R help - Jun 2020 - Error message in meta-analysis package Metafor-weights =""

Dear All,
I am using the example from one of the tutorial about "Metafor"
package and
"escalc" function, to learn how this package can be applied to do
meta-analysi; the code and the data is directly from the tutorials but
"weights=freq" option in the escalc function is given me error message
This is the code below:

library(metafor) # Load package
#####DATASET 1: BCG Vaccine Trials
data(dat.bcg) # BCG meta-analytic dataset

##Formula based Specification
##That is, what if I have multiple rows per study, corresponding to
difference treatment groups?

library(reshape2) # Load package for data reshaping

bcg.long <- melt(dat.bcg[, c("trial", "tpos",
"tneg", "cpos", "cneg")], id
= "trial")
bcg.long$pos <- ifelse(bcg.long$var == "tpos" | bcg.long$var ==
"cpos", 1,
0)
bcg.long$group <- ifelse(bcg.long$var == "tpos" | bcg.long$var ==
"tneg",
1, 0)

##sample of the data, the first 6 rows
head(bcg.long)
  trial variable value pos group
1     1     tpos     4     1     1
2     2     tpos     6     1     1
3     3     tpos     3     1     1
4     4     tpos    62    1     1
5     5     tpos    33    1     1
6     6     tpos   180   1     1

##Now applying the " escalc " function

escalc(factor(pos)~factor(group)| factor(trial),weights = value,data bcg.long,
measure = "OR")

##Then I got this error message
Error in escalc(factor(pos) ~ factor(group) | factor(trial), weights value,  :
  object 'value' not found

I used the same data with different example from another author and got a
similar error message
Second code with the same data but different coding
Sample data

with the first 6 rows of the rearranged data shown below. (T=treatment,
C=Control group, Out=outcome whether positive or negative, and then
frequency)
    study grp out freq
1        1    T    +      4
2        1    T    -    119
3        1    C   +      11
4        1    C   -     128
5        2    T   +        6
6        2    T   -      300
>escalc(out ~ grp | study, weights = freq, data = dat.fm, measure =
"OR")
Error in escalc(out ~ grp | study, weights = freq, data = dat.fm, measure
"OR") :
  object 'freq' not found

I am not sure what I am doing wrong since both authors were able to get
their results while I am getting error messages.

Any help will be very much appreciated

Amoatwi

	[[alternative HTML version deleted]]

Dear Amoatwi,

This way of using the escalc() function has been deprecated. It might be added
back once there is actually any benefit from having this functionality, but for
years it just meant that I had to maintain two different ways of doing the exact
same thing without any additional benefits.

Best,
Wolfgang

-- 
Wolfgang Viechtbauer, Ph.D., Statistician | Department of Psychiatry and    
Neuropsychology | Maastricht University | P.O. Box 616 (VIJV1) | 6200 MD    
Maastricht, The Netherlands | +31 (43) 388-4170 | http://www.wvbauer.com    
>-----Original Message-----
>From: R-help [mailto:r-help-bounces at r-project.org] On Behalf Of K Amoatwi
>Sent: Tuesday, 16 June, 2020 4:50
>To: r-help at r-project.org
>Subject: [R] Error message in meta-analysis package Metafor-weights
=""
>
>Dear All,
>I am using the example from one of the tutorial about "Metafor"
package and
>"escalc" function, to learn how this package can be applied to do
>meta-analysi; the code and the data is directly from the tutorials but
>"weights=freq" option in the escalc function is given me error
message
>This is the code below:
>
>library(metafor) # Load package
>#####DATASET 1: BCG Vaccine Trials
>data(dat.bcg) # BCG meta-analytic dataset
>
>##Formula based Specification
>##That is, what if I have multiple rows per study, corresponding to
>difference treatment groups?
>
>library(reshape2) # Load package for data reshaping
>
>bcg.long <- melt(dat.bcg[, c("trial", "tpos",
"tneg", "cpos", "cneg")], id
>= "trial")
>bcg.long$pos <- ifelse(bcg.long$var == "tpos" | bcg.long$var ==
"cpos", 1,
>0)
>bcg.long$group <- ifelse(bcg.long$var == "tpos" | bcg.long$var
== "tneg",
>1, 0)
>
>##sample of the data, the first 6 rows
>head(bcg.long)
>  trial variable value pos group
>1     1     tpos     4     1     1
>2     2     tpos     6     1     1
>3     3     tpos     3     1     1
>4     4     tpos    62    1     1
>5     5     tpos    33    1     1
>6     6     tpos   180   1     1
>
>##Now applying the " escalc " function
>
>escalc(factor(pos)~factor(group)| factor(trial),weights = value,data
>bcg.long, measure = "OR")
>
>##Then I got this error message
>Error in escalc(factor(pos) ~ factor(group) | factor(trial), weights
>value,  :
>  object 'value' not found
>
>I used the same data with different example from another author and got a
>similar error message
>Second code with the same data but different coding
>Sample data
>
>with the first 6 rows of the rearranged data shown below. (T=treatment,
>C=Control group, Out=outcome whether positive or negative, and then
>frequency)
>    study grp out freq
>1        1    T    +      4
>2        1    T    -    119
>3        1    C   +      11
>4        1    C   -     128
>5        2    T   +        6
>6        2    T   -      300
>
>>escalc(out ~ grp | study, weights = freq, data = dat.fm, measure =
"OR")
>
>Error in escalc(out ~ grp | study, weights = freq, data = dat.fm, measure
>"OR") :
>  object 'freq' not found
>
>I am not sure what I am doing wrong since both authors were able to get
>their results while I am getting error messages.
>
>Any help will be very much appreciated
>
>Amoatwi

