Ch 1-6 Intro to Stats Flashcards
Manipulated variable by the researcher. Has different experimental conditions
Independent variable
Measured variable by researcher as it naturally responds to other factors
Dependent variable
Typically a range of techniques and procedures that are used to analyze, interpret, display, or make decisions based on data.
Statistics
Represents the measured value of variables
Data
Characteristic/feature of the subject/item that we are interested in understanding.
Variable
Variables that express an attribute that do not imply a numerical ordering. Ex: hair color, eye color, religion, gender, etc.
Qualitative variables (categorical)
Variables that are measured in terms of numbers. Ex: height, weight, grip strength, levels of testosterone
Quantitative variables (numerical)
Specific values that cannot be subdivided. They have no decimals, but the averages of them can be factorial. Ex: number of siblings
Discrete (quantitative) variables
Can be meaningfully split into smaller parts. They are generally measured using a scale. Ex: time to respond
Continuous (quantitative) variables
Categorizes variables into mutually exclusive labeled categories (not in rank order). Ex: gender categories- male, female, nonbinary, transgender, other
Nominal scales
Classifies variables into categories that have a natural order or rank. Ex: Strongly agree, somewhat agree, neither agree nor disagree, somewhat disagree, strongly disagree
Ordinal scales
Measures variables on a numerical scale that has equal intervals between adjacent values. There is NO true zero (not a complete absence of something) Ex: Temperature (zero doesn’t mean absence of heat)
Interval scales
Interval scales but with a true zero. Ex: You can answer “0” on a question that asks how many children you have.
Ratio scales
A specified group that a researcher is interested in. Can be really broad or narrow. Ex: “All people” or “all psychology students at CSUF”
Population
subset of a population Ex: 50 out of 5000 people
Sample
Conclusions that are only applicable to a sample but not the general population
Sampling bias
every member of the population has an equal chance of being selected into the sample. It is completely random. Ex: Using a random number generator to pick participants.
Simple random sampling (SRS)
Identify members of each group, then randomly sample within subgroups. Ex: Dividing members based on their ethnic backgrounds. If there’s more people in a certain subgroup, there might be more people of that subgroup in the population.
Stratified sampling
Picking a sample that is close at hand. Ex: TitanWalk booths just pick a random student that walks by closest to their booth.
Convenience sampling
Ex: Low GPA is associated with low levels of sleep
Associable claims
Ex: The more caffeine you take, the more hyperactive you get.
Casual claims
Involves manipulation of an independent variable, identifiable when a research has different conditions (different IV levels). Supports causal claims. (that X caused Y)
Experimental design
Involves manipulation of an independent variable but DOESN’T USE random assignment. Can somewhat support causal claims. (It is very likely X caused Y)
Quasi-experimental designs
Involves observing things as they occur naturally and recording observations. Supports association claims, also called correlation research.
Non-experimental designs
Use dot summarize and DESCRIBE data from a sample. You can’t generalize things with these types of statistics. Ex: mean, median, mode, frequencies, range, etc.
Descriptive statistics
Used to generalize the data from our sample to the population or to other samples. These types of statistics are used to DRAW CONCLUSIONS. Ex: t tests, regression, ANOVA, etc.
Inferential statistics
Percentage Formula
Relative Frequency x 100
Relative Frequency Formula
Frequency/total
thin part (fewer scores) to the right
Positively skewed
thin part (fewer scores) to the left
Negatively skewed
number describing a sample Ex: X-bar = 3,800
Statistic
number describing a whole population. Ex: μ = 4,000
Parameter
Utilizing terms to make a graph universally understood. Ex: Using one of the most representable breeds of a mixed dog to describe what a dog looks like. Three features: form, central tendency, and variability
distributions
A value that attempts to describe a whole set of data with a single value that represents a distribution’s middle/center. Allows us to describe our sample ONLY
DOESN’T allow us to make general conclusions about a broader population/confirm differences between other samples
Central tendency
Arithmetic average, sum of the scores divided by the number of scores
Mean
Point that divides a distribution of scores into equal halves
Median
Score that occurs most frequently in a distribution
Mode
Mean, median, & mode are the same
Symmetric distribution
Mean, median, & mode are NOT the same
Skewed distribution
Mean is smaller than median
Negative skew
Mean is larger than median
Positive skew
Refers to how spread out a group of scores are. Used synonymously with spread and dispersion.
Variability
75th percentile - 25th percentile. Range of scores that contains the middle 50% of a distribution.
Interquartile Range
Descriptive measure of the dispersion of scores around the mean
Standard deviation
A bell-shaped, theoretical distribution that predicts the frequency of occurrence of chance events.
Normal distribution
Hypothesized scores based on mathematical formulas and logic
Theoretical distributions
A distribution that comes from direct observations
Empirical distribution
A standardized version of a raw score (X) that gives information about the relative location of that score within its distribution
Z-score
Tells you the distance of the score between the center and the mean
magnitude
Sample statistics tend to differ from true population values.
Sampling error
Probability of an event (A). Ranges from .00 (no possibility to 1.00 (guaranteed to happen. These can be converted into percentages by multiplying by 100. Ex: The probability of getting heads by flipping a coin. P(Heads) = ½ = .50 = 50%
Probability: P(A)
probability distributions created by drawing many random samples of a given size (n) from the same population for a given statistic.
sampling distribution
When we take a sample from a population and interpret the data of that sample.
Sample distribution
“For any population of scores, regardless of form, the sampling distribution of the mean approaches a normal distribution as N (sample size) gets larger. Furthermore, the sampling distribution of the mean has a mean equal to μ and a standard deviation (standard error) equal to 2/n.
Central Limit Theorem
