topic Re: Regression in Statistical Procedures

Regression

Jahanzaib — Fri, 17 Jun 2016 19:41:46 GMT

I want to apply regression analysis by following way.

leverage=a+family+tangibility+market+sales+profit+e

here i want to analyze the leverage on family firms. family is a binary variable it has value 0 and 1, while other are control variables.

can anyone guide?

Re: Regression

Reeza — Fri, 17 Jun 2016 19:48:24 GMT

What's your question?

Here's a tutorial on regression with SAS

http://www.ats.ucla.edu/stat/sas/webbooks/reg/chapter1/sasreg1.htm

And here are a list of topics/tutorials on SAS topcis. The first SAS course in data analysis, which includes regression is free, see the bottom right hand side of the page.

http://support.sas.com/training/tutorial/

Re: Regression

Rick_SAS — Fri, 17 Jun 2016 19:50:56 GMT

I assume your question is "Wht procedure do I use?"

Try PROC LOGISTIC. The basic syntax is

proc logistic data=Have;

model leverage = family tangibility market sales profit;

run;

If any of those variable are discrete classification variables, put them on a CLASS statement, like this:

class family;

Re: Regression

Jahanzaib — Fri, 17 Jun 2016 20:07:21 GMT

yes right.

my data also contain country name. what to add to get results for each country?

Re: Regression

Rick_SAS — Fri, 17 Jun 2016 20:12:34 GMT

Reeza linked to several resources, which I hope you will find time to watch or read. Simples questions like this are covered in the examples and in the syntax section for PROC LOGISTIC.

To get an analysis for each unique country name, you can sort the data by country and use the BY statement:

BY CountryName;

Re: Regression

Jahanzaib — Sat, 18 Jun 2016 15:46:27 GMT

When i applied this regression

proc logistic data=have;

model bdr = fam tang MTB size prof;
class fam;
by count;

run;

Than i got this error. how to handle this?

ERROR: Variable F should be either numeric or specified in the CLASS statement

I want to get country wise results. and fam is the dummy variable having value 0 and 1

Regression

Jahanzaib — Sat, 18 Jun 2016 16:44:34 GMT

I applied this regression

proc logistic data=have;

model bdr = fam tang MTB size prof;
class fam;
by count;

run;

Than i got this error. how to handle this?

ERROR: Variable Fam should be either numeric or specified in the CLASS statement

I want to get country wise results. and fam is the dummy variable having value 0 and 1

Re: Regression

Reeza — Sat, 18 Jun 2016 18:19:24 GMT

What values do the variable BDR take on?

Please post your log, your error doesn't align with the code you've posted and we'd just be guessing at what the issue might be.

Re: Regression

Jahanzaib — Sat, 18 Jun 2016 18:29:07 GMT

I have again attached the file.

Re: Regression

Reeza — Sat, 18 Jun 2016 18:32:59 GMT

You don't need logistic regression, you need a regression model, try PROC GLM. Your dependent variable is continuous not binary, logistic regression is intended for variables that take a binary outcome.

If you get errors please post your log, otherwise we can't tell where you went wrong. As I mentioned above, your error doesn't match your code.

Re: Regression

Jahanzaib — Sun, 19 Jun 2016 05:07:21 GMT

i have applied following regression everytime same error. i have pasted my log over here. please take a look. i have applied regression by putting class fam and also without putting class fam, both time same error.

proc glm data=d9;

model bdr = fam tang MTB size prof;
class fam;
by count;

run;

275 *logistic regression;
276 proc glm data=d9;
277
278 model bdr = fam tang MTB size prof;
ERROR: Variable Fam should be either numeric or specified in the CLASS statement.
NOTE: The previous statement has been deleted.
279 class fam;
280 by count;
281
282 run;

NOTE: Interactivity disabled with BY processing.
NOTE: PROCEDURE GLM used (Total process time):
real time 0.01 seconds
cpu time 0.01 seconds

Re: Regression

Reeza — Sun, 19 Jun 2016 05:11:43 GMT

The log is clear. The variable FAM is a character variable but it's being included as a continuous variable. Convert it to numeric if it's a number or include it in the Class statement if it's a categorical variable.

Proc glm is one of the few Procs that requires a quit at the end, in addition to the run statement.

Re: Regression

Jahanzaib — Sun, 19 Jun 2016 05:17:17 GMT

but in table i have seen fam has values 0 or 1.

how to delete fam values if they are other than 0 or 1.

Re: Regression

Reeza — Sun, 19 Jun 2016 05:29:00 GMT

Run a proc contents on the dataset to see variable type.

Run a proc freq to see what values your variable contains.

Proc contents data=mydata;
Run;

Proc freq data= mydata;
Table FAM;
Run;

data converted;
set mydata;
fam_num = input(fam, 2.);
run;

Numbers can be stored in a character variable.

Also, if it's 0/1 you can treat it as a categorical variable and include it in the Class statement.

