Accident Analysis: Cyclists and Pedestrians

Cyclist MidBlock

Analysis for Cyclist MidBlock This analysis focuses on mode: cyclist | intersection: no
Variable	Level	Injury	p0	Non-Injury	p1	OddsRatio	Lower	Upper	P-Value
oneway	No	167	0.9598	72	0.9863	1
	Yes	7	0.0402	1	0.0137	0.3313	0.04	2.7424	0.4424
twoways	No	6	0.0345	0	0	1
	Yes	168	0.9655	73	1	Inf		Inf	0.1837
clearzone	No	174	1	71	0.9726	1
	Yes	0	0	2	0.0274	Inf		Inf	0.0865
onstreetparking	No	97	0.5575	33	0.4521	1
	Yes	77	0.4425	40	0.5479	1.527	0.8814	2.6452	0.1624
parkinglotgarage	No	57	0.3276	31	0.4247	1
	Yes	117	0.6724	42	0.5753	0.66	0.3764	1.1576	0.1491
concretebarrier	No	172	0.9885	73	1	1
	Yes	2	0.0115	0	0	0	0		1
laneofparkedcars	No	170	0.977	73	1	1
	Yes	4	0.023	0	0	0	0		0.3224
bikelanewithbarrier	No	174	1	71	0.9726	1
	Yes	0	0	2	0.0274	Inf		Inf	0.0865
offroadbikepathcycletrack	No	172	0.9885	73	1	1
	Yes	2	0.0115	0	0	0	0		1
raisedbikelane	No	171	0.9828	72	0.9863	1
	Yes	3	0.0172	1	0.0137	0.7917	0.081	7.7388	1
twowayprotectedbicyclelane	No	171	0.9828	72	0.9863	1
	Yes	3	0.0172	1	0.0137	0.7917	0.081	7.7388	1
onewayprotectedbicyclelane	No	174	1	72	0.9863	1
	Yes	0	0	1	0.0137	Inf		Inf	0.2955
bufferedbicyclelaneadjacenttocurb	No	169	0.9713	72	0.9863	1
	Yes	5	0.0287	1	0.0137	0.4694	0.0539	4.0897	0.6732
bufferedbicyclelaneoffsetfromcurb	No	174	1	72	0.9863	1
	Yes	0	0	1	0.0137	Inf		Inf	0.2955
paintedbicyclelaneadjacenttocurb	No	138	0.7931	57	0.7808	1
	Yes	36	0.2069	16	0.2192	1.076	0.5535	2.092	0.8648
paintedbicyclelaneoffsetfromcurb	No	165	0.9483	68	0.9315	1
	Yes	9	0.0517	5	0.0685	1.348	0.4358	4.1694	0.5621
bikeaccessibleshoulder	No	162	0.931	68	0.9315	1
	Yes	12	0.069	5	0.0685	0.9926	0.3368	2.926	1
sharedlanewithmarkings	No	166	0.954	72	0.9863	1
	Yes	8	0.046	1	0.0137	0.2882	0.0354	2.3468	0.2884

NULL

if (nrow(odds_ratios_data) > 0) {
  

  odds_ratios_restructured <- odds_ratios_data %>%
    filter(!is.na(OddsRatio)) %>%  
    mutate(Reference = ifelse(Level == "No", "Yes", "No")) %>%  
    select(Variable, Level, Reference, OddsRatio, Lower, Upper, PValue)

  
  odds_ratios_restructured$Variable <- factor(odds_ratios_restructured$Variable, levels = unique(odds_ratios_restructured$Variable))
  
  
  restructured_table_html <- odds_ratios_restructured %>%
    kable("html", caption = "Restructured Odds Ratio Analysis for Medical Interpretation",
          col.names = c("Variable", "Level", "Reference", "Odds Ratio", "Lower 95% CI", "Upper 95% CI", "P-Value")) %>%
    kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"), full_width = FALSE) %>%
    row_spec(0, bold = TRUE, background = "#333333", color = "white") %>%
    row_spec(1:nrow(odds_ratios_restructured), background = rep(c("#f9f9f9", "#ffffff"), length.out = nrow(odds_ratios_restructured))) %>%
    add_header_above(c(" " = 3, "Odds Ratio Analysis" = 5)) 

  print(restructured_table_html)
} else {
  cat("<p><strong>Warning:</strong> No data available for restructuring. Skipping this section.</p><br>")
}

