Search
Create
Log in
Sign up
Log in
Sign up
Psyc 300 Exam 1
STUDY
Flashcards
Learn
Write
Spell
Test
PLAY
Match
Gravity
Chapters 1-5
Terms in this set (92)
statistics
set of methods and rules for organizing and interpreting observations
concerns: anxiety and value
descriptive
type of statistic - summarize, organize, and simplify data
inferential
type of statistic - techniques that allow us to study samples and make generalizations about the population
sampling error
amount of difference between a sample value and a population value that becomes an issue when trying to use a sample to represent an entire population
experimental
research design - manipulate IV, randomly assign subjects
quasi experimental
research design - manipulate IV, no random assignment of subjects
non experimental
research design - no manipulation of IV, no random assignment of subjects
operational definition
set of operations for measuring a construct that defines the construct in terms of the resulting measurements
nominal
label and categorize data
ordinal
category and order
interval
category and order and equal size intervals (arbitrary zero point)
ratio
category and order and equal interview with an absolute zero point
discrete
separate, indivisible categories; no values exist between neighboring categories
continuous
infinite number of possible values fall between any two observed values
real limits
boundaries of intervals for scores on a continuous number line - halfway between the scores. EG 4 has 3.5 (lower) and 4.5 (higher)
frequency distribution
organized tabulation of the number of the individuals located in each category on the scale of measurement
proportion
fraction of the total group that is associated with each score. (also called relative frequency)
percentile rank
percentage of individuals in the distribution with scores at or below the particular value
percentile
score that has a particular percentile rank
cumulative frequency
(cf) - number of individuals who are located at or below each point in the distribution
cumulative percentage
is equal to the percentile rank [rank = cf/N] - always associated with the upper real limit of the score
interpolation
process used to estimate intermediate values that are not explicitly present in the given table
grouped frequency distribution
used when a set of data covers a wide range of values
range
calculated by subtracting the LRL of X min from the URL of X max
simple widths
2, 5, 10, 20, 50
bar
[graph] - discrete data; bars with space between
histogram
[graph] - continuous data; bars come down to X axis at LRL and URL
line
graph - IV on the X axis; DV on the Y axis
normal
shape - bell shaped curve; specific probabilities at each point on the curve
skewed
shape - scores pile up at one end with a few extreme scores in the other end.
positively
______ skewed - extreme tail points to the positive end
negatively
______ skewed - extreme tail points to the negative end
kurtosis
a concentration - relative to the normal distribution - of scores in the center, shoulders, and tails
mesokurtic
normal kurtosis
platykurtic
more scores in the shoulders and fewer in the center and tails than normal
leptokurtic
more scores in center and tails with fewer scores in the shoulder than normal
inferential statistics
The process of using sample data to answer general questions about a population is called
positively
In a given distribution, median =26, mean =29 and mode =24. This distribution is probably _____ skewed
bar
What kind of graph would you use to represent the frequency of aggressive behaviors (e.g. teasing, hitting, gesturing)in a preschool playroom?
mean
The value of one score in a distribution is changed from x=20 to X=30. Which measure(s) of central tendency is(are) certain to be changed?
standard deviation
The football team's punter wants to determine how consistent his punting distances have been during the past season. Which of the following should he compute?
far above the mean in the extreme right side
A z score of z=+3.00 indicates a location that is
SS
the sum of squared deviation scores
variance
- average squared distance from the mean
- SD squared
- inferential statistics
standard deviation
the square root of the variance that provides a measure of the distance from the mean
- approx. avg. distance from mean
- most commonly used
- most important
- uses mean as point of reference
- uses all scores
sign; magnitude
The ______ of the z-score tells whether the location is above (+) or below (-) the mean, and the _____ tells the distance from the mean in terms of the number of standard deviations.
statistic
a sample value
parameter
a population value
mean, median, mode
measures of central tendency
mode
- easy to compute
- only measure of central tendency that can be used with NOMINAL level of measurement
- tells about the distribution shape
mean
preferred if the distribution is not skewed, all scores are available, interval/ratio levels of measurement
median
- divides the distribution in half
- 50th percentile
- skewed distribution
- ordinal or higher levels of measurement
mode < median < mean
positively skewed shape/central tendency
mean < median < mode
negatively skewed shape/central tendency
mean=median=mode
normal shape/central tendency
variability
is important for descriptive purposes and inferential purposes
SIQR
= (Q3-Q1)/2
- focuses on middle 50% of the scores
- typically use with the median
- at least ordinal level of measurement
degrees of freedom
(n-1).
