Epiconcept is made up of a team of doctors, epidemiologists, data scientists and digital specialists. For more than 20 years, Epiconcept has contributed to the improvement of public health by writing software, carrying out epidemiological studies, research, evaluation and training to better detect, monitor and prevent disease and to improve treatment.

Package Epistats

Description

The EpiStats package is a set of functions aimed at epidemiologists. They include commands for measures of association and impact for case control studies and cohort studies. They may be particularly useful for outbreak investigations and include univariate and stratified analyses.

The generic function crossTable provides a contingency table with optional parameters percent and statistic

The functions for cohort studies include the CS, CSTable and CSInter commands.

The functions for case control studies include the CC, CCTable and CCInter commands.

All variables used need to be numeric binary variables and coded as 0 and 1 or as factors.

Cohort study functions:

The cohort study functions relate to cohort studies that measure risks, rather than rates in person- time.

The CS function provides a 2 by 2 table and measures the association between the outcome and one exposure. It includes the risk ratio and its 95% confidence intervals, the attributable fraction among the exposed and unexposed, and a chi square test and its p-value.

The CSTable function displays the measures of association between the outcome and a set of exposures in a table (risk ratios, confidence intervals and p-values). This helps the researcher to compare between exposures and provides a nice table for reports.

The CSInter function investigates the effect of a third variable on the association between an exposure and the outcome. It presents two by two tables stratified by the levels of a third value. It provides the Woolf test for homogeneity between stratum-specific risk ratios. It provides the crude risk ratio between an exposure and an outcome and the risk ratio adjusted by the third variable. CSInter helps the researcher understand whether a third variable may have an effect modifying or confounding effect on the association between an exposure and the outcome.

Case control study functions:

The CC function provides a 2 by 2 table and measures the association between the outcome and one exposure. It includes the odds ratio and its 95% confidence intervals, the attributable fraction among the exposed, and a chi square test and its p-value.

The CCTable function displays the measures of association between the outcome and a set of exposures in a table (odds ratios, confidence intervals and p-values). This helps the researcher to compare between exposures and provides a nice table for reports.

The CCInter function investigates the effect of a third variable on the association between an exposure and the outcome. It presents two by two tables stratified by the levels of a third value. It provides the Woolf test for homogeneity between stratum-specific odds ratios. It provides the crude odds ratio between an exposure and an outcome and the odds ratio adjusted by the third variable. CCInter helps the researcher understand whether a third variable may have an effect modifying or confounding effect on the association between an exposure and the outcome.

The “Tiramisu” dataset

The dataset used in this vignette is from an outbreak investigation carried out in Germany in 1998 by Anja Hauri, Robert Koch Institute. It is used in case studies by organisations including EPIET, ECDC and EpiConcept.

The CSTable, CSInter, CCTable and CCInter functions are based on commands written in Stata by Gilles Desve, who we gratefully acknowledge.

Working with Epistats and “Tiramisu” dataset

Loading and recoding the dataset

library(EpiStats)
library(dplyr)
library(knitr)

options(knitr.kable.NA = '')
#options(width=200)

data(Tiramisu)
DF <- Tiramisu

DF <- DF %>%
  # Recoding all variables as binary '0' or '1'
  mutate(salmon = ifelse(salmon == 9, NA, salmon)) %>% 
  mutate(horseradish = ifelse(horseradish == 9, NA, horseradish)) %>% 
  mutate(pork = ifelse(pork == 9, NA, pork)) %>% 
  mutate(sex01 = case_when(sex == "females" ~ 1, sex == "males" ~ 0)) %>% 
  mutate(agegroup = case_when(age < 30 ~ 0, age >= 30 ~ 1)) %>%
  mutate(tportion = case_when(tportion == 0 ~ 0, tportion == 1 ~ 1, tportion >= 2 ~ 2)) %>%
  mutate(tportion = as.factor(tportion)) %>%
  as.data.frame(stringsAsFactors=TRUE)

Colnames <- DF %>% 
  select(-ill, -age, -sex, -dateonset, -uniquekey, -tportion, -mportion) %>% 
  colnames()

crossTable

Creates a contingency table of variable of interest and exposure. Percentage are optionals by row or by column. It can provides an optional statistic (fisher or chisquare).

