Chapter 3 – Variables and Hypothesis (Fraenkel)
- not all research questions suggest relationships
o can be to identify characteristics, behaviors, feelings or thoughts (can be important information for making educational decisions or designing research)
o problem with purely descriptive research questions – we mayu learn what happened, where, when or even how, but not why it happened; understanding of a situation, group or phenomenon is limited – why scientists highly value research questions that suggest relationships to be investigated
§ answers help explain nature of world we live in by explaining how parts of the world are related (detect patterns or connections between parts) (pp 39)
§ may be times when researcher wants to hypothesize that a relationship does not exist to contradict a widespread belief
· methodological mistakes (i.e., not enough instruments or too small a sample of participants) in research increase chance of finding no relationship between variables
- variables – concepts that have variation within a class of objects that differ, or vary, which allows the class to be a variable. If all members of a class are identical, there is no variable – called a constant. (will always have some of each in a study)
o cannot manipulate a variable if we cannot define it
o researchers choose variables to investigate b/c they think they are related and believe that if they discover the relationship b/w them, it will help to make more sense of the world we live in
- quantitative variables – exist in some degree in a continuum from less to more, and we can assign numbers to different individuals or objects to indicate how much of the variable they possess (i.e., height and weight, interest levels, etc)
- categorical variables – do not vary in degree, amount or quantity but are qualitatively different (i.e., eye color, gender, religious preference, occupation, position on a baseball team)
o you are either in one or the other category, not somewhere in between (pp 40)
o not categorical if it is a matter of degree, if there is the elimination of the possibility of using more detailed info about the variable and if the dividing line between groups is arbitrary (pp. 42)
- Researchers in education often study the relationship between or among either2 or more quantitative variables, one categorical variable and one quantitative variable, or two or more categorical variables.
- Independent variables – studied to assess their possible effect(s) on one or more other variables; presumed to affect or at least partly cause or somehow influence at least one other variable.
- Dependent variable – affected by independent variable (dependent variable depends on what the independent variable does to it; how it affects it)
o Can investigate more than 1 independent and dependent variable in one study
- Manipulated variable – one the researcher creates – independent variable can be manipulated or selected, often found in experimental studies
o i.e., researcher can manipulate conditions of experiment to create varied amount of reinforcement
o a.k.a. experimental or treatment variables (pp 42)
o selected indep variables found in causal comparative and correlational studies; can be categorical or quantitative; either way, indep variable affects dep one.
o Indep/dep relationship can be reversed depending on what the researcher thinks is the cause of the other (43)
o Most educational research studies have 1 quantitative and 1 categorical variable that compares different methods or treatments (indep is often categorical; dep is often quantitative and is referred to as an outcome variable)
- Moderator variable – secondary independent variable that has been selected for study in order to determine if it affects or modifies the basic relationship b/w primary indep variable and dep variable
o Its inclusion can provide more information than just studying a single indep variable alone (can be more than 1 moderator variable) - inclusion is recommended wherever appropriate
- Extraneous variables – variables that can influence or affect the other variables – need to be controlled or eliminated to minimize their effects
o Independent variables that have not been controlled
§ Can control them by holding them constant
- Hypothesis – prediction of possible outcomes of a study
Advantages to Stating Hypotheses In Addition to Research Question
- forces us to think deeper and more specifically a/b possible outcomes of a study
- can lead to more sophisticated understanding of what question implies and exactly what variables are involved
o when more than one hypothesis exists, forces us to think more carefully about what we really want to investigate
- “If one is attempting to build a body of knowledge in addition to answering a specific question, then stating hypothesis is a good strategy b/c it enables one to make specific predictions based on prior evidence or theoretical argument. If the predictions are borne out by subsequent research, the entire procedure gains both in persuasiveness and efficiency” (46).
- Helps us see if we are, or are not, investigating a relationship. If not, we may be prompted to form one.
Disadvantages to Stating Hypotheses
- May lead to bias, conscious or unconscious, on part of researcher
- Tempted to arrange procedures or manipulate data to bring about desired outcome (tends to be exception, as researchers are assumed to be intellectually honest, although this isn’t always the rule)
o Should be subject to peer review (the study)
o Any particular study can be replicated to verify findings, although this rarely happens
o Desirable for researchers to make known their predilections regarding a hypothesis so that they are clear to others interested in their research
§ Allows investigators to guard against personal biases
- Hypothesis may sometimes be unnecessary or inappropriate in some types of research like descriptive surveys and ethnographoi studies
o Unduly presumptuous and futile to predict what the findings of the inquiry will be
- Focusing attention on hypothesis may prevent researchers from noticing other phenomena that might be important (46)
- Significant hypothesis = lead to more useful info (useful to higher quantity of people)
- Directional hypothesis – indicates specific direction (higher, lower, more, less) that a researcher expects to emerge in a relationship – expected direction based on what researcher has found in the literature, from personal experience, or from experience of others
- Nondirectional hypothesis – does not make a specific prediction about what direction the outcome of a study will take
o I.e. = man wants to cross street. He can either look left, look right or continue to look straight ahead. Nondirectional hypothesis would predict he will look one way or the other; directional hypothesis predicts he looks in a particular direction. (pp.47)