- used to compensate for fact that sample SD tends to underestimate population SD
- lose when using M to calculate sample SD
extreme scores, sample size, open ended distribution, stability under sampling
factors that affect variability
extreme scores
range - large influence
SIQR - not influenced
SD - influenced
sample size
range - yes
SIQR - relatively unaffected
SD - relatively unaffected
open ended distribution
range - can not be determined
SIQR - only measure that can be used
SD - can not be determined
stability under sampling
range - unstable
SIQR - reasonably stable
SD - stable
z score
finding the location of a single score in a distribution rather than describing a whole distribution
(x-mu)/sigma
z-distribution
created by changing every X in a distribution to a z score.
- same shape as original X distribution
- central tendency mean (mu Z)=0
- variability (std dev z) =1
population; sample
Although research questions typically concern a __________, a research study typically examines a __________.
descriptive
Statistical techniques that summarize, organize, and simplify data are classified as __________.
ratio
Determining a person's reaction time would involve measurement on a(n) __________ scale of measurement.
ratio
After measuring a set of individuals, a researcher finds that Bob's score is three times greater than Jane's score. These measurements must come from a(n) __________ scale.
continuous
A variable that has an infinite number of possible values between any two specific measurements is called a(n) __________ variable.
true
The goal of descriptive statistics is to simplify, summarize, and organize data. (T/F)
true
A recent report concluded that participants given a diet containing oat bran had lower cholesterol levels than participants on a similar diet without oat bran. For this study, cholesterol level is the dependent variable. (T/F)
false
Last week the three major networks were ranked as follows: CBS first, NBC second, and ABC third. This is an example of measurement on a nominal scale. (T/F)
false
For any set of scores, EX2 = (EX)2. (T/F)
false
For the following scores, (EX)2 = 30. Scores: 1, 2, 3, 4 (T/F)
ten percent scored higher than helen
Helen's percentile rank on a math exam was 90 while Paul's percentile rank was 30 on the same exam. We may say, therefore, that
true
One purpose for central tendency is to find a single score that can serve as a representative value for an entire distribution (T/F)
false
When you calculate a weighted mean, its value will be closer to the mean of the sample with the smaller sample size (T/F)
true
It is impossible to compute the mean for data that have been measured on a nominal scale (T/F)
false
The mean is considered to be the "balance" point for a distribution because exactly half of the scores are located above the mean and exactly half are below the mean (T/F)
true
Extreme scores in a distribution are more likely to affect the value of the mean than the value of the median (T/F)
true
A professor recorded the academic major for each student in an introductory psychology class. If these data were organized in a frequency distribution table, the first column would be a list of academic majors (T/F)
true
In a grouped frequency distribution table, all of the class intervals should have exactly the same width (T/F)
false
There is enough information in a grouped frequency distribution table to obtain a complete listing of the original set of scores (T/F)
true
The class interval of 25 - 29 has real limits of 24.5 and 29.5 (T/F)
true
A professor records the height (in inches) for each student in a class. If these data are presented in a frequency distribution graph, it would be acceptable to use a histogram (T/F)
smaller
_____ variability gives better chance of making accurate predictions about a population from a sample (smaller/greater)
true
A positive z-score always corresponds to a score greater than the mean (T/F)
true
Transforming X values into z-scores will not change the shape of the distribution (T/F)
true
Whenever a population is transformed into z-scores, ∑z = 0 (T/F)
false
In any population of scores, at least one individual will have a z-score of zero (T/F)
false
If a population of N=10 scores is transformed into z-scores, there will be five positive z-scores and five negative z-scores (T/F)
;