Syntax

crosTable(data, var1, var2, percent=“none”, statistic=“none”)

Examples

Recoding some data to have ordered factors

DF2 <- DF
DF2$ill <- factor(DF2$ill, levels=c(1,0), ordered = TRUE)
DF2$beer <- factor(DF2$beer, levels=c(1,0), ordered = TRUE)
DF2$tira <- factor(DF2$tira, levels=c(1,0), ordered = TRUE)
DF2$sex <- factor(DF2$sex, levels = c("males", "females"), ordered = TRUE)

Example 1: crossTable ill - tira

ret <- crossTable(DF2, var1="ill", var2="tira")
ret

##   tira / ill   1   0 Total
## 1          1  94  27   121
## 2          0   7 158   165
## 3      Total 101 185   286

kable(ret, align="r")

tira / ill	1	0	Total
1	94	27	121
0	7	158	165
Total	101	185	286

Example 2: crossTable ill - sex with column percentage and chi2 stat

ret <- crossTable(DF2, "ill", "sex", "col", "chi2")
kable(ret, align="r", caption = "with columns %")

with columns %
sex / ill	1	0	Total
males	50	102	152
%	48.54	54.26	52.23
females	53	86	139
%	51.46	45.74	47.77
Total	103	188	291
%	100.00	100.00	100.00
-	-	-	-
Pearson CHI2	0.8701	Pr	0.351

Example 3: CrossTable ill - sex with row percentage and Fisher stat

NB: All parameters are unquoted

ret <- crossTable(DF2, ill, sex, row, fisher)
ret

##        sex / ill     1     %   0     % Total   %
## 1          males    50 32.89 102 67.11   152 100
## 2        females    53 38.13  86 61.87   139 100
## 3          Total   103 35.40 188 64.60   291 100
## 4              -     -     -   -     -     -   -
## 5 Fisher's exact 0.391     -   -     -     -   -

kable(ret, align="r")

sex / ill	1	%	0	%	Total	%
males	50	32.89	102	67.11	152	100
females	53	38.13	86	61.87	139	100
Total	103	35.40	188	64.60	291	100
-	-	-	-	-	-	-
Fisher’s exact	0.391	-	-	-	-	-

CrossTable beer - sex with column and row percentages and Chi2 stat

NB: All parameters are unquoted

ret <- crossTable(DF2, beer, sex, both, chi2)
ret

##     sex / beer       1     %      0     %  Total      %
## 1        males      84 59.15     58 40.85    142 100.00
## 2            %   79.25     -  35.15     -      -      -
## 3      females      22 17.05    107 82.95    129 100.00
## 4            %   20.75     -  64.85     -      -      -
## 5        Total     106 39.11    165 60.89    271 100.00
## 6            %  100.00     - 100.00     - 100.00      -
## 7            -       -     -      -     -      -      -
## 8 Pearson CHI2 50.3078    Pr      0     -      -      -

kable(ret, align="r", caption = "% rows and columns")

% rows and columns
sex / beer	1	%	0	%	Total	%
males	84	59.15	58	40.85	142	100.00
%	79.25	-	35.15	-	-	-
females	22	17.05	107	82.95	129	100.00
%	20.75	-	64.85	-	-	-
Total	106	39.11	165	60.89	271	100.00
%	100.00	-	100.00	-	100.00	-
-	-	-	-	-	-	-
Pearson CHI2	50.3078	Pr	0	-	-	-

CS

CS analyses cohort studies with equal follow-up time per subject. The risk (the proportion of individuals who become cases) is calculated overall and among the exposed and unexposed. Note that all variables need to be numeric and binary and coded as “0” and “1”.

Point estimates and confidence intervals for the risk ratio and risk difference are calculated, along with attributable or preventive fractions for the exposed and the total population. Additionally you can select if you want to display the Fisher’s exact test, by specifying exact = TRUE. If you specify full = TRUE you can easily access useful statistics from the output tables.

Syntax

CS(x, cases, exposure, exact, full=FALSE)

Example 1: CS ill - mousse (unformatted)

CS(DF, "ill", "mousse", exact = FALSE)

## $df1
##           Cases Non Cases Total Risk
## Exposed      81        42   123 0.66
## Unexposed    22       144   166 0.13
## Total       103       186   289 0.36
## 
## $df2
##                 Point estimate 95%CI.ll 95%CI.ul
## Risk difference           0.53     0.43     0.62
## Risk ratio                4.97     3.30     7.48
## Attr. frac. ex.           0.80     0.70     0.87
## Attr. frac. pop           0.63       NA       NA
## chi2(1)                  85.22       NA       NA
## Pr>chi2                  0.000       NA       NA

Example 2: CS ill - beer (formatted)

The following results tables are outputs in “markdown” using the kable function.

result <- CS(DF, "ill", "beer", exact = TRUE, full = TRUE)
kable(result$df1, align = "r")

	Cases	Non Cases	Total	Risk
Exposed	30	76	106	0.28
Unexposed	69	96	165	0.42
Total	99	172	271	0.37

kable(result$df2, align = result$df2.align )

	Point estimate	95%CI.ll	95%CI.ul
Risk difference	-0.14	-0.25	-0.02
Risk ratio	0.68	0.48	0.96
Prev. frac. ex.	0.32	0.04	0.52
Prev. frac. pop	0.13	NA	NA
chi2(1)	5.09	NA	NA
Pr>chi2	0.024	NA	NA
Fisher p.value	0.028	NA	NA

By storing the results in the object “result”, you are able to use the result tables in Markdown as shown above. By specifying “full = TRUE” you can also easily use individual elements of the results. For example if you would like to view just the risk ratio, you can view it by typing:

result$st$risk_ratio$point_estimate

## [1] 0.6767842

CSTable - Summary table for cohort studies

CSTable is used for univariate analysis of cohort studies with several exposures. The results are summarised in one table with one row per exposure making comparisons between exposures easier and providing a useful table for integrating into reports. Note that all variables need to be numeric and binary and coded as “0” and “1”.

