I tried to analyzed Aids2 and I want to apply "prop.test" for proportion of infected by "hs" method in men vs. women. How can I do that?
This is a part of my dataset:
state sex diag death status T.categ age
1 NSW M 10905 11081 D hs 35
2 NSW M 11029 11096 D hs 53
3 NSW M 9551 9983 D hs 42
4 NSW M 9577 9654 D haem 44
5 NSW M 10015 10290 D hs 39
6 NSW M 9971 10344 D hs 36
7 NSW M 10746 11135 D other 36
8 NSW M 10042 11069 D hs 31
9 NSW M 10464 10956 D hs 26
10 NSW M 10439 10873 D hsid 27
11 NSW M 10416 10432 D hs 45
12 NSW M 10216 10524 D hs 36
13 NSW M 10385 10477 D hs 27
14 NSW M 10366 10631 D hs 35
15 NSW M 10452 11504 A hs 30
16 NSW M 10552 10684 D hs 39
17 NSW M 10673 11200 D hs 30
18 NSW M 10923 11504 A haem 21
19 NSW M 10993 11504 A hs 56
20 NSW M 11020 11171 D hs 41
21 NSW M 10805 10877 D hs 28
22 NSW M 10996 11504 A hs 38
23 NSW M 10738 11504 A het 26
24 NSW M 11063 11504 A id 39
25 NSW M 10885 11196 D hs 46
26 NSW M 11056 11504 A haem 13
27 NSW M 11283 11504 A hs 34
28 NSW M 11195 11504 A het 39
29 NSW M 10848 11504 A hs 31
30 NSW M 11289 11504 A mother 1
31 NSW F 10961 11504 A id 30
32 NSW M 11311 11312 D blood 37
33 NSW M 11337 11504 A hs 38
34 NSW M 11458 11463 D hs 33
35 NSW M 11480 11504 A hs 30
36 NSW M 11462 11504 A hs 40
37 NSW M 8302 8469 D hs 51
38 NSW M 8711 8850 D hs 29
39 NSW M 8726 9254 D hsid 29
40 NSW M 8760 8959 D hsid 37
41 NSW M 8802 8879 D hs 46
42 NSW M 8877 9180 D hs 37
43 NSW M 9011 9696 D blood 54
44 NSW M 8990 9175 D hs 30
45 NSW M 9063 9172 D blood 25
46 NSW M 9003 9109 D hsid 26
47 NSW M 9022 9218 D hs 41
48 NSW M 8985 9254 D hs 41
49 NSW M 9030 9781 D hs 27
50 NSW M 9086 9314 D hs 35
51 NSW M 9015 9943 D hs 35
52 NSW M 9009 9350 D hs 25
53 NSW M 8970 9240 D hs 34
54 NSW M 9171 9309 D hs 35
55 NSW M 9087 9598 D hs 33
56 NSW M 9115 9686 D hs 31
57 NSW M 9065 9262 D hs 43
58 NSW M 9104 9126 D hs 59
59 NSW M 9028 9532 D hs 31
60 NSW M 9101 9268 D hs 41
61 NSW M 9096 9226 D hs 34
62 NSW M 9128 9660 D hs 37
63 NSW M 9125 9207 D hs 31
64 NSW M 9083 9682 D hs 37
65 NSW M 9150 9285 D hs 38
66 NSW F 9014 9152 D blood 44
67 NSW M 9157 9962 D hs 41
68 NSW M 9098 9418 D hs 41
69 NSW M 8913 9082 D hs 32
70 NSW M 9141 9222 D hs 40
71 NSW M 9158 9920 D hs 23
72 NSW M 9167 10461 D hs 42
73 NSW M 9244 9379 D hs 33
74 NSW M 9138 9565 D hs 47
75 NSW M 9222 9536 D hs 52
76 NSW M 9272 9290 D hs 35
77 NSW M 9131 9392 D hs 38
78 NSW M 9236 10013 D hs 23
79 NSW M 9145 9250 D hs 45
80 NSW M 8964 9300 D haem 48
81 NSW M 9207 9768 D hs 32
82 NSW M 9240 9447 D hs 38
83 NSW M 9281 9723 D hs 25
84 NSW M 9300 9736 D hs 36
85 NSW M 9294 10070 D hs 39
86 NSW F 9258 9259 D blood 25
87 NSW M 9145 9436 D hs 33
88 NSW M 9310 9533 D hs 35
89 NSW M 9344 11320 D hs 49
90 NSW M 9185 9214 D hs 38
91 NSW M 9247 9549 D hs 30
92 NSW M 9201 9315 D hs 44
93 NSW F 9349 9392 D blood 55
94 NSW M 9246 9956 D hs 31
95 NSW M 9273 10018 D hs 32
96 NSW M 9241 9576 D hs 29
97 NSW M 9264 9451 D hs 42
98 NSW M 9310 9730 D hs 28
Can you help me, because I'm beginner in data analysis and I don't know how to apply this type of test ("prop.test).
Thank you in advances for your help!
