Research Methods, Tests of Means, and Chi Squares
How many times is each participant given each treatment in the incomplete design?
0 times
"Oberlin College Lanes wanted to see which lighting was most appropriate for students to bowl. The College Lanes claim that the current lighting, fluorescent lighting, is best suited and have advantage over other types of lighting available, including disco-ball lighting, spotlight lighting, and tungsten lighting. The researchers randomly assigned 48 students in Bowling I class into four groups. Each group bowled a game in four different lighting conditions. Group 1 bowled in a disco-ball lighting, group 2 bowled in a spotlight lighting, group 3 bowled in a fluorescent lighting, and group 4 bowled in tungsten lighting. Their performance was measured according to the number of pins they knocked down. What test should be run to test if their hypothesis is true?"
Between Subject One-Way ANOVA
"Researchers are looking to analyze how different genres of music affect individual's heart rate. The three genres examined included country music, rap music, and classical music. Researchers randomly assigned 50 people to listen to a specific genre of music, either country, rap, or classical. After listening to music for five minutes, each individual's heart rate was taken. The groups of each genre are then compared. What test would you run to test your hypothesis?"
Between Subject One-Way ANOVA
"Researchers wanted to find out whether taking notes on computer, as opposed to taking notes on paper or not taking notes but only listening, predicted better understanding of the material. The researchers randomly assigned 60 students into 3 groups. The first group watched a short clip of lecture while they took notes on computer. The second group did the same but took notes on paper. The third group just listened to the lecture. Ten minutes after the lecture, the students were given 10 multiple-choice questions to test their understanding of the material. What statistical test should they run to determine if their hypothesis is supported?"
Between Subject One-Way ANOVA
Reasearchers want to look at how having a parent die or having parents divorce effects high school students grades. They compare the GPAs of students who's parents divored with those of students who lost a parent and those of students who did not lose a parent or experience a divorce. What test should they run to determine if the GPAs of the different groups are significantly different?
Between Subjects One Way ANOVA
"Are college professors smarter than elementary school teachers? In order to test whether there is a difference in intelligence between educators at different levels of education, samples of 50 educators from 5 different levels of education (elementary school, middle school, high school, college, and graduate school) all took identical IQ tests. What test could be used to determine if there are statistically significant differences in intelligence between educators?"
Between Subjects One-Way ANOVA
"Researchers want to see if drinking different kinds of dairy products affects teenagers' growth. Four groups of 30 randomly assigned subjects are instructed to consume 16 oz per day of cow's milk, soy milk, almond milk, or no milk. Participants' height is measured before and after the one-year period. What test should the researchers run to determine if there is a difference in the growth between these groups?"
Between Subjects One-Way ANOVA
"Researchers want to test whether different kinds of noises in the sleeping environment affect stress level upon waking. They randomly assign 90 students into 3 groups of 30. All groups sleep for 8 hours in a controlled setting. Group 1 sleeps in silence (the control), group 2 sleeps with violent television programs on in the background, and group 3 sleeps with classical music playing in the background. Upon waking each subject is measured for the amount of stress hormones in their body. They are measured again later on in the day to see if their stress level has changed. What statistical test should the researchers run to tell whether different kinds of noises in the sleeping environment affect stress level upon waking?"
Between Subjects One-Way ANOVA
"esearchers want to test to see if a persons diet will affect their hair growth. Four groups of 40 randomly assigned participants are given four different types of diets for a month. Before they are put on these strict diets the researchers measure the persons natural diet and natural hair growth. The first group is put on a grain based diet. The second, on a protein based diet. The third, on a fruit based. The fourth, on a vegetable based diet. After a month the hair growth will be measured and compared between each of the four groups. What test should be ran?"
Between Subjects One-Way ANOVA
Oberlin college wants to compare the GPAs of students by department. What test should they use to compare the mean difference between the different majors?
Between Subjects One-Way ANOVA
An Oberlin professor taught 3 sections of introductory Spanish and noticed that student participation in each of the 3 sections seemed different. Students in the 9 am section seemed to pay attention less than students in the 4 pm section, who seemed to pay attention less than students in the 11 am section. The professor decided to test whether this perceived difference in participation presented itself in the students' midterm test scores, so she compared the average test grades for each of the three classes. She hypothesized that students in the 11 am section would do better on average than those in the 4 pm section, who would do better than those in the 9 am section. What type of test should she use to test her hypothesis?"
