stat 121 lesson 4

The individuals studied in an experiment are often called ________, particularly when they are ______.

subjects, people

Suppose an experiment has a control group and a treatment group, but not randomization. Can we still conclude causation?

no. Without randomization, there could be bias and/or confounding. In addition, laws of probability cannot be applied.

What are 3 key factors for a good experiment?

compare two active treatments compare active treatment with a placebo randomly assign subjects to treatments

The explanatory variables in an experiment are often called _______.

factors

Does ripping off a band-aid hurt less than slowly pulling it off? Researchers plan to compare the two methods by applying two medium sized band-aids to the underside of the right forearm of each of 50 volunteer subjects. One band-aid will be randomly selected to be pulled off with a quick yank while the other will be gently pealed off. The order in which the band-aids are removed will also be randomized. After each band-aid is removed, the subject will be asked, "On a scale of 0 to 10, how much did the removal hurt?--with zero for "no pain" and 10 for "the worst pain imaginable." What is the explanatory variable? What type of study is this?

-Method of band-aid removal (yanking or gentle pealing). --This is a matched pairs study because two measurements were taken on each subject—one pain score for the quick yank removal and the other for the gently peel removal. The order in which the treatments were applied was randomized. Subjects did not choose order of type of removal.

Does ripping off a band-aid hurt less than slowly pulling it off? Researchers plan to compare the two methods by applying two medium sized band-aids to the underside of the right forearm of each of 50 volunteer subjects. One band-aid will be randomly selected to be pulled off with a quick yank while the other will be gently pealed off. The order in which the band-aids are removed will also be randomized. After each band-aid is removed, the subject will be asked, "On a scale of 0 to 10, how much did the removal hurt?--with zero for "no pain" and 10 for "the worst pain imaginable." What is the response variable? What is the replication?

-Pain score. -Since this is a matched pairs experiment and fifty subjects participated, we have 50 measurements for each type of removal. Thus, fifty is the replication.

Why is "presence or absence of other smokers in the home" a lurking variable?

A lurking variable is one not studied, but which affects the relationship between the explanatory variable (type of patch) and the response variable (whether subject quit smoking).

Wat are the possible consequences of not having randomization in a study? B PC CALOP CCC&E

A. Bias B. Possible confounding C. Cannot apply laws of probability D. Cannot conclude cause and effect

How do the media often report observational studies?

As if there is a cause and effect relationship

What is the advantage of an experiment over an observational study?

Because the researcher imposes a treatment on each individual in the study and measures the response, the researcher can use the results to establish whether the treatments "cause" changes in the response.

Which of the following involves two variables whose effects on the response variable cannot be separated? Lurking variable Confounding variable interaction

Confounding variable.

What are the 2 keys of Randomized comparative experimentation?

Copmarison and chance assignment

What is replication in an experiment?

Having more than one individual receive each treatment

Which one of the following is NOT a consequence of lack of randomization? a. Results could be biased. b. A lurking variable is likely confounded with the explanatory variable. c. Laws of probability cannot be used to measure uncertainty in conclusions. d. Not enough individuals will be available to measure chance variation. e. Causation cannot be concluded.

Not enough individuals will be available to measure chance variation.

Whenever the response variable is ____________, means are compared. Whenever the response variable is ___________, percentages are compared.

QUANTITATIVE, CATEGORICAL

Which principle of experimentation is lacking in observational studies?

Random allocation of subjects to treatments

What is randomization in an experiment?

Randomly allocating subjects to treatment groups

Which best describes the measurement of the response variable?

Some students mistakenly think that the mean or the proportion of the responses in a treatment group is the measurement of the response variable. But the response is measured on the individual, never on a group of individuals.

When is the response variable determined?

The response to the treatment is measured at the end of the study.

Five of the following express potential problems the band-aid removal study, but one is NOT a potential problem. Which one of the following is NOT a potential problem with the study? a. Amount of hair a subject has may affect the degree of pain. b. The study lacks realism because the subjects can't tell how each band-aid is removed. c. Results may be biased because there is no blinding of subjects as to when they receive each treatment. d. Subjects may already prefer one method of removal over another so their pain score report may be biased. e. The study was not double blind. In fact, it wasn't even single blind. f. The person doing all of the quick yanks may not be able to do them exactly the same for all subjects.

study lacks realism because subjects can't tell how each band-aid is removed. Duh.