The results of this function contain: The name of exposure variables, the total number of exposed, the number of exposed cases, the attack rate among the exposed, the total number of unexposed, the number of unexposed cases, the attack rate among the unexposed, risk ratios, 95% confidence intervals, 95% p-values.

You can optionally choose to display the Fisher’s exact p-value instead of the Chi squared p-value, with the option exact = TRUE.

You can specify the sort order, with the option sort=“rr” to order by risk ratios. The default sort order is by p-values.

The option “full = TRUE” provides you with useful formatting information, which can be handy if you’re using “markdown”.

Syntax

CSTable(x, cases, exposure=c(), exact=FALSE, sort = “pvalue”, full=FALSE)

Example 1: CSTable results ordered by p-value (unformatted)

CSTable(DF,
        "ill",
        exposure = c("sex01", "agegroup", "tira", "beer", "mousse", "wmousse", "dmousse",
                     "redjelly", "fruitsalad", "tomato", "mince", "salmon", "horseradish",
                     "chickenwin", "roastbeef", "pork"))

## $df
##             Tot.Exp Cases.Exp AR.Exp% Tot.Unexp Cases.Unexp AR.Unexp%    RR
## tira            121        94   77.69       165           7      4.24 18.31
## mousse          123        81   65.85       166          22     13.25  4.97
## wmousse          72        49   68.06       205          49     23.90  2.85
## dmousse         113        76   67.26       174          26     14.94  4.50
## redjelly         79        45   56.96       212          58     27.36  2.08
## fruitsalad       71        46   64.79       220          57     25.91  2.50
## beer            106        30   28.30       165          69     41.82  0.68
## tomato           83        35   42.17       208          68     32.69  1.29
## pork            120        48   40.00       169          54     31.95  1.25
## horseradish      72        30   41.67       217          72     33.18  1.26
## sex01           139        53   38.13       152          50     32.89  1.16
## roastbeef        29         8   27.59       262          95     36.26  0.76
## chickenwin       84        33   39.29       207          70     33.82  1.16
## mince            87        32   36.78       204          71     34.80  1.06
## agegroup         68        25   36.76       215          75     34.88  1.05
## salmon          104        37   35.58       183          63     34.43  1.03
##             CI.ll CI.ul p(Chi2)
## tira         8.81 38.04   0.000
## mousse       3.30  7.48   0.000
## wmousse      2.13  3.81   0.000
## dmousse      3.09  6.56   0.000
## redjelly     1.56  2.79   0.000
## fruitsalad   1.89  3.31   0.000
## beer         0.48  0.96   0.024
## tomato       0.94  1.77   0.127
## pork         0.92  1.71   0.158
## horseradish  0.90  1.75   0.192
## sex01        0.85  1.58   0.351
## roastbeef    0.41  1.40   0.354
## chickenwin   0.84  1.61   0.377
## mince        0.76  1.48   0.747
## agegroup     0.73  1.51   0.777
## salmon       0.75  1.43   0.844

Example 2: CSTable results ordered by risk ratio (formatted)

The following results tables are outputs in “markdown” using the kable function.

res = CSTable(DF, "ill", sort = "rr", exposure = Colnames, full = TRUE)

kable(res$df, digits=res$digits, align=res$align)

	Tot.Exp	Cases.Exp	AR.Exp%	Tot.Unexp	Cases.Unexp	AR.Unexp%	RR	CI.ll	CI.ul	p(Chi2)
tira	121	94	77.69	165	7	4.24	18.31	8.81	38.04	0.000
mousse	123	81	65.85	166	22	13.25	4.97	3.30	7.48	0.000
dmousse	113	76	67.26	174	26	14.94	4.50	3.09	6.56	0.000
wmousse	72	49	68.06	205	49	23.90	2.85	2.13	3.81	0.000
fruitsalad	71	46	64.79	220	57	25.91	2.50	1.89	3.31	0.000
redjelly	79	45	56.96	212	58	27.36	2.08	1.56	2.79	0.000
tomato	83	35	42.17	208	68	32.69	1.29	0.94	1.77	0.127
horseradish	72	30	41.67	217	72	33.18	1.26	0.90	1.75	0.192
pork	120	48	40.00	169	54	31.95	1.25	0.92	1.71	0.158
chickenwin	84	33	39.29	207	70	33.82	1.16	0.84	1.61	0.377
sex01	139	53	38.13	152	50	32.89	1.16	0.85	1.58	0.351
mince	87	32	36.78	204	71	34.80	1.06	0.76	1.48	0.747
agegroup	68	25	36.76	215	75	34.88	1.05	0.73	1.51	0.777
salmon	104	37	35.58	183	63	34.43	1.03	0.75	1.43	0.844
roastbeef	29	8	27.59	262	95	36.26	0.76	0.41	1.40	0.354
beer	106	30	28.30	165	69	41.82	0.68	0.48	0.96	0.024

