library(readxl)
library(ggplot2)
library(gridExtra)
library(table1)
## 
## Attaching package: 'table1'
## The following objects are masked from 'package:base':
## 
##     units, units<-
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following object is masked from 'package:gridExtra':
## 
##     combine
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

Reading data

ig = read_excel("~/Dropbox/NHMRC and Grants/NHMRC 2019/Investigator Grant v2/Outcome/List of investigator grants.xlsx")
ig$Budget = ig$Total/1000
ig$Rank[ig$Rank=="Ms" | ig$Rank=="Mr"] <- "Mr/Ms"
ig$Rank[ig$Rank=="Dr"] <- "Dr"
ig$Rank[ig$Rank=="A/Prof"] <- "A/Prof"
ig$Rank[ig$Rank=="Prof"] <- "Prof"
ig$Rank = factor(ig$Rank, levels=c("Mr/Ms", "Dr", "A/Prof", "Prof"))
head(ig)
## # A tibble: 6 x 17
##       ID Rank  Name  Type  SubType Institution State Sector  Total Area  Field
##    <dbl> <fct> <chr> <chr> <chr>   <chr>       <chr> <chr>   <dbl> <chr> <chr>
## 1 1.19e6 A/Pr… A/Pr… Inte… Collab… University… VIC   Unive… 1.22e6 Clin… Clin…
## 2 1.19e6 Dr    Dr S… Inte… Collab… Commonweal… ACT   Gover… 4.89e5 Clin… Neur…
## 3 1.19e6 Dr    Dr V… Inte… Collab… Griffith U… QLD   Unive… 4.22e5 Publ… Ment…
## 4 1.19e6 Prof  Prof… Inte… Collab… University… VIC   Unive… 4.98e5 Clin… Medi…
## 5 1.20e6 Prof  Prof… Inte… Collab… RMIT Unive… VIC   Unive… 4.97e5 Clin… Paed…
## 6 1.19e6 Prof  Prof… Inte… Collab… University… NSW   Unive… 4.99e5 Clin… Neur…
## # … with 6 more variables: KW1 <chr>, KW2 <chr>, KW3 <chr>, KW4 <chr>,
## #   KW5 <chr>, Budget <dbl>
ig1 = filter(ig, Type %in% "Investigator Grants")