Which of the following gives evidence of a cause and effect relationship between the explanatory and response variables? A. A well-designed experiment with randomization and control/comparison B. A well-designed survey with random selection of individuals to be studied

well designed experiment

What is the population in the probability statistics unit study? What type of study is it?

1. All students in the ninth-grade General Mathematics course in this school district 2. An experiment.

What are the 3 experimental design principals (C.R.R.)?

1. Comparison 2. Randomization 3. Replication

An experiment was designed using school children as subjects to determine whether drinking milk prevented their catching colds. The researcher randomly assigned 100 school children to two groups—one group of 50 to receive a cup of milk at school each day and the other group of 50 to receive no milk at school. What is the response variable? Remember: The response variable is measured on the individual. What is the explanatory variable? Is the principle of control/comparison incorporated in the study? Is there replication? What lurking variables might be present?

1. Response variable is if any of the kids caught a cold. 2. Whether child received a cup of milk at school each day. 3. Yes. The group that drinks milk will be compared to the one that does not. 4. Yes, because replication is having more than one subject in each treatment group. Fifty qualifies as more than one. Statistically speaking, replication is NOT reproducing the experiment. 5. Whether child was weak or robust at the beginning. Time of the year maybe.

Questions 1 - 8 apply to the following : Because more questions about Statistics have been added to the state exam, a school district decided to add a probability-statistics unit to their ninth-grade General Mathematics course. To determine whether the unit will have an impact on scores on the state exam, all ninth-grade students enrolled in a General Mathematics course in the largest high school in the school district were randomly allocated to two groups. One group of 281 students received instruction in a new probability and statistics unit in addition to the traditional instruction; the other group of 311 students received only traditional instruction. Students in both groups were given the state exam at the end of ninth grade to determine whether the group receiving additional instruction in probability and statistics had a higher average score than the group receiving just traditional instruction. What is the response variable? Does the study described above incorporate the principle of control or comparison?

1. Score on the state exam 2. Yes, because the group of students receiving only traditional instruction can be considered a control or comparison group. The group of students receiving the additional instruction of probability-statistics can be considered the active treatment group.

Two hundred twenty-eight surveyed parents reported the amount of caffeine their 8 to 12 year old children consumed on a typical day. They also gave the average time their children slept each night. The purpose of the study was to determine whether amount of caffeine consumed affected how much children 8 to 12 year olds sleep. What type of study is this? What is the explanatory variable?

1. Since the parents were surveyed, this is an observational study. Not enough information is given to determine the type of survey. 2. Amount of caffeine consumed by child

For the milk drinking experiment, When the experiment was actually conducted, the teachers disagreed with the researcher's assignment because some of the frail children were in the group to receive NO milk. They switched all the frail children in the "NO milk" group to the "Receive milk" group and all the robust children in the "Receive milk" group to the "NO milk" group. In what way did these teachers ruin the experiment?

1. They removed randomization by assigning treatment groups. They confounded the health condition of the children with the explanatory variable.

For the stat instruction vs no stat instruction experiment, What is the explanatory variable? Hint: The explanatory variable must describe all of the treatments, not just one of the treatments. Does the study incorporate the principle of replication?

1. Whether instruction includes the probability-statistics unit or not 2. Yes, there are more than one individual in both the control and active treatment groups.

An educational software company wants to compare the effectiveness of its computer animation for teaching about supply and demand curves with that of a textbook presentation. The company tests the economic knowledge of a number of first-year college students, then randomly divides them into two groups. One group uses the animation, and the other studies the text. The company retests all the students and compares the increase in economic understanding in the two groups. 1. Is the study described above an experiment? Why or why not? 2. What is the explanatory variable? 3. what is the response variable? Remember the response variable is the measurement variable on each individual.

