nps_trend {marketr}

Tidy Calculation of Net Promoter Score trends by group

Description

Simplifies the calculation of Net Promoter Score (NPS) trends over time from raw survey data within the tidyverse framework.

Usage

nps_trend(survey_data, trend_var, ..., min_surveys = 1, avg_surveys = 0)

Arguments

survey_data

Raw survey data. Needs to be one row per survey with the nps question in a numeric column called nps_question

trend_var

Column that represents an element of time, eg week number, date, month & year

...

Optional columns by which to group the nps calculation. There is no limit to the number of grouping variables chosen. Too many will likely result in nps calculations that are too fragmented / based on very small survey counts.

min_surveys

Minimum surveys found in every period for each group to be included

avg_surveys

Average surveys found in every period for each group to be included

Details

Net Promoter Score was originally developed by Fred Reichheld and now is owned by Bain Company and Satmetrix Systems. According to Wikipedia it "is a management tool that can be used to gauge the loyalty of a firm's customer relationships."

The trend version of the function allows you to specify one column as a date over which to trend the data. This allows quick filtering to eliminate groupings that fail to meet user-specified thresholds for average or minimum survey counts per time period.

The resulting data set is set up for creating faceted line plots using ggplot2.

Value

Data frame with nps and survey count for each combination of the grouping variables over the time variable.

Examples

nps_question <- sample(10, 100, replace = TRUE)
nps_date <- rep(seq.Date(from = as.Date("2019-01-01"), to = as.Date("2019-01-10"), by = "day"), 10)
nps_group <- rep(c("a", "b", "c", "d"), 25)
df <- data.frame(nps_question, nps_date, nps_group)
nps_trend(df, nps_date, nps_group)