Data Science Quiz 1 (9/8)

Univariate

Single variable

Mean

Average

Mode

Most popular data point

Median

Order data, find the value in the middle

SD

Is a measure of spread. Calculate the mean, take difference of each point vs the mean, divide by total number of elements.

IQR

Difference between 75th and 25th percentile.

Bivariate

Two variables

Scatter plots

Bivariate. Used when both variables are numerical. It places one variable on the x-axis and the other on the y-axis to spot trends

Correlation coefficients

A number from -1 to 1 that shows the strength and direction of a link between two numbers

Cross tab

A data table that shows the relationship between two or more categorical variables by grouping data into intersecting rows and columns

Multivariate

3+ variables. Examples include 3-way descriptive, partial correlation, matrix plots, and conditional subsets.

Categorical variables

A data type that assigns each observation or individual to one of a limited, fixed number of distinct groups or categories

Nominal variables

A type of categorical variable. Categories with no inherent order or ranking (e.g., eye color, car brand, or gender).

Ordinal variables.

A type of categorical variable. Categories that have a meaningful order or sequence, but the exact distance between values cannot be measured (e.g., survey ratings like "poor, average, excellent" or military ranks).

Numerical variables

A characteristic that represents a measurable quantity or amount using numbers

Discrete variables

Type of numerical variable. Whole numbers resulting from counting (e.g., number of pets, siblings, or goals scored).

Continuous variables

Type of numerical variable. Any value within a range resulting from measurement (e.g., height, weight, or temperature)

Dichotomous variable

A type of categorical variable that can take on exactly two possible values or categories. Examples: pass or fail, yes or no.

Inferential statistics

Use a smaller sample to make predictions, test hypotheses, or generalize conclusions about a larger population

Descriptive statistics

Summarize and describe the features of a specific dataset

Positive correlation

Both variables move in the same direction; as one increases, the other increases too (e.g., height and weight).

Negative correlation

Variables move in opposite directions; as one increases, the other decreases (e.g., exercise frequency and body weight).

Zero or No Correlation

There is no relationship or pattern between the variables (e.g., eye color and blood type)

pwcorr

a Stata command used to compute and display a matrix of pairwise  correlation coefficients using pairwise deletion for missing values

STATA

A statistical software package used by researchers for data manipulation, visualization, statistics, and automated reporting

R vs r squares

R measures the strength and direction of a linear relationship between two variables, can be positive or negative telling you if the values increase together or move in opposite directions. Shows how well two variables move together in a straight line. It ranges from -1 to 1.

R-squared (the coefficient of determination) measures the percentage of variation in the dependent variable that is explained by a model. Doesn’t show direction. Shows how much of the scatter or variance in your data is accounted for by your regression line or model. It ranges from 0 to 1, or 0 to 100%.

Bar graph

For categorical data. This graph compares separate categories. Have spaces between the bars to show that categories are independent

Histogram

For numerical data. Shows how continuous numerical data is spread out

Pie chart

Used to display categorical data (qualitative data) that represents parts of a whole