Restructured Odds Ratio Analysis for Medical Interpretation

			Odds Ratio Analysis
	Variable	Level	Reference	Odds Ratio	Lower 95% CI	Upper 95% CI	P-Value
oneway.No	oneway	No	Yes	1.0000	NA	NA	NA
oneway.Yes		Yes	No	0.3313	0.0400	2.7424	0.4424
twoways.No	twoways	No	Yes	1.0000	NA	NA	NA
twoways.Yes		Yes	No	Inf	NaN	Inf	0.1837
clearzone.No	clearzone	No	Yes	1.0000	NA	NA	NA
clearzone.Yes		Yes	No	Inf	NaN	Inf	0.0865
onstreetparking.No	onstreetparking	No	Yes	1.0000	NA	NA	NA
onstreetparking.Yes		Yes	No	1.5270	0.8814	2.6452	0.1624
parkinglotgarage.No	parkinglotgarage	No	Yes	1.0000	NA	NA	NA
parkinglotgarage.Yes		Yes	No	0.6600	0.3764	1.1576	0.1491
concretebarrier.No	concretebarrier	No	Yes	1.0000	NA	NA	NA
concretebarrier.Yes		Yes	No	0.0000	0.0000	NaN	1.0000
laneofparkedcars.No	laneofparkedcars	No	Yes	1.0000	NA	NA	NA
laneofparkedcars.Yes		Yes	No	0.0000	0.0000	NaN	0.3224
bikelanewithbarrier.No	bikelanewithbarrier	No	Yes	1.0000	NA	NA	NA
bikelanewithbarrier.Yes		Yes	No	Inf	NaN	Inf	0.0865
offroadbikepathcycletrack.No	offroadbikepathcycletrack	No	Yes	1.0000	NA	NA	NA
offroadbikepathcycletrack.Yes		Yes	No	0.0000	0.0000	NaN	1.0000
raisedbikelane.No	raisedbikelane	No	Yes	1.0000	NA	NA	NA
raisedbikelane.Yes		Yes	No	0.7917	0.0810	7.7388	1.0000
twowayprotectedbicyclelane.No	twowayprotectedbicyclelane	No	Yes	1.0000	NA	NA	NA
twowayprotectedbicyclelane.Yes		Yes	No	0.7917	0.0810	7.7388	1.0000
onewayprotectedbicyclelane.No	onewayprotectedbicyclelane	No	Yes	1.0000	NA	NA	NA
onewayprotectedbicyclelane.Yes		Yes	No	Inf	NaN	Inf	0.2955
bufferedbicyclelaneadjacenttocurb.No	bufferedbicyclelaneadjacenttocurb	No	Yes	1.0000	NA	NA	NA
bufferedbicyclelaneadjacenttocurb.Yes		Yes	No	0.4694	0.0539	4.0897	0.6732
bufferedbicyclelaneoffsetfromcurb.No	bufferedbicyclelaneoffsetfromcurb	No	Yes	1.0000	NA	NA	NA
bufferedbicyclelaneoffsetfromcurb.Yes		Yes	No	Inf	NaN	Inf	0.2955
paintedbicyclelaneadjacenttocurb.No	paintedbicyclelaneadjacenttocurb	No	Yes	1.0000	NA	NA	NA
paintedbicyclelaneadjacenttocurb.Yes		Yes	No	1.0760	0.5535	2.0920	0.8648
paintedbicyclelaneoffsetfromcurb.No	paintedbicyclelaneoffsetfromcurb	No	Yes	1.0000	NA	NA	NA
paintedbicyclelaneoffsetfromcurb.Yes		Yes	No	1.3480	0.4358	4.1694	0.5621
bikeaccessibleshoulder.No	bikeaccessibleshoulder	No	Yes	1.0000	NA	NA	NA
bikeaccessibleshoulder.Yes		Yes	No	0.9926	0.3368	2.9260	1.0000
sharedlanewithmarkings.No	sharedlanewithmarkings	No	Yes	1.0000	NA	NA	NA
sharedlanewithmarkings.Yes		Yes	No	0.2882	0.0354	2.3468	0.2884