Re: Regression

Jahanzaib — Sun, 19 Jun 2016 05:37:24 GMT

here is the frequency of fam. it contains value 0 and 1 but its types says that it is a character variable. i dont know how to run regression if it is so.

Fam
Fam	Frequency	Percent	Cumulative Frequency	Cumulative Percent
0	119807	94.31	119807	94.31
1	7234	5.69	127041	100.00

Re: Regression

Reeza — Sun, 19 Jun 2016 05:57:04 GMT

@Reeza wrote:

Also, if it's 0/1 you can treat it as a categorical variable and include it in the Class statement.

Let me repeat myself.

Also, the code sample above demonstrated how to convert it to numeric.

Heres a SAS that explains it as well.

http://support.sas.com/kb/24/590.html

Re: Regression

Jahanzaib — Sun, 19 Jun 2016 06:07:22 GMT

i have applied conversion code that you sent after that still it shows its character variable(after applying that converstion code activity do not show any erro) meanwhile i am trying to understand the link you sent.

Re: Regression

Reeza — Sun, 19 Jun 2016 09:29:19 GMT

Please post proc contents of new dataset. Note that fam will be character and fam_num would be numeric and you can use fam_num
Instead of fam.

Re: Regression

Rick_SAS — Sun, 19 Jun 2016 10:11:49 GMT

Put the CLASS statement before the MODEL statement. That will resolve this error.

Re: Regression

ValeriaRodz — Wed, 13 Mar 2019 20:07:20 GMT

I'm having the same problem, but I'm already using proc glm.

proc glm data = cross;

model tern_co tern_cr col_L col_a col_b pH hume intra_fat rendi = sexo edad musc;
class = sexo, edad, musc;

Can I only put one variable for class? I really don't get what's wrong with it.

Here's the whole code:

data cross;
infile datalines dlm='09'x;
input sexo$ edad$ musc$ tern_co tern_cr col_L col_a col_b pH hume intra_fat rendi;

