Regression Analysis for Business in Excel

What you'll build

What you will be able to do

Each lab ends with a concrete result that you build yourself and the checker confirms, cell by cell.

• Measure how strongly weekly ad spend and sales move together: the correlation coefficient by hand, then with CORREL, and as a scatter chart with a trendline.
• Fit sales = b0 + b1 × store size with nothing but sums of squares, then measure the fit with R² and the standard error, and compare with Excel's built-in functions.
• Test whether email volume really drives online orders: standard error of the slope, t statistic, two-tailed p-value and a 95% confidence interval for the slope.
• Forecast monthly sales for two planned stores, put a 95% prediction interval around each forecast and see why the interval widens away from the average store, and why it is wider than a confidence interval for the mean.
• Fit sales on foot traffic, local ads and competitors with LINEST, read each coefficient with INDEX, check R² and forecast a new site.
• Turn text categories (region, season) into 0/1 dummy variables, fit them with LINEST, read the region effect against the base region and forecast a West store in peak season.
• Check a warehouse labour model the way a careful analyst does: residuals, standardised residuals, an outlier count and a residual plot.
• Fit a log-log demand model with LN to read the price elasticity directly, check two predictors for multicollinearity with a correlation matrix and flag an extrapolation before anyone trusts the forecast.