NULL

if (nrow(odds_ratios_data) > 0) {
  
 
  odds_ratios_restructured <- odds_ratios_data %>%
    filter(!is.na(OddsRatio)) %>%  
    mutate(Reference = ifelse(Level == "No", "Yes", "No")) %>%  
    select(Variable, Level, Reference, OddsRatio, Lower, Upper, PValue)

  
  odds_ratios_restructured$Variable <- factor(odds_ratios_restructured$Variable, levels = unique(odds_ratios_restructured$Variable))
  
  
  restructured_table_html <- odds_ratios_restructured %>%
    kable("html", caption = "Restructured Odds Ratio Analysis for Medical Interpretation",
          col.names = c("Variable", "Level", "Reference", "Odds Ratio", "Lower 95% CI", "Upper 95% CI", "P-Value")) %>%
    kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"), full_width = FALSE) %>%
    row_spec(0, bold = TRUE, background = "#333333", color = "white") %>%
    row_spec(1:nrow(odds_ratios_restructured), background = rep(c("#f9f9f9", "#ffffff"), length.out = nrow(odds_ratios_restructured)))

  print(restructured_table_html)
} else {
  cat("<p><strong>Warning:</strong> No data available for restructuring. Skipping this section.</p><br>")
}

Restructured Odds Ratio Analysis for Medical Interpretation

	Variable	Level	Reference	Odds Ratio	Lower 95% CI	Upper 95% CI	P-Value
oneway.No	oneway	No	Yes	1.0000	NA	NA	NA
oneway.Yes		Yes	No	0.3313	0.0400	2.7424	0.4424
twoways.No	twoways	No	Yes	1.0000	NA	NA	NA
twoways.Yes		Yes	No	Inf	NaN	Inf	0.1837
clearzone.No	clearzone	No	Yes	1.0000	NA	NA	NA
clearzone.Yes		Yes	No	Inf	NaN	Inf	0.0865
onstreetparking.No	onstreetparking	No	Yes	1.0000	NA	NA	NA
onstreetparking.Yes		Yes	No	1.5270	0.8814	2.6452	0.1624
parkinglotgarage.No	parkinglotgarage	No	Yes	1.0000	NA	NA	NA
parkinglotgarage.Yes		Yes	No	0.6600	0.3764	1.1576	0.1491
concretebarrier.No	concretebarrier	No	Yes	1.0000	NA	NA	NA
concretebarrier.Yes		Yes	No	0.0000	0.0000	NaN	1.0000
laneofparkedcars.No	laneofparkedcars	No	Yes	1.0000	NA	NA	NA
laneofparkedcars.Yes		Yes	No	0.0000	0.0000	NaN	0.3224
bikelanewithbarrier.No	bikelanewithbarrier	No	Yes	1.0000	NA	NA	NA
bikelanewithbarrier.Yes		Yes	No	Inf	NaN	Inf	0.0865
offroadbikepathcycletrack.No	offroadbikepathcycletrack	No	Yes	1.0000	NA	NA	NA
offroadbikepathcycletrack.Yes		Yes	No	0.0000	0.0000	NaN	1.0000
raisedbikelane.No	raisedbikelane	No	Yes	1.0000	NA	NA	NA
raisedbikelane.Yes		Yes	No	0.7917	0.0810	7.7388	1.0000
twowayprotectedbicyclelane.No	twowayprotectedbicyclelane	No	Yes	1.0000	NA	NA	NA
twowayprotectedbicyclelane.Yes		Yes	No	0.7917	0.0810	7.7388	1.0000
onewayprotectedbicyclelane.No	onewayprotectedbicyclelane	No	Yes	1.0000	NA	NA	NA
onewayprotectedbicyclelane.Yes		Yes	No	Inf	NaN	Inf	0.2955
bufferedbicyclelaneadjacenttocurb.No	bufferedbicyclelaneadjacenttocurb	No	Yes	1.0000	NA	NA	NA
bufferedbicyclelaneadjacenttocurb.Yes		Yes	No	0.4694	0.0539	4.0897	0.6732
bufferedbicyclelaneoffsetfromcurb.No	bufferedbicyclelaneoffsetfromcurb	No	Yes	1.0000	NA	NA	NA
bufferedbicyclelaneoffsetfromcurb.Yes		Yes	No	Inf	NaN	Inf	0.2955
paintedbicyclelaneadjacenttocurb.No	paintedbicyclelaneadjacenttocurb	No	Yes	1.0000	NA	NA	NA
paintedbicyclelaneadjacenttocurb.Yes		Yes	No	1.0760	0.5535	2.0920	0.8648
paintedbicyclelaneoffsetfromcurb.No	paintedbicyclelaneoffsetfromcurb	No	Yes	1.0000	NA	NA	NA
paintedbicyclelaneoffsetfromcurb.Yes		Yes	No	1.3480	0.4358	4.1694	0.5621
bikeaccessibleshoulder.No	bikeaccessibleshoulder	No	Yes	1.0000	NA	NA	NA
bikeaccessibleshoulder.Yes		Yes	No	0.9926	0.3368	2.9260	1.0000
sharedlanewithmarkings.No	sharedlanewithmarkings	No	Yes	1.0000	NA	NA	NA
sharedlanewithmarkings.Yes		Yes	No	0.2882	0.0354	2.3468	0.2884

