For Professor Ryan ONLY
lken82
chp8.docxStatistics for Business and Economics, Ch. 8
· Observational vs designed experiment The thread has 4 unread messages.
created by ARACHEAL VENTRESS
Last updated Feb 26, 2015, 7:57 PM
4
· Comment on Feb 25, 2015, 10:44 AM
Message collapsed. Message unread Observational vs designed experiment
posted by ARACHEAL VENTRESS at Feb 25, 2015, 10:44 AM
Last updated Feb 25, 2015, 10:44 AM
·
What is the difference between an observational experiment and a designed experiment?
A designed experiment is one for which the analyst controls the specification of the treatments and the method of assigning the experimental units to each treatment. An observational experiment is one for which the analyst simply observes the treatments and the response on a sample of experimental units.
Our text went further to provide examples to help differentiate between the two concepts: if you give one randomly selected group of employees a training program and withhold it from another randomly selected group to evaluate the effect of the training on worker productivity, then you are designing an experiment. If, on the other hand, you compare the productivity of employees with college degrees with the productivity of employees without college degrees, the experiment is observational.
Reference
McClave, J. T., Benson, P. G., & Sincich, T. (2011). Statistics for Business and Economics (11th ed.). Boston, MA: Prentice Hall
· Comment on Feb 25, 2015, 8:29 PM
Message collapsed. Message unread Re: Observational vs designed experiment
posted by KIM DUNLAP at Feb 25, 2015, 8:29 PM
Last updated Feb 25, 2015, 8:29 PM
·
Hi Aracheal,
When I was reading our textbook regarding observational versus designed experimental research, I was thinking that because of the control aspect of experimental research - it is probably more expensive to conduct. I then did a little additional research and found that yes, indeed designed experimental research is more expensive. When I think about this in a common sense way - it is very easy to understand why it is more expensive because of the control that is involved - in regards to the subjects, controlling the situation - whether it is the environment or the object, ensuring consistency, and then controlling all of these throughout the various samples.
I'm sure this fact is a contributing factor to the expense of health care supplies - whether we are researching medication or a supply to be used on a patient. There is a lot of control required in the testing of objects to be used on humans.
· Comment on Feb 26, 2015, 10:32 AM
Message collapsed. Message unread Re: Observational vs designed experiment
posted by ARACHEAL VENTRESS at Feb 26, 2015, 10:32 AM
Last updated Feb 26, 2015, 10:32 AM
·
Kim Thanks for your post. From reading your post- I can see why a designed experiment could be considered more expensive because of the experimenter's control involved. With budget constraints- I can see that being an issue.
According to our text, there are advantages of a designed experiment. Our text states that designed experiments are generally preferred to observational experiments. Not only do we have better control of the amount and quality of the information collected, but we also avoid the biases inherent in observational experiments in the selection of the experimental units representing each treatment.
Reference
McClave, J. T., Benson, P. G., & Sincich, T. (2011). Statistics for Business and Economics (11th ed.). Boston, MA: Prentice Hall
· Comment on Feb 26, 2015, 7:57 PM
Message collapsed. Message unread Re: Observational vs designed experiment
posted by CRYSTAL RAMOS at Feb 26, 2015, 7:57 PM
Last updated Feb 26, 2015, 7:57 PM
·
(An observational study measures the value of response variable without attempting to influence any of the response or explanatory variables of the individual). That is, in an observational study, the researcher observes the behavior of the individuals in the study without trying to influence the outcome of the study.
(In Designed Experiments, individuals are assigned to groups where explanatory variables are intentionally changed and the values of the response variables are rewarded). If a researcher assigns the individuals in a study to a certain group, intentionally changes the value of the explanatory variable (remember radiation to rats), and then records the value of the response variable for each group, the researcher is conducting a designed experiment. (Drug testing - Placebo vs. active drub).
·
ANOVA The thread has 7 unread messages.
created by LOUIS DAILY
Last updated Feb 26, 2015, 7:52 PM
7
· Comment on Feb 22, 2015, 10:46 PM
Message collapsed. Message unread ANOVA
posted by LOUIS DAILY at Feb 22, 2015, 10:46 PM
Last updated Feb 22, 2015, 10:46 PM
Despite its name, Analysis of Variance is used to test means. If we have more than two groups to compare, we cannot use a t or z test. We must use ANOVA. The test statistic is F, and we compare it to critical F from the chart. If F is greater than critical F, then we reject the null. The null is: Ho: Mu1=Mu2=Mu3.... For instance, we might have a low dose drug group, a high dose drug group, and a placebo group.
The F statistic is a ratio, a ratio of two Variances, the Between Groups Variance to the Within Groups Variance.
Discuss. Questions?
· Comment on Feb 25, 2015, 12:41 PM
Message collapsed. Message unread Re: ANOVA
posted by PATRICIA MARCUS at Feb 25, 2015, 12:41 PM
Last updated Feb 25, 2015, 12:41 PM
·
Many organizations use various tools to ensure quality assurance and management for their business. The challenge for them is to ensure that they provide the best quality of service to their clients in a time effective manner. As such, having a diversity of tool options in place helps the organization identify daily challenges and increase overall effectiveness practices in their decision making processes. Implicitly, identifying the problems is the first key component towards making a sound decision. Once the problems are identified organizations can use tests such as ANOVA, nonparametric test and Kruskal-Wallis test for operational research methods and total quality management. These methods will allow researchers to analyze significant data that will subsequently result in implementation of the found solutions. Utilizing these tools can assist in analyzing information in order to make the best possible decision for the organization.
