1/94
Looks like no tags are added yet.
Data
The facts and figures collected, analyzed, and summarized for presentation and interpretation.
Dataset
All the data collected for a particular analysis.
Element
The specific entity on which data is collected.
Variable
A characteristic of interest for an element.
Observation
The set of all variables associated with an individual element.
Categorical Data
Uses numeric or ordinal measurement values to identify distinct categories.
Quantitative Data
Uses explicit numeric measures that indicate how much or how many.
Cross-sectional Data
Data collected at or approximately at a single point in time.
Time Series Data
Data collected over several consecutive time periods.
Panel Data
A database combining cross-sectional and time-series data.
Descriptive Statistics
Summaries used to describe or outline data and variables.
Population
The complete set of all data or variables of interest in a statistical analysis.
Sample
A gathered subset of the larger population.
Statistical Inference
The process of using sample data to make estimates and test hypotheses about a population's characteristics.
Data Analytics
The scientific process of transforming raw data into insights for decision-making.
Descriptive Analytics
Focuses on summarizing what has already happened in the past.
Predictive Analytics
Uses past patterns and models to forecast the future or determine directional impacts.
Prescriptive Analytics
Focuses on finding a best or optimal solution using optimization models.
Big Data Dimensions
Differentiated from standard data by its scale, consisting of Volume (amount), Velocity (speed), Variety (different forms), and Veracity (reliability).
Data Mining
Extracting actionable, predictive info specifically out of massive big data sets.
Frequency Distribution
A tabular summary showing the exact number of observations within separate, non-overlapping categories.
Bar Chart
A graphical device for depicting categorical data summarized in a frequency, relative frequency, or percent frequency distribution.
Pie Chart
A visual display format used to show the relative or percent frequency distribution among categorical classes.
Histogram
A visual display of a quantitative distribution where variables sit on the horizontal axis and frequencies sit on the vertical axis.
Distribution Shape
Evaluated by its skewness (Left-skewed = negative skewness; right-skewed = positive skewness; perfectly balanced = zero skewness).
Crosstabulation
A tabular data summary managing two variables simultaneously to locate joint patterns.
Scatter Diagram
A graphical plot modeling the relationship between two quantitative variables, accompanied by a trendline to approximate the relationship.
Side-by-Side Bar Chart
Depicts multiple distinct bar charts nested on a single display to compare two variables.
Stacked Bar Chart
A singular bar divided into shaded segments to track the relative frequency changes of an underlying class.
Cumulative Distribution
Shows the total number, proportion, or percentage of items with values less than or equal to the upper limit of each class.
Mean
The core average value calculated for a variable (matches median in symmetric data; larger than median in positively skewed data).
Median
The exact center value when data is organized in ascending order; avoids bias from extreme outliers.
Mode
The specific value occurring with the single greatest frequency in a dataset.
Weighted Mean
An average adjusted when certain data points hold more relative importance (weight) than others.
Geometric Mean
Measures center locations across multi-period growth by extracting the nth root of the product of n factors.
Percentile
Divides a dataset into two parts; approximately p% of items fall below the pth percentile.
Quartiles
Splits a data distribution into four equal chunks (Q1=25th percentile, Q2=Median, Q3=75th percentile).
Range
The arithmetic difference between the largest value and smallest value.
Interquartile Range (IQR)
The distance between Q3 and Q1, mapping the middle 50% spread.
Variance
Measures data dispersion based on squared deviations from the dataset mean.
Standard Deviation
The positive square root of variance, returning the dispersion metrics back to original un-squared units.
Coefficient of Variation
A percentage tracking how large a standard deviation is relative to its mean.
z-Score
A standardized value representing the exact number of standard deviations a data observation sits away from its mean.
Chebyshev's Theorem
Determines the minimum percentage of data points that must fall within standard deviations (at least 75% for z=2; 89% for z=3).
Empirical (Bell-Shaped) Rule
Dictates that roughly 68% of data falls within +/-1σ, 95% falls within +/-2σ, and 99.7% falls within +/-3σ for symmetric datasets.
Outliers
Extreme values identified by a z-score greater than 3, or via IQR limits (below Q1 - 1.5xIQR or above Q3 + 1.5xIQR).
Covariance
A descriptive measure tracking the baseline direction of linear association between two distinct variables.
