Complete this markdown for today’s lab. You may work with your classmates, but each person needs to fill out their own markdown file. At the end of class, you can submit either this compiled document as a word or pdf file, or a separate document with your figures and answers.

Recall, we tested for the effects of location and seine size on diversity. Before we start, write out some hypotheses for your data.

Hypothesis: Species diversity will differ between St. John’s and Waterfront because the two locations have different environmental conditions.

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(ggplot2)
library(tidyr)
library(emmeans)
## Welcome to emmeans.
## Caution: You lose important information if you filter this package's results.
## See '? untidy'

Wrangling the Data

In this section, you will need to read in and summarize your data.

Read in data

Data <- read.csv("SeiningData (1).csv") # Loads the seining dataset into R
Data$Location <- trimws(Data$Location) # Removes extra spaces from location names
head(Data) # Displays the first six rows to check that the data loaded correctly
##     Location Seine_Num   Organism Number
## 1 St. John's         1 Silverside      4
## 2 St. John's         1 Silverside      1
## 3 St. John's         1 Silverside      5
## 4 St. John's         1  Killifish      1
## 5 St. John's         2  Mummichog      1
## 6 St. John's         2  Blue Crab      1

Calculate Diversity Indices, grouping by each seine and seine size

Job 1: Calculate the parts needed for the Shannon index. Name your new dataframe Diversity_data.

Hint: 1) Remember that you can use group_by() to group your variables before a calculation, 2) Last lab you used summarize. This time (and this time only) you’ll use reframe() because you want multiple rows to reference the same Total_Ind value. You can write the code with summarize, and just replace summarize with reframe to make the deprecation warning go away. When you’re done, you should have a dataframe with a column for Location, Seine Size, Total Individuals, Proportion of Individuals (pi), and the pi*logpi (pilogpi).
\[ H = -\Sigma p_i ln p_i \]

  1. calculate the total number of individuals in each seine using sum(Number). Call this Total_ind
  2. calculate the proportion of individuals in each seine (call it Prop_ind = Number/Total_ind).
  3. calculate plog(p) for each row this is p_logp = Prop_ind*log(Prop_ind)
All_seines <- Data %>% distinct(Location, Seine_Num) # Saves all seine samples, including ones with zero organisms

Species_counts <- Data %>% # Starts organizing the seining data
  filter(!is.na(Organism), !is.na(Number), Number > 0) %>% # Removes missing organisms and zero catches
  group_by(Location, Seine_Num, Organism) %>% # Groups the data by location, seine number, and species
  summarise(Number = sum(Number), .groups = "drop") # Adds together the number of individuals for each species

Diversity_data <- Species_counts %>% # Starts calculating the Shannon diversity components
  group_by(Location, Seine_Num) %>% # Groups organisms within each seine sample
  mutate(Total_ind = sum(Number)) %>% # Calculates the total number of individuals in each seine
  mutate(Prop_ind = Number / Total_ind) %>% # Calculates the proportion of individuals belonging to each species
  mutate(p_logp = Prop_ind * log(Prop_ind)) %>% # Calculates the proportion multiplied by its natural logarithm
  ungroup() # Removes grouping from the completed dataframe

print(Diversity_data) # Displays the diversity calculations
## # A tibble: 19 × 7
##    Location   Seine_Num Organism          Number Total_ind Prop_ind  p_logp
##    <chr>          <int> <chr>              <int>     <int>    <dbl>   <dbl>
##  1 St. John's         1 Killifish              1        11   0.0909 -0.218 
##  2 St. John's         1 Silverside            10        11   0.909  -0.0866
##  3 St. John's         2 Blue Crab              1         3   0.333  -0.366 
##  4 St. John's         2 Mummichog              1         3   0.333  -0.366 
##  5 St. John's         2 Silverside             1         3   0.333  -0.366 
##  6 St. John's         3 Silverside            20        20   1       0     
##  7 St. John's         4 Silverside             7         7   1       0     
##  8 St. John's         5 Mummichog              1         4   0.25   -0.347 
##  9 St. John's         5 Silverside             3         4   0.75   -0.216 
## 10 Waterfront         3 Blue Crab              1        12   0.0833 -0.207 
## 11 Waterfront         3 Mummichog              3        12   0.25   -0.347 
## 12 Waterfront         3 Shrimp                 1        12   0.0833 -0.207 
## 13 Waterfront         3 Silverside             7        12   0.583  -0.314 
## 14 Waterfront         4 Shrimp                17        27   0.630  -0.291 
## 15 Waterfront         4 Shripped Killfish      1        27   0.0370 -0.122 
## 16 Waterfront         4 Silverside             9        27   0.333  -0.366 
## 17 Waterfront         5 Killifish              2         8   0.25   -0.347 
## 18 Waterfront         5 Shrimp                 1         8   0.125  -0.260 
## 19 Waterfront         5 Silverside             5         8   0.625  -0.294

