Graphs for adjusted odds ratios with CI and P-value

[SEMAN OSMAN]

Hi, Stata Users,
I am not so much good in posting on the forum, please excuse me for not adhering the rules.
My setup (Windows 10, Stata 16.1 MP)
I am interested to explore the relationship between emotional IPV and ANC service visits stratified by level of education (Low Vs. High) and household wealth status (Low Vs. High). I have adjusted four models (each subgroups) using the following Stata commands:
Low education Model
melogit anc_visits i.emo_vio1 i.mom_age i.birth_order i.hus_educ i.wealth_hh i.media_expo i.wempower1 i.V102 i.contex_regions if mom_educ ==0|| psu :,or nolog

I have found that (attached Table), significant in exposure to spousal emotional IPV effect on receiving adequate ANC service were seen with women living in low household wealth (P = 0.031), and with those low levels of education (P = 0.021).
All other covariates result omitted.

My concern is how I can plot the graph to show these relationships (emotionally IPV with ANC visits and education/wealth - relationship) like the sample graph attached (Pdf file), here with its AOR, CI and P-values.

Thank you so much for help!

[Clyde Schechter]

I think you can get this from -coefplot-, authored by Ben Jann, available from SSC.

(Note: I'm slightly guessing what you want here as your description is not entirely clear. I have not looked at your attachments because I do not download attachments from people I do not know. Please read the FAQ--attachments are discouraged here. Where it is necessary to show an image, the Forum editor does support inserting an image file directly into the post.)

[SEMAN OSMAN]

Dear Clyde Schechter,
Thank you so much for your guidance. I also, apologize for wrong way to upload the file. Indeed, I have tried these command ( -coefplot-, authored by Ben Jann,) from the information I had on these forum post previously but failed to get the assumed graph. What way do you think that possible, please? I can also forward any prior information on these variables if you need them.
Best regards,

[Clyde Schechter]

Well, if you repost showing the graph embedded, rather than as an attachment, so everyone can see it, probably someone can answer you. (Maybe me, if I know the answer.)

[SEMAN OSMAN]

Dear Clyde Schechter,
Thank you for your positive response. I here, attached the graph looks like.
But I am using the following command to generate the relationship between emotional IPV and ANC stratified by education level (Low = 0 Vs. High = 1) and wealth status (Low = 0 Vs High = 1).

1. Low education

melogit anc_visits i.emo_vio1 i.mom_age i.hus_educ i.wealth_hh i.media_expo i.birth_order i.wempower1 i.V102 i.contex_regions if mom_educ==0 > || psu :,or nolog

Mixed-effects logistic regression Number of obs = 2,548
Group variable: psu Number of groups = 580

Obs per group:
min = 1
avg = 4.4
max = 12

Integration method: mvaghermite Integration pts. = 7

Wald chi2(15) = 160.53
Log likelihood = -1384.4603 Prob > chi2 = 0.0000
------------------------------------------------------------------------------------------------
anc_visits | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval]
-------------------------------+----------------------------------------------------------------
emo_vio1 |
Yes | .7386871 .0969893 -2.31 0.021 .5710815 .955483



B. Low Wealth status

melogit anc_visits i.emo_vio1 i.mom_age i.mom_educ i.hus_educ i.media_expo i.birth_order i.wempower1 i.V102 i.contex_regions if wealth_hh == > 0 || psu :,or nolog

Mixed-effects logistic regression Number of obs = 1,929
Group variable: psu Number of groups = 443

Obs per group:
min = 1
avg = 4.4
max = 12

Integration method: mvaghermite Integration pts. = 7

Wald chi2(15) = 62.54
Log likelihood = -997.19729 Prob > chi2 = 0.0000
------------------------------------------------------------------------------------------------
anc_visits | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval]
-------------------------------+----------------------------------------------------------------
emo_vio1 |
Yes | .7088675 .1133807 -2.15 0.031 .518106 .9698655




From the above output, we can see that:
Significant in exposure to spousal emotional IPV effect on receiving adequate ANC service were seen with women living in low household wealth (AOR = 0.79, CI: 0.52 – 0.97; P = 0.031), and with those low levels of education (AOR = 0.74, CI: 0.57 – 0.96; P = 0.021).
All other covariates result omitted.

Please, anyone could give me hint to plot the relationship between emotional IPV and ANC stratified by education level (Low) and wealth status (Low) showing with its AOR, CI and P-values. Something like the attached figure.
Thank you so much in advance.

[Clyde Schechter]

It looks like you want what -coefplot-, by Ben Jann, available from SSC, does. I have only a little experience using it myself, so I'm not going to try to give you the exact syntax. But I'm pretty sure it's the right tool for this job.

[SEMAN OSMAN]

Dear Clyde Schechter,
I am not sure about SSC??
Best,

[Rich Goldstein]

not clear what your question is but the place to start is

help ssc