data <- data.frame( consumer_id = 1:40, age = c(23,25,26,27,24,28,30,29,22,25, 24,27,23,26,28,24,25,26,23,27, 29,24,28,27,22,26,24,25,23,27, 28,29,25,26,24,23,27,25,26,24), brand = rep(c(“Lincoln Financial”, “Prudential Financial”, “John Hancock”, “Principal Group”), each = 10), perception_score = c(4.6,3.9,4.2,3.8, 4.7,3.7,4.1,3.9, 4.5,3.8,4.0,3.7, 4.8,3.9,4.2,3.8, 4.6,3.8,4.1,3.7, 4.7,3.9,4.0,3.8, 4.5,3.8,4.2,3.9, 4.6,3.7,4.1,3.8, 4.7,3.9,4.0,3.7) )

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(readxl)
df <- read_excel("perceptions.xlsx")
colnames(df) <- trimws(colnames(df))
df$Age <- as.numeric(df$Age)
younger <- df %>%
  filter(Age < 28) %>%
  mutate(group = ifelse(brand == "Lincoln Financial", "Lincoln", "Competitors"))
head(younger)

## # A tibble: 4 × 5
##   Consumer_id   Age brand                perception_score group      
##         <dbl> <dbl> <chr>                           <dbl> <chr>      
## 1           1    22 Lincoln Financial                   2 Lincoln    
## 2           2    23 Prudential Financial                3 Competitors
## 3           3    21 John Hancock                        2 Competitors
## 4           4    25 Principal Financial                 1 Competitors

table(younger$group)

## 
## Competitors     Lincoln 
##           3           1

t_test_result <- t.test(perception_score ~ group, data = younger, var.equal = TRUE)
print(t_test_result)

## 
##  Two Sample t-test
## 
## data:  perception_score by group
## t = 0, df = 2, p-value = 1
## alternative hypothesis: true difference in means between group Competitors and group Lincoln is not equal to 0
## 95 percent confidence interval:
##  -4.968275  4.968275
## sample estimates:
## mean in group Competitors     mean in group Lincoln 
##                         2                         2