Exam prep Flashcards
An experimental design is a set of procedures specifying:
- the test units and how these units are to be divided into homogeneous samples.
- what independent variables or treatments are to be manipulated
- what dependent variables are to be measured
- how the extraneous variables are to be controlled
There are 2 kinds of experimentation validity:
- Internal
2. External
Internal validity
refers to whether the manipulation of the independent variables or treatments actually caused the observed effects on the dependent variables. The control of extraneous variables is a necessary condition for establishing internal validity.
External validity
Refers to whether the cause-and-effect relationships found in the experiment can be generalized. To what populations, settings, times, independent variables, and dependent variables can the results be projected?
Etraneous variables
Extraneous Variables are undesirable variables that influence the relationship between the variables that an experimenter is examining. Another way to think of this, is that these are variables the influence the outcome of an experiment, though they are not the variables that are actually of interest. These variables are undesirable because they add error to an experiment. A major goal in research design is to decrease or control the influence of extraneous variables as much as possible.
Example- Say you wanted to work out how clever a fish species were in finding food depending on how long since they had eaten. But if their ability to find food also depended on the temperature of the water and you were not able to either control or measure accurately the temperature of the water. Then the temperature could be described as an extraneous variable.
Independent variables:
These are the individual variables that you believe may have an effect on the dependent variable. They are sometimes called “explanatory variables,” “manipulated variables,” or “controlled variables.”
Dependent variables
This is the output variable you are really interested in monitoring to see if it was affected or not. It can also be called the “measured variable,” the “responding variable,” the “explained variable,” etc. I think it is easy to remember this one because it is dependent on the other variables.
Independent vs Dependent example
- Here’s a simple situation: Suppose you want to test golf ball flight distances, so you set up a simple experiment in which various golf balls are placed into a mechanical chute and fired into the air. The variable you really care about, the “output” or dependent variable is golf ball distance. Independent variables are the variables you are going to test to see how they affect distance. In this case, they are going to be things like air temperature, golf ball brand, and color of the golf ball.
- Here’s another simple example: Imagine that you have a bunch of ice cubes and you want to test how long it takes them to melt in various situations. You have an experiment with 1,000 equally shaped ice cubes. Some of them are made of frozen cranberry juice and some of them are frozen lemonade. You are going to set some of them on a metal sheet and others are going to be placed on a wooden plank. Air temperature, wind, and every other condition you can think of will remain constant. So, in this case, your dependent variable is ice cube melting time. Your two independent variables are: juice type (cranberry or lemonade) and melting surface (metal or wood).
Qualitative research method:
Unlike quantitative research, qualitative research is typically unstructured and exploratory in nature. The researcher is not interested in determining objective statistical conclusions or in testing a hypothesis, but rather in gaining insights about a certain topic. Common qualitative research techniques include focus groups, interviews, and observation.
Example - Since the data is unstructured–imagine a bunch of handwritten notes from a focus group meeting–it can be tricky drawing conclusions and presenting the findings. In the case of interviews and focus groups, the moderator may simply take some time to write up the key points heard in the meeting, and then present those key points to the interested parties. For example, in a focus group about pizza, you might see the following summary: “common concerns among partipants were cheese overuse, greasiness, and bland sauce.”
Quantitative research method:
This research aims to objectively measure the topic at hand, using mathematics and statistics. If you are doing quantitative research, you will most likely be analyzing raw data with the help of a spreadsheet software program like Microsoft Excel, or a statistical package like SPSS. To facilitate this type of analysis, your data will need to be gathered in a structured format. Quantitative research is often conducted using market research methods like surveys and experiments, which are best at collecting structured data.
Conclusive research
Providing information which helps the manager decide on a correct decision, conclusive research consists of formal research procedures including clearly defined goals and needs. Usually, a questionnaire is designed in conjunction with a sampling plan. There must be a clear link between the alternatives in the evaluation and the information that is to be collected. This line of research can include simulation, surveys, observations and experiments.
Descriptive research
is used to describe characteristics of a population or phenomenon being studied. It does not answer questions about how/when/why the characteristics occurred.
Casual research
Causal research is conducted in order to identify the extent and nature of cause-and-effect relationships. Causal research can be conducted in order to assess impacts of specific changes on existing norms, various processes etc. Experiments are the most popular primary data collection methods in studies with causal research design.
Cross sectional design
A type of research design involving the collection of information from any given sample of population only once.
Example - any segment, no targeting
Single cross sectional design
A cross sectional design in which one sample of respondents is drawn from a target population and information is obtained only once from this sample.
Example - drawn from targeted population
