Key Variables, Research Design, and Hypotheses - PDF

**Identification of Key Variables and Research Design** Once you have brainstormed Thesis (project) topics, narrowed down the list, and reviewed the research related to that narrowed list, select a topic that seems most appealing to you. However, this project (thesis) topic is not set in stone yet....

**Identification of Key Variables and Research Design** Once you have brainstormed Thesis (project) topics, narrowed down the list, and reviewed the research related to that narrowed list, select a topic that seems most appealing to you. However, this project (thesis) topic is not set in stone yet. After you begin working through the project, you may realize that the topic needs to be revised, or even entirely changed to a different topic. The next step is to identify the key variables and the research design. **Key Variables** All research projects are based around variables. A variable is the characteristic or attribute of an individual, group, educational system, or the environment that is of interest in a research study. Variables can be straightforward and easy to measure, such as gender, age, or course of study. Other variables are more complex, such as socioeconomic status, academic achievement, or attitude toward school. Variables may also include an aspect of the educational system, such as a specific teaching method or counseling program. Characteristics of the environment may also be variables, such as the amount of school funding or availability of computers. Therefore, once the general research topic has been identified, the researcher should identify the key variables of interest. For example, a researcher is interested in low levels of literacy. Literacy itself is still a broad topic. In most instances, the broad topic and general variables need to be specifically identified. For example, the researcher needs to identify specific variables that define literacy: reading fluency (the ability to read a text out loud), reading comprehension (understanding what is read), vocabulary, interest in reading, etc. If a researcher is interested in motivation, what specific motivation variables are of interest: external motivation, goals, need for achievement, etc? Reading other research studies about your chosen topic will help you better identify the specific variables of interest. **Identifying the key variables is important for the following reasons:** - The key variables provide focus when writing the Introduction section. - The key variables are the major terms to use when searching for research articles for the Literature Review. - The key variables are the terms to be operationally defined if an *Operational Definition of Terms* section is necessary. - The key variables provide focus to the Methods section. - The Instrument will measure the key variables. These key variables must be **directly** measured or manipulated for the research study to be valid. **Research Design** After the key variables have been identified, the researcher needs to identify how those variables will be studied, which is the heart of the research design. There are four primary research designs: - **Descriptive:** Describes the current state of variables. For example, a descriptive study might examine teachers\' knowledge of literacy development. This is a descriptive study because it simply describes the current state of teachers\' knowledge of literacy development. - **Causal Comparative:** Examines the effect of one variable that cannot be manipulated on other variables. An example would be the effect of gender on examination malpractice. A researcher cannot manipulate a person\'s gender, so males and females are compared on examination malpractice behavior. Because the variable of interest cannot be manipulated, causal-comparative studies (sometimes also called *ex post facto)* compare two groups that differ on the independent variable (e.g., gender) on the dependent variable (e.g., examination malpractice). Thus, the key identifying factor of a causal-comparative study is that it compares two or more groups on a different variable. - **Correlational: **Describes the relationship between variables. Correlational studies must examine two variables that have continuous values. For example, academic achievement is a continuous variable because students\' scores have a wide range of values - oftentimes from 0 to 100. However, gender is not a continuous variable because there are only two categories that gender can have: male and female. A correlational study might examine the relationship between motivation and academic achievement - both continuous variables. Note that in a correlational design, both variables must be studied within the same group of individuals. In other words, it is acceptable to study the relationship between academic achievement and motivation in students because the two variables (academic achievement and motivation) are in the same group of individuals (students). However, it is extremely difficult to study two variables in two groups of people, such as the relationship between teacher motivation and student achievement. Here, the two variables are compared between two groups: teachers and students. I strongly advise against this latter type of study. - **Experimental and Quasi-Experimental: **Examines the effect of a variable that the researcher manipulates on other variables. An experimental or quasi-experimental study might examine the effect of telling stories on children\'s literacy skills. In this case, the researcher will \"manipulate\" the variable of telling stories by placing half of the children in a treatment group that listens to stories and the other half of children in a control group that gets the ordinary literacy instruction. **Once the key variables and the research design have been identified, the rest of the study falls into place.