statistics exam 1
central tendency
- a single value used to represent the typical score in a set of scores
median
-cuts a ranked distribution in half -If N is odd, there is one middle score. If N is even, find the two middle scores and find the midpoint.
7
10, 6, 6, 4, 2, 1, 10, what is the value of N
range interquartile range variance standard deviation
4 of the many ways to summarize the variability of a distribution:
164
A cognitive psychologist reads a list of 20 adjectives to a sample of eight people and asks them to recall the words after one week. The number of words remembered by each participant was 5, 4, 17, 5, 4, 6, 13, and 10. what is the sum of squares:
gender of the study participants
A community psychologist is interested in the civic engagement of men and women in a large urban area. Focusing on a specific downtown neighborhood, he gathers data on the number of male and female volunteers who participated in the last six citywide cleanup events. Consider the description of the civic engagement design; the quasi-independent variable in this example is the:
an experimental design; use random assignment for the independent variable
A community psychologist is interested in the civic engagement of men and women in a large urban area. Focusing on a specific downtown neighborhood, he gathers data on the number of male and female volunteers who participated in the last six citywide cleanup events. The civic engagement design, as it is described, could never be turned into _____ because it could never _____.
number of citywide cleanup volunteers.
A community psychologist is interested in the civic engagement of men and women in a large urban area. Focusing on a specific downtown neighborhood, he gathers data on the number of male and female volunteers who participated in the last six citywide cleanup events.Consider the description of the civic engagement design; the dependent variable in this example is the:
mode
A health psychologist is interested in knowing whether the people in the local community exercise on a regular basis. She collects data from 100 local residents and classifies them as regular exercisers and nonregular exercisers. Which measure of central tendency would be appropriate to report?
ratio
A nurse measures how many minutes patients must wait before being seen by the triage nurse after they enter an emergency room. Wait time is measured at what level (nominal, ordinal, interval, or ratio)?
interval
A researcher in the area of eating disorders has created a 50-item inventory to assess risk of developing an eating disorder. The inventory has been standardized to yield scores ranging from 10 to 90. What type of measurement does the inventory utilize? (nominal, ordinal, interval, or ratio)
nominal
An administrator surveys the hospital's psychotherapists to determine the most commonly utilized type of therapy provided for its patients. Type of therapy is measured at what level? (nominal, ordinal, interval, or ratio)
1.00
Any given outcome cannot have a probability higher than:
54
Charley has a data set that includes the numbers 2, 3, 4, and 5. If he uses the statistical formula ΣX2, what is the number Charley obtains?
draw conclusions about cause and effect
Experimental designs allow researchers to:
3.47
For a given set of sample data, the sum of the squares equals 45.13 and the sample size is 14. What is the variance? s2=
1.86
For a given set of sample data, the sum of the squares equals 45.13 and the sample size is 14. what is standard deviation
median
For skewed distribution or open-ended distribution you use :
by dividing by the standard deviation
How would a researcher transform a deviation score into a z score?
Both ranges would contain an equal percentage of scores.
In a normal distribution, you would expect to see a greater percentage of scores falling within which of these ranges?
cases
In quasi-experimental designs, _____ are classified into different groups based on a characteristic they already possess.
D. Ashley collects data on people's reaction times on a task.
In which of these examples would one use the standard deviation? A. Kali collects data on people's religious affiliations. B. Brooke collects data on people's political affiliations. C. Lacey collects data on students' class rankings. D. Ashley collects data on people's reaction times on a task.
Jeanie and Bert have the same average, but Bert shows more variability.
Jeanie and Bert bowl four games each. Jeanie's scores are 120, 120, 120, and 120, whereas Bert's scores are 100, 110, 130, and 140. Based on these sets of scores, which of these shows more variability
interval and ratio level data
Measures of variability are appropriate for use with
samples, populations
Most statistical techniques in the behavioral sciences have been created to test _____ directly and _____ indirectly.
can be used when researchers collect nominal data
One advantage of the mode over both the mean and median is that the mode:
SS
Sum of square deviations symbol
ordinal
The World Health Organization ranked the health systems of its 191 member states in its World Health Report. These health system rankings would be considered what scale of measurement? (nominal, ordinal, interval, or ratio)
ratio
The admissions committee at a college does not distinguish between different types of high school extracurricular activities. As far as it is concerned, being a member of the tiddlywinks club is equivalent to being student council president. On the admission form to the college, applicants are asked to report the number of extracurricular activities in which they were involved in high school. The college is measuring extracurricular activities at what level (nominal, ordinal, interval, or ratio)?
parameter
The developmental psychologist reports to the local school board saying, "The average reading score for all second-grade students on this standardized test is 175.42." Does 175.42 refer to a statistic or a parameter?