NULL

if (nrow(odds_ratios_data) > 0) {
  
  
  odds_ratios_restructured <- odds_ratios_data %>%
    filter(!is.na(OddsRatio)) %>% 
    mutate(
      Reference = ifelse(Level == "No", "Yes", "No"), 
      Significant = ifelse(PValue < 0.05, TRUE, FALSE),  
      CI_95 = ifelse(!is.na(Lower) & !is.na(Upper), paste0("(", round(Lower, 2), ", ", round(Upper, 2), ")"), "NA") 
    ) %>%
    select(Variable, Level, Reference, OddsRatio, CI_95, PValue, Significant)  

 
  odds_ratios_restructured_filtered <- odds_ratios_restructured %>%
    filter(!(OddsRatio == 1 & CI_95 == "NA"))

 
  odds_ratios_restructured_filtered$Variable <- factor(odds_ratios_restructured_filtered$Variable, levels = unique(odds_ratios_restructured_filtered$Variable))
  
 
  if (nrow(odds_ratios_restructured_filtered) > 0) {
    
    
    odds_ratios_restructured_filtered_for_table <- odds_ratios_restructured_filtered %>%
      select(-Significant)

    
    restructured_table_html <- odds_ratios_restructured_filtered_for_table %>%
      kable("html", caption = "Restructured Odds Ratio Analysis for Medical Interpretation",
            col.names = c("Variable", "Level", "Reference", "Odds Ratio", "CI (95%)", "P-Value")) %>%
      kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"), full_width = FALSE) %>%
      row_spec(0, bold = TRUE, background = "#333333", color = "white")
    
   
    if (any(odds_ratios_restructured_filtered$Significant == TRUE)) {
      restructured_table_html <- restructured_table_html %>%
        row_spec(
          which(odds_ratios_restructured_filtered$Significant == TRUE), 
          background = "#ffcccc"  
        )
    }
    
   
    restructured_table_html <- restructured_table_html %>%
      row_spec(1:nrow(odds_ratios_restructured_filtered_for_table), background = rep(c("#f9f9f9", "#ffffff"), length.out = nrow(odds_ratios_restructured_filtered_for_table)))

    
    print(restructured_table_html)
  } else {
    cat("<p><strong>Warning:</strong> No data available for restructuring after filtering. Skipping this section.</p><br>")
  }
  
} else {
  cat("<p><strong>Warning:</strong> No data available for restructuring. Skipping this section.</p><br>")
}

Restructured Odds Ratio Analysis for Medical Interpretation

	Variable	Level	Reference	Odds Ratio	CI (95%)	P-Value
oneway.Yes		Yes	No	0.3313	(0.04, 2.74)	0.4424
twoways.Yes		Yes	No	Inf	NA	0.1837
clearzone.Yes		Yes	No	Inf	NA	0.0865
onstreetparking.Yes		Yes	No	1.5270	(0.88, 2.65)	0.1624
parkinglotgarage.Yes		Yes	No	0.6600	(0.38, 1.16)	0.1491
concretebarrier.Yes		Yes	No	0.0000	NA	1.0000
laneofparkedcars.Yes		Yes	No	0.0000	NA	0.3224
bikelanewithbarrier.Yes		Yes	No	Inf	NA	0.0865
offroadbikepathcycletrack.Yes		Yes	No	0.0000	NA	1.0000
raisedbikelane.Yes		Yes	No	0.7917	(0.08, 7.74)	1.0000
twowayprotectedbicyclelane.Yes		Yes	No	0.7917	(0.08, 7.74)	1.0000
onewayprotectedbicyclelane.Yes		Yes	No	Inf	NA	0.2955
bufferedbicyclelaneadjacenttocurb.Yes		Yes	No	0.4694	(0.05, 4.09)	0.6732
bufferedbicyclelaneoffsetfromcurb.Yes		Yes	No	Inf	NA	0.2955
paintedbicyclelaneadjacenttocurb.Yes		Yes	No	1.0760	(0.55, 2.09)	0.8648
paintedbicyclelaneoffsetfromcurb.Yes		Yes	No	1.3480	(0.44, 4.17)	0.5621
bikeaccessibleshoulder.Yes		Yes	No	0.9926	(0.34, 2.93)	1.0000
sharedlanewithmarkings.Yes		Yes	No	0.2882	(0.04, 2.35)	0.2884