Job 2: Summarize the following for each location so that you can make a figure

  1. Species richness -> Richness = length(!is.na(p_logp))
  2. Shannon H -> ShannonH = -sum(p_logp)
  3. Evenness = ShannonH/Richness
Diversity_data_Summary <- Diversity_data %>% # Starts summarizing diversity for each seine
  group_by(Location, Seine_Num) %>% # Groups the data by location and seine number
  summarise(Richness = n_distinct(Organism), # Counts the different species collected
            ShannonH = -sum(p_logp), # Calculates Shannon diversity
            Evenness = ShannonH / Richness, # Calculates evenness using the assignment's formula
            .groups = "drop") # Removes grouping from the summary

Diversity_data_Summary <- All_seines %>% # Starts with all seine samples, including empty ones
  left_join(Diversity_data_Summary, by = c("Location", "Seine_Num")) %>% # Combines all seines with their diversity values
  mutate(Richness = coalesce(Richness, 0L)) # Gives empty seines a richness of zero

print(Diversity_data_Summary) # Displays the completed diversity summary table
##      Location Seine_Num Richness  ShannonH  Evenness
## 1  St. John's         1        2 0.3046361 0.1523180
## 2  St. John's         2        3 1.0986123 0.3662041
## 3  St. John's         5        2 0.5623351 0.2811676
## 4  St. John's         3        1 0.0000000 0.0000000
## 5  St. John's         4        1 0.0000000 0.0000000
## 6  Waterfront         1        0        NA        NA
## 7  Waterfront         2        0        NA        NA
## 8  Waterfront         3        4 1.0751393 0.2687848
## 9  Waterfront         4        3 0.7795536 0.2598512
## 10 Waterfront         5        3 0.9002561 0.3000854

Note that we cannot divide by 0, so seines with 0 species cannot be counted (this occured twice at the waterfront). You should report this.

Two seines at Waterfront had no species collected. These samples were counted as zero for species richness but were left out of the Shannon diversity and evenness calculations because we cannot divide by zero. So we just ignored the values.(NA)

Summarize Data for Diversity Indices

Summarize both richness and the Shannon index. Name your dataframe Diversity_plotdata

You can ignore NAs using na.rm=TRUE (e.g.Mean_ShannonH = mean(ShannonH,na.rm=TRUE) ), but you must report and discuss this.

Diversity_plotdata <- Diversity_data_Summary %>% # Starts summarizing the diversity data for each location
  group_by(Location) %>% # Groups the seine samples by location
  summarise(Mean_Richness = mean(Richness, na.rm = TRUE), # Calculates average species richness
            SE_Richness = sd(Richness, na.rm = TRUE) / sqrt(sum(!is.na(Richness))), # Calculates standard error for richness
            Mean_ShannonH = mean(ShannonH, na.rm = TRUE), # Calculates average Shannon diversity
            SE_ShannonH = sd(ShannonH, na.rm = TRUE) / sqrt(sum(!is.na(ShannonH))), # Calculates standard error for Shannon diversity
            Mean_Evenness = mean(Evenness, na.rm = TRUE), # Calculates average evenness
            SE_Evenness = sd(Evenness, na.rm = TRUE) / sqrt(sum(!is.na(Evenness))), # Calculates standard error for evenness
            n_Richness = sum(!is.na(Richness)), # Counts the number of valid richness samples
            n_ShannonH = sum(!is.na(ShannonH)), # Counts the number of valid Shannon diversity samples
            n_Evenness = sum(!is.na(Evenness)), # Counts the number of valid evenness samples
            .groups = "drop") # Removes grouping from the completed summary