Analysis

table1(~SubType + Budget | Rank, data=ig1)
Mr/Ms
(N=3)
Dr
(N=91)
A/Prof
(N=34)
Prof
(N=109)
Overall
(N=237)
SubType
EL1 3 (100%) 76 (83.5%) 4 (11.8%) 0 (0%) 83 (35.0%)
EL2 0 (0%) 14 (15.4%) 20 (58.8%) 5 (4.6%) 39 (16.5%)
L1 0 (0%) 1 (1.1%) 10 (29.4%) 31 (28.4%) 42 (17.7%)
L2 0 (0%) 0 (0%) 0 (0%) 28 (25.7%) 28 (11.8%)
L3 0 (0%) 0 (0%) 0 (0%) 45 (41.3%) 45 (19.0%)
Budget
Mean (SD) 645 (0) 766 (384) 1520 (602) 2240 (590) 1550 (856)
Median [Min, Max] 645 [645, 645] 645 [280, 2590] 1470 [463, 3140] 2180 [900, 3760] 1540 [280, 3760]
table1(~ SubType + Budget | Area , data=ig1)
Basic Science
(N=71)
Clinical Medicine and Science
(N=100)
Health Services Research
(N=20)
Public Health
(N=46)
Overall
(N=237)
SubType
EL1 21 (29.6%) 36 (36.0%) 6 (30.0%) 20 (43.5%) 83 (35.0%)
EL2 13 (18.3%) 11 (11.0%) 7 (35.0%) 8 (17.4%) 39 (16.5%)
L1 14 (19.7%) 15 (15.0%) 2 (10.0%) 11 (23.9%) 42 (17.7%)
L2 5 (7.0%) 15 (15.0%) 4 (20.0%) 4 (8.7%) 28 (11.8%)
L3 18 (25.4%) 23 (23.0%) 1 (5.0%) 3 (6.5%) 45 (19.0%)
Budget
Mean (SD) 1750 (913) 1540 (869) 1350 (664) 1340 (758) 1550 (856)
Median [Min, Max] 1790 [570, 3760] 1540 [280, 3740] 1340 [448, 2740] 1390 [359, 3290] 1540 [280, 3760]
table1(~ KW1, data=ig1)
Overall
(N=237)
KW1
aboriginal child 2 (0.8%)
aboriginal health 3 (1.3%)
addiction 1 (0.4%)
adjuvant 1 (0.4%)
adolescent health 1 (0.4%)
age-related 1 (0.4%)
aged care 1 (0.4%)
ageing 1 (0.4%)
alcohol use disorders 1 (0.4%)
alternative splicing 1 (0.4%)
androgens 1 (0.4%)
antibiotic resistance 1 (0.4%)
antibiotics 2 (0.8%)
antimicrobial resistance 2 (0.8%)
ataxia 1 (0.4%)
autoimmunity 1 (0.4%)
axonal reconnection 1 (0.4%)
bacteria 1 (0.4%)
bioinformatics 2 (0.8%)
biomarkers 2 (0.8%)
biomedical engineering 1 (0.4%)
biostatistics 1 (0.4%)
blood transfusion 1 (0.4%)
blood-borne communicable diseases 1 (0.4%)
brain imaging 1 (0.4%)
brain mapping 1 (0.4%)
breast cancer 5 (2.1%)
breast cancer aetiology 1 (0.4%)
bronchiolitis 1 (0.4%)
cancer biology 1 (0.4%)
cancer control 1 (0.4%)
cancer immunotherapy 1 (0.4%)
cancer screening 1 (0.4%)
cardiology 1 (0.4%)
cardiovascular disease prevention 2 (0.8%)
cerebral palsy treatments 1 (0.4%)
child development 2 (0.8%)
child health 1 (0.4%)
chronic infection 1 (0.4%)
chronic obstructive pulmonary disease (copd) 1 (0.4%)
chronic pain 1 (0.4%)
circadian rhythms 1 (0.4%)
cognition 1 (0.4%)
colorectal cancer 2 (0.8%)
colorectal cancer prevention 2 (0.8%)
combination therapy 1 (0.4%)
crohn's disease 2 (0.8%)
cytokine receptor 1 (0.4%)
dementia 2 (0.8%)
dementia care 1 (0.4%)
dendritic cell lineages 1 (0.4%)
depression 1 (0.4%)
developmental disorders 1 (0.4%)
diabetes 1 (0.4%)
diagnostic imaging 1 (0.4%)
diagnostic methods 1 (0.4%)
diarrhoeal disease 1 (0.4%)
diet 1 (0.4%)
dna replication 1 (0.4%)
drug delivery 1 (0.4%)
drug delivery systems 2 (0.8%)
dyspnoea 1 (0.4%)
eating disorders 1 (0.4%)
electroconvulsive therapy (ect) 1 (0.4%)
endometrial cancer 1 (0.4%)
enteric bacteria 1 (0.4%)
enteric nervous system 1 (0.4%)
epidemiology 2 (0.8%)
epigenetics 2 (0.8%)
epilepsy 2 (0.8%)
evidence-based health care 1 (0.4%)
exercise intolerance 1 (0.4%)
falls prevention 1 (0.4%)
fatty liver disease 1 (0.4%)
food 1 (0.4%)
functional magnetic resonance imaging (fmri) 1 (0.4%)
g protein-coupled receptors 2 (0.8%)
gene regulation 1 (0.4%)
genetics 1 (0.4%)
genomics 2 (0.8%)
haematology 1 (0.4%)
haemodialysis 1 (0.4%)
health literacy 1 (0.4%)
health services research 1 (0.4%)
human immunodeficiency virus (hiv) 1 (0.4%)
