apply solutions to situations, to explore, or to describe an object or phenomenon.

The advantages of the case study method are its applicability to real-life, contemporary, human situations; its public accessibility through written reports and its ability to facilitate an understanding of complex real-life situations (the case study as a research method). In case studies, there is a detailed and holistic discussion of the context and operation as well as themes, issues and implications of the case or cases. Statistical methods are only able to deal with situations where behavior is homogeneous and routine while case studies can deal with creativity, innovation, and context (Case study: Strengths and weaknesses). Another major advantage of the case study is the potential for the development of novel hypotheses for later testing (Case study in psychology). The case study can also provide detailed descriptions of specific and rare cases that aren't appropriate for quantitative research (Case study in psychology). In addition, the case study offers flexibility (Case studies). Because project design emphasizes exploration and because they have a loose format, researchers are comparatively freer to discover and address issues as they arise in their experiments and can begin with broad questions and narrow their focus as their work progresses.

However, despite their utility, case studies have many disadvantages. First, and most importantly, the study of a small number of cases provides no grounds for establishing reliability or generality of findings (the case study as a research method). Therefore, case study research as most useful as an exploratory tool. This means that there is no ability to form cause and effect relationships or to test hypotheses and that it is impossible to generalize the findings to a wider population (Christensen, 1994). Second, the researcher's intense exposure to study of a case can bias the findings (the case study as a research method); at the least, there are significant opportunities for subjectivity in the implementation, presentation, and evaluation of case study research (Case studies). This high degree of subjectivity opens the door for ethical issues, particularly if the study is being sponsored by a special interest. Third, case studies involve too much investment of time and money to be appropriate for large-scale research projects (Case studies).

Beyea and Nicoll (1997) discuss the many factors that researchers need to consider when selecting a sample for a research project. A researcher must first determine the population of interest (every person, event, or object that meets specific characteristics). If the population of interest has too many members to study, the researcher then needs to formulate a sampling strategy to obtain a subset of the population of interest. The main objective in developing a sampling strategy is to obtain unbiased samples that are representative of entire populations of interest.