Between Subjects One-way ANOVA
Researchers wanted to test the effectiveness of three different generic drugs on pain relief. They drew from a pool of patients who had just had their wisdom teeth removed and randomly assigned 25 participants to each drug and 25 participants to a placebo in the form of a sugar pill. Participants filled out a 20 question survey designed to create an overall score describing the amount of pain that they were feeling. What statistical test should they use to determine which of the three drugs provided the best results?
Between Subjects One-way ANOVA
"Does Type of Food (1. a donut 2. a banana 3. chocolate bar) eaten before SAT test affect the performance score? Of a 450 students taking the SATs, 150 were given a donut, 150 were given a banana, and 150 were given a chocolate bar."
Between Subjects one-way ANOVA
"A group of researchers are looking to see if watching tv or being active on the computer screen before bed has an affect on how quickly you fall asleep. They assign 80 people to each group (watching tv, being active on the computer, and staring at a blank wall). Within each group, they have three different measures. The first is doing the activity for 10 minutes, the second is doing the activity for 20 minutes, and the third is doing the activity for 30 minutes. Which test would they use to see which activity keeps the participants up longer?"
Between subjects one-way ANOVA
"A group of researchers want to see whether the color of interior walls affects people's short-term memory ability. They randomy divide 120 participants into 3 groups. These groups are assigned to three conditions: memorize words in a red, a blue and a green room. In the end, researchers compare results from the groups. Which test would they use to test the effects of the colors?"
Between subjects one-way ANOVA
"The past 9 out of 17 winners on the TV show So You Think You Can Dance have been female, what test would you use to determine if female and male dancers differ in terms of the judge's scores?
C) Independent Sample t-test
What test would you use to compare the average GPA at Oberlin to all other private colleges in Ohio?
C) One sample t-test
Researchers want to know if political party affiliation in the US varies by race. What kind of test should they conduct?
Chi-square
A study is conducted to figure out when Oberlin Conservatory students give their most satisfying performance. However, if the researcher only visits the conservatory in the morning, what aspect of the data is being damaged?
External Validity
Is the male:female ratio in Research Methods 1 similar to the Oberlin College male:female ratio?
Goodness of FIt
"Jelly Belly produces variety boxes of their jelly beans and claim that 50% are traditional flavors, 20% are sour flavors, and 30% are brand new flavors. Selecting a variety box at random from the candy store, you see that it contains 36 traditional flavors, 20 sour flavors, and 24 new flavors. What test would you use to determine whether Jelly Belly's claim is valid?"
Goodness of Fit
How would you answer this question? 35% of all beer consumed by US college students is Miller Lite. A recent survey showed that 42% of all beer consumed at Oberlin is Miller Lite. Is Oberlin typical of US colleges?
Goodness of Fit
Oberlin College student health wants to test whether the amount of students who smoke cigarettes is comparable with the national average. Which test would you use?
Goodness of Fit
Oberlin Community Services on Food Distribution Day gave away 200 bags of onions, which test would you use to compare to the United State's Foodbank database on onion giveaways?"
Goodness of Fit
Researches know the percent of people in New York City who use public transportation to get to work. How does this compare to the amount of public transportation used to get to work in other cities in the US?
Goodness of Fit
What test would be used to answer the question: 5% of Lady Gaga fans faint when they see her at a live concert. How does this compare to the fans that have fainted at famous pop concerts throughout history?
Goodness of Fit
"Orville Orangenbacher" claims that 98% of his popcorn kernels pop. The national average according to FarmAgro Foods is 83% popped kernels. What test would you use to determine if Orangenbacher popcorn pops statistically better than average popcorn?"
Goodness of Fit Test
How would you test this question: Is the student body at Oberlin as racially diverse as the rest of the United States?
Goodness of Fit Test
You browse this week's board packet and notice a chart detailing all of OSCA's spending for this week. What test would you use to determine whether your Co-op's spending on non-food items is representative of all of OSCA's spending on non-food items?
Goodness of Fit Test
Oberlin wants to know whether the number of students that major in a language and study abroad is representative of the number of people in the entire student body who study abroad. What kind of test could the school use to analyze their data?
Goodness of fit test
What test t-test would you use to compare the average about of practice time for conservatory students versus non-conservatory students who also play an instrument?
Independent sample t-test
What test would be used to see if the difference between children with a single parent or two parents on state-based assessments is statistically significant?
Independent sample t-test
You want to compare how much TV an average 7 year old watches a day to how much an average 10 year old watches a day. What test would you use?
