Discovering Statistics Using R – Chapter 1 – Flashcards
75 test answers
Unlock all answers in this set
Unlock answers 75question
Binary variable
answer
A categorical variable that can take on one of two categories
Unlock the answer
question
Boredom effect
answer
Participants may perform differently in the second condition because they are tired or bored from having completed the first condition
Unlock the answer
question
Categorical variable
answer
A variable that can take on one of a limited, and usually fixed, number of possible values
Unlock the answer
question
Central tendency
answer
The centre of a distribution. Three common measures of central tendency are mean, median and mode.
Unlock the answer
question
Confounding variable
answer
An extraneous variable in a statistical model that correlates (directly or inversely) with both the dependent variable and the independent variable
Unlock the answer
question
Content validity
answer
aka Logical validity, refers to the extent to which a measure represents all facets of a given construct
Unlock the answer
question
Continuous variable
answer
A variable that gives a score to each entity and can take on any value on the measurement scale that we are using / Two types are Interval variables and Ratio variables
Unlock the answer
question
Correlational research aka
answer
Cross-sectional research
Unlock the answer
question
Counterbalancing
answer
A method for controlling order effects in a repeated measures design. Randomization is used to determine the order in which conditions are completed.
Unlock the answer
question
Criterion validity
answer
A measure of how well a variable or set of variables measures what they claim to measure. Ideally this is assessed by relating outcomes to known real-world observations
Unlock the answer
question
Cross-sectional research
answer
Observational research where we observe what naturally goes on in the world without directly interfering with it
Unlock the answer
question
Dependent variable
answer
A variable (often denoted by y ) whose value we suspect depends on that of another / Proposed outcome / Outcome variable
Unlock the answer
question
Discrete variable vs. Continuous variable
answer
The distinction between a discrete and continuous variable can be blurred. Age is continuous, but usually described in discrete terms. The number of children is discrete, but the average number may be meaningfully described in continuous terms.
Unlock the answer
question
Ecological validity
answer
A measure of how much the methods, materials and setting of the study approximate the real-world that is being examined
Unlock the answer
question
Experimental hypothesis aka
answer
Alternative hypothesis
Unlock the answer
question
Experimental research
answer
Where one variable is directly manipulated to test it's effect on another
Unlock the answer
question
Falsification
answer
The act of disproving a hypothesis or theory.
Unlock the answer
question
Frequency distribution
answer
A mathematical function showing the number of instances in which a variable takes each of its possible values
Unlock the answer
question
Histogram
answer
A diagram consisting of rectangles whose area is proportional to the frequency of a variable and whose width is equal to the class interval
Unlock the answer
question
Hypothesis
answer
A prediction from a theory / Used to test a theory
Unlock the answer
question
Independent design aka
answer
Between-group design / Between-subject design
Unlock the answer
question
Independent variable
answer
A variable (often denoted by x ) whose variation we suspect does not depend on that of another / Proposed cause / Predictor variable
Unlock the answer
question
Interquartile range
answer
The middle fifty. IQR = Q3 - Q1
Unlock the answer
question
Interval variable
answer
Equal intervals on the scale represent equal differences in the property being measured
Unlock the answer
question
Kurtosis
answer
The sharpness of the peak of a frequency distribution curve
Unlock the answer
question
Leptokurtic
answer
Having a greater kurtosis than the normal distribution (sharper)
Unlock the answer
question
Level of measurement aka
answer
Scales of measure
Unlock the answer
question
Lower quartile
answer
The median of the lower half of the dataset. Q1
Unlock the answer
question
Mean aka
answer
Expected value. Mean is to a frequency distribution what Expected value is to a random variable.
Unlock the answer
question
Measurement error
answer
The difference between a measured value of quantity and its true value
Unlock the answer
question
Median
answer
The value lying at the midpoint of a frequency distribution
Unlock the answer
question
Mode
answer
The score that occurs most frequently in a dataset
Unlock the answer
question
Multimodal
answer
Describes a frequency distribution having more than two modes
Unlock the answer
question
Negative skew
answer
Tail on the left
Unlock the answer
question
Nominal variable
answer
A categorical variable that can take on one of more than two categories
Unlock the answer
question
Normal distribution
answer
A function that represents the distribution of many random variables as a symmetrical bell-shaped graph
Unlock the answer
question
Null hypothesis
answer
A statistical hypothesis that is tested for possible rejection under the assumption that it is true (usually that observations are the result of chance) / Effect is absent
Unlock the answer
question
Ordinal variable
answer
A step up from nominal variables in that the categories have a logical order. A step down from continuous variables.