cards; 
c	1	LD	4.00	1.20	28.47	19.34	17.22	5.64	73.09	1.49	51.65
c	1	LM	3.60	1.50	47.90	13.02	17.87	5.48	71.62	1.88	51.65
c	1	LD	3.90	1.20	29.57	20.11	16.55	5.49	70.33	3.94	53.16
c 	1	LM	4.40	1.40	42.41	16.10	17.13	5.38	74.29	2.25	53.16
c	1	LD	6.40	1.30	33.67	13.82	10.52	5.66	70.33	3.94	51.14
c	1	LM	3.50	3.10	51.67	11.48	15.29	5.62	74.29	2.25	51.14
c	2	LD	4.00	0.80	32.35	21.36	19.52	5.51	72.44	2.32	52.56
c	2	LM	2.80	1.70	41.68	17.34	18.90	5.42	74.09	1.77	52.56
c	2	LD	2.80	1.70	34.40	15.96	11.63	5.42	72.53	2.71	51.39
c	2	LM	3.00	1.80	43.85	15.23	14.98	5.43	67.65	0.62	51.39
c	2	LD	4.20	2.10	37.96	15.01	11.91	5.61	73.74	1.35	52.38
c	2	LM	2.40	0.80	48.28	13.37	15.36	5.58	76.92	0.52	52.38
c	2	LD	2.60	1.10	36.98	20.32	19.54	5.40	71.99	3.94	51.16
c	2	LM	3.70	2.10	46.82	16.23	19.29	5.50	74.18	2.27	51.16
c	3	LD	3.80	1.10	33.16	15.43	11.33	5.97	72.59	2.72	46.08
c	3	LM	5.00	2.80	42.88	16.69	15.50	5.80	72.28	2.80	46.08
c	3	LD	5.00	1.20	34.05	16.38	11.67	5.94	69.29	3.01	53.26
c	3	LM	4.50	1.50	45.51	16.17	15.48	5.84	75.85	2.38	53.26
c	3	LD	7.70	0.60	33.44	17.43	12.74	5.96	72.81	2.74	53.25
c	3	LM	5.60	1.80	39.77	18.77	16.32	5.67	70.98	3.54	53.25
c	3	LD	6.80	1.00	33.95	15.53	11.65	5.71	75.52	2.69	50.51
c	3	LM	4.60	2.00	45.97	16.00	16.85	5.78	76.03	1.80	50.51
c	3	LD	8.20	0.90	33.79	18.33	19.79	5.90	73.31	3.23	54.61
c	3	LM	8.60	1.30	42.51	18.53	16.88	5.62	70.80	2.90	54.61
c	3	LD	7.70	5.60	33.44	17.43	12.74	5.34	72.81	2.74	51.99
c	3	LM	0.60	1.80	39.77	18.77	16.32	5.67	70.98	3.54	51.99
c	3	LD	0.90	3.90	32.26	17.96	13.32	5.66	69.66	5.35	50.97
i	3	LM	1.70	3.80	42.48	16.66	15.73	5.62	70.06	1.80	50.97
i	1	LD	4.90	1.40	29.33	20.27	17.91	5.60	72.15	1.37	53.79
i	1	LM	3.30	2.00	44.92	15.46	17.80	5.13	74.60	1.47	53.79
i	1	LD	2.60	1.60	33.22	18.53	17.29	5.55	71.58	2.17	52.71
i	1	LM	3.60	1.60	44.38	14.74	17.66	5.53	75.81	0.98	52.71
i	1	LD	5.20	1.20	38.74	17.49	15.40	5.47	74.88	0.99	55.05
i	1	LM	3.90	1.40	47.97	12.14	14.44	5.51	73.09	2.32	55.05
i	1	LD	4.50	1.30	36.49	15.43	12.05	5.49	72.73	1.69	52.44
i	1	LM	4.10	4.10	44.86	14.32	14.64	5.43	74.23	0.89	52.44
i	2	LD	7.40	1.00	35.84	21.48	19.73	5.52	71.47	3.10	48.01
i	2	LM	3.10	3.20	42.18	15.83	18.07	5.66	73.12	0.89	48.01
i	2	LD	4.70	3.20	32.12	16.24	11.50	5.54	70.20	2.06	56.11
i	2	LM	3.50	1.70	39.48	15.74	13.24	5.80	74.94	0.69	56.11
i	2	LD	1.60	1.60	27.52	12.71	11.48	5.57	72.79	2.00	52.04
i	2	LM	2.20	2.00	32.95	12.72	15.71	5.29	73.67	1.19	52.04
i	2	LD	6.60	1.80	31.88	18.85	12.78	5.47	74.86	1.13	51.90
i	2	LM	1.70	2.10	43.81	12.96	13.28	6.26	72.62	1.99	51.90
i	2	LD	4.20	1.20	33.35	15.53	11.08	5.94	75.22	1.06	55.94
i	2	LM	3.70	1.70	44.54	12.78	13.52	5.93	72.44	3.62	55.94
i	3	LD	9.60	1.30	30.95	15.13	11.43	5.92	76.41	0.48	52.74
i	3	LM	4.40	3.40	37.87	14.27	12.79	5.75	76.43	0.64	52.74
i	3	LD	6.50	1.20	33.78	18.41	13.29	6.78	75.11	1.17	56.79
i	3	LM	5.20	1.50	41.18	16.67	14.65	5.89	76.52	1.17	56.79
i	3	LD	5.80	1.20	32.89	16.03	11.48	5.87	75.46	1.20	57.22
i	3	LM	8.50	2.20	46.38	15.79	15.71	5.85	74.35	1.32	57.22
i	3	LD	5.90	0.90	30.26	15.53	10.17	5.95	73.92	1.44	56.84
i	3	LM	6.60	2.30	36.56	14.05	11.12	5.89	74.46	0.92	56.84
i	3	LD	8.50	1.30	30.27	14.22	19.76	5.22	76.41	0.48	57.32
i	3	LM	5.10	3.40	40.15	16.14	13.27	5.45	76.43	0.64	57.32
i	3	LD	7.30	0.90	33.28	15.78	10.61	5.41	74.69	1.69	53.36
i	3	LM	4.90	1.60	43.02	16.74	15.99	5.61	75.79	0.64	53.36
i	3	LD	9.70	1.10	31.73	14.19	10.61	5.86	73.94	1.90	49.49
i	3	LM	4.40	1.70	38.97	19.47	16.52	5.80	67.65	0.62	49.49


;
proc glm data = cross;

model tern_co tern_cr col_L col_a col_b pH hume intra_fat rendi = sexo edad musc;
class = sexo, edad, musc;

And here's the log:

         OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 72         
 73         
 74         
 75         
 76         data cross;
 77         infile datalines dlm='09'x;
 78         input sexo$ edad$ musc$ tern_co tern_cr col_L col_a col_b pH hume intra_fat rendi;
 79         
 80         cards;
 
 NOTE: LOST CARD.
 RULE:      ----+----1----+----2----+----3----+----4----+----5----+----6----+----7----+----8----+----9----+----0                     
 143        ;
 sexo=  edad=  musc=  tern_co=. tern_cr=. col_L=. col_a=. col_b=. pH=. hume=. intra_fat=. rendi=. _ERROR_=1 _N_=61
 NOTE: SAS went to a new line when INPUT statement reached past the end of a line.
 NOTE: The data set WORK.CROSS has 60 observations and 12 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.01 seconds
       cpu time            0.02 seconds
       
 
 143        ;
 144        proc glm data = cross;
 145        
 146        model tern_co tern_cr col_L col_a col_b pH hume intra_fat rendi = sexo edad musc;
 ERROR: Variable sexo should be either numeric or specified in the CLASS statement.
 NOTE: The previous statement has been deleted.
 147        class = sexo, edad, musc;
            _____
            180
 NOTE: The previous statement has been deleted.
 ERROR 180-322: Statement is not valid or it is used out of proper order.
 
 148        
 149        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 162