Independent sample t-test
What is a false description of situation sampling?
It involves studying behavior in the same locations
What is not an example of observation with intervention?
Naturalistic Observation
What is not a method to control reactivity?
Observation of physical traces.
An example of situation sampling is:
Observations of pigeon feeding are made when different types of bread (breadcrumbs, white, wheat) are strewn on the ground
How would you determine if on average the population in Texas has a higher rate of teen pregnancies thant the national average?
One Sample t-test
What test would you use to compare the average number of pounds of food thrown away by an Oberlin student to students at other American liberal arts schools? t
One Sample t-test
The Student Senate wishes to survey the Oberlin student population based on their transportation needs. During this research process, they wish to know how preferences for transportation to Cleveland differed between people requesting the service in the early morning (7-10), mid-morning/early afternoon (10-2), afternoon (2 - 5), evening (5-8), and late night (8-midnight). What statistical test would compare the central tendencies of each of these time slots on the matter of transportation to Cleveland?"
One Way ANOVA
Psychologists wanted to know if Oberlin students had higher or lower rates of depression than the general population of college age people. They created a scale to rank depression (1 being not depressed to 10 being very depressed). The mean for Oberlin students was 3.4 and the mean for the college age population was 4.2. The standard deviation of the Oberlin sample was 1.3 and they surveyed 124 students. What type of test would be used to see if Oberlin students are representative of the college aged population?
One sample t-test
What measurement scale involves ordering or ranking observations?
Ordinal
"Researches want to determine if a vegan diet has an effect on blood pressure. Blood pressure is taken from 200 omnivores before their switch to veganism. After following a year long diet (no cheating allowed at penalty of death), blood pressure is taken again. What t-test would be used to determine if there was a mean change in bloodpressure after the diet?"
Paired sample t-test
Observation with intervention involves the following:
Participant Observation, and Field Experiment
Do men and women differ in what size coffee they drink, small, medium, and large? How would you best analyze your data?"
Pearson Chi-Square
What test would be used to answer the question: is there any difference between how many male and female adolescents like the new Hannah Montana video game?
Pearson Chi-Square
Researchers asked boys and girls whether they would prefer to read a mystery novel or a fantasy novel. They want to know whether has gender has an effect on the type of novel that is preferred. What test should they use to interpret the data?
Pearson Chi-square
What test would you use if you wanted to look at the relationship betwwen the amount of sleep you get on an average night and your grades in school?
Pearson Chi-square
Ben and Jerry's wanted to determine if there was a relationship between preference of ice cream flavor and age group. Which test would they run to see if whether the participant was a child, a teenager, or an adult could predict which of the two ice cream flavors they preferred?
Pearson chi-square
What is NOT a prerequisite to imply a causal inference?
Random Assignment
The essential difference between field experiments and other observational methods is:
Researchers exert more control in field experiments when they manipulate an independent variable.
"What problem arises when subjects are aware of the presence of an observer?
Subjects "react" to the observer's presence and change their behavior, so their behavior may not represent their normal behavior.
"How do narrative records differ from other forms of recording and measuring behavior?
The classification of behaviors is done after the observations are made.
Give an example of a field expierement.
The observer is the receptionist of a hotel. When the customer turns around the observer performs a switch with another person. Obeserving if the customer notices the switch.
Researchers want to test a drug to see if it is effective. What would be a threat to the experiment's internal validity?
The researchers accidentally give a placebo pill to one of the subjects in the test group
"According to the answers from my three questions and the Anticipation Effect, a participant would be most likely to choose the answer [a, b, c] for this question."
a
What is an example of structured observation?
a researcher intervenes in order to exert some control over the events that are been observed
What is an example of mechanical subject loss?
an experimenter reads the wrong set of instructions.
What test would you use to compare how upset Village People fans and Parliament-Funkadelic fans are at Nicki Minaj on a 1-5 scale?
an independent sample t-test
What could be the underlying cause of a spirious relationship?
an unidentified third variable
What is block randomization good for?
assigning participants to conditions in random groups, and order conditions for each participant in a complete
The most important facor in dealing with observer bias is:
awareness of its presence
What test would you use to compare the average practice time of professional musicians versus conservatory student musicians?
b) independent sample t-test
What method is NOT used to combat observer bias?
being aware of the outcomes for previous similar studies
In a double blind procedure
both the participant and observer are blind to what treatment is being administered
Researchers would use a repeated measure design to achieve which of the following:
c) To account for the changes in participants' behavior over time
What test would you use to compare the blood pressure of the elderly at Kendal to the mean blood pressure of elderly people in the United States?
c) a one sample t-test
Demand characteristics are
cues that participant's use to guess what is expected of them and that can guide participants behavior.
