QUIZZES before MIDTERM#1 Flashcards
In studying the results of his most recent exam, Professor Simmons noticed that although almost all students got between 65 percent and 80 percent on the exam, one student answered 98 percent of the questions correctly. Scientists refer to this type of extreme data as a(n):
an outlier
If we created a histogram of sample data and noticed that most of the scores fell in the middle of the distribution with smaller numbers in either tail, we would probably refer to this as a _____ distribution.
normal distribution
Which of the following is a continuous variable?
a) Likert rating for a restaurant (choose one to four stars)
b) The number of coffees purchased at a local coffee shop
c) Driving speed
d) Left- or right-handedness
c) driving speed
Continous variables are those that can take intermediate values. Since people cannot buy half a coffee, cannot be half right or left handed, and in our likert scale cannot choose 3.5 stars, these are all discrete variables.
Driving speed, however, can take intermediate values (for example, one can imagine driving at 65.4 kilometers per hour).
Daniela asked students in her introductory psychology class to report their majors. Her data was as follows: psychology, psychology, psychology, sociology, psychological, criminal justice, psychology, education. In this example, the individual, untransformed reports of major are:
a) normally distributed
b) histogram points
c) frequency scores
d) raw scores
d) raw scores
Daniela has ‘untransformed’ data meaning she hasn’t done anyting with the raw data yet.
One of the ways that graphs may mislead is by assuming that some value between the data points lies on a straight line between those data points. This is referred to as the _____ lie.
interpolation lie
For which of the following variables would you need to use midpoints on a histogram?
a) The number of ant colonies in a park
b) The weight of animals found in Stanley Park
c) Results of a coin toss
d) Type of animal at the Vancouver Aquarium
b) weight of animals found in Stanley Park
You will need to use midpoints any time you use a continuous variable. You will also use midpoints for any grouped frequency tables. Since weight is both a continuous variable and a large variable that will involve grouping, you will need to use midpoints.
Jackson wants to graph the relation between scores on the SAT and first-semester grade-point average in college. What type of graph should he use?
Scatterplot
When we are trying to display a relationship between two variables, it is best to use a scatterplot
Imagine that you calculated Body Mass Index (BMI) for a group of college students and created the grouped frequency table below:
BMI Frequency
40-44.99 1
35-39.99 4
30-34.99 * 6*
25-29.99 10
20-24.99 20
15-19.99 3
If you decide to depict this data with a histogram, what would be the midpoint for the top interval?
42.5
NOT 42.49
(40 + 45 divided by 2 = 42.5 exactly)
Recall that when we say the interval is between 40 - 44.99, we really mean 44.9999999 onto infinity (its upper limit). Thus, the midpoint is 42.5, not 42.99.
Suppose that, as part of a larger survey, we measure the variable “year in school.” The variable has the possible values of freshman, sophomore, junior, or senior. These possible values are called:
levels (or conditions)
The different values that a variable can take are called the ‘levels.’
College students at 50 campuses around the country were polled to find out how many students own smartphones. The small representative group of students is called a:
a sample
(the population would be called ‘all the college students’ at every college)
Psychologists studying infant memory want to determine at what age babies can remember specific events. An experimenter uses several puppets to demonstrate a series of actions while the infant watches. After a delay, the experimenter records how many of the actions the child imitates when playing with the puppets. The dependent variable is the:
number of imitation actions
Recall: the dependent variable is what we MEASURE
A market research company is studying the online streaming television purchase of 2000 randomly selected families. They then use that information to make inferences about the viewing habits of all families in Canada. They are utilizing:
inferential statistics
a between-group research design
a within-group research design
descriptive statistics
Inferential statistics
A bar graph is appropriate if the independent variable is THIS and the dependent variable is THIS.
- nominal
- scale (interval)
THESE studies are useful for simply establishing an association between variables but do not provide information regarding cause and effect.
Correlational
(Not experimental or between-groups or within-groups)
Because we do not manipulate a variable in correlational studies, we cannot establish cause and effect. Only experiments can establish causal relationships.
Note that between-groups and within-groups studies are types of experiments.
If we believe we are creating a measure of personality but in fact it measures intelligence, we would say that our measure lacks:
VALIDITY
Recall: Validity is interested in whether the test measures what we THINK it measures. In this case, we think the test is measuring personality but it is measuring intelligence.
Reliability is interested in consistently in the measure across time. This measure could be reliable (you could get consistent results) without being valid.
Imagine that you collected eye color data for 500 people. Would you present individual data values or grouped data when creating a frequency distribution?
a) Individual, because the number of possible eye colors is limited
b) Grouped, because data for 500 people would be hard to summarize if ungrouped
c) Grouped, because it is always preferable to presenting individual values
d) Both individual and grouped data would work in this situation
A) individual
Eye colours only come in so many shades - blue, brown, green, etc. Thus, you would not group the data (even though there are 500 responses!). Grouped data is best when there is a large set of continuous values.
Suppose a researcher randomly assigns participants to one of three groups and examines their ability to solve complex mathematical problems under conditions of no noise, continuous noise, or random noise. What type of research design is the researcher using?
a) between-groups
b) within-groups
c) repeated-measures
d) correlational
a) BETWEEN GROUPS
Since participants are only assigned to ONE of the conditions, this is a between-group design.
Note that repeated-measures is another term for within-group designs.
The open science practice that involves outlining the research design and analysis plans before conducting the study is called:
‘preregistration’
literally on a science website, you enter your experiment details.
Measuring a person’s weight in pounds would involve using a(n) THIS variable and is a THIS observation.
- RATIO
- CONTINUOUS
Recall : Because weight has a true zero point (zero = absence of weight), this is a ratio variable. Interval variables do not have a true zero point (such as temperature in Celsius). Both interval and ratio variables are considered SCALE variables.