-1.645
The extreme 5 percent of scores in the lower end of a normal distribution is established with a z score
dependent variable
The outcome variable is another name for the:
always be equal to zero
The sum of a set of deviation scores will:
independent variable
The variable that is controlled or manipulated by an experimenter is the:
modality skewness kurtosis
Three aspects of shapes and frequency distributions to describe :
13.59
What percentage of scores fall between 1 and 2 standard deviations above the mean?
35 percent
What percentage of scores would fall between the mean and z on each side of the distribution if one is looking for the middle 70 percent of scores?
50th
What percentile rank is associated with the mean of a normal distribution?
.96
What would the standard deviation be if the sample size were 50?
sample size minus 1
When calculating the sample variance, the sum of the squared deviation scores is divided by the:
50
When given a list of 20 words, Tonya is able to recall 7 words. If the average number of words recalled by other participants in the study is also 7, what is Tonya's percentile rank?
standard deviation
Which is a measure of variability A. mean B. mode C. median D. standard deviation
range
Which measure does not provide information about central tendency?
interval
Which of the following levels of measurement allows researchers to use the most informative measure of central tendency?
set 1
Which of the following sets of scores has more variability? Set 1: 5, 10, 15, 20 Set 2: 10, 11, 12, 13
The standard deviation is the square root of the variance.
Which of these best describes the relationship between the variance and the standard deviation?
standard score (z score)
a raw score expressed in terms of how many standard deviations it is from the mean
outlier
a score that is very different from the rest of you're data
variables
are characteristics that change or have different values for different individuals,
quasi- experimental studies
are similar to experimental studies except there is no random assignment. predefined groups. The variable that defines the groups is the grouping variable. Confounding variable - predefined groups. ex: males and females on levels of aggression. this is 2 predefined groups: male and female.
cases
are the subjects ( participants) who are measured on the variables, what you are collecting the data from
correlational studies
can suggest that a relationship exists between variables. However, it CANNOT prove that one variable causes a change in another. If there are no associations between the variables tested, then there are no causal connections between them. Ex: relationship between height & weight, ex: relationship between aggressive television and the children's behavior. Program on tv: predictor variable. Children behavior: criteria variable or outcome variable.
continuous numbers
can take on values between whole numbers ( fractional) -continuous numbers have real limits. Ex: real limits of 67 : 66.5---67.5 ex: real limits of 65-70 : 64.5---70.5
nominal
categories. You might assign them a number, but they don't mean anything, it is just numbering the list, like names. Ex: zipcodes
constant remains the same, variable takes on different values
difference between variable and constant
ratio
equal distances between numbers on the scale but has a meaningful zero point which allows ratio-type comparisons. Ex: asking how much money is in your pocket, it could be zero. Ex: how many parking tickets have you gotten. Ex: number of facebook friends. Ex: time. Ex: weight and height, no you can't be 0 lbs, but the scale has a 0.
interval
equal distances between numbers on the scale but has no meaningful zero point. Ex: temperature- fahrenheit, it could be zero degrees, but doesn't mean there is an absence of temperature. Ex: standard scores: ACT scores , IQ scores,
interval
ex: if the zero has zero point that is actually used, or doesn't have to have a zero at all
ordinal
ex: list in order you're fav foods
nominal
ex: list you're favorite foods
ratio
ex: the zero in absence, height and weight
it depends on the shape of the distribution
for interval or ratio data, you use which measure of central tendency
mode
for nominal data you use which measure of central tendency
use mean (although the mean, median, and mode are the same value in normal distribution) bc you need the mean to do further statistics.
for normal distribution you use which measure of central tendency
median
for ordinal data you use which measure of central tendency
median
for skewed distribution you use which measure of central tendency
x= zσ+ μ
formula for computing value of x with the z score
z= x-μ/σ
formula for computing z score for any x value.
f
frequency symbol
experimental studies
groups are measured on 2 variables with random assignment.