Example 3: CSTable results ordered by p-value from the Fisher’s exact test (formatted)

The following results tables are outputs in “markdown” using the kable function.

res = CSTable(DF, "ill", exact = TRUE, exposure = Colnames, full = TRUE)
kable(res$df, digits=res$digits, align=res$align)

	Tot.Exp	Cases.Exp	AR.Exp%	Tot.Unexp	Cases.Unexp	AR.Unexp%	RR	CI.ll	CI.ul	p(Fisher)
tira	121	94	77.69	165	7	4.24	18.31	8.81	38.04	0.000
wmousse	72	49	68.06	205	49	23.90	2.85	2.13	3.81	0.000
dmousse	113	76	67.26	174	26	14.94	4.50	3.09	6.56	0.000
mousse	123	81	65.85	166	22	13.25	4.97	3.30	7.48	0.000
redjelly	79	45	56.96	212	58	27.36	2.08	1.56	2.79	0.000
fruitsalad	71	46	64.79	220	57	25.91	2.50	1.89	3.31	0.000
beer	106	30	28.30	165	69	41.82	0.68	0.48	0.96	0.028
tomato	83	35	42.17	208	68	32.69	1.29	0.94	1.77	0.137
pork	120	48	40.00	169	54	31.95	1.25	0.92	1.71	0.171
horseradish	72	30	41.67	217	72	33.18	1.26	0.90	1.75	0.203
sex01	139	53	38.13	152	50	32.89	1.16	0.85	1.58	0.391
roastbeef	29	8	27.59	262	95	36.26	0.76	0.41	1.40	0.417
chickenwin	84	33	39.29	207	70	33.82	1.16	0.84	1.61	0.418
agegroup	68	25	36.76	215	75	34.88	1.05	0.73	1.51	0.773
mince	87	32	36.78	204	71	34.80	1.06	0.76	1.48	0.789
salmon	104	37	35.58	183	63	34.43	1.03	0.75	1.43	0.898

By storing the results in the object “res”, you are able to use the result table in Markdown as shown above. You can also use individual elements of the results. For example if you would like to view just the risk ratio, you can view it by typing (for example):

res$df$RR[2]

## [1] "2.85"

CSInter - Stratified analysis for cohort studies

CSInter is useful to determine the effects of a third variable on the association between an exposure and an outcome. CSInter produces 2 by 2 tables with stratum specific risk ratios, attributable risk among exposed and population attributable risk. Note that the outcome and exposure variable need to be numeric and binary and coded as “0” and 1”. The third variable needs to be numeric, but may have more categories, such as “0”, “1” and “2”.

CSInter displays a summary with the crude RR, the Mantel Haenszel adjusted RR and the result of a “Woolf” test for homogeneity of stratum-specific RR.

The option “full = TRUE” provides you with useful formatting information, which can be handy if you’re using “markdown”.

Syntax

CSInter(x, cases, exposure, by, full=FALSE)

Example 1 : CSInter ill - wmousse by tira (unformatted)

CSInter(DF, cases="ill", exposure = "wmousse", by = "tira")

## $df1
##   CSInter ill - wmousse by(tira) Total Cases Risk %          P.est. Stats
## 1                       tira = 1   112  <NA>     NA Risk difference  0.06
## 2                        Exposed    52    43  82.69      Risk Ratio  1.08
## 3                      Unexposed    60    46  76.67 Attrib.risk.exp  0.07
## 4                                   NA  <NA>     NA Attrib.risk.pop  0.04
## 5                       tira = 0   161  <NA>     NA Risk difference  0.21
## 6                        Exposed    17     4  23.53      Risk Ratio 11.29
## 7                      Unexposed   144     3   2.08 Attrib.risk.exp  0.91
## 8                                   NA  <NA>     NA Attrib.risk.pop  0.52
## 9            Missing / Missing %    18  6.2%     NA            <NA>    NA
##   95%CI.ll 95%CI.ul
## 1    -0.09     0.21
## 2     0.89     1.30
## 3    -0.12     0.23
## 4       NA       NA
## 5     0.01     0.42
## 6     2.76    46.26
## 7     0.64     0.98
## 8       NA       NA
## 9       NA       NA
## 
## $df2
##                    Point Estimate  Chi2 p.value  Stats 95%CI.ll 95%CI.ul
## 1       Woolf test of homogeneity 10.47   0.001     NA       NA       NA
## 2            Crude RR for wmousse    NA      NA   2.84     2.12     3.80
## 3 MH RR wmousse adjusted for tira    NA      NA   1.23     1.02     1.48
## 4  Adjusted/crude relative change    NA      NA -56.70       NA       NA