illicit drug use 1 (0.4%)
infection 3 (1.3%)
infection control 1 (0.4%)
infectious diseases 1 (0.4%)
inflammation 2 (0.8%)
inflammatory bowel disease (ibd) 1 (0.4%)
influenza 3 (1.3%)
influenza virus 1 (0.4%)
insomnia 1 (0.4%)
intensive care 1 (0.4%)
iron 1 (0.4%)
iron transport 1 (0.4%)
knee osteoarthritis 1 (0.4%)
lipid metabolism 1 (0.4%)
low back pain 1 (0.4%)
lung development 1 (0.4%)
lupus 1 (0.4%)
macrophage biology 1 (0.4%)
magnetic resonance imaging (mri) 1 (0.4%)
malaria 3 (1.3%)
mammography 1 (0.4%)
maternal health 2 (0.8%)
medical physics 1 (0.4%)
medications 1 (0.4%)
melanoma 2 (0.8%)
memory t-cells 1 (0.4%)
menopause 1 (0.4%)
mental health 2 (0.8%)
microbial ecology 1 (0.4%)
midwifery 1 (0.4%)
molecular chaperones 1 (0.4%)
molecular epidemiology 1 (0.4%)
motor disability 1 (0.4%)
mouse models 1 (0.4%)
multiple sclerosis (ms) 2 (0.8%)
muscle strength 1 (0.4%)
muscular dystrophy 1 (0.4%)
musculoskeletal disorders 2 (0.8%)
myeloid leukaemia 1 (0.4%)
nanotechnology 1 (0.4%)
natural killer cells 1 (0.4%)
nephrology 1 (0.4%)
neurodegenerative disorders 1 (0.4%)
neurodevelopmental disorders 1 (0.4%)
neuropsychiatric disorders 1 (0.4%)
neuroradiology 1 (0.4%)
neuroscience 1 (0.4%)
nursing 1 (0.4%)
nutrition 1 (0.4%)
obesity 1 (0.4%)
ophthalmology 1 (0.4%)
organ growth and development 1 (0.4%)
osteoarthritis 2 (0.8%)
osteoporosis 3 (1.3%)
paediatric 1 (0.4%)
pain 1 (0.4%)
pain management 1 (0.4%)
parkinson disease 1 (0.4%)
patient participation 1 (0.4%)
patient safety 1 (0.4%)
periodontitis 1 (0.4%)
pharmacoepidemiology 1 (0.4%)
physical activity 2 (0.8%)
poisoning 1 (0.4%)
pregnancy complications 2 (0.8%)
premature birth 1 (0.4%)
prevention 1 (0.4%)
preventive health 1 (0.4%)
primary care 1 (0.4%)
prostate cancer 1 (0.4%)
protein structure 1 (0.4%)
psychopathology 1 (0.4%)
public health policy 1 (0.4%)
randomised trial 1 (0.4%)
rehabilitation 1 (0.4%)
retinal degeneration 1 (0.4%)
rhinosinusitis 1 (0.4%)
schistosoma 1 (0.4%)
schizophrenia 1 (0.4%)
schizophrenia and related disorders 1 (0.4%)
scleroderma 1 (0.4%)
secondary prevention 1 (0.4%)
sepsis 2 (0.8%)
sleep 1 (0.4%)
sleep apnoea 1 (0.4%)
sleep breathing disorders 1 (0.4%)
streptococcus pyogenes 1 (0.4%)
stroke 1 (0.4%)
structural biology 4 (1.7%)
survivorship 1 (0.4%)
systemic lupus erythematosus (sle) 1 (0.4%)
t cell immunity 2 (0.8%)
thromboembolic disease 1 (0.4%)
tobacco control 1 (0.4%)
transcranial magnetic stimulation (tms) 1 (0.4%)
translational research 2 (0.8%)
transplantation 1 (0.4%)
tropoelastin 1 (0.4%)
tuberculosis 3 (1.3%)
vaccination 1 (0.4%)
ventricular fibrillation 1 (0.4%)
virus eradication 1 (0.4%)
visual development 1 (0.4%)
zebrafish 1 (0.4%)
ggplot(data=ig1, aes(x=Total/1000, col="blue")) + geom_histogram(color="white", fill="blue") + facet_grid(. ~SubType) + labs(x="Budget ($1000)", y="Number of grants", title="Budget by fellowship type")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(data=ig1, aes(x=Rank, fill=Rank)) + geom_bar(stat="count") + theme(legend.position="none") + labs(x="Academic rank", y="Number of grants", title="Number of successful grants by academic rank")

ggplot(data=ig1, aes(x=SubType, fill=Rank)) + geom_bar(stat="count") + labs(x="Subtype", y="Number of grants", title="Number of successful grants by Type and Rank")

ggplot(data=ig1, aes(x=SubType, fill=Area)) + geom_bar(stat="count") + labs(x="Subtype", y="Number of grants", title="Number of successful grants by Type and Area")