Unlock the answer
question
Outcome variable aka
answer
Dependent variable
Unlock the answer
question
Platykurtic
answer
Having a lesser kurtosis than the normal distribution. (flatter)
Unlock the answer
question
Positive skew
answer
Tail on the right
Unlock the answer
question
Practice effect
answer
Participants my perform differently in the second condition because of familiarity with the experimental situation and/or the measures being used
Unlock the answer
question
Predictor variable aka
answer
Independent variable
Unlock the answer
question
Probability distribution (Rules)
answer
1. The events listed must be disjoint. 2. Each probability might, must be between 0 and 1. 3. The sum of the probabilities listed in the probability distribution must total 1.
Unlock the answer
question
Qualitative methods
answer
Methods that rely primarily on words as its unit of analysis and its means of understanding
Unlock the answer
question
Quartile
answer
Each of the three values of the random variable that divide a population into four groups
Unlock the answer
question
Randomization is used to
answer
keep unsystematic variation to a minimum in order to get a more sensitive measure of the experimental manipulation.
Unlock the answer
question
Range
answer
The difference between the lowest and highest values in a frequency distribution
Unlock the answer
question
Ratio variable
answer
A step up from Interval variables also requiring that ratios of scores on the scare also make sense. For this to be true the scare must have a true and meaningful zero point
Unlock the answer
question
Reliability
answer
The degree to which a tool can be interpreted consistently across different situations. A prerequisite to Validity.
Unlock the answer
question
Repeated measures design aka
answer
Within-subject design
Unlock the answer
question
Second quartile
answer
The median
Unlock the answer
question
Skew
answer
Skewness is a measure of the asymmetry of the probability distribution of a real-valued random variable about its mean
Unlock the answer
question
Systematic variation
answer
Variability due to specific experimental manipulation / Applies to both Independent-measures design and Repeated-measures design
Unlock the answer
question
Tertium quid
answer
A third thing that is indefinite and undefined but is related to two definite or known things
Unlock the answer
question
Test-retest reliability aka
answer
Repeatability
Unlock the answer
question
Theory
answer
A supposition or a system of ideas intended to explain something, especially one based on general principles independent of the thing to be explained
Unlock the answer
question
Unsystematic variation
answer
Variability is due to random factors / Bigger in Independent-measures design than in Repeated-measures design
Unlock the answer
question
Upper quartile
answer
The median of the upper half of the dataset. Q3
Unlock the answer
question
Validity
answer
The degree to which a tool measures what it claims to measure
Unlock the answer
question
Within-subject design
answer
A type of experimental design in which all participants are exposed to every treatment or condition.
Unlock the answer
question
Z-scores (in R code)
answer
(X - mean(X)) / sd(X)
Unlock the answer
question
Quantitative methods
answer
Methods that rely primarily on numbers as the main unit of analysis
Unlock the answer
question
Positive kurtosis
answer
Peak is sharper than that of the normal curve
Unlock the answer
question
Negative kurtosis
answer
Peak is flatter than that of the normal curve
Unlock the answer
question
The only way a nominal variable can be used is to consider _______
answer
frequencies
Unlock the answer
question
Unsystematic variation is bigger in Independent-measures design than in Repeated-measures design, therefore,
answer
the effect of experimental manipulation is likely to be more apparent in Repeated-measures design
Unlock the answer
question
95 percent of z-scores lie between
answer
-1.96 and 1.96
Unlock the answer
question
99 percent of z-scores lie between
answer
-2.58 and 2.58
Unlock the answer
question
99.9 percent of z-scores lie between
answer
-3.29 and 3.29
Unlock the answer
question
The null hypothesis is needed because
answer
we can't prove the alternative hypothesis using statistics, but we can reject the null hypothesis.
Unlock the answer