print(Diversity_plotdata) # Display as a table
## # A tibble: 2 × 10
##   Location   Mean_Richness SE_Richness Mean_ShannonH SE_ShannonH Mean_Evenness
##   <chr>              <dbl>       <dbl>         <dbl>       <dbl>         <dbl>
## 1 St. John's           1.8       0.374         0.393      0.205          0.160
## 2 Waterfront           2         0.837         0.918      0.0858         0.276
## # ℹ 4 more variables: SE_Evenness <dbl>, n_Richness <int>, n_ShannonH <int>,
## #   n_Evenness <int>

Statistical analyses

I have given you the code for an anova with species richness, you will need to do the same for Shannon’s H and Evenness.

mod1 <- lm(Richness ~ Location, data = Diversity_data_Summary) # Tests whether species richness differs between locations
anova(mod1) # Displays the ANOVA results for species richness
## Analysis of Variance Table
## 
## Response: Richness
##           Df Sum Sq Mean Sq F value Pr(>F)
## Location   1    0.1     0.1  0.0476 0.8327
## Residuals  8   16.8     2.1
mod2 <- lm(ShannonH ~ Location, data = Diversity_data_Summary) # Tests whether Shannon diversity differs between locations
anova(mod2) # Displays the ANOVA results for Shannon diversity
## Analysis of Variance Table
## 
## Response: ShannonH
##           Df  Sum Sq Mean Sq F value Pr(>F)
## Location   1 0.51719 0.51719  3.4967 0.1107
## Residuals  6 0.88744 0.14791
mod3 <- lm(Evenness ~ Location, data = Diversity_data_Summary) # Tests whether evenness differs between locations
anova(mod3) # Displays the ANOVA results for evenness
## Analysis of Variance Table
## 
## Response: Evenness
##           Df   Sum Sq  Mean Sq F value Pr(>F)
## Location   1 0.025362 0.025362  1.3915 0.2828
## Residuals  6 0.109353 0.018226

Reporting

Generate a figure for each metric (you may include them in one multi-panel figure) and write a caption that includes the following:

  1. Labels for both axes, including units if applicable

  2. Number of replicates in each group (n) if applicable

  3. Any abbreviations used

  4. What error bars represent (e.g. ± SE) and what any colors/shapes etc. mean

  5. A brief takehome point

Then write a short results section that references yoru figures, is supported by statistical analysis, (e.g. P < 0.001). As always, lead with the biology, and use stats to support. E.g. Species richness was 10 times higher in the upland marsh compared to the lowland marsh (P=0.025).

Diversity_long <- Diversity_plotdata %>% # Starts preparing the diversity averages for graphing
  pivot_longer(cols = starts_with("Mean_"), names_to = "Metric", values_to = "Mean") %>% # Combines the three diversity metrics into one column
  mutate(Metric = sub("Mean_", "", Metric)) %>% # Removes Mean_ from the metric names
  mutate(SE = case_when(Metric == "Richness" ~ SE_Richness, Metric == "ShannonH" ~ SE_ShannonH, TRUE ~ SE_Evenness)) %>% # Matches each diversity metric with its standard error
  mutate(n = case_when(Metric == "Richness" ~ n_Richness, Metric == "ShannonH" ~ n_ShannonH, TRUE ~ n_Evenness)) # Matches each metric with its sample size

ggplot(Diversity_long, aes(x = Location, y = Mean, fill = Location)) + # Sets up the graph using location and mean diversity
  geom_col() + # Creates bars showing average diversity at each location
  geom_errorbar(aes(ymin = pmax(0, Mean - SE), ymax = Mean + SE), width = 0.2) + # Adds standard error bars
  geom_text(aes(label = paste0("n = ", n)), vjust = -0.7) + # Shows the number of samples above each bar
  facet_wrap(~Metric, scales = "free_y") + # Creates separate panels for richness, Shannon diversity, and evenness
  labs(x = "Sampling Location", y = "Mean Diversity Value", title = "Species Diversity by Location") + # Adds the graph title and axis labels
  theme_minimal() + # Gives the graph a clean appearance
  theme(legend.position = "none") + # Removes the extra legend
  scale_y_continuous(expand = expansion(mult = c(0, 0.25))) # Adds room above the bars for sample sizes