Weight can also take on a full range of values. For example, someone can weight 62. 456 kg.
When creating histograms the x-axis typically represents THIS, while the y-axis represents THIS.
a) midpoints; reaction times
b) values or intervals; the sum of squares
c) frequencies; the sum of squares
d) values or intervals; frequencies
D) values or intervals ; frequencies
Recall: Recall that for histograms, frequency is ALWAYS on the y-axis! The different intervals or categories will go on the x-axis. This is what differentiates a histogram from a bar graph.
**A researcher collects data on car accidents over time. Although he only has data for the years 1986 - 2004, and 2008 - 2020, he adds a straight line connecting the number of accidents between 2004 and 2008. What type of lie does this demonstrate?
interpolation
A researcher is studying the effect of age on motivation in school, with the belief that older adults tend to be more motivated in higher education. She determines the age of her participants and then asks them to rate their motivation in the fall and spring semesters. What is the independent variable in this study?
age
A researcher investigated the relationship between amount of food consumed (measured in calories) and reaction time on an attention task (measured in ms). What type of graph should the researcher use to illustrate their finding?
scatterplot
In this case, we have two scale variables. Consequently, it is best visualized as a scatterplot.
The number of times a person eats fast food each week would be a(n) THIS variable.
RATIO & DISCRETE
It is ratio because zero is the absence of going out to eat fast food (a true zero point).
You would like to see the effect of language on categorization. You have bilingual students complete a categorization task in their native language as well as their second language. You then compare the results. What type of design is this?
Within-groups
Between-groups
Random assignment design
Correlational research
Within-groups design
Recall : the participants are exposed to each level of the independent variable
A grouped frequency table with discrete data has the following intervals: 1 - 8, 9 - 16, and 17 - 24. The midpoints would include:
4.5, 12.5, 20.5
This histogram represents the distribution of the number of years of education completed by twins who attended the 16th Annual Twins Day Festival in Twinsburg, Ohio, in August of 1991.
Approximately how many people at the festival scored as 12 or 13 years of education?
20
40
60
80
80
A researcher would like to see if asthma symptoms improve after being exposed to an exercise program. The researcher recruits 48 asthma patients that either participate in an exercise or control program. Patients were asked to rate their symptoms at regular intervals using a scale from “0 – no symptoms” to “20 – maximum asthma symptoms” and the change in asthma symptoms over the course of the program is recorded. The average change was -5.82 of the exercise group and 1.83 for the control group.What is the sample in this study?
the 48 asthma patients
(the population would be ALL asthma patients)
A z score is defined as the:
a) mean score
b) number of standard deviations a score is from the mean
c) square of the difference or deviation of the score from the mean
d) square of the mean score
B) number of standard deviations a score is from the mean
Note the formula:
This formula demonstrates that the z score is looking at how far the score is from the mean, divided by the standard deviation. Thus, it calculates the number of standard deviations from the mean.
As sample size increases, the mean of the sampling distribution:
a) remains unchanged
b) decreases
c) less accurately represents the mean of the population
d) increases
A) REMAINS UNCHANGED
The mean of the sampling distribution equals the mean of our population. We can describe that in this formula:
See also the Characteristics of the Distribution of Means.
How is a distribution of sample means different from a distribution of raw scores?
a) The distribution of the means is more tightly packed.
b) The distribution of means has a greater standard deviation.
c) The distribution of means cannot be plotted on a graph.
d) All of these are true
A) more tightly packed
Imagine that you sample 30 students and find that their average LSAT score is 165. You want to know the percentile for this group of students. What type of distribution will you need to use to determine this value?
a) a distribution of variance
b) a distribution of deviations
c) a distribution of scores
d) a distribution of means
D) DISTRIBUTION OF MEANS
Imagine a statistics exam has a mean of 42 and a standard deviation of 12. Tia has a z-score of 1.27. What is her raw score?
57.24
A school psychologist would like to compare their patients’ Verbal SAT scores to the population. The Verbal SAT test has a mean of 505 and a standard deviation of 110. The school psychologist finds his 10 patients have an average Verbal SAT score of 482 with a standard deviation of 40. Calculate the z statistic for the patients.
-1.82
-0.21
-0.56
-0.66
If the variance of some data is 2.83, what is the standard deviation?
1.68
8.01
0.28
28.30
1.68
Pia completes a happiness questionnaire. If the mean for the population is 66 with a standard deviation of 8.7, what percentile is Pia if she scored a 57.3?
32
34
66
16
16th percentile
Arianna has just completed her Grade Record Examination test. She would like to determine her z-score. Which of the following formulas should she use?
1ST FORMULA
In this case, we need to compare a raw score (X) to a distribution of scores. Consequently, we need to use the formula for a z-score based on a distribution of scores.
A teacher would like to compare her classes standardized English scores to the population. This test has a mean of 100 and a standard deviation of 12. Her class consists of 34 students and they scored 110 on the test. Based on this information, what value should the teacher use for the standard error (rounded to two decimal places)?
3.46
10
2.06
12
2.06
PRACTICE TEST #1:
The distribution of means based on a sample size of 20, pulled from a population distribution with a mean of 100 and a standard deviation of 15, would have a standard error of:
1.33.
3.35.
5.16.
5.33.
A standardized test contains a mean of 25 with a standard deviation of 5. If Harry scores 30 on the test, what is his percentile?
34
16
84
50
This figure depicts gas prices for the month of August from 1976 to 2004. (Data were extracted from the Bureau of Labor Statistics Web site.)
A)histogram
B)pareto chart
C)line graph
D)time series plot
D) TIME SERIES PLOT
Imagine that a test has an average of 29.48 and a standard deviation of 4.53. What is the z score of a person who obtains a score of 19? (Round to two decimal places)
-2.31
