by asalas

Slides
17 slides

Observational vs Experiments.ppt

Published Nov 12, 2014 in
Direct Link :

Observational vs Experiments.ppt... Read more

Read less


Comments

comments powered by Disqus

Presentation Slides & Transcript

Presentation Slides & Transcript

ExperimentsSection 4.2(Be ready for a LOT of new vocabulary)

Observational Study vs. ExperimentIn an observational study, we observe individuals and measure variables of interest but do not attempt to influence the responses. (A survey is one type of observational study).In an experiment, we deliberately impose some treatment on (or do something to) individuals in order to observe their responses.

Two (Possible) Types of Variables in an Observational Study or ExperimentResponse Variable or Dependent VariableMeasures an outcomeExplanatory Variable or Independent Variable Explains (or possibly influences changes in) the response variable

Observational Study or Experiment?i) Tell whether the following situations describe an observational study or an experiment and ii) Identify the explanatory & response variablesA researcher want to determine if consuming alcohol raises a person’s body temperature. The researcher takes the temperature of 25 college students. He then asks them to consume 3 beers within one hour in a lab setting. At the end of the hour, he measures each student’s body temperature again.

Observational Study or Experiment?i) Tell whether the following situations describe an observational study or an experiment and ii) Identify the explanatory & response variablesA researcher wants to determine if smoking causes a person to have higher blood pressure. He recruits 25 non-smokers and 25 smokers and takes each person’s blood pressure. He then compares the blood pressure of each group.

Beware of the Lurking VariableWhen you are trying to draw conclusions about the relationship between two variables, always consider that an association might be caused by another variable that you haven’t considered. We call this type of variable a lurking variable.

Lurking Variables & ConfoundingDefinition:A lurking variable is a variable that is not among the explanatory or response variables in a study but that may influence the response variable.Confounding occurs when two variables are associated in such a way that their effects on a response variable cannot be distinguished from each other.

Lurking VariablesGive a possible lurking variable & say whether or not it may be confounding. A researcher want to determine if consuming alcohol raises a person’s body temperature. The researcher takes the temperature of 25 college students. He then asks them to consume 3 beers within one hour in a lab setting. At the end of the hour, he measures each student’s body temperature again.

Lurking VariablesGive a possible lurking variable & say whether or not it may be confounding. A researcher wants to determine if smoking causes a person to have higher blood pressure. He recruits 25 non-smokers and 25 smokers and takes each person’s blood pressure. He then compares the blood pressure of each group.

Lurking VariablesA study at a high school in California compared academic performance of music students with that of non-music students. They found that music students had a much higher average GPA than non-music students, 3.59 to 2.91.As a result, educators and parent groups pressed for expanded music program in the nation’s schools. They argued that the work ethic, discipline, and feeling of accomplishment fostered by learning to play an instrument also enhance a person’s ability to succeed in school. Evaluate the conclusions of the educators and parents based on the validity study.

Observational Study vs. ExperimentWhen our goal is to understand cause and effect, well-designed experiments are the only source of fully convincing data*. For this reason, the distinction between observational studies and experiments is one of the most important in statistics.*See Section 4.3 for other ways to show causation

Experiments vs. Observational Studies A carefully designed experiment can be used to show cause and effect since the researcher can control for the effects of variables that are not included as part of the study.This is not true for observational studies, since the researcher is not controlling the situation, but simply observing.

The Language of ExperimentsA treatment is a specific experimental condition applied to the experimental units. (A treatment is a general term that does not imply something specifically medical).When the units are human beings, they are called subjects.

TreatmentsWhat are the treatments and the subjects in this experiment?A researcher want to determine if consuming alcohol raises a person’s body temperature. The researcher takes the temperature of 50 college students. He then asks 25 of them to consume three 8 oz. beers within one hour in a lab setting. He asks the other 25 to consume and equivalent volume of water at the same temperature. At the end of the hour, he measures each person’s body temperature.

TreatmentsSome treatments are formed by combining the levels (specific values) of each of the factors (another name for explanatory variables).

Combined Effects StudyA researcher wants to study the combined effects of Vitamin C and exercise on middle aged men. He screens 180 men with similar health habits. He wants to test Vitamin C dosages at 60, 90 and 120 milligrams, and exercise durations of 30 and 60 minutes.

Combined Effect Study QuestionsWhat are the experimental units in this study?What are the factors in this study? What are the levels of each factor?How many treatments can he apply to his subjects? List them.How many subjects should be in each group?