1. Yes it is an experiment because the students were randomly assigned to either the animation group or the textbook group 2. Whether the student used the animation or textbook presentation Correct 3. Improvement in the student's comprehension of economics (as measured by their increase in test score)

Ability to grow in shade may help pines found in the dry forests of Arizona resist drought. How well do these pines grow in shade? Investigators planted pine seedlings in either full light, light reduced to 25% of normal light by shade cloth, or reduced to 5% of normal light. At the end of the study, they dried the young trees and weighed them. 1. What is the individual in this experiment? 2. What are the treatments? 3. What is the response variable?

1. pine seedlings 2. The treatments are the three light amounts: Full light, light reduced to 25% of normal by shade cloth, and light reduced to 5% of normal. 3. weight of dried young trees.

True or false: In certain circumstances, cause and effect can be concluded even though random allocation of subjects to treatments is not done.

False.

True or False: A major difference between an observational study and an experiment is that an observational study does not have an explanatory variable with treatment levels.

False. A major difference between an observational study and an experiment is that in an observational study the subjects (or someone like their guardian or doctor) chooses their treatments, but in an experiment the treatments are randomly assigned to the subjects. Both an observational study and an experiment can have an explanatory variable with treatment levels.

True or false: Observational studies always include random assignment of treatments to subjects.

False. Observational studies do not include random assignments. Experiments do.

True or false: observational studies cannot have replication.

False. due to there being large numbers of people involved, replication is achieved easily.

A study was conducted to test the effectiveness of using an antidepressant called imipramine in treating bulimia, an eating disorder. Twenty patients were randomly assigned to one of two groups with ten in each. One group received imipramine and the other received a placebo. The response measured was binge frequency. What type of study is this?

First of all, since the treatments (imipramine and placebo) were assigned to the subjects, this was an experiment. Second, since the randomization was done using all twenty subjects and allocating them to treatments, this was a completely randomized experiment.

Gas mileage was compared for Premium and Regular gas for twenty Toyota Prius's. (A Prius is a new hybrid car.) Each car was run on a tank of Premium gas and on a tank of Regular gas. Before the study, a coin was tossed for each car. If the coin was heads, the car was first tested with Premium gas; if the coin was tails, the car was first tested with Regular gas. At the end of the study, average miles per gallon for the two types of gas was compared. What type of study is this?

First of all, this is an experiment because the type of gas was assigned, not merely observed. Second, since the randomization is done for each car and there are two measurements on each car, this is a matched pairs experiment. Note: We say that we randomized within each pair (i.e., for each car.)

How is randomization implemented in a good experiment?

In an experiment, randomization has to do with randomly assigning subjects to treatments. Randomization in a survey has to do with randomly selecting the individuals to be in the survey.

Upon what is a treatment applied?

In an experiment, the treatment is applied on the subject.

To compare 3 new test fertilizers, a farmer applies them to several cornfields. Each field is divided into three plots in the three fertilizers are randomly assigned, one to each plot with in each field. Harvested corn yield is compared for the three fertilizers. What is the individual on which a treatment is applied? What are the treatments? What is the explanatory variable? What is the response variable?

Individual: A plot of corn in a field. Treatment: 3 test fertilizers Explanatory variable: The type of fertilizer Response variable: corn yield on each plot.

Which of the following involves two variables and how the effect of one changes the effect of the other on the response variable? Lurking variable Confounding variable interaction

Interaction

What type of study is the pine seedling study and why? a. It is an experiment because it only measures a variable of interest. b. It is an experiment because the pine seedlings were assigned to either the full light, reduced to 25% of normal light, or reduced to 5% of normal light. c. It is an observational study because it does not deliberately impose a condition on the pine seedlings. d. It is an observational study because there is no attempt to influence the response.

It is an experiment because the pine seedlings were assigned to either the full light, reduced to 25% of normal light, or reduced to 5% of normal light.

Which of the following involves two variables and how the effect of one affects the relationship between the other and the response variable, but is not among those variables studied? Lurking variable Confounding variable interaction

Lurking variable

Which one of the following is a benefit of randomized block designs (RBD)? a. RBD removes bias. b. RBD reduces chance variation by removing variation associated with the blocking (lurking) variable. c. RBD eliminates the placebo effect. d. RBD eliminates all lurking variables.

Randomize block designs remove variation associated with the blocking variable from the measure of overall experimental variation. This gives more precise estimates of chance variation which helps in determining whether results are statistically significant.