Figure 1: This graph compares species richness, Shannon diversity, and evenness at St. John’s and Waterfront. Pink bars represent St. John’s, and blue bars represent Waterfront. Error bars show standard error (SE). Each location had five samples for richness, but only three Waterfront samples were used for Shannon diversity and evenness. Overall, Waterfront had higher average diversity.

Results: Species diversity was higher at Waterfront compared to St. John’s (Figure 1). Waterfront had slightly more species on average (2.0 vs. 1.8), but the difference was not significant (p = 0.833). Shannon diversity (p = 0.111) and evenness (p = 0.283) were also higher at Waterfront, but neither difference was statistically significant. Overall, the two locations had similar diversity based on our statistical tests.

Questions

Statistics:

  1. Why is the p-value reported as Pr(>F)? What does this mean relative to hypothesis testing? The p-value is shown as Pr(>F) because Anova compares the groups. If the p-value is below 0.05, the difference is significant. Since all our p-values were above 0.05, there was no significant difference between the locations.

2)What insights (if any) did using multiple metrics for species diversity provide? Using multiple metrics helped us understand species diversity better. Richness showed how many species were collected, Shannon diversity and evenness showed how the organisms were distributed. Waterfront had higher averages, but the differences were not statistically significant.

Water Quality

We took a lot of measurements of water quality. In this section of the lab, I want you to do something interesting. You can use either a regression or anova design, but be sure to choose the appropriate one. Here, provide

  1. A figure with appropriate caption

  2. An appropriate statistical analysis

  3. A paragraph written in the style of a results section properly referencing your figure and reporting your results.

#Water Quality

Water <- read.csv("WaterQualityData (1).csv") # Loads the water quality dataset

Water$Location <- trimws(Water$Location) # Removes extra spaces from location names

Water_groupmeans <- Water %>% # Starts organizing the water quality data
  group_by(Group, Location) %>% # Groups measurements by student group and location
  summarise(Salinity = mean(Salinity, na.rm = TRUE), .groups = "drop") # Calculates average salinity for each group

Water_summary <- Water_groupmeans %>% # Starts summarizing salinity by location
  group_by(Location) %>% # Groups the data by sampling location
  summarise(Mean_Salinity = mean(Salinity), # Calculates the average salinity
            SE_Salinity = sd(Salinity) / sqrt(n()), # Calculates the standard error
            .groups = "drop") # Removes grouping from the summary

water_mod <- lm(Salinity ~ Location + Group, data = Water_groupmeans) # Tests location differences while accounting for student group

anova(water_mod) # Displays the ANOVA results
## Analysis of Variance Table
## 
## Response: Salinity
##           Df Sum Sq Mean Sq  F value    Pr(>F)    
## Location   2 425.64 212.819 482.0956 1.707e-05 ***
## Group      2   2.27   1.136   2.5723    0.1913    
## Residuals  4   1.77   0.441                       
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
ggplot(Water_summary, aes(x = Location, y = Mean_Salinity, fill = Location)) + # Sets up the salinity graph
  geom_col() + # Creates bars showing average salinity
  geom_errorbar(aes(ymin = pmax(0, Mean_Salinity - SE_Salinity), ymax = Mean_Salinity + SE_Salinity), width = 0.2) + # Adds standard error bars
  labs(x = "Sampling Location", y = "Mean Salinity (dataset units)", title = "Salinity by Location") + # Adds axis labels and a graph title
  theme_minimal() + # Makes the graph easier to read
  theme(legend.position = "none") # Removes the unnecessary legend

Figure 2:This graph shows the average salinity at Schafer, St. John’s, and Waterfront. The different colors represent each location, and the error bars show standard error (SE). Each location had three samples (n = 3). Schafer had the lowest salinity, while Waterfront had the highest.