Example 2 : CSInter ill - beer by tira (formatted)

The following results tables are outputs in “markdown” using the kable function.

res <- CSInter(DF, "ill", "beer", "tira", full = TRUE)

CSInter ill - beer by(tira)	Total	Cases	Risk %	P.est.	Stats	95%CI.ll	95%CI.ul
tira = 1	116		NA	Risk difference	-0.18	-0.35	-0.01
Exposed	41	27	65.85	Risk ratio	0.78	0.62	1.00
Unexposed	75	63	84.00	Prev. frac. ex.	0.22	0.00	0.38
			NA	Prev. frac. pop	0.08	NA	NA
tira = 0	150		NA	Risk difference	0.00	-0.07	0.07
Exposed	63	3	4.76	Risk Ratio	1.04	0.24	4.47
Unexposed	87	4	4.60	Attrib.risk.exp	0.03	-3.16	0.78
			NA	Attrib.risk.pop	0.01	NA	NA
Missing / Missing %	25	8.6%	NA		NA	NA	NA

Point Estimate	Chi2	p.value	Stats	95%CI.ll	95%CI.ul
Woolf test of homogeneity	0.14	0.713	NA	NA	NA
Crude RR for beer	NA		0.70	0.49	0.99
MH RR beer adjusted for tira	NA		0.80	0.62	1.03
Adjusted/crude relative change	NA		14.93	NA	NA

Example 3: CSInter ill - beer by tportion (formatted)

The following results tables are outputs in “markdown” using the kable function.

res <- CSInter(DF, "ill", "beer", "tportion", full = TRUE)
kable(res$df1, align="r")

CSInter ill - beer by(tportion)	Total	Cases	Risk %	P.est.	Stats	95%CI.ll	95%CI.ul
tportion = 2	53		NA	Risk difference	0.01	-0.16	0.19
Exposed	19	17	89.47	Risk Ratio	1.01	0.83	1.23
Unexposed	34	30	88.24	Attrib.risk.exp	0.01	-0.20	0.19
			NA	Attrib.risk.pop	0.01	NA	NA
tportion = 1	63		NA	Risk difference	-0.35	-0.59	-0.11
Exposed	22	10	45.45	Risk ratio	0.56	0.35	0.91
Unexposed	41	33	80.49	Prev. frac. ex.	0.44	0.09	0.65
			NA	Prev. frac. pop	0.15	NA	NA
tportion = 0	150		NA	Risk difference	0.00	-0.07	0.07
Exposed	63	3	4.76	Risk Ratio	1.04	0.24	4.47
Unexposed	87	4	4.60	Attrib.risk.exp	0.03	-3.16	0.78
			NA	Attrib.risk.pop	0.01	NA	NA
Missing / Missing %	25	8.6%	NA		NA	NA	NA

kable(res$df2, align="r")

Point Estimate	Chi2	p.value	Stats	95%CI.ll	95%CI.ul
Woolf test of homogeneity	4.87	0.087	NA	NA	NA
Crude RR for beer	NA		0.70	0.49	0.99
MH RR beer adjusted for tportion	NA		0.80	0.62	1.02
Adjusted/crude relative change	NA		14.62	NA	NA

By storing the results in the object “res”, you are able to use the result table in Markdown as shown above. You can also use individual elements of the results. For example if you would like to view just the Mantel-Haenszel risk ratio for beer adjusted for tportion, you can view it by typing:

 res$df2$Stats[3]

## [1] "0.80"

CC

CC is used for case control studies to determine the association between an exposure and an outcome. Variables need to be binary and coded as “0” and “1”. Point estimates and confidence intervals for the odds ratio are calculated along with attributable or preventive fractions for the exposed and total population. Additionally you can select if you want to display the Fisher’s exact test, by specifying exact = TRUE. If you specify full = TRUE you can easily access useful statistics from the output tables.