· Comment on Feb 25, 2015, 6:13 PM
Message collapsed. Message unread Re: ANOVA
posted by KIM DUNLAP at Feb 25, 2015, 6:13 PM
Last updated Feb 25, 2015, 6:13 PM
·
The Anova F test is equal to the square of the calculated t (if you ran the F test on a 2 sample test). This indicates that F-test and t-test are really the same. The big difference is that the F-test can be used to compare more than two treatment means, whereas the t-test is applicable to only two samples.
When calculating the F- statistic - when the value of the MST to MSE ratio is near one, it indicates that the two sources of variation between treatment means and within treatment means are approximately equal. Values of F that are not close to 1(in excess of 1) would indicate that the variation among treatment means well exceeds that within treatments and therefore support the alternative hypothesis.
· Comment on Feb 25, 2015, 8:47 PM
Message collapsed. Message unread Re: ANOVA
posted by SAID SHEIK ABDI at Feb 25, 2015, 8:47 PM
Last updated Feb 25, 2015, 8:47 PM
·
The reason for doing an ANOVA is to see if there is any difference between groups on some variable. For example, you might have data on student performance in non-assessed tutorial exercises as well as their final grading. You are interested in seeing if tutorial performance is related to final grade. ANOVA allows you to break up the group according to the grade and then see if performance is different across these grades. ANOVA is available for both parametric (score data) and non-parametric (ranking/ordering) data
The following assumptions exist when you perform an analysis of variance :
· The expected values of the errors are zero.
· The variances of all errors are equal to each other.
· The errors are independent from one another.
· The errors are normally distributed.
http://www.investopedia.com/terms/a/anova.asp
· Comment on Feb 26, 2015, 11:06 AM
Message collapsed. Message unread Re: ANOVA
posted by ARACHEAL VENTRESS at Feb 26, 2015, 11:06 AM
Last updated Feb 26, 2015, 11:06 AM
·
The ANOVA has long enjoyed the status of being the most used statistical technique in psychological research. The popularity of this technique can be attributed to two main reasons. First, like the t test, it deals with differences between and among sample means; however, it imposes no restrictions on the number of means. second, theANOVA allows dealing with two or more independent variables simultaneously, and it provides information not onlyof each variable effect, but also of the interacting effects of two or more variables
Reference
Ximénez, C., & Revuelta, J. (2007). Extending the CLAST sequential rule to one-way ANOVA under group sampling. Behavior Research Methods, 39(1), 86-100. Retrieved from http://search.proquest.com/docview/204304311?accountid=35812
· Comment on Feb 26, 2015, 2:24 PM
Message collapsed. Message unread Re: ANOVA
posted by STEPHANIE RECTOR at Feb 26, 2015, 2:24 PM
Last updated Feb 26, 2015, 2:24 PM
·
According to McClave, "Conditions Required for a Valid ANOVA F-test: Completely Randomized Design
· 1. The samples are randomly selected in an independent manner from the k treatment populations. (This can be accomplished by randomly assigning the experimental units to the treatments.)
· 2. All k sampled populations have distributions that are approximately normal.
· 3. The k population variances are equal (i.e., )" (McClave, 2011).
An example of this would be if ASA (Amateur Softball Association) wanted to compare the mean distances between four competing brands when hit with a particular bat. These brands could be Worth, Dudley, Wilson, and Rawlings. Closely relating the example in our material, ten random sample balls of each brand would be hit in random sequence. This could be done with a robotic swinger and the distance can be recorded for each hit. At this point, a comparison of mean distances for each brand would be determined (α=.10) can be used. Then you can compute the test statistic and p-value to analyze results. The ANOVA involves two or more independent variables. Although we only used four brands and ten hits for this example, ANOVA does not contain limits to the number of means you can have.
Reference
McClave, J. T., Benson, P. G., & Sincich, T. (2011). Statistics for Business and Economics (11th ed.). Boston, MA: Prentice Hall
· Comment on Feb 26, 2015, 7:52 PM
Message collapsed. Message unread Re: ANOVA
posted by CRYSTAL RAMOS at Feb 26, 2015, 7:52 PM
Last updated Feb 26, 2015, 7:52 PM
·
In the typical application of ANOVA, the null hypothesis is that all groups are simply random samples of the same population. For example, when studying the effect of different treatments on similar samples of patients, the null hypothesis would be that all treatments have the same effect (perhaps none). Rejecting the null hypothesis would imply that different treatments result in altered effects.
By construction, hypothesis testing limits the rate of Type I errors (false positives leading to false scientific claims) to a significance level. Experimenters also wish to limit Type II errors (false negatives resulting in missed scientific discoveries). The Type II error rate is a function of several things including sample size (positively correlated with experiment cost), significance level (when the standard of proof is high, the chances of overlooking a discovery are also high) and effect size (when the effect is obvious to the casual observer, Type II error rates are low).
The terminology of ANOVA is largely from the statistical design of experiments. The experimenter adjusts factors and measures responses in an attempt to determine an effect. Factors are assigned to experimental units by a combination of randomization and blocking to ensure the validity of the results. Blinding keeps the weighing impartial. Responses show a variability that is partially the result of the effect and is partially random error.
ANOVA is the synthesis of several ideas and it is used for multiple purposes. As a consequence, it is difficult to define concisely or precisely.
