Reference no: EM132852467
A.What is the null hypothesis (H0)?; the alternative hypothesis (H1)?.
B. Should this be a one- or two-tailed test? Why?
C. Which inferential statistic is most appropriate to use? (be specific)
D. Assuming alpha = 0.05, should the researcher reject or fail to reject the null hypothesis?
1. Dr. M. Ceerup is interested in knowing whether exam performance differs depending upon whether students eat a high-sugar breakfast versus a sugar-free breakfast. There is no existing literature on the subject so she has no idea what to expect in terms of results. To test this, she divides the class into two groups of equal size, each group getting only one type of breakfast, and gives them all a test. After data analysis she finds that the probability value was 0.04.
2. Dr. Button has decided to investigate if incorporating the 'clicker feedback system' into the classroom improves students' attention to the course material. He has observed a demonstration of the technology and believes test scores will improve by using the new device. He teaches the first half of the semester without the system and then, after the first two exams, starts using the feedback system for the second half of the course and compares performance to the last two exams. Dr. B writes in his notes: "...after comparing test scores for the first and second halves of the semester, the mean test scores for the second half of the semester were higher than those from the first half of the semester - the test statistic had a probability of p=.035".
3. A high school chess teacher believes that the students who enroll in the chess club have above average intelligence when compared to the general student population. To test this idea, she gives each member of the chess club a standardized I.Q. test and compares this with the established population parameters. Looking at the results of the statistical tests indicates that p=.058.
4. Dr. Wa Chin Yu is a developmental psychologist who believes that children who play with Lego building blocks at a young age develop better spatial skills. To examine this, he follows two groups of kindergarten children over the course of a year. Each week the children are brought into the observational playroom; one group is given building blocks to play with while the other group is given crayons and coloring books to play with. At the end of the year he gives both groups of children a spatial configuration test and finds that the group who played with the blocks scored higher than the other group - the probability from the analysis was p=0.06.
5. A researcher, Dr. Max Well, believes that caffeine influences driving ability. To test this, he randomly selects three groups of participants who will be given a beverage to drink before completing a driving test using a virtual reality, driving simulator. One group receives a caffeine-free beverage, another group receives a beverage with 50% caffeine, and the third group receives a beverage that is 100% caffeine. Driving performance varied dramatically for all three groups, however, the researcher completes the statistical analysis to find a resulting p-value of .0024.
6. Dr. Ambidex is interested in the old adage that people get dressed the same way - one leg at a time. However, she wonders if there is a difference such that people may have a preferred leg in much the same way that they have a preferred hand for performing certain tasks. To test this idea, she takes a sample of 45 college students and observes their natural dressing habits by simply asking them to put on a pair of sweat pants (over their existing clothes). She first measures the amount of time it takes students to put on the pants their natural way (observing which leg they prefer to insert first), then measures the time it takes to dress after asking students to start with their opposite leg first. After measuring and recording her data, she is surprised to find a variety of dressing habits (including those who shove both legs in simultaneously) and time differences. Her final statistical analysis indicates that p=0.03.
7. Dr. Com Onsense believes that global warming is real and that the mean summer temperatures in Tennessee are increasing each year. To examine this, he records the daily high temperature for the months of June, July, and August of this year, computes the mean summer temperature, and compares this mean with the known mean (i.e., the 'population' mean gathered from historical temperature data). After compiling the data, he finds that this year's mean temperature is indeed greater than those of years past - his resulting p-value is 0.017.
8. Dr. Stench hypothesizes that human parents are just as adept as other mammals when it comes to recognizing their offspring by the sense of smell. To test this, he asks parents to provide their childs' pajamas after it was worn. The researcher places these pajamas and a 'control' item of clothing into two unmarked boxes with a small slit cut from the top. Critically, there are no identifying cues for the parents to use other than their sense of smell. The parents smell the item in each box and must choose which box they believe contains their child's clothing. Dr. Stench compares their performance to the theoretical probability of a correct response (i.e., 50%). He finds that the mean score for clothing identification is greater than this theoretical value and has an associated p-value of .065.
9. Dr. Flapjack believes that temperature and test performance are somehow related. That is, she believes that significant differences in classroom temperature will affect how well students perform on mathematical exams. To test this, she has three different class take the same math exam, on the same day, after receiving the same instruction regarding particular problem solving techniques. Importantly, her classes meet for an hour and then there is an hour break between classes. This gives the researcher time to adjust and stabilize a new temperature before the next class. For the first class, the temperature is set at 55 degrees, the second class takes the exam in a 70 degree classroom, and the last class suffers through the exam in 85 degrees. Upon grading the exams for all three classes, she enters this data and their corresponding class temperatures into her statistical program and finds that the resulting probability is 0.085.
10. Dr. Ty Linall wonders if students attending KSU are more conservative or more liberal in their drinking habits. She estimates that the typical college student drinks enough to induce a hangover about three times a month (although she doesn't really know the population parameters, she theoretically derives this estimate). To examine this, she takes a sample of undergraduate students and asks them to do an anonymous questionnaire regarding their party habits (frequency of drinking, number of drinks, number of headaches the next morning, number of times waking in an unfamiliar location, etc). After tabulating the results of her survey, she finds that KSU students are more likely to need analgesics than the typical college student; p= 0.000315.