Syntax

CC(x, cases, exposure, exact, full=FALSE)

Example 1: CC ill - mousse (unformatted)

cc(DF, "ill", "mousse", exact = TRUE)

## $df1
##                    Cases Controls Total
## Exposed               81       42   123
## Unexposed             22      144   166
## Total                103      186   289
## Proportion exposed  0.79     0.23  0.43
## 
## $df2
##                 Point estimate 95%CI.ll 95%CI.ul
## Odds ratio               12.62     6.80    23.70
## Attr. frac. ex.           0.92     0.85     0.96
## Attr. frac. pop           0.72       NA       NA
## chi2(1)                  85.22       NA       NA
## Pr>chi2                  0.000       NA       NA
## Fisher p-value           0.000       NA       NA

Example 2: CC ill - beer (formatted)

The following results tables are outputs in “markdown” using the kable function.

result <- CC(DF, "ill", "beer", exact = TRUE, full = TRUE)
kable(result$df1, align="r")

	Cases	Controls	Total
Exposed	30	76	106
Unexposed	69	96	165
Total	99	172	271
Proportion exposed	0.30	0.44	0.39

kable(result$df2, align=result$df2.align)

	Point estimate	95%CI.ll	95%CI.ul
Odds ratio	0.55	0.31	0.95
Prev. frac. ex.	0.45	0.05	0.69
Prev. frac. pop	0.20	NA	NA
chi2(1)	5.09	NA	NA
Pr>chi2	0.024	NA	NA
Fisher p-value	0.028	NA	NA

By storing the results in the object “result”, you are able to use the result tables in Markdown as shown above. By specifying “full = TRUE” you can also easily use individual elements of the results.For example if you would like to view just the odds ratio, you can view it by typing:

result$st$odds_ratio$point_estimate

## [1] 0.5491991 0.3127957 0.9547369

CCTable - Summary table for case control studies

CCTable is used for univariate analysis of case control studies with several exposures. The results are summarised in one table with one row per exposure making comparisons between exposures easier and providing a useful table for integrating into reports. Note that all variables need to be numeric and binary and coded as “0” and “1”.

The results of this function contain: The name of exposure variables, the total number of cases, the number of exposed cases, the percentage of exposed among cases, the number of controls, the number of exposed controls, the percentage of exposed among controls, odds ratios, 95%CI intervals, p-values.

You can optionally choose to display the Fisher’s exact p-value instead of the Chi squared p-value, with the option exact = TRUE.

You can specify the sort order, with the option sort=“or” to order by odds ratios. The default sort order is by p-values.

The option “full = TRUE” provides you with useful formatting information, which can be handy if you’re using “markdown”.

Syntax

CCTable(x, cases, exposure=c(), exact=FALSE, sort = “pvalue”, full=FALSE)

Example 1: CCTable results ordered by p-value (unformatted)

CCTable(DF, "ill",
        exposure = c("sex01", "agegroup", "tira", "beer", "mousse", "wmousse", "dmousse",
                     "redjelly", "fruitsalad", "tomato", "mince", "salmon", "horseradish",
                     "chickenwin", "roastbeef", "pork"))

## $df
##             Tot.Cases Exp.Cases %Cases Tot.Ctrls Exp.Ctrls %Ctrls    OR CI.ll
## tira              101        94  93.07       185        27  14.59 78.58 31.45
## mousse            103        81  78.64       186        42  22.58 12.62  6.80
## wmousse            98        49  50.00       179        23  12.85  6.78  3.62
## dmousse           102        76  74.51       185        37  20.00 11.69  6.36
## redjelly          103        45  43.69       188        34  18.09  3.51  1.98
## fruitsalad        103        46  44.66       188        25  13.30  5.26  2.86
## beer               99        30  30.30       172        76  44.19  0.55  0.31
## tomato            103        35  33.98       188        48  25.53  1.50  0.86
## pork              102        48  47.06       187        72  38.50  1.42  0.85
## horseradish       102        30  29.41       187        42  22.46  1.44  0.80
## sex01             103        53  51.46       188        86  45.74  1.26  0.75
## roastbeef         103         8   7.77       188        21  11.17  0.67  0.25
## chickenwin        103        33  32.04       188        51  27.13  1.27  0.72
## mince             103        32  31.07       188        55  29.26  1.09  0.62
## agegroup          100        25  25.00       183        43  23.50  1.09  0.59
## salmon            100        37  37.00       187        67  35.83  1.05  0.61
##              CI.ul p(Chi2)
## tira        217.15   0.000
## mousse       23.70   0.000
## wmousse      12.83   0.000
## dmousse      21.64   0.000
## redjelly      6.24   0.000
## fruitsalad    9.75   0.000
## beer          0.95   0.024
## tomato        2.61   0.127
## pork          2.38   0.158
## horseradish   2.57   0.192
## sex01         2.09   0.351
## roastbeef     1.65   0.354
## chickenwin    2.20   0.377
## mince         1.89   0.747
## agegroup      1.98   0.777
## salmon        1.79   0.844

Example 2: CCTable results ordered by odds ratio (formatted)

The following results tables are outputs in “markdown” using the kable function.

res = CCTable(DF, "ill", sort = "or", exposure = Colnames)
kable(res$df)

