ITBAL Assignment 8

Analysis using 3 models:

1. Pool Effect model
2. Fixed Effect model.
3. Random Effect model.

There are two types of index of panel data:

1> ID index
2> Time index.

Step 1:

Read the data.

Commands:
> data("Produc",package = "plm")
> head(Produc)

Step 2:

Pooled Model:

Commands:
>pool<-plm(log(pcap)~log(hwy)+log(water)+log(util)+log(pc)+log(gsp)+log(emp)+log(unemp),data=Produc,model=("pooling"), index= c("state","year"))
> summary(pool)

Step 3:

Fixed effect model

commands:
>fixed<-plm(log(pcap)~log(hwy)+log(water)+log(util)+log(pc)+log(gsp)+log(emp)+log(unemp),data=Produc,model=("within"), index= c("state","year"))
> summary(fixed)

Step 4:

Random effect model:

 commands:

>random1<-plm(log(pcap)~log(hwy)+log(water)+log(util)+log(pc)+log(gsp)+log(emp)+log(unemp),data=Produc,model=("random"), index= c("state","year"))
> summary(random1)

Step 5: Test for fixed vs OLS

pFtest(fixed,pool)

Null hypothesis: Pooled effect model

Alternate hypothesis:  Fixed effect model

Commands:

> pFtest(fixed,pool)

Step 6:  Test for pooled data vs random data

Null hypothesis: Pool effect model
Alternate hypothesis: Random effect model

Command:

> plmtest(pool)

p value is very less. Reject null hypothesis and accept alternate hypothesis i.e.Random effect model.  

Step 7: Test for random effect model vs pool effect model.

Null hypothesis: Random effect model
Alternate hypothesis: Fixed effect model.


command:
phtest(random1,fixed)

P value is too less . So reject Null hypothesis and accept alternate hypothesis i.e.Fixed effect model.
Aritro Ghosh
12BM60087