3.16
if SS = 100 and N = 11, what is s?
negative
if you're mean is lower than you're mode, it will be pulled towards you're tail to the left so it is:
mean
in a skewed distribution which is not a good representation bc it gets influenced by outliers and is pulled out towards the tail
inferential statistics
includes methods for making inferences about a larger group of individuals (population) on the basis of data actually collected on a much smaller group (Sample). predictions about the population.
explanatory variable
is a generic term for the variable that causes influences or precedes the other. Called "predictor variable" in experimental design; and "grouping variable" in quasi-experimental design. (x)
outcome variable
is a generic term for the variable that is caused, influenced, or comes after the explanatory variable. Called "criterion variable" in correlational design; "dependent variable in experimental and quasi-experimental design. the variable you are measuring. (y)
cofounding variable
is an outside influence that changes the effect of a dependent and independent variable.
lower
is mean is _____ than mode you are dealing with a negatively skewed distribution
raw score distribution
listing of your raw scores in no particular order. Ex: your exam grades this semester in no order.
N
number of case symbol
ordinal
ordered or ranked. Ex: position on a waitlist, class ranks. We know where someone falls, but doesn't know the numbers between the orders, like first place and second, you don't know how close the 2nd place person came to first place. Ex: grades (A, B, C, D, F)
X
outcome variable symbol
50 %
percentile rank for median
μ
population mean symbol
p
probability symbol
P
proportion symbol
high to low
range and interquartile range are often reported as two numbers:
standard deviation
raw scores are expressed in terms of :
descriptive statistics
refer to procedure for organizing, summarizing and describing data, says things about the sample, for example: the sample's mean
modality
refers to how many high points there are, a distribution with 2 or more peaks
kurtosis
refers to how peaked ( leptokurtic) or flat (platykurtic) the distribution is, it is the sharpness of the curve A common shape is bell-shaped or "normal" curve. It is perfectly symmetrical, unimodal, and neither too peaked nor too flat (mesokurtic)
variability
refers to the "spread" of scores in a distribution, how much they vary.
skewness
refers to whether the distribution is symmetrical.
M or x̅
sample mean symbol
s
sample standard deviation symbol
left: negative skew right: postive skew
skewed to the left is __________ or skewed to the right is __________
σ
standard deviation symbol
z scores
standard scores are commonly called ________
constants
stay the same
∑
summation sign symbol
true
t/f : the variability statistics will always underestimate variability parameters ( biased estimate)
true
t/f : the variability within a population is greater than the variability within a sample.
discrete numbers
take whole number values only - never fractional -nominal and ordinal variable are always ________ -interval and ratio variables may be _____ or continuous.
standard deviation
tells us how much scores deviate from the mean average. Advantage : It is easier to interpret the variance bc it is the same units as the original data. Also, it uses all of the scores so it isn't heavily influenced by outliers. 1. Find the variance 2. Take the square root of the variance
mean
the "average"
variance
the average of the squared deviations from the mean. Advantage : uses all of the scores so isn't heavy influenced by outliers. Disadvantage : difficult to interpret. square Units
the mean
the middle of the curve is :
mode
the score that occurs with the highest frequency in the distribution of scores. It is reflected by the peak(s) of a simple frequency distribution. appears most often
range
the simplest measure of variability, high score minus low score. Disadvantage: not very stable bc it uses only two scores and therefore is heavily influenced by outliers.
experimental studies
this is an example of : show a group of children aggressive television - experimental group. Show a group of children a semi aggressive- control group.
an inferential statistic
uses a sample of cases to draw a conclusion about the larger population.
interquartile range
uses only the middle 50% of the scores. High minus low of the middle 50% of the distribution.
σ^2
variance d (variances are squared values ) symbol
its always below, if someone scores at 30% percentile, they are below the mean, 30% of the scores are below theirs.
what is percentile rank
experimental is randomly assigned
what is the difference between experimental and quasi-experimental studies.
Parameters are numbers that summarize data for an entire population. Statistics are numbers that summarize data from a sample.
what is the difference between parameters and statistics ?
0-1, 0: 0% chance it will happen, 1: 100% chance it will happen
what is the range of probability values?
unbiased estimate
when calculating variance and standard deviation on a sample, a correction is made in the formula to yield an _________ of the population of variance.
it only takes in account 2 numbers, the highest and the lowest.
why is the range unstable to calculate variablity
nominal and ordinal
you can only use a bar graph for
interval or ratio
you can only use histogram or polygon for
correlational
you cannot define cause and effect from a _____ study
x
you're ____ variable is the first variable you use to make a prediction
