turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

Find a Community

- Home
- /
- Analytics
- /
- Stat Procs
- /
- LD50 calculation for mixture of dose concentration...

Topic Options

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

05-02-2017 10:51 AM - last edited on 05-02-2017 11:04 AM by Rick_SAS

Normally for Calculation of LC50 calculation firstly according to method we have to add dose concentration, total number of animals and then number of mortality like the example below.Here 2,4,6.. represents dose concentration.

```
data A;
input dose n response;
cards;
```

2 50 10
4 50 25
6 50 35
8 50 40
10 50 45

;
proc probit log 10;
var dose n response;
run;

As i mentioned previously i am using two different concentrations as one dose.how I write them.problm is I have my dose concentration in this form220/50300/100400/150when i put this this doesnt work.(both are different drugs which are taken as one dose concentration)please reply me as soon as possible

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

05-03-2017 08:33 AM

I think your code got garbled when you pasted it into the SAS code window. Use the INVERSECL option to find the LD50 value:

```
data A;
input dose n response;
cards;
2 50 10
4 50 25
6 50 35
8 50 40
10 50 45
;
proc probit data=A log10;
model response / n = dose / InverseCL(prob=0.1 to 0.9 by 0.1);
run;
```

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

05-03-2017 11:16 AM

```
data A;
input dose n response;
cards;
220/50 50 10
250/100 50 25
300/150 50 35
350/200 50 40
400/250 50 45;
proc probit log 10;
var dose n response;
run;
proc probit data=A log10;
model response / n = dose / InverseCL(prob=0.1 to 0.9 by 0.1);
run;
```

did u mean ike that?

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

05-03-2017 11:36 AM

I'll try one more time. If you have two independent design variables that represent the concentration of a mixture, the locus of points for which half the population will die is generally a curve. It is the prob=0.5 contour of the surface of predicted probability. You can approximate this curve by using the EFFECTPLOT statement in PROC LOGISTIC to generate the contour plot. As far as I know, you can't generate this curve by using a procedure, although if you are an advanced programmer you can use PROC IML to trace contours.

```
data A;
input d1 d2 n response;
cards;
220 50 50 10
250 100 50 25
300 150 50 35
350 200 50 40
400 250 50 45
;
proc logistic data=A ;
model response / n = d1 d2;
effectplot;
run;
```

Good luck.

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

05-04-2017 03:05 AM

this didnt work.

i told u i have one dose having two concentration of differnt drugs.

the way You told me give error