People who eat lots of fruits and vegetables have lower rates of colon cancer than those who eat little of these foods. Fruits and vegetables are rich in "antioxidants" such as vitamins A, C, and E. Will taking antioxidants help prevent colon cancer? A medical experiment studied this question with 864 people who were at risk of colon cancer. The subjects were divided into four groups: daily beta-carotene, daily vitamins C and E, all three vitamins (beta-carotene, vitamins C and E) every day, or daily placebo. After four years, the researchers were surprised to find no significant difference in colon cancer rates among the groups. What is the explanatory variable?

There are four treatments: daily beta-carotene, daily vitamins C and E, all three vitamins (beta-carotene, vitamins C and E) every day, or daily placebo. So the explanatory variable is which vitamins (if any) were received daily.

In the stat class study, if the study were designed differently so that all the students in ninth-grade General Mathematics course were taught the probability-statistics unit, what principle(s) of experimentation would NOT have been incorporated? Would replication be included still?

There would be no control/comparison and randomization. Since there would have been 281 + 311= 592 students in the study, replication would have been incorporated.

True or false: All three experimental design principals are always required for a valid experiment.

True dat

True or false: Without random allocation in an experiment or random selection in a sample, we cannot appropriately apply the laws of probability to perform inference.

True.

The vitamins/colon cancer study is what type of study?

This is an experiment since treatments are assigned to the subjects rather than subjects self-selecting their treatments. Since all subjects are randomly allocated to the treatments, this is a completely randomized design. Randomization is carried out for all subjects and not within certain groups.

Why is the principle of control/comparison so important in an experiment?

To neutralize the effect of lurking variables and measure treatment differences. By randomly allocate subjects into two or more groups, the characteristics of a potential lurking variable are distributed evenly in these groups. This will neutralize the effect of the potential lurking variable. Further, we cannot measure treatment differences unless we have two or more treatment groups.

Which type of control/comparison allows a researcher to decide which active treatment works best?

Treatment 1 versus treatment 2

Give 2 examples of control vs. treatment:

Treatment vs. control (with no treatment): exercise vs. ordinary lifestyle Treatment vs. control (placebo) vaccine vs. saline

True or false: A control is any treatment without the active ingredient.

True

True or false: A placebo is basically a fake treatment.

True

True or false: A placebo is one type of control.

True

True or false: Hidden bias can be reduced by treating all subjects identically.

True

True or false: if there is no control group, there is no placebo.

True

True or false: In a randomized block design, treatments are randomly assigned to subjects within each block.

True. Randomly assigning treatments to subjects within each block is what distinguishes randomized block designs from completely randomized designs. In completely randomized designs, all subjects are randomly allocated to the treatments, regardless of any personal characteristics. In matched pairs designs (which are a special case of randomized block designs), the order of the treatment application is randomized if there are two measurements on each individual. If there are two individuals in each pair, then the pairs are randomly assigned to the treatments.

True or false: A randomized block design should be used when the subjects within groups (called blocks) are similar in ways that affect the response variable, but different from one block to the next.

True. When the subjects are similar within a block, but different from block to block, a randomized block design is recommended. This allows us to remove differences or variation associated with blocks from the experimental error. A completely randomized design should only be used when the subjects are as similar as possible in ways that affect the response variable.

Describe confounding?

Two variables are said to be confounded when their effect on the response variable cannot be separated. This often happens with a lurking variable and the explanatory variable in an observational study.

Referring to the vitamins study on colon cancer, what is the response variable? Remember: the response variable is the measurement variable on the individual (not the group) at the end of the study.

Whether or not each subject contracted colon cancer.

Why is a control necessary?

Without a control and randomization, a researcher will not know if the treatment worked or if a lurking variable affected the response variable. To determine a treatment's effect on the response variable

Which one of the following does NOT meet the comparison/control principle of an experiment? a. Active treatment versus no treatment b. Active treatment versus a placebo (fake) treatment c. An active treatment applied to individuals to observe response d. Active treatment #1 versus active treatment #2

an active treatment applied to individuals to observe response. This is bad because you have nothing to compare it to.