1/80
Comprehensive vocabulary flashcards covering fundamental psychological statistics concepts including levels of measurement, descriptive statistics, probability distributions, hypothesis testing, correlation, assumptions, and Jamovi parametric and non-parametric test selections.
Statistics
The process of collecting, organizing, analyzing, and understanding information or data to help understand people, their behavior, emotions, thoughts, and experiences using numbers.
Descriptive Statistics
The branch of statistics that summarizes and describes the characteristics of the collected data (e.g., mean, median, mode, standard deviation, and frequency).
Inferential Statistics
The branch of statistics that uses information collected from a smaller sample to make conclusions or generalizations about a larger population.
Variable
Any characteristic, number, or quantity that can change or have different values across individuals or conditions.
Independent Variable (IV)
The variable that a researcher uses as a predictor or manipulates in an experiment to examine its effect on another variable.
Dependent Variable (DV)
The outcome variable that the researcher measures to determine the effect of the independent variable.
Qualitative (Categorical) Variable
A variable that describes groups, labels, names, or categories rather than measuring numerical amounts.
Quantitative (Numerical) Variable
A variable whose values consist of numbers or amounts that can be counted or measured.
Discrete Variable
A quantitative variable consisting of separate, countable values, typically represented by whole numbers without fractional parts.
Continuous Variable
A quantitative variable that represents measurements and can take on any numerical value, including decimals and fractions.
Nominal Level of Measurement
The level of measurement that classifies data into distinct named categories or labels without any inherent order or ranking.
Ordinal Level of Measurement
The level of measurement that arranges categories in an ordered ranking from lowest to highest, but without equal distances between ranks.
Interval Level of Measurement
The level of measurement characterized by equal distances between numerical values, but lacking a true or absolute zero point.
Ratio Level of Measurement
The level of measurement with equal intervals between values and an absolute, true zero point indicating the complete absence of the measured variable.
Operational Definition
A precise explanation of exactly how an abstract psychological concept or variable is measured or quantified in a study.
Frequency Distribution
An organized tabular arrangement of data that shows the count of how many times each individual score or value occurs.
Relative Frequency (RF)
The proportion of total observations belonging to a specific value, calculated using the formula RF=Nf.
Percentage Frequency
The percentage of all observations represented by a particular value, computed as Percentage=(Nf)×100.
Cumulative Frequency
A running total of frequencies calculated by progressively adding each class frequency to the sum of all preceding frequencies.
Class Midpoint
The exact center value of a class interval, determined by the formula Class Midpoint=2Lower Limit+Upper Limit.
Bar Graph
A graphical representation used for categorical or grouped data where the bars are displayed with spaces between them.
Histogram
A graphical representation of continuous or interval numerical data grouped into bins where adjacent bars touch each other without spaces.
Frequency Polygon
A graph that connects data points with straight lines to display the overall shape and pattern of a frequency distribution.
Ogive
A line graph that displays cumulative frequency to show how many observations fall at or below specific numerical values.
Percentile
A positional measure indicating the percentage of observations in a reference distribution that fall at or below a specific score.
Quartiles
Values that split an ordered dataset into four equal parts: the first quartile (Q1=P25), the second quartile or median (Q2=P50), and the third quartile (Q3=P75).
Interquartile Range (IQR)
A measure of statistical dispersion representing the spread of the middle 50% of observations, calculated as IQR=Q3−Q1.
Mean
The arithmetic average of a dataset obtained by summing all values and dividing by the total count: xˉ=n∑x.
Median
The middle score in a dataset that has been ordered from lowest to highest, which is resistant to extreme outliers.
Mode
The most frequently occurring value or category in a distribution.
Range
The difference between the maximum and minimum observed values: Range=Highest Value−Lowest Value.
Variance
A measure of variability that calculates the average of squared deviations from the mean, expressed in squared units.
Bessel's Correction
The mathematical adjustment of dividing by n−1 rather than n when calculating sample variance to correct for underestimation of the population variance.
Standard Deviation (SD)
The square root of the variance (SD=Variance), measuring the average dispersion of scores around the mean in original measurement units.
Coefficient of Variation (CV)
A relative measure of dispersion expressing the standard deviation as a percentage of the mean: CV=(MeanSD)×100.
Empirical Rule (68–95–99.7 Rule)
A rule stating that in a normal distribution, approximately 68% of observations lie within ±1SD, 95% within ±2SD, and 99.7% within ±3SD of the mean.
Z-Score
A standardized score indicating the distance of a raw score from the mean in units of standard deviation, calculated as z=σX−μ.
Positive Skew (Right-Skewed)
An asymmetric distribution whose tail extends toward the right (higher values), with most scores clustering on the left, typically exhibiting Mean>Median>Mode.
Negative Skew (Left-Skewed)
An asymmetric distribution whose tail extends toward the left (lower values), with most scores clustering on the right, typically exhibiting Mean<Median<Mode.
Kurtosis
A statistical parameter describing the heaviness or thickness of the tails of a probability distribution relative to a normal distribution.