** - The *purpose, research questions, and hypotheses* will be written about the variables based on the research design. - The *Instruments* will be developed to measure the key variables and the *Instruments* section is written to describe the instruments. - The *Procedures* section describes the treatment for experimental studies and/or how the instrument will be administered. - The* Method of Data Analysis* describes how the data is summarized and tested based on the research questions and hypotheses. Thus, the most difficult part of planning the research study is identifying the research variables and research design. Considerable time and thought needs to be given to this step. Once the key variables have been identified, then the research study can be developed. **Write Purposes, Research Questions and Research Hypotheses** **Overview** The Purposes, Research Questions, and Research Hypotheses are closely related. Each Purpose should directly relate to either a Research Question or a Research Hypothesis. There is debate about whether the Research Questions and Research Hypotheses should match. Since each Research Question and Research Hypothesis has to be analyzed separately, I advise that Research Questions should focus on descriptive topics only while Research Hypotheses need to be written for all comparisons. For example, if the researcher wants to determine whether males and females differ on science achievement test scores, then this should be written as a research hypothesis. A Research Question could be written as \"Do males and females differ on science achievement test scores?\" This would be analyzed by comparing the mean science test scores of males and females. Imagine that the average score for males is 50.6 while the average score for females is 50.2. Indeed, males scored higher, but only by 0.4 points on the test. Is this difference large enough to be significant? There will virtually *always* be differences between two groups, although the differences can be very small. The purpose of inferential statistics (e.g., t-tests, ANOVA, and ANCOVA) is to statistically determine whether the difference between two or more groups is significant enough to meaningfully say that there is a difference between these two groups of individuals. Therefore, analyzing this Research Question separately from the Research Hypothesis is meaningless. Do **not** write a Research Question that is better written as a Research Hypothesis. Instead, research questions should focus on describing a variable, such as \"How often do students use a computer in the classroom?\" Some research studies might not have Research Questions, which is generally ok. Let\'s return to the example of the effect of telling stories on children\'s literacy skills. The Purposes, Research Questions, and Research Hypotheses will be described for this study. **Purposes** The purposes of the study should explain the final conclusions that the research study hopes to reach. Purposes should be written as statements. Sometimes it is easier to start with the Research Questions and Hypotheses first and then write the Purposes, other times it is easier to start with the Purposes. When writing the *Purposes* section, it is best to start with the general purpose of the study: - **The overall purpose of this study is to examine the effect of telling stories on nursery children\'s literacy skills.** Once the overall purpose has been explained, then write a specific purpose about every key variable identified from Step 2. In the literacy example, the following specific variables were identified: telling stories, reading fluency, reading comprehension, vocabulary, and interest in reading. Specific purposes for the research study might include: - Identify how often nursery teachers tell stories in the classroom. - Determine the effect of telling stories on nursery children\'s reading fluency. - Determine the effect of telling stories on nursery children\'s reading comprehension. - Determine the effect of telling stories on nursery children\'s vocabulary. - Determine the effect of telling stories on nursery children\'s interest in reading. **Research Questions** As previously stated, the Research Questions should only be written for descriptive topics only. The only research question for the purposes above is: - **How often do nursery teachers tell stories in the classroom?** **Research Hypotheses** Typically, research hypotheses are stated as a *null hypothesis.* Null hypotheses are based on probability theory. In other words, there are always \"chance\" events that may influence scores on research instruments - perhaps one person guessed very well on an achievement test and scored higher than they should have, or another person was quite tired and misunderstood the purpose of the questionnaire. To determine whether differences in mean scores are truly different, inferential statistics (e.g., t-tests, ANOVA, ANCOVA) are used to mathematically determine the probability that the difference between two scores is due to chance. Researchers want to be quite confident that their conclusions are true, so they want a low probability that their conclusion is due to chance, typically less than 5 in 100. (This is exactly the p-value that identifies statistical significance: p\