NULL

if (nrow(odds_ratios_data) > 0) {
  
  
  odds_ratios_restructured <- odds_ratios_data %>%
    filter(!is.na(OddsRatio)) %>%  
    mutate(
      Reference = ifelse(Level == "No", "Yes", "No"), 
      Significant = ifelse(!is.na(PValue) & PValue < 0.05, TRUE, FALSE),  
      CI_95 = ifelse(!is.na(Lower) & !is.na(Upper), paste0("(", round(Lower, 2), ", ", round(Upper, 2), ")"), "NA")  
    ) %>%
    select(Variable, Level, Reference, OddsRatio, CI_95, PValue, Significant)  

  
  odds_ratios_restructured$Variable <- factor(odds_ratios_restructured$Variable, levels = unique(odds_ratios_restructured$Variable))
  
  if (nrow(odds_ratios_restructured) > 0) {
    
    
    odds_ratios_restructured_for_table <- odds_ratios_restructured %>%
      select(-Significant)

    
    restructured_table_html <- odds_ratios_restructured_for_table %>%
      kable("html", caption = "Restructured Odds Ratio Analysis for Medical Interpretation (Showing Both Levels)",
            col.names = c("Variable", "Level", "Reference", "Odds Ratio", "CI (95%)", "P-Value")) %>%
      kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"), full_width = FALSE) %>%
      row_spec(0, bold = TRUE, background = "#333333", color = "white")
    
    
    if (any(odds_ratios_restructured$Significant == TRUE, na.rm = TRUE)) {
      restructured_table_html <- restructured_table_html %>%
        row_spec(
          which(odds_ratios_restructured$Significant == TRUE), 
          background = "#ffcccc" 
        )
    }
    
   
    restructured_table_html <- restructured_table_html %>%
      row_spec(1:nrow(odds_ratios_restructured_for_table), background = rep(c("#f9f9f9", "#ffffff"), length.out = nrow(odds_ratios_restructured_for_table)))

   
    print(restructured_table_html)
  } else {
    cat("<p><strong>Warning:</strong> No data available for restructuring after filtering. Skipping this section.</p><br>")
  }
  
} else {
  cat("<p><strong>Warning:</strong> No data available for restructuring. Skipping this section.</p><br>")
}

Restructured Odds Ratio Analysis for Medical Interpretation (Showing Both Levels)

