Introduction

This report analyzes survey data on investment behavior and demographics. The dataset includes age, gender, education, investing experience, and crowdfunding activity. We present descriptive statistics and five distinct visualizations.

Load and Prepare Data

Descriptive Statistics

psych::describe(data[vars])
##                       vars   n mean   sd median trimmed  mad min max range
## Age                      1 320 2.97 0.93      3    2.86 0.00   1   6     5
## Gender                   2 320 0.54 0.50      1    0.55 0.00   0   1     1
## Education                3 320 3.98 1.12      4    4.14 0.00   1   6     5
## Accredited               4 320 0.58 0.49      1    0.60 0.00   0   1     1
## Professional_Investor    5 320 0.42 0.50      0    0.41 0.00   0   1     1
## Entrepreneur             6 320 0.63 0.48      1    0.67 0.00   0   1     1
## Raised_CF                7 320 1.50 1.00      2    1.50 1.48   0   3     3
## Invested_Outside_CF      8 320 0.75 0.43      1    0.81 0.00   0   1     1
## Investing_Experience     9 320 3.58 0.97      4    3.62 1.48   1   5     4
##                        skew kurtosis   se
## Age                    1.05     1.62 0.05
## Gender                -0.15    -1.98 0.03
## Education             -1.17     1.62 0.06
## Accredited            -0.31    -1.91 0.03
## Professional_Investor  0.30    -1.91 0.03
## Entrepreneur          -0.56    -1.70 0.03
## Raised_CF             -0.15    -1.08 0.06
## Invested_Outside_CF   -1.15    -0.68 0.02
## Investing_Experience  -0.20    -0.53 0.05

Visualization 1: Age Distribution

ggplot(data, aes(x = Age)) +
  geom_histogram(binwidth = 1, fill = "skyblue", color = "white") +
  labs(title = "Participant Age Distribution",
       x = "Age Group (Ordinal Code)",
       y = "Number of Participants")

Visualization 2: Gender Distribution

ggplot(data, aes(x = factor(Gender))) +
  geom_bar(fill = "#FDC086") +
  labs(title = "Gender Distribution of Respondents",
       x = "Gender (0 = Female, 1 = Male)",
       y = "Count")

Visualization 3: Investing Experience by Gender

ggplot(data, aes(x = factor(Gender), y = Investing_Experience)) +
  geom_boxplot(fill = "#BEAED4") +
  labs(title = "Investing Experience by Gender",
       x = "Gender (0 = Female, 1 = Male)",
       y = "Self-Rated Investing Experience (1–5)")

Visualization 4: Raised vs. Invested

ggplot(data, aes(x = Raised_CF, y = Invested_Outside_CF)) +
  geom_jitter(width = 0.2, height = 0.1, alpha = 0.6, color = "#7FC97F") +
  geom_smooth(method = "lm", color = "darkred", se = FALSE) +
  labs(title = "Raised vs Invested in Startups",
       x = "Raised via Crowdfunding (0 = No, 1+ = Yes/Multiple)",
       y = "Invested Outside Crowdfunding (0 = No, 1 = Yes)")

Visualization 5: Correlation Heatmap

corr_data <- na.omit(data[vars])
corr_matrix <- cor(corr_data)
corrplot(corr_matrix, method = "color", type = "lower", tl.cex = 0.8)

Summary of Findings