Part 1:

  1. Introduction

In this tutorial, I use a dataset originally sourced from https://www.kaggle.com/datasets/harrimansaragih/dummy-advertising-and-sales-data that contains information about advertising spend across different channels and corresponding sales figures. For this analysis, I focused on the first 100 observations to maintain a clear and concise dataset. The variables include TV, Radio, Social Media, Influencer Type, and Sales. I chose to examine the impact of Social Media advertising on Sales, using a simple linear regression approach to explore whether higher investment in social media correlates with greater sales performance. This subset allows us to better understand how digital marketing budgets relate to consumer purchasing behavior.

  1. Analysis
# Load required libraries
library(ggplot2)
library(readr)

# Load dataset
data <- read_csv("Dummy Data HSS.csv")
## Rows: 4572 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): Influencer
## dbl (4): TV, Radio, Social Media, Sales
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
# Select first 100 rows and relevant columns
df <- data[1:100, c("Social Media", "Sales")]
colnames(df) <- c("SocialMedia", "Sales")

# Build simple linear regression model
model <- lm(Sales ~ SocialMedia, data = df)

# Summary of the model
summary(model)
## 
## Call:
## lm(formula = Sales ~ SocialMedia, data = df)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -169.578  -45.266   -9.591   47.661  161.877 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept)   73.983     14.533   5.091 1.72e-06 ***
## SocialMedia   32.100      3.476   9.234 5.56e-15 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 74.71 on 98 degrees of freedom
## Multiple R-squared:  0.4653, Adjusted R-squared:  0.4598 
## F-statistic: 85.27 on 1 and 98 DF,  p-value: 5.564e-15
# Plot the data with regression line
ggplot(df, aes(x = SocialMedia, y = Sales)) +
  geom_point(color = "blue", alpha = 0.6) +
  geom_smooth(method = "lm", color = "red", se = FALSE) +
  labs(
    title = "Simple Linear Regression: Sales ~ Social Media Advertising",
    x = "Social Media Advertising Spend",
    y = "Sales"
  ) +
  theme_minimal()
## `geom_smooth()` using formula = 'y ~ x'

  1. Interpretations, Findings, and Conclusions

The results show a strong link between spending on social media ads and overall sales. Basically, for every extra dollar spent on social media advertising, sales go up by about 32 units on average. About 46.5% of the changes in sales can be explained by how much is spent on social media, which is a pretty large portion. This means social media has a big effect on what people decide to buy and how much money a business can earn.

From a marketing point of view, this shows why it’s smart and effective to spend money on digital ads. The clear and statistically strong connection between social media and sales means that these ads really do help improve performance. Companies might want to look more closely into what types of social media posts or content work best, or whether different platforms like Instagram, Facebook, or TikTok give better results. Even though this simple model doesn’t explain everything about how marketing works, it’s a helpful starting point for using data to guide future advertising strategies.

References:

Saragih, H. (n.d.). Dummy Advertising and Sales Data [Dataset]. Kaggle. https://www.kaggle.com/datasets/harrimansaragih/dummy-advertising-and-sales-data

Part 2:

RPubs Link: https://rpubs.com/sreyes44/1309392

Part 3:

How many meetings did your group organize? I’m unsure of how many meetings we had, but we had our meetings during our class time.

How many group meetings did you attend in person? All of the meetings we had were attended in person.

How many group meetings did you attend online? None of our meetings were done online.

How many times have you visited a math tutor specialized in R? I did not visit a math tutor specialized in R, unless you count trusty ChatGPT.

What I did: (explain what you did to finish your project.) I was in charge of creating the slides and going over the key takeaways, managerial implications, limitations, and future directions.

Which skills did you bring to the experience that helped you meet your goal? I would have to say that I brought my creative skills into the project. What did others do?
The rest of my peers did the different charts, research overview, and sampling and descriptive statistics.

What else happened that might be important (e.g., equipment failure, weather-related issues, etc.) Thankfully I can’t recall that anything happened that was important.

What I enjoyed: (write about what you liked most about the project) What I enjoyed the most about the project was the topic we chose, which was the effect of urbanization on anxiety & stress-related disorders because it’s a topic that effects people of all ages and deserves the awareness.

What I found difficult: (write about any part of the project you found hard to do.) Although I wasn’t in charge of this portion of the project, I do know that my peers who were in charge of the charts had some difficulty getting the right results but were fortunately able to figure it all out.

What really worked: (write about any part that you thought worked well). What really worked for this project was the way that we split the work up because everyone who was good at specific things was assigned something that fit their strength.

Next time: (write what you would do differently next time). I don’t believe that I would do anything differently next time.

I feel good about…
having taken this course and expanding my knowledge of marketing.

I used to think that marketing was just about social media and build boards, but now I know that it’s so much more than that.