When a research subject knows what behavior to show in order to give the researcher good results, the subject is exhibiting
demand characteristics
What is an effect under observer bias?
expectancy effects
External Validity is the
extent to which the results of a research study can be generalized to other settings
"A student has a history of lying. What is an example of an occurence of statistical observer bias?
in a survey of her class, a teacher assumes that this particular student has not honestly filled out the questionnaire and excludes it from her report to her principal.
"A sample of 28 people who read the New York Times daily were given a quiz on current events over the last 10 years and, on a scale of 1 to 10 scored an average of 8.0 with a standard deviation of 0.8. A different sample of 32 people who read the Washington Post daily were give the same test and score an average of 7.3 with a standard deviation of 1.1. What test should be used to analyze the data?
independent sample t-test
What test would you use to compare the average birth weight of females as opposed to males?
independent sample t-test
What test would you use to compare the number of ExCos that women take as compared to men?
independent sample t-test
What test would you use to compare the number of hours spent studying per week for law school students versus medical school students?
independent sample t-test
The degree to which two independent observers agree is referred to as:
interobserver reliability
What is a major benefit of using event-based sampling in research?
it allows you to record unpredictable phenomena
If the two female student observers on the subway from Piliavin, Rodin, & Piliavin (1969) had had differing observations of the people on the subway, this would indicate they have:
low interobserver reliability.
When a subject fails to complete the experiment because of an equipment failure this is known as
mechanical subject loss
After reading several similar studies that demonstrate significantly different effect sizes for the same dependent variable, a researcher decides to examine the entire existing body of research investigating that variable in order to draw a conclusion about the effect size. The technique the researcher will employ is called:
meta-analysis
When intact groups formed prior to the start of the experiment are randomly assigned, the result is
non-comparable groups
which test would you perform to compare the average calorie intake of college students to the U.S average person calorie intake per day
one Sample T-Test
"Studies have shown that talking on a phone while driving impairs driving performance. A national scale experiment has shown that on a scale from 1 to 10 (1 being the worst and 10 being the best), the mean driving performance while talking on a phone was 4.3 with a standard deviation of 1.5. This study was replicated in Oberlin by psychology department. 50 drivers were tested and the mean was 5.6 with a standard deviation of 2.0. If we were to test that Oberlin sample is representative of the US population, which test would we use?
one sample t-test
What test would you use to compare the average weight of 50 year old females from California as opposed to the national average for 50 year old females?
one sample t-test
What test would you use to compare anxiety test scores of parents and their children?
paired sample t-test
What test would you use to test whether, on average, children or their parents eat more vegetables?
paired sample t-test
Describe a situation: random groups design employed?
participants in a drug trial study are randomly assigned programs of either the real drug or a placebo sugar tablet control.
Which of the following is a type of unobtrusive measure?
physical traces
Complete and incomplete repeated measures designs differ in the specific ways in which they control for
practice effects
Which of the following is a threat to internal validity?
randomly assigning intact groups
"A person participating in a study is asked to type words on sitting at a computer in silence, then sitting while listening to music, then while standing, and finally standing while listening to music. The person is participating in a:
repeated measures design study
What is the best way to determine the reliability of an experiment:
replicate the experiment
Forty high school students volunteered to be part of a study. They were randomly divided into two groups of 20. Half were placed in an Honors Biology course and the other group was placed in an AP Biology Course. At the end of the study both groups took the AP test to evaluate whether the AP Biology course helped prepare students for the test. By the time of the AP test 17 of the honors students and 11 of the AP students showed up to take the test. The AP students scored higher but the study was determined to be an inaccurate indicator of the amount the AP course prepared the students. What phenomenon caused this study to be invalid?
selective subject loss
What does effect size measure?
strength of relationship between variables
An independent variable in which a characteristic or trait varies among individuals.
subject variable
What is not an advantage that researchers gain when they use a repeated measures design?
the researchers want more practice effects
Why are repeated measure designs good for conduction an experiment?
they administer all conditions in the experiment to each participant
observer bias happens when?
uses structured observation and determines which behaviors they choos to observe, and when observers expectations about behavior lead to systematic errors in identifying and recording behavior
When does differential transfer occur?
when the effects of one condition influence the performance in subsequent conditions