Correlation Coefficient
A standardized metric ranging from -1 to +1 that gauges both the direction and exact strength of a linear relationship.
Probability
A numerical measure from 0 to 1 indicating the likelihood of an event occurring.
Experiment
A process that generates well-defined, distinct outcomes.
Combinations
A counting rule used to find total outcomes when picking items and selection order does not matter.
Permutations
A counting rule used to find total outcomes when picking items and selection order is critically important.
Classical Method
Assigns probabilities based on the assumption that all experimental outcomes are equally likely.
Relative Frequency Method
Assigns probabilities using available historic data to track past proportion rates.
Subjective Method
Assigns probabilities using personal judgment or intuition when data is unavailable.
Event
A specified collection of targeted sample points within an experiment.
Complement (A^C)
All alternative sample points in an experiment that do not belong to Event A.
Union (A U B)
An event containing all sample points belonging to event A, event B, or both.
Intersection (A n B)
An event containing only the specific sample points shared by both A and B.
Addition Law
Computes the probability that at least one of two events occurs: P(A U B) = P(A) + P(B) - P(A n B).
Mutually Exclusive
Events with no sample points in common; their intersection probability is zero.
Conditional Probability (P(A|B))
The probability of an event A occurring given that a related event B has already taken place.
Independent Events
Occur when the probability of one event is completely unaffected by whether a separate event has occurred.
Random Variable
A quantitative numeric description of an experimental outcome (discrete or continuous).
Discrete Random Variable
Can assume either a finite number of values or an infinite sequence of countable values; calculated for specific values of x.
Continuous Random Variable
Can assume any numerical value across an unbroken interval; probability at a single exact point is always zero.
Binomial Distribution
Measures identical, independent trials where only two outcomes are possible (success/failure) and probability remains constant.
Poisson Distribution
Estimates the exact number of independent occurrences of an event over a specified interval where mean equals variance.
Hypergeometric Distribution
Dependent trials sampled without replacement, causing the success probability to change from trial to trial.
Uniform Distribution
A continuous framework where the probability is balanced and identical for any two intervals of equal length (rectangular shape).
Exponential Distribution
A continuous framework useful for measuring the actual time or distance between consecutive occurrences in a Poisson process.
Normal Distribution
Symmetrical, bell-shaped continuous distribution where the peak represents the mean, median, and mode simultaneously.
Standard Normal Distribution
A unique normal curve scaled precisely to a mean of 0 and a standard deviation of 1, utilizing z-scores.
Excel: Mean
=AVERAGE(Data_Range)
Excel: Median
=MEDIAN(Data_Range)
Excel: Mode
=MODE.SNGL(Data_Range)
Excel: Geometric Mean
=GEOMEAN(Growth_Range)
Excel: Percentile
=PERCENTILE.EXC(Data_Range, p/100)
Excel: Quartile
=QUARTILE.EXC(Data_Range, Quartile_Number)
Excel: Sample Variance
=VAR.S(Data_Range)
Excel: Sample Std. Deviation
=STDEV.S(Data_Range)
Excel: Skewness
=SKEW(Data_Range)
Excel: Sample Covariance
=COVARIANCE.S(Range_X, Range_Y)
Excel: Correlation Coefficient
=CORREL(Range_X, Range_Y)
Excel: Expected Value (μ)
=SUMPRODUCT(X_Range, Probability_Range)
Excel: Binomial Exact Probability
=BINOM.DIST(x, n, p, FALSE)
Excel: Binomial Cumulative Probability
=BINOM.DIST(x, n, p, TRUE)
Excel: Poisson Exact Probability
=POISSON.DIST(x, mean, FALSE)
Excel: Poisson Cumulative Probability
=POISSON.DIST(x, mean, TRUE)
Excel: Hypergeometric Probability
=HYPERGEOM.DIST(x, n, r, N, FALSE)
Excel: Exponential Cumulative Probability
=EXPON.DIST(x, 1/mean, TRUE)
Excel: Normal Cumulative Probability
=NORM.DIST(x, mean, stdev, TRUE)
Excel: Inverse Normal (Find x)
=NORM.INV(probability, mean, stdev)
Excel: Std. Normal Cumulative (z)
=NORM.S.DIST(z, TRUE)
Excel: Inverse Std. Normal (Find z)
=NORM.S.INV(probability)