Thank you, very much appreciated.

On Tue, Jun 16, 2020 at 12:50 PM Viechtbauer, Wolfgang (SP) <
wolfgang.viechtbauer at maastrichtuniversity.nl> wrote:
> Dear Amoatwi,
>
> This way of using the escalc() function has been deprecated. It might be
> added back once there is actually any benefit from having this
> functionality, but for years it just meant that I had to maintain two
> different ways of doing the exact same thing without any additional
> benefits.
>
> Best,
> Wolfgang
>
> --
> Wolfgang Viechtbauer, Ph.D., Statistician | Department of Psychiatry and
>
> Neuropsychology | Maastricht University | P.O. Box 616 (VIJV1) | 6200 MD
>
> Maastricht, The Netherlands | +31 (43) 388-4170 | http://www.wvbauer.com
>
>
> >-----Original Message-----
> >From: R-help [mailto:r-help-bounces at r-project.org] On Behalf Of K
Amoatwi
> >Sent: Tuesday, 16 June, 2020 4:50
> >To: r-help at r-project.org
> >Subject: [R] Error message in meta-analysis package Metafor-weights
=""
> >
> >Dear All,
> >I am using the example from one of the tutorial about
"Metafor" package
> and
> >"escalc" function, to learn how this package can be applied
to do
> >meta-analysi; the code and the data is directly from the tutorials but
> >"weights=freq" option in the escalc function is given me
error message
> >This is the code below:
> >
> >library(metafor) # Load package
> >#####DATASET 1: BCG Vaccine Trials
> >data(dat.bcg) # BCG meta-analytic dataset
> >
> >##Formula based Specification
> >##That is, what if I have multiple rows per study, corresponding to
> >difference treatment groups?
> >
> >library(reshape2) # Load package for data reshaping
> >
> >bcg.long <- melt(dat.bcg[, c("trial", "tpos",
"tneg", "cpos", "cneg")], id
> >= "trial")
> >bcg.long$pos <- ifelse(bcg.long$var == "tpos" |
bcg.long$var == "cpos", 1,
> >0)
> >bcg.long$group <- ifelse(bcg.long$var == "tpos" |
bcg.long$var == "tneg",
> >1, 0)
> >
> >##sample of the data, the first 6 rows
> >head(bcg.long)
> >  trial variable value pos group
> >1     1     tpos     4     1     1
> >2     2     tpos     6     1     1
> >3     3     tpos     3     1     1
> >4     4     tpos    62    1     1
> >5     5     tpos    33    1     1
> >6     6     tpos   180   1     1
> >
> >##Now applying the " escalc " function
> >
> >escalc(factor(pos)~factor(group)| factor(trial),weights = value,data
> >bcg.long, measure = "OR")
> >
> >##Then I got this error message
> >Error in escalc(factor(pos) ~ factor(group) | factor(trial), weights
> >value,  :
> >  object 'value' not found
> >
> >I used the same data with different example from another author and got
a
> >similar error message
> >Second code with the same data but different coding
> >Sample data
> >
> >with the first 6 rows of the rearranged data shown below. (T=treatment,
> >C=Control group, Out=outcome whether positive or negative, and then
> >frequency)
> >    study grp out freq
> >1        1    T    +      4
> >2        1    T    -    119
> >3        1    C   +      11
> >4        1    C   -     128
> >5        2    T   +        6
> >6        2    T   -      300
> >
> >>escalc(out ~ grp | study, weights = freq, data = dat.fm, measure =
"OR")
> >
> >Error in escalc(out ~ grp | study, weights = freq, data = dat.fm,
> measure > >"OR") :
> >  object 'freq' not found
> >
> >I am not sure what I am doing wrong since both authors were able to get
> >their results while I am getting error messages.
> >
> >Any help will be very much appreciated
> >
> >Amoatwi
>
	[[alternative HTML version deleted]]