Mesokurtic
A distribution possessing tail heaviness and peakedness similar to a normal distribution, typically characterized by an excess kurtosis near 0.
Leptokurtic
A distribution displaying heavier tails and a higher concentration of extreme observations than a normal distribution, characterized by positive excess kurtosis.
Platykurtic
A distribution displaying lighter tails and fewer extreme observations compared to a normal distribution, characterized by negative excess kurtosis.
Population
The complete collection of all individuals, items, or scores of interest in a study.
Sample
A subgroup or subset of individuals chosen from a larger population to participate in a study.
Parameter
A numerical descriptive measurement summarizing a characteristic of an entire population (e.g., μ or σ).
Statistic
A numerical descriptive measurement calculated from sample data (e.g., xˉ or s).
Sampling Error
The natural discrepancy or difference between a sample statistic and its corresponding population parameter resulting from studying only a sample.
Null Hypothesis (H₀)
A formal statement asserting that there is no significant difference, effect, or relationship between variables in the population.
Alternative Hypothesis (H₁ or Hₐ)
The formal research hypothesis proposing that a real, statistically significant effect, difference, or relationship exists in the population.
P-Value
The probability of obtaining an observed result, or one more extreme, assuming that the null hypothesis and statistical model are completely true.
Significance Level (Alpha, α)
The pre-specified threshold (commonly α=0.05) used as a decision criterion to reject the null hypothesis.
Confidence Interval (CI)
A range of plausible values for an unknown population parameter calculated from sample data at a specified confidence level (e.g., 95%).
Statistical Power
The probability that a statistical test will correctly reject a false null hypothesis, calculated as Power=1−β.
Correlation Coefficient (r)
A standardized numerical index bounded between −1.00 and +1.00 that indicates the direction and strength of the relationship between two variables.
Pearson's Product-Moment Correlation (Pearson's r)
A parametric correlation coefficient used to measure the strength and direction of a linear relationship between two quantitative variables.
Spearman's Rank-Order Correlation (Spearman's ρ)
A non-parametric correlation coefficient used to assess the strength and direction of a monotonic relationship between two ranked or ordinal variables.
Kendall's Tau (τ)
A non-parametric measure of association based on the concordance and discordance of paired ranks between two variables.
One-Tailed Test
A directional statistical hypothesis test that places the entire critical alpha rejection region into one specific tail of the distribution.
Two-Tailed Test
A non-directional statistical test that splits the significance level into both tails of the distribution to detect an effect in either direction.
Directional Hypothesis
A research prediction that specifies the expected positive or negative direction or relative magnitude (higher/lower) of a relationship or difference.
Non-Directional Hypothesis
A research hypothesis predicting that a difference or relationship exists without specifying the direction of the outcome.
Type I Error (Alpha Error)
The error that occurs when a researcher incorrectly rejects a null hypothesis that is actually true (a false positive).
Type II Error (Beta Error)
The error that occurs when a researcher fails to reject a null hypothesis that is actually false (a false negative).
Statistical Assumptions
Underlying conditions (e.g., normality, independence, homogeneity of variance) that must be satisfied for statistical tests to yield valid results.
Shapiro-Wilk Test
A formal statistical test evaluating whether sample data deviate significantly from a normal distribution (p≤0.05 indicates deviation from normality).
Homogeneity of Variance
The assumption that multiple comparison groups possess approximately equal variances on the dependent variable.
Levene's Test
An inferential test assessing the equality of variances across groups (p≤0.05 indicates unequal variances).
Welch's t-test
A parametric alternative to the conventional independent-samples t-test designed for comparing two group means when variances are unequal.
Linearity Assumption
The assumption that the mathematical relationship connecting two variables can be modeled effectively by an approximately straight line.
Outlier
An observation located an abnormal distance from other values, commonly identified as falling beyond Q1−1.5(IQR) or Q3+1.5(IQR).
Independence of Observations
The research assumption that each data point collected from a participant is unaffected by and independent of any other participant's response.
Parametric Tests
Inferential statistical procedures that make specific assumptions regarding the distribution of the data (such as normality) and population parameters.
Non-Parametric Tests
Distribution-free inferential tests that rely on ranks or categories and make fewer distributional assumptions than parametric counterparts.
Independent-Samples t-test
A parametric test used to compare the mean scores of two separate, unrelated groups on a single quantitative outcome.
Paired-Samples t-test
A parametric test used to evaluate the mean difference between two related measurements taken from the same participants or matched pairs.
Mann-Whitney U Test
A non-parametric test that evaluates rank differences between two independent groups, serving as the counterpart to the independent-samples t-test.
Wilcoxon Signed-Rank Test
A non-parametric test evaluating the ranks and signs of differences between two related or repeated measures, serving as the counterpart to the paired-samples t-test.
One-Way ANOVA
A parametric omnibus test used to determine whether statistically significant mean differences exist among three or more independent groups.
Kruskal-Wallis Test
A non-parametric test using ranks to compare three or more independent groups, serving as the counterpart to one-way ANOVA.
Friedman Test
A non-parametric test evaluating differences across three or more related or repeated measurements, serving as the counterpart to repeated-measures ANOVA.