	Variable	Level	Reference	Odds Ratio	CI (95%)	P-Value
oneway.No	oneway	No	Yes	1.0000	NA	NA
oneway.Yes		Yes	No	0.3313	(0.04, 2.74)	0.4424
twoways.No	twoways	No	Yes	1.0000	NA	NA
twoways.Yes		Yes	No	Inf	NA	0.1837
clearzone.No	clearzone	No	Yes	1.0000	NA	NA
clearzone.Yes		Yes	No	Inf	NA	0.0865
onstreetparking.No	onstreetparking	No	Yes	1.0000	NA	NA
onstreetparking.Yes		Yes	No	1.5270	(0.88, 2.65)	0.1624
parkinglotgarage.No	parkinglotgarage	No	Yes	1.0000	NA	NA
parkinglotgarage.Yes		Yes	No	0.6600	(0.38, 1.16)	0.1491
concretebarrier.No	concretebarrier	No	Yes	1.0000	NA	NA
concretebarrier.Yes		Yes	No	0.0000	NA	1.0000
laneofparkedcars.No	laneofparkedcars	No	Yes	1.0000	NA	NA
laneofparkedcars.Yes		Yes	No	0.0000	NA	0.3224
bikelanewithbarrier.No	bikelanewithbarrier	No	Yes	1.0000	NA	NA
bikelanewithbarrier.Yes		Yes	No	Inf	NA	0.0865
offroadbikepathcycletrack.No	offroadbikepathcycletrack	No	Yes	1.0000	NA	NA
offroadbikepathcycletrack.Yes		Yes	No	0.0000	NA	1.0000
raisedbikelane.No	raisedbikelane	No	Yes	1.0000	NA	NA
raisedbikelane.Yes		Yes	No	0.7917	(0.08, 7.74)	1.0000
twowayprotectedbicyclelane.No	twowayprotectedbicyclelane	No	Yes	1.0000	NA	NA
twowayprotectedbicyclelane.Yes		Yes	No	0.7917	(0.08, 7.74)	1.0000
onewayprotectedbicyclelane.No	onewayprotectedbicyclelane	No	Yes	1.0000	NA	NA
onewayprotectedbicyclelane.Yes		Yes	No	Inf	NA	0.2955
bufferedbicyclelaneadjacenttocurb.No	bufferedbicyclelaneadjacenttocurb	No	Yes	1.0000	NA	NA
bufferedbicyclelaneadjacenttocurb.Yes		Yes	No	0.4694	(0.05, 4.09)	0.6732
bufferedbicyclelaneoffsetfromcurb.No	bufferedbicyclelaneoffsetfromcurb	No	Yes	1.0000	NA	NA
bufferedbicyclelaneoffsetfromcurb.Yes		Yes	No	Inf	NA	0.2955
paintedbicyclelaneadjacenttocurb.No	paintedbicyclelaneadjacenttocurb	No	Yes	1.0000	NA	NA
paintedbicyclelaneadjacenttocurb.Yes		Yes	No	1.0760	(0.55, 2.09)	0.8648
paintedbicyclelaneoffsetfromcurb.No	paintedbicyclelaneoffsetfromcurb	No	Yes	1.0000	NA	NA
paintedbicyclelaneoffsetfromcurb.Yes		Yes	No	1.3480	(0.44, 4.17)	0.5621
bikeaccessibleshoulder.No	bikeaccessibleshoulder	No	Yes	1.0000	NA	NA
bikeaccessibleshoulder.Yes		Yes	No	0.9926	(0.34, 2.93)	1.0000
sharedlanewithmarkings.No	sharedlanewithmarkings	No	Yes	1.0000	NA	NA
sharedlanewithmarkings.Yes		Yes	No	0.2882	(0.04, 2.35)	0.2884

NULL

if (nrow(odds_ratios_data) > 0) {
  
  
  odds_ratios_restructured <- odds_ratios_data %>%
    filter(!is.na(OddsRatio)) %>% 
    mutate(
      Reference = ifelse(Level == "No", "Yes", "No"),  
      Significant = ifelse(!is.na(PValue) & PValue < 0.05, TRUE, FALSE),  
      CI_95 = ifelse(!is.na(Lower) & !is.na(Upper), paste0("(", round(Lower, 2), ", ", round(Upper, 2), ")"), "-"),  
      PValue = ifelse(is.na(PValue), "-", as.character(round(PValue, 4))),  
      OddsRatio = ifelse(is.na(OddsRatio), "-", as.character(round(OddsRatio, 4))),  
      NonInjury = ifelse(is.na(NonInjury), "-", as.character(NonInjury)), 
      p1 = ifelse(is.na(p1), "-", paste0(round(as.numeric(p1) * 100, 2), "%"))  
    ) %>%
    select(Variable, Level, Reference, NonInjury, p1, OddsRatio, CI_95, PValue, Significant)

  
  odds_ratios_grouped <- odds_ratios_restructured %>%
    arrange(Variable) %>%
    group_by(Variable) %>%
    mutate(
      Level_Grouped = paste(Level, collapse = " / "),  
      OddsRatio_Grouped = paste(OddsRatio, collapse = " / "),
      CI_95_Grouped = paste(CI_95, collapse = " / "),
      PValue_Grouped = paste(PValue, collapse = " / "),
      NonInjury_Grouped = paste(NonInjury, collapse = " / "),
      p1_Grouped = paste(p1, collapse = " / ")
    ) %>%
    slice(1) %>%  
    ungroup() %>%
    select(Variable, Level_Grouped, Reference, NonInjury_Grouped, p1_Grouped, OddsRatio_Grouped, CI_95_Grouped, PValue_Grouped, Significant)

 
  odds_ratios_grouped$Variable <- factor(odds_ratios_grouped$Variable, levels = unique(odds_ratios_grouped$Variable))
  
