In doomlab/learnSTATS: Introduction to Statistics (ANLY 500)

library(learnr)
library(learnSTATS)
library(faux)
library(ggplot2)
library(reshape)

##simulated data
between <- list(biz_focus = c(forward = "Forward Thinking",
                                 traditional = "Traditional"),
                internet = c(high = "High",
                             medium = "Medium",
                             low = "Low"))

within <- list(rm_var = c("time1", "time2"))

##time 1 is first, then time 2, can flip them here if you want to change the interpretation
mu <- data.frame(
  forward_high = c(7, 10),
  forward_medium = c(4, 7),
  forward_low = c(2, 5),
  traditional_high = c(4, 3),
  traditional_medium = c(3, 3),
  traditional_low = c(2, 3),
  row.names = within$rm_var)

vis_data <- sim_design(within, between, 
                       n = sample(25:100, 1), 
                       mu = mu, 
                       sd = 1, r = .10,
                       interactive = FALSE,
                       empirical = FALSE, 
                       plot = FALSE)

cleanup <- theme(panel.grid.major = element_blank(), 
                panel.grid.minor = element_blank(), 
                panel.background = element_blank(), 
                axis.line.x = element_line(color = "black"),
                axis.line.y = element_line(color = "black"),
                legend.key = element_rect(fill = "white"),
                text = element_text(size = 15))

vis_data$biz_focus <- factor(vis_data$biz_focus,
                             levels = levels(vis_data$biz_focus),
                             labels = c("Forward Thinking", "Traditional"))

vis_data$internet <- factor(vis_data$internet,
                             levels = levels(vis_data$internet),
                             labels = c("High", "Medium", "Low"))

vis_data <- vis_data[ , -1]

knitr::opts_chunk$set(echo = FALSE)

Data Visualization

The best half of statistics is data visualization! You will learn the basic components of ggplot2, how to add new layers, and how to format data appropriately for graphs. You will learn the following:

• ggplot2 basics and customization
• How to build histograms
• How to build scatterplots and regression lines
• How to build bar graphs
• How to build a line graph

Data Visualization Video Part 1

The following videos are provided as a lecture for the class material. The lectures are provided here as part of the flow for the course. You can view the lecture notes within R using vignette("Data-Visualization", "learnSTATS"). You can skip these pages if you are in class to go on to the assignment.

Data Visualization Video Part 2

Exercises

In this next section, you will answer questions using the R code blocks provided. Be sure to use the solution option to see the answer if you need it!

Please enter your name for submission. If you do not need to submit, just type anything you'd like in this box.

question_text(
  "Student Name:",
  answer("Your Name", correct = TRUE),
  incorrect = "Thanks!",
  try_again_button = "Modify your answer",
  allow_retry = TRUE
)

The Data

Citation: Trends in Internet-based business-to-business marketing

Abstract: The Internet is changing the transactional paradigms under which businesses-to-business marketers operate. Business-to-business marketers that take advantage of the operational efficiencies and effectiveness that emerge from utilizing the Internet in transactions are out performing firms that utilize traditional transactional processes. As an example, Dell computers, by utilizing business-to-business processes that take advantage of the Internet, has gained the largest market share in the PC business when compared to traditional manufacturers such as Compaq. This paper first examines the genesis of the Internet movement in business-to-business markets. The long-term impact of the increase of business-to-business utilization of the Internet on the marketing theory and marketing process is then discussed. Finally, managerial implications and directions for future research are highlighted.

Dataset vis_data includes:

1) Business marketing focus - traditional or forward thinking. 2) Internet use - low, medium, or high levels of business marketing use on the internet. 3) Time 1 - sales scores at the first measurement time. 4) Time 2 - sales scores at the second measurement time.

head(vis_data)

Graph Cleanup

When you are assessed for graphs in the course, we will use the following checklist. Use this assignment to make sure you understand how to add each of the following components.

1) Is it readable? 2) Is X-axis labeled appropriately? 3) Is Y-axis labeled appropriately? 4) Is it the right graph? 5) Do the labels in the legend look appropriate? 6) Are there error bars when appropriate?

Histogram

The ggplot2 and reshape libraries have been loaded for you. You will use the vis_data as the dataframe for each graph. The cleanup code from class is also loaded for you to use (or you can use theme_bw() or theme_classic()).

Make a simple histogram for sales at time 1.

saleshist <- ggplot(vis_data, aes(time1))
saleshist + 
  geom_histogram(binwidth=.4, 
                 color = "black", 
                 fill = "white") + 
  xlab("Sales Time 1") +
  ylab("Frequency") +
  cleanup

Bar Graphs

Make a bar graph with two categorical independent variables: business focus (biz_focus) and internet. Use sales at time 2 as the dependent variable.

twobar <- ggplot(vis_data, aes(internet, time2, fill = biz_focus))
twobar + 
  stat_summary(fun = mean, 
               geom = "bar", 
               position="dodge") +
  stat_summary(fun.data = mean_cl_normal, 
               geom = "errorbar", 
               position = position_dodge(width = 0.90), 
               width = 0.2) +
  xlab("Internet Useage") + 
  ylab("Sales Time 2") +
  scale_fill_discrete(name="Business Focus") +
  cleanup

Bar Graphs with Repeated Measures

Make a bar chart using Time as an independent variable. Time is currently two different columns, so you will need to reshape the data into one column for time and one column for sales as the dependent variable. Use business focus as the second independent variable.

long_data <- melt(vis_data, 
                  id = c("biz_focus", "internet"), 
                  measured = c("time1", "time2"))
##change the column names - not necessary
colnames(long_data) = c("biz_focus", "internet", "sales_time", "sales_score")

##because this one has the repeated component it must be the long data
##otherwise it's the same as a two iv graph
rmbar2 <- ggplot(long_data, aes(sales_time, sales_score, fill = biz_focus))
rmbar2 + 
  stat_summary(fun = mean, 
               geom = "bar", 
               position="dodge") +
  stat_summary(fun.data = mean_cl_normal, 
               geom = "errorbar", 
               position = position_dodge(width = 0.90), 
               width = 0.2) +
  xlab("Measurement Time") + 
  ylab("Sales Score") +
  scale_x_discrete(labels=c("Time 1", "Time 2")) + 
  scale_fill_grey(name="Business Focus") + 
  cleanup

Scatterplots

Use vis_data to create a scatterplot of sales at time 1 versus sales at time 2. You can switch the X and Y axes from the solution for this graph, as the direction doesn't matter for correlation type graphs (unless you add a regression line!).

scatter <- ggplot(vis_data, aes(time1, time2))
scatter +
  geom_point() +
  xlab("Sales Time 1") +
  ylab("Sales Time 2") +
  cleanup

Using the same solution from the previous exercise, add business focus as a grouping variable for your graph.

grouped <- ggplot(vis_data, aes(time1, time2, color = biz_focus))
grouped +
  geom_point() +
  xlab("Sales Time 1") +
  ylab("Sales Time 2") +
  scale_color_manual(values = c("gray", "gray50"), 
                     name="Business Focus") + 
  cleanup

Submit

On this page, you will create the submission for your instructor (if necessary). Please copy this report and submit using a Word document or paste into the text window of your submission page. Click "Generate Submission" to get your work!

encoder_logic()

encoder_ui()

doomlab/learnSTATS documentation built on June 9, 2022, 12:54 a.m.