	Tot.Cases	Exp.Cases	%Cases	Tot.Ctrls	Exp.Ctrls	%Ctrls	OR	CI.ll	CI.ul	p(Chi2)
tira	101	94	93.07	185	27	14.59	78.58	31.45	217.15	0.000
mousse	103	81	78.64	186	42	22.58	12.62	6.80	23.70	0.000
dmousse	102	76	74.51	185	37	20.00	11.69	6.36	21.64	0.000
wmousse	98	49	50.00	179	23	12.85	6.78	3.62	12.83	0.000
fruitsalad	103	46	44.66	188	25	13.30	5.26	2.86	9.75	0.000
redjelly	103	45	43.69	188	34	18.09	3.51	1.98	6.24	0.000
tomato	103	35	33.98	188	48	25.53	1.50	0.86	2.61	0.127
horseradish	102	30	29.41	187	42	22.46	1.44	0.80	2.57	0.192
pork	102	48	47.06	187	72	38.50	1.42	0.85	2.38	0.158
chickenwin	103	33	32.04	188	51	27.13	1.27	0.72	2.20	0.377
sex01	103	53	51.46	188	86	45.74	1.26	0.75	2.09	0.351
mince	103	32	31.07	188	55	29.26	1.09	0.62	1.89	0.747
agegroup	100	25	25.00	183	43	23.50	1.09	0.59	1.98	0.777
salmon	100	37	37.00	187	67	35.83	1.05	0.61	1.79	0.844
roastbeef	103	8	7.77	188	21	11.17	0.67	0.25	1.65	0.354
beer	99	30	30.30	172	76	44.19	0.55	0.31	0.95	0.024

Example 3: CCTable results ordered by p-value from the Fisher’s exact test (formatted)

The following results tables are outputs in “markdown” using the kable function.

res = CCTable(DF, "ill", exposure = Colnames, exact=TRUE)
kable(res$df)

	Tot.Cases	Exp.Cases	%Cases	Tot.Ctrls	Exp.Ctrls	%Ctrls	OR	CI.ll	CI.ul	p(Fisher)
tira	101	94	93.07	185	27	14.59	78.58	31.45	217.15	0.000
wmousse	98	49	50.00	179	23	12.85	6.78	3.62	12.83	0.000
dmousse	102	76	74.51	185	37	20.00	11.69	6.36	21.64	0.000
mousse	103	81	78.64	186	42	22.58	12.62	6.80	23.70	0.000
redjelly	103	45	43.69	188	34	18.09	3.51	1.98	6.24	0.000
fruitsalad	103	46	44.66	188	25	13.30	5.26	2.86	9.75	0.000
beer	99	30	30.30	172	76	44.19	0.55	0.31	0.95	0.028
tomato	103	35	33.98	188	48	25.53	1.50	0.86	2.61	0.137
pork	102	48	47.06	187	72	38.50	1.42	0.85	2.38	0.171
horseradish	102	30	29.41	187	42	22.46	1.44	0.80	2.57	0.203
sex01	103	53	51.46	188	86	45.74	1.26	0.75	2.09	0.391
roastbeef	103	8	7.77	188	21	11.17	0.67	0.25	1.65	0.417
chickenwin	103	33	32.04	188	51	27.13	1.27	0.72	2.20	0.418
agegroup	100	25	25.00	183	43	23.50	1.09	0.59	1.98	0.773
mince	103	32	31.07	188	55	29.26	1.09	0.62	1.89	0.789
salmon	100	37	37.00	187	67	35.83	1.05	0.61	1.79	0.898

By storing the results in the object “res”, you are able to use the result table in Markdown as shown above. You can also use individual elements of the results. For example if you would like to view just the odds ratio, you can view it by typing (for example):

res$df$OR[1]

## [1] "78.58"

CCInter - Stratified analysis for case control studies

CCInter is useful to determine the effects of a third variable on the association between an exposure and an outcome. CCInter produces 2 by 2 tables with stratum specific odds ratios, attributable risk among exposed and population attributable risk.

Note that the outcome and exposure variable need to be numeric and binary and coded as “0” and 1”. The third variable needs to be numeric, but may have more categories, such as “0”, “1” and “2”.

CCInter displays a summary with the crude OR, the Mantel Haenszel adjusted OR and the result of a Woolf test for homogeneity of stratum-specific OR.

The option “full = TRUE” provides you with useful formatting information, which can be handy if you’re using “markdown”.