 
  if (nrow(odds_ratios_grouped) > 0) {
    
  
    odds_ratios_for_table <- odds_ratios_grouped %>%
      select(-Significant)

  
    restructured_table_html <- odds_ratios_for_table %>%
      kable("html", caption = "Restructured Odds Ratio Analysis for Medical Interpretation (Grouped Levels)",
            col.names = c("Variable", "Level (Yes / No)", "Reference", "Non-Injury (Count)", "Non-Injury (%)", "Odds Ratio (Yes / No)", "CI (95%) (Yes / No)", "P-Value (Yes / No)")) %>%
      kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"), full_width = FALSE, position = "center") %>%
      row_spec(0, bold = TRUE, background = "#333333", color = "white") %>%
      column_spec(1:8, width = "5em", border_left = TRUE, border_right = TRUE)  

    
    if (any(odds_ratios_grouped$Significant == TRUE, na.rm = TRUE)) {
      restructured_table_html <- restructured_table_html %>%
        row_spec(
          which(odds_ratios_grouped$Significant == TRUE), 
          background = "#ffcccc"  
        )
    }
      
    restructured_table_html <- restructured_table_html %>%
      row_spec(1:nrow(odds_ratios_for_table), background = rep(c("#f9f9f9", "#ffffff"), length.out = nrow(odds_ratios_for_table)))

    
    print(restructured_table_html)
  } else {
    cat("<p><strong>Warning:</strong> No data available for restructuring after filtering. Skipping this section.</p><br>")
  }
  
} else {
  cat("<p><strong>Warning:</strong> No data available for restructuring. Skipping this section.</p><br>")
}

Error in `mutate()`:
ℹ In argument: `NonInjury = ifelse(is.na(NonInjury), "-", as.character(NonInjury))`.
Caused by error:
! object 'NonInjury' not found
Backtrace:
  1. ... %>% ...
 10. base::ifelse(is.na(NonInjury), "-", as.character(NonInjury))

Cyclist Intersection

---

pedestrian_midblock_data

---

---

Pedestrian Intersection

¹

Odds ratio Interpretation

OddsRatio:	This value measures the odds of the event (e.g., injury) occurring in the exposed group compared to the unexposed group. An OR of 1 indicates no difference in odds between the groups. An OR greater than 1 suggests that exposure is associated with higher odds of the event. An OR less than 1 indicates that the exposure may be protective or reduce the odds of the event.
Lower and Upper (Confidence Interval):	These values represent the confidence interval (typically 95%) around the odds ratio. A 95% confidence interval means we are 95% confident that the true OR lies within this range. If the confidence interval includes the value 1, the OR is not statistically significant (i.e., there is not enough evidence to state there’s a difference between the groups). The Lower limit is the lower bound of the confidence interval, and the Upper limit is the upper bound.
P-Value:	This value indicates the statistical significance of the association between exposure and the outcome. A low p-value (usually less than 0.05) suggests that there is sufficient evidence to reject the null hypothesis, indicating a significant association between exposure and the outcome. A high p-value implies that the association is not statistically significant.
Injury (Cases with event) and Non-Injury (Cases without event):	These are the counts of cases in each category (exposed and unexposed) that have or do not have the event of interest (injury). These values show the total number of observations in each group, are helpful in assessing the stability of the results since very low counts can indicate an insufficient sample size to estimate the OR accurately.
p0 and p1:	These represent the proportions of cases with the event (injury) and without the event within each group. p0 is the proportion of cases in the unexposed group that have the event of interest. p1 is the proportion of cases in the exposed group that have the event of interest. These proportions allow for a quick visualization of the difference in event rates between the groups.

Example Interpretation:

If you obtain an OR of 1.5 with a confidence interval of 1.2 to 1.8 and a p-value of 0.01, you could interpret this as: * There is a significant association (p-value < 0.05) between the exposure and the event. * The exposed group has a 50% higher chance of experiencing the event (injury) compared to the unexposed group. * Since the confidence interval does not include 1, this relationship is statistically significant.

On the other hand, if the OR is close to 1, the confidence interval includes 1 (e.g., OR = 1.1, CI = 0.9 to 1.3), and the p-value is high (> 0.05), then there is not enough evidence to conclude that there is an association between the exposure and the outcome.

---

1. When using the epitab function from the epitools package in R to calculate odds ratios (OR), it generates several important statistics and measures that help interpret the relationship between an exposure (e.g., a particular road feature) and an outcome (e.g., injury).↩︎