Hi Wolfgang and All,
I am still practising my meta-analysis with the "Metafor" package, I
tried
to run the code for "Forest plot" and got error message as shown
below:
forest(result.md)
> forest(result.md)
Error in UseMethod("forest") :
  no applicable method for 'forest' applied to an object of class
"c('rma.uni', 'rma')"

Thank you in advance for your support

regards
Kobby


On Tue, Jun 16, 2020 at 12:50 PM Viechtbauer, Wolfgang (SP) <
wolfgang.viechtbauer at maastrichtuniversity.nl> wrote:
> Dear Amoatwi,
>
> This way of using the escalc() function has been deprecated. It might be
> added back once there is actually any benefit from having this
> functionality, but for years it just meant that I had to maintain two
> different ways of doing the exact same thing without any additional
> benefits.
>
> Best,
> Wolfgang
>
> --
> Wolfgang Viechtbauer, Ph.D., Statistician | Department of Psychiatry and
>
> Neuropsychology | Maastricht University | P.O. Box 616 (VIJV1) | 6200 MD
>
> Maastricht, The Netherlands | +31 (43) 388-4170 | http://www.wvbauer.com
>
>
> >-----Original Message-----
> >From: R-help [mailto:r-help-bounces at r-project.org] On Behalf Of K
Amoatwi
> >Sent: Tuesday, 16 June, 2020 4:50
> >To: r-help at r-project.org
> >Subject: [R] Error message in meta-analysis package Metafor-weights
=""
> >
> >Dear All,
> >I am using the example from one of the tutorial about
"Metafor" package
> and
> >"escalc" function, to learn how this package can be applied
to do
> >meta-analysi; the code and the data is directly from the tutorials but
> >"weights=freq" option in the escalc function is given me
error message
> >This is the code below:
> >
> >library(metafor) # Load package
> >#####DATASET 1: BCG Vaccine Trials
> >data(dat.bcg) # BCG meta-analytic dataset
> >
> >##Formula based Specification
> >##That is, what if I have multiple rows per study, corresponding to
> >difference treatment groups?
> >
> >library(reshape2) # Load package for data reshaping
> >
> >bcg.long <- melt(dat.bcg[, c("trial", "tpos",
"tneg", "cpos", "cneg")], id
> >= "trial")
> >bcg.long$pos <- ifelse(bcg.long$var == "tpos" |
bcg.long$var == "cpos", 1,
> >0)
> >bcg.long$group <- ifelse(bcg.long$var == "tpos" |
bcg.long$var == "tneg",
> >1, 0)
> >
> >##sample of the data, the first 6 rows
> >head(bcg.long)
> >  trial variable value pos group
> >1     1     tpos     4     1     1
> >2     2     tpos     6     1     1
> >3     3     tpos     3     1     1
> >4     4     tpos    62    1     1
> >5     5     tpos    33    1     1
> >6     6     tpos   180   1     1
> >
> >##Now applying the " escalc " function
> >
> >escalc(factor(pos)~factor(group)| factor(trial),weights = value,data
> >bcg.long, measure = "OR")
> >
> >##Then I got this error message
> >Error in escalc(factor(pos) ~ factor(group) | factor(trial), weights
> >value,  :
> >  object 'value' not found
> >
> >I used the same data with different example from another author and got
a
> >similar error message
> >Second code with the same data but different coding
> >Sample data
> >
> >with the first 6 rows of the rearranged data shown below. (T=treatment,
> >C=Control group, Out=outcome whether positive or negative, and then
> >frequency)
> >    study grp out freq
> >1        1    T    +      4
> >2        1    T    -    119
> >3        1    C   +      11
> >4        1    C   -     128
> >5        2    T   +        6
> >6        2    T   -      300
> >
> >>escalc(out ~ grp | study, weights = freq, data = dat.fm, measure =
"OR")
> >
> >Error in escalc(out ~ grp | study, weights = freq, data = dat.fm,
> measure > >"OR") :
> >  object 'freq' not found
> >
> >I am not sure what I am doing wrong since both authors were able to get
> >their results while I am getting error messages.
> >
> >Any help will be very much appreciated
> >
> >Amoatwi
>
	[[alternative HTML version deleted]]