Syntax

CCInter (x, cases, exposure, by, full=FALSE)

Example 1: CCInter ill - wmousse by tira (unformatted)

CCInter(DF, cases="ill", exposure = "wmousse", by = "tira")

## $df1
##    CCInter ill - wmousse by(tira) Cases Controls          P.est. Stats 95%CI.ll
## 1                        tira = 1  <NA>     <NA>      Odds ratio  1.45     0.52
## 2                         Exposed    43        9 Attrib.risk.exp  0.31    -0.92
## 3                       Unexposed    46       14 Attrib.risk.pop  0.15     <NA>
## 4                           Total    89       23                  <NA>     <NA>
## 5                       Exposed % 48.3%    39.1%                  <NA>     <NA>
## 6                  ______________  <NA>     <NA>                  <NA>     <NA>
## 7                        tira = 0  <NA>     <NA>      Odds ratio 14.46     2.12
## 8                         Exposed     4       13 Attrib.risk.exp  0.93     0.53
## 9                       Unexposed     3      141 Attrib.risk.pop  0.53     <NA>
## 10                          Total     7      154                  <NA>     <NA>
## 11                      Exposed % 57.1%     8.4%                  <NA>     <NA>
## 12                 ______________  <NA>     <NA>                  <NA>     <NA>
## 13                  Number of obs   273     <NA>            <NA>  <NA>     <NA>
## 14                        Missing    18     <NA>            <NA>  <NA>     <NA>
##    95%CI.ul
## 1      4.22
## 2      0.76
## 3      <NA>
## 4      <NA>
## 5      <NA>
## 6      <NA>
## 7    106.00
## 8      0.99
## 9      <NA>
## 10     <NA>
## 11     <NA>
## 12     <NA>
## 13     <NA>
## 14     <NA>
## 
## $df2
##                         P.estimate  Stats 95%CI.ll 95%CI.ul
## 1 MH test of Homogeneity (p-value)   0.01                  
## 2             Crude OR for wmousse   6.76     3.57    12.93
## 3  MH OR wmousse adjusted for tira   2.25     1.01     5.05
## 4   Adjusted/crude relative change -66.65        _        _

Example 2: CCInter ill - beer by tira (formatted)

The following results tables are outputs in “markdown” using the kable function.

res <- CCInter(DF, cases="ill", exposure = "beer", by = "tira", full = TRUE)
kable(res$df1, align=res$df1.align)

CCInter ill - beer by(tira)	Cases	Controls	P.est.	Stats	95%CI.ll	95%CI.ul
tira = 1			Odds ratio	0.37	0.14	0.99
Exposed	27	14	Prev. frac. ex.	0.63	0.01	0.86
Unexposed	63	12	Prev. frac. pop	0.34
Total	90	26
Exposed %	30.0%	53.8%
______________
tira = 0			Odds ratio	1.04	0.15	6.38
Exposed	3	60	Attrib.risk.exp	0.04	-5.82	0.84
Unexposed	4	83	Attrib.risk.pop	0.02
Total	7	143
Exposed %	42.9%	42.0%
______________
Number of obs	266
Missing	25

kable(res$df2)

P.estimate	Stats	95%CI.ll	95%CI.ul
MH test of Homogeneity (p-value)	0.22
Crude OR for beer	0.57	0.33	1.00
MH OR beer adjusted for tira	0.48	0.22	1.05
Adjusted/crude relative change	-15.83	_	_

Example 3: CCInter ill - beer by tportion (formatted)

The following results tables are outputs in “markdown” using the kable function.

res <- CCInter(DF, cases="ill", exposure = "beer", by = "tportion", full = TRUE)
kable(res$df1, align=res$df1.align)

CCInter ill - beer by(tportion)	Cases	Controls	P.est.	Stats	95%CI.ll	95%CI.ul
tportion = 2			Odds ratio	1.13	0.14	13.73
Exposed	17	2	Attrib.risk.exp	0.12	-5.94	0.93
Unexposed	30	4	Attrib.risk.pop	0.04
Total	47	6
Exposed %	36.2%	33.3%
______________
tportion = 1			Odds ratio	0.20	0.06	0.73
Exposed	10	12	Prev. frac. ex.	0.80	0.27	0.94
Unexposed	33	8	Prev. frac. pop	0.48
Total	43	20
Exposed %	23.3%	60.0%
______________
tportion = 0			Odds ratio	1.04	0.15	6.38
Exposed	3	60	Attrib.risk.exp	0.04	-5.82	0.84
Unexposed	4	83	Attrib.risk.pop	0.02
Total	7	143
Exposed %	42.9%	42.0%
______________
Number of obs	266
Missing	25

kable(res$df2, align=res$df2.align)

P.estimate	Stats	95%CI.ll	95%CI.ul
MH test of Homogeneity (p-value)	0.13
Crude OR for beer	0.57	0.33	1.00
MH OR beer adjusted for tportion	0.47	0.21	1.02
Adjusted/crude relative change	-18.73	_	_

By storing the results in the object “res”, you are able to use the result table in Markdown as shown above. You can also use individual elements of the results. For example if you would like to view just the Mantel-Haenszel odds ratio for beer adjusted for tportion, you can view it by typing:

res$df2$Stats[3]

## [1] "0.47"

- Package Epistats
- Working with Epistats and “Tiramisu” dataset