I'm using your example dataset:
df = read.table(text = "
state sex diag death status T.categ age
1 NSW M 10905 11081 D hs 35
2 NSW M 11029 11096 D hs 53
3 NSW M 9551 9983 D hs 42
4 NSW M 9577 9654 D haem 44
5 NSW M 10015 10290 D hs 39
6 NSW M 9971 10344 D hs 36
7 NSW M 10746 11135 D other 36
8 NSW M 10042 11069 D hs 31
9 NSW M 10464 10956 D hs 26
10 NSW M 10439 10873 D hsid 27
11 NSW M 10416 10432 D hs 45
12 NSW M 10216 10524 D hs 36
13 NSW M 10385 10477 D hs 27
14 NSW M 10366 10631 D hs 35
15 NSW M 10452 11504 A hs 30
16 NSW M 10552 10684 D hs 39
17 NSW M 10673 11200 D hs 30
18 NSW M 10923 11504 A haem 21
19 NSW M 10993 11504 A hs 56
20 NSW M 11020 11171 D hs 41
21 NSW M 10805 10877 D hs 28
22 NSW M 10996 11504 A hs 38
23 NSW M 10738 11504 A het 26
24 NSW M 11063 11504 A id 39
25 NSW M 10885 11196 D hs 46
26 NSW M 11056 11504 A haem 13
27 NSW M 11283 11504 A hs 34
28 NSW M 11195 11504 A het 39
29 NSW M 10848 11504 A hs 31
30 NSW M 11289 11504 A mother 1
31 NSW F 10961 11504 A id 30
32 NSW M 11311 11312 D blood 37
33 NSW M 11337 11504 A hs 38
34 NSW M 11458 11463 D hs 33
35 NSW M 11480 11504 A hs 30
36 NSW M 11462 11504 A hs 40
37 NSW M 8302 8469 D hs 51
38 NSW M 8711 8850 D hs 29
39 NSW M 8726 9254 D hsid 29
40 NSW M 8760 8959 D hsid 37
41 NSW M 8802 8879 D hs 46
42 NSW M 8877 9180 D hs 37
43 NSW M 9011 9696 D blood 54
44 NSW M 8990 9175 D hs 30
45 NSW M 9063 9172 D blood 25
46 NSW M 9003 9109 D hsid 26
47 NSW M 9022 9218 D hs 41
48 NSW M 8985 9254 D hs 41
49 NSW M 9030 9781 D hs 27
50 NSW M 9086 9314 D hs 35
51 NSW M 9015 9943 D hs 35
52 NSW M 9009 9350 D hs 25
53 NSW M 8970 9240 D hs 34
54 NSW M 9171 9309 D hs 35
55 NSW M 9087 9598 D hs 33
56 NSW M 9115 9686 D hs 31
57 NSW M 9065 9262 D hs 43
58 NSW M 9104 9126 D hs 59
59 NSW M 9028 9532 D hs 31
60 NSW M 9101 9268 D hs 41
61 NSW M 9096 9226 D hs 34
62 NSW M 9128 9660 D hs 37
63 NSW M 9125 9207 D hs 31
64 NSW M 9083 9682 D hs 37
65 NSW M 9150 9285 D hs 38
66 NSW F 9014 9152 D blood 44
67 NSW M 9157 9962 D hs 41
68 NSW M 9098 9418 D hs 41
69 NSW M 8913 9082 D hs 32
70 NSW M 9141 9222 D hs 40
71 NSW M 9158 9920 D hs 23
72 NSW M 9167 10461 D hs 42
73 NSW M 9244 9379 D hs 33
74 NSW M 9138 9565 D hs 47
75 NSW M 9222 9536 D hs 52
76 NSW M 9272 9290 D hs 35
77 NSW M 9131 9392 D hs 38
78 NSW M 9236 10013 D hs 23
79 NSW M 9145 9250 D hs 45
80 NSW M 8964 9300 D haem 48
81 NSW M 9207 9768 D hs 32
82 NSW M 9240 9447 D hs 38
83 NSW M 9281 9723 D hs 25
84 NSW M 9300 9736 D hs 36
85 NSW M 9294 10070 D hs 39
86 NSW F 9258 9259 D blood 25
87 NSW M 9145 9436 D hs 33
88 NSW M 9310 9533 D hs 35
89 NSW M 9344 11320 D hs 49
90 NSW M 9185 9214 D hs 38
91 NSW M 9247 9549 D hs 30
92 NSW M 9201 9315 D hs 44
93 NSW F 9349 9392 D blood 55
94 NSW M 9246 9956 D hs 31
95 NSW M 9273 10018 D hs 32
96 NSW M 9241 9576 D hs 29
97 NSW M 9264 9451 D hs 42
98 NSW M 9310 9730 D hs 28
", header=T, stringsAsFactors=F)
You can create a dataset with the counts of hs / other infections by gender and apply the prop.test function
library(dplyr)
library(tidyr)
df_counts = df %>%
mutate(T.categ2 = ifelse(T.categ == "hs", T.categ, "other")) %>% # flag hs or other
count(sex, T.categ2) %>% # count how many times each sex was infected by hs or other
spread(T.categ2, n, fill = 0) %>% # reshape dataset
mutate(Total = hs+other) # count totals
# see how your aggregated dataset with counts looks like
df_counts
# # A tibble: 2 x 4
# sex hs other Total
# <chr> <dbl> <dbl> <dbl>
# 1 F 0 4.00 4.00
# 2 M 78.0 16.0 94.0
# apply prop test using the appropriate columns
prop.test(df_counts$hs, df_counts$Total)