Beginner Statistics for Data Analytics - Learn the Easy Way!

Learn the difference between a population and a sample, why random sampling represents the population, and how samples enable predictions and inferential statistics.

Identify the two main data types—categorical data and numerical data—and learn how categorical data can be converted into numbers for analysis.

Explore five popular data visuals: bar charts, line graphs, pie charts, histograms, and scatter plots, and learn how histograms and scatter plots reveal data distribution and relationships.

Explore why no single statistic suffices and how using a toolbox of tools, including descriptive statistics, helps predict outcomes and describe data.

Explore the mean, or simple average, as a foundational descriptive statistic that describes data, and see how outliers influence the average with Excel’s average formula.

Learn how the median identifies the middle value after sorting data, averages the two middles for even sets, and why it remains robust to outliers alongside the mean in Excel.

Identify the mode as the most frequently occurring value in a data set, illustrated by 25, and use the Excel formula =mode for simple descriptive statistics alongside mean and median.

Learn to compute mean, median, and mode from online retailer December sales, interpret their differences to reveal outliers and skew, and apply these descriptive statistics with simple Excel formulas.

Dive into histograms to see data distribution and understand mean, median, and outliers; learn to create two Excel histograms of transactions, adjusting bin width to 5–8 bins, about $250 increments.

Create histograms to visualize daily transactions and identify busy days, popular items, and seasonal spikes, then format axes to interpret data for staffing and store hours.

Explore how histograms reveal data distribution through skewness, including left, right, and normal shapes, tails and outliers, and the relationship between mean and median.

Explore how variance measures data spread around the mean, compare high and low variance examples, and learn that standard deviation is used to calculate variance.

Learn how standard deviation measures how spread out data is from the mean. Use Excel's stdev.s to compute it and compare scenarios with low versus high spread.

Compute the standard deviation for sales and daily transactions in Excel, and interpret its meaning alongside the mean, median, and data distribution.

Use the coefficient of variation to compare variability by standardizing the standard deviation with the mean, via the formula sd divided by mean times 100 percent in descriptive statistics.

Explore probability distribution as the visual counterpart to a histogram, and compare uniform, binomial, standard (bell curve), and student t distributions, noting their use for samples versus populations.

Explore the normal distribution, the bell curve where mean, median, and mode align. Understand how standard deviation defines 68/95/99 percent ranges and underpins regression.

Explore how the central limit theorem lets small samples reveal the population mean and standard deviation, with averages becoming normally distributed and enabling inferential statistics.

Explore how random samples from a population produce a near-normal distribution of sample means, illustrating the central limit theorem and enabling reliable estimates of the population mean and standard deviation.

Learn to make confidence interval estimates rather than single point numbers, using two standard deviations of the normal distribution to bound sales between 15 and 25 phones with 95% confidence.

learn to calculate a confidence interval estimate using the mean plus or minus a reliability factor times the standard error, with a t score for samples.

Learn to compute confidence interval estimates from sample data using mean, standard deviation, standard error, and t-statistics from August wand sales. Then explore regression analysis for more accurate estimates.

Explore regression analysis to identify linear trends, understand correlation, and build a predictive model using a dependent variable and independent variables, visualized with scatter plots.

Explore scatter plots and how they reveal relationships between variables, with the independent variable on the x-axis and the dependent on the y-axis, and learn to quantify it with correlation.

Explore correlation as a fixed measure between -1 and 1, and distinguish positive and negative relationships through real examples, while recognizing that correlation does not imply causation.

Explore how to compute correlation between gold prices and wand sales using a spreadsheet, interpret a 0.74 positive correlation, and recognize correlation does not equal causation.

Interpret correlation strength with ranges like 0.7 to 1 for strong and 0.3 to 0.5 for weak, with field context, and add line of best fit to a scatter plot.

Learn how to use a trend line or line of best fit on a scatter plot to obtain a linear equation for forecasting future sales from temperature data, using Excel.

Learn the line equation y equals mx plus b to predict daily sales from outside temperature, and preview a deeper regression analysis of model accuracy and predictor strength.

Learn how to set up an Excel workbook for regression by enabling the Analysis Toolpak, then run a single-variable regression using the Data Analysis tool on the data tab.

Create your first regression by setting the Y input range and the X input range. Include labels, keep the 95% confidence interval, and place the output on the same sheet.

Identify the three key regression statistics—multiple r (correlation), r-squared, and adjusted r-squared—and learn how r-squared measures how well the data fit the model, illustrated by temperature versus sales.

R square shows how closely data fit the trend line, and higher values indicate a better model fit; adding education, skills, and location increases it, with Excel doing the calculation.

Examine how the p value reveals whether a model variable truly adds value or is random, using the 0.05 threshold and the coin example.

Explore how p-values and significance F assess model reliability in regression, interpret coefficients and the intercept, and decide which variables to keep in simple or multivariable models.

Tie together the regression outputs to predict sales with the line equation, noting r square around 0.54 and p values below 0.05; correlation around 0.7 signals a fairly strong relationship.

Predict wand sales from gold price using a simple regression model Y = Mx + B. Interpret the 95% confidence interval with lower and upper bounds to gauge prediction uncertainty.

Apply statistics to real world case studies and use your foundation to advance in data analytics, then explore SQL for data access, dashboards, and Power BI for insights.

Apply the tools you've learned to your data, using mean, median, mode, and standard deviation. Practice with scatter plots, histograms